51 files changed, 1746 insertions, 1854 deletions
diff --git a/dynamic-layers/clang-layer/recipes-core/dnn/files/run-ptest b/dynamic-layers/clang-layer/recipes-core/dnn/files/run-ptest
new file mode 100755
index 00000000..82d4df58
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-core/dnn/files/run-ptest
@@ -0,0 +1,15 @@
+#!/bin/sh
+cd tests
+./api-c
+if [ $? -eq 0 ]; then
+  echo 'PASS: api-c'
+else
+  echo 'FAIL: api-c'
+fi
+./test_c_symbols-c
+if [ $? -eq 0 ]; then
+  echo 'PASS: test_c_symbols-c'
+else
+  echo 'FAIL: test_c_symbols-c'
+fi
diff --git a/dynamic-layers/clang-layer/recipes-core/dnn/onednn_3.5.3.bb b/dynamic-layers/clang-layer/recipes-core/dnn/onednn_3.5.3.bb
new file mode 100644
index 00000000..6d4f69a3
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-core/dnn/onednn_3.5.3.bb
@@ -0,0 +1,56 @@
+HOMEPAGE = "https://www.oneapi.com"
+SUMMARY  = "Deep Neural Network Library"
+DESCRIPTION = "This software is a user mode library that accelerates\
+deep-learning applications and frameworks on Intel architecture."
+LICENSE  = "Apache-2.0 & BSD-3-Clause & BSL-1.0"
+LIC_FILES_CHKSUM = "file://LICENSE;md5=3b64000f6e7d52516017622a37a94ce9 \
+                    file://tests/gtests/gtest/LICENSE;md5=cbbd27594afd089daa160d3a16dd515a \
+                    file://src/cpu/x64/xbyak/COPYRIGHT;md5=3b9bf048d063d54cdb28964db558bcc7 \
+                    file://src/common/ittnotify/LICENSE.BSD;md5=e671ff178b24a95a382ba670503c66fb \
+                    "
+SECTION = "lib"
+inherit pkgconfig cmake ptest
+DNN_BRANCH = "rls-v${@'.'.join(d.getVar('PV').split('.')[0:2])}"
+SRCREV = "66f0cb9eb66affd2da3bf5f8d897376f04aae6af"
+SRC_URI = "git://github.com/oneapi-src/oneDNN.git;branch=${DNN_BRANCH};protocol=https \
+           file://run-ptest \
+           "
+UPSTREAM_CHECK_GITTAGREGEX = "^v(?P<pver>(\d+(\.\d+)+))$"
+CVE_PRODUCT = "intel:math_kernel_library"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = 'null'
+EXTRA_OECMAKE += " \
+                   -DDNNL_LIBRARY_TYPE=SHARED \
+                   -DDNNL_BUILD_EXAMPLES=ON \
+                   -DDNNL_BUILD_TESTS=ON \
+                   -DDNNL_CPU_RUNTIME=OMP \
+                   -DDNNL_ARCH_OPT_FLAGS="" \
+                   -DCMAKE_SKIP_RPATH=ON \
+                   -DONEDNN_BUILD_GRAPH=OFF \
+                   "
+PACKAGECONFIG ??= "gpu"
+PACKAGECONFIG[gpu] = "-DDNNL_GPU_RUNTIME=OCL, , opencl-headers virtual/opencl-icd, intel-compute-runtime"
+do_install:append () {
+    install -d ${D}${bindir}/mkl-dnn/tests/benchdnn/inputs
+    install -m 0755 ${B}/tests/benchdnn/benchdnn ${D}${bindir}/mkl-dnn/tests/benchdnn
+    cp -r ${B}/tests/benchdnn/inputs/* ${D}${bindir}/mkl-dnn/tests/benchdnn/inputs
+}
+do_install_ptest () {
+    install -d ${D}${PTEST_PATH}/tests
+    install -m 0755 ${B}/tests/api-c ${D}${PTEST_PATH}/tests
+    install -m 0755 ${B}/tests/test_c_symbols-c ${D}${PTEST_PATH}/tests
+}
+PACKAGES =+ "${PN}-test"
+FILES:${PN}-test = "${bindir}/mkl-dnn/*"
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/clang_%.bbappend b/dynamic-layers/clang-layer/recipes-devtools/clang/clang_%.bbappend
deleted file mode 100644
index f8d5a252..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/clang_%.bbappend
+++ /dev/null
@@ -1,13 +0,0 @@
-FILESEXTRAPATHS_prepend_intel-x86-common := "${THISDIR}/files:"
-DEPENDS_append = " opencl-clang-native"
-LLVM_TARGETS_TO_BUILD = "X86"
-do_install_append_intel-x86-common() {
-        DESTDIR=${D} ninja -v install-cmake-exports
-}
-LIBCPLUSPLUS = ""
-# undefined reference to `__atomic_load' on i*86.
-COMPATIBLE_HOST = '(x86_64).*-linux'
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-OpenCL-Change-type-of-block-pointer-for-OpenCL.patch b/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-OpenCL-Change-type-of-block-pointer-for-OpenCL.patch
deleted file mode 100644
index 1c491402..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-OpenCL-Change-type-of-block-pointer-for-OpenCL.patch
+++ /dev/null
@@ -1,156 +0,0 @@
-From 39a3ac0065c23d1e2d55dfd8792cc28a146a4307 Mon Sep 17 00:00:00 2001
-From: Alexey Bader <alexey.bader@intel.com>
-Date: Tue, 19 Feb 2019 15:19:06 +0000
-Subject: [PATCH 1/2] [OpenCL] Change type of block pointer for OpenCL
-Summary:
-For some reason OpenCL blocks in LLVM IR are represented as function pointers.
-These pointers do not point to any real function and never get called. Actually
-they point to some structure, which in turn contains pointer to the real block
-invoke function.
-This patch changes represntation of OpenCL blocks in LLVM IR from function
-pointers to pointers to `%struct.__block_literal_generic`.
-Such representation allows to avoid unnecessary bitcasts and simplifies
-further processing (e.g. translation to SPIR-V ) of the module for targets
-which do not support function pointers.
-Patch by: Alexey Sotkin.
-Reviewers: Anastasia, yaxunl, svenvh
-Reviewed By: Anastasia
-Subscribers: alexbatashev, cfe-commits
-Tags: #clang
-Differential Revision: https://reviews.llvm.org/D58277
-git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@354337 91177308-0d34-0410-b5e6-96231b3b80d8
-Upstream-Status: Backport
-[https://github.com/llvm-mirror/clang/commit/283f308bdb5893bab1f36791711346e746045f94]
-Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
---
- lib/CodeGen/CodeGenTypes.cpp                   |  4 +++-
- test/CodeGenOpenCL/blocks.cl                   | 18 ++++++++----------
- test/CodeGenOpenCL/cl20-device-side-enqueue.cl | 18 +++++++++---------
- 3 files changed, 20 insertions(+), 20 deletions(-)
-diff --git a/lib/CodeGen/CodeGenTypes.cpp b/lib/CodeGen/CodeGenTypes.cpp
-index 2acf1ac..93b3ebf 100644
--- a/lib/CodeGen/CodeGenTypes.cpp
-+++ b/lib/CodeGen/CodeGenTypes.cpp
-@@ -637,7 +637,9 @@ llvm::Type *CodeGenTypes::ConvertType(QualType T) {
- 
-   case Type::BlockPointer: {
-     const QualType FTy = cast<BlockPointerType>(Ty)->getPointeeType();
-    llvm::Type *PointeeType = ConvertTypeForMem(FTy);
-+    llvm::Type *PointeeType = CGM.getLangOpts().OpenCL
-+                                  ? CGM.getGenericBlockLiteralType()
-+                                  : ConvertTypeForMem(FTy);
-     unsigned AS = Context.getTargetAddressSpace(FTy);
-     ResultType = llvm::PointerType::get(PointeeType, AS);
-     break;
-diff --git a/test/CodeGenOpenCL/blocks.cl b/test/CodeGenOpenCL/blocks.cl
-index 675240c..19aacc3 100644
--- a/test/CodeGenOpenCL/blocks.cl
-+++ b/test/CodeGenOpenCL/blocks.cl
-@@ -35,11 +35,10 @@ void foo(){
-   // SPIR: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]], i32 0, i32 3
-   // SPIR: %[[i_value:.*]] = load i32, i32* %i
-   // SPIR: store i32 %[[i_value]], i32* %[[block_captured]],
-  // SPIR: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to i32 ()*
-  // SPIR: %[[blk_gen_ptr:.*]] = addrspacecast i32 ()* %[[blk_ptr]] to i32 () addrspace(4)*
-  // SPIR: store i32 () addrspace(4)* %[[blk_gen_ptr]], i32 () addrspace(4)** %[[block_B:.*]],
-  // SPIR: %[[blk_gen_ptr:.*]] = load i32 () addrspace(4)*, i32 () addrspace(4)** %[[block_B]]
-  // SPIR: %[[block_literal:.*]] = bitcast i32 () addrspace(4)* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
-+  // SPIR: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to %struct.__opencl_block_literal_generic*
-+  // SPIR: %[[blk_gen_ptr:.*]] = addrspacecast %struct.__opencl_block_literal_generic* %[[blk_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
-+  // SPIR: store %struct.__opencl_block_literal_generic addrspace(4)* %[[blk_gen_ptr]], %struct.__opencl_block_literal_generic addrspace(4)** %[[block_B:.*]],
-+  // SPIR: %[[block_literal:.*]] = load %struct.__opencl_block_literal_generic addrspace(4)*, %struct.__opencl_block_literal_generic addrspace(4)** %[[block_B]]
-   // SPIR: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 2
-   // SPIR: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)*
-   // SPIR: %[[invoke_func_ptr:.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* %[[invoke_addr]]
-@@ -50,11 +49,10 @@ void foo(){
-   // AMDGCN: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]], i32 0, i32 3
-   // AMDGCN: %[[i_value:.*]] = load i32, i32 addrspace(5)* %i
-   // AMDGCN: store i32 %[[i_value]], i32 addrspace(5)* %[[block_captured]],
-  // AMDGCN: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]] to i32 () addrspace(5)*
-  // AMDGCN: %[[blk_gen_ptr:.*]] = addrspacecast i32 () addrspace(5)* %[[blk_ptr]] to i32 ()*
-  // AMDGCN: store i32 ()* %[[blk_gen_ptr]], i32 ()* addrspace(5)* %[[block_B:.*]],
-  // AMDGCN: %[[blk_gen_ptr:.*]] = load i32 ()*, i32 ()* addrspace(5)* %[[block_B]]
-  // AMDGCN: %[[block_literal:.*]] = bitcast i32 ()* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic*
-+  // AMDGCN: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]] to %struct.__opencl_block_literal_generic addrspace(5)*
-+  // AMDGCN: %[[blk_gen_ptr:.*]] = addrspacecast %struct.__opencl_block_literal_generic addrspace(5)* %[[blk_ptr]] to %struct.__opencl_block_literal_generic*
-+  // AMDGCN: store %struct.__opencl_block_literal_generic* %[[blk_gen_ptr]], %struct.__opencl_block_literal_generic* addrspace(5)* %[[block_B:.*]],
-+  // AMDGCN: %[[block_literal:.*]] = load %struct.__opencl_block_literal_generic*, %struct.__opencl_block_literal_generic* addrspace(5)* %[[block_B]]
-   // AMDGCN: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic* %[[block_literal]], i32 0, i32 2
-   // AMDGCN: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic* %[[block_literal]] to i8*
-   // AMDGCN: %[[invoke_func_ptr:.*]] = load i8*, i8** %[[invoke_addr]]
-diff --git a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
-index 4732194..8445016 100644
--- a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
-+++ b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
-@@ -11,7 +11,7 @@ typedef struct {int a;} ndrange_t;
- 
- // For a block global variable, first emit the block literal as a global variable, then emit the block variable itself.
- // COMMON: [[BL_GLOBAL:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* [[INV_G:@[^ ]+]] to i8*) to i8 addrspace(4)*) }
-// COMMON: @block_G =  addrspace(1) constant void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*)
-+// COMMON: @block_G = addrspace(1) constant %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*)
- 
- // For anonymous blocks without captures, emit block literals as global variable.
- // COMMON: [[BLG1:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) }
-@@ -77,9 +77,9 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
-   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
-   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
-   // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL1:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke
-  // B32: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block to void ()*
-  // B64: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32 addrspace(1)*, i32 }>* %block to void ()*
-  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* [[BL]] to i8 addrspace(4)*
-+  // B32: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block to %struct.__opencl_block_literal_generic*
-+  // B64: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32 addrspace(1)*, i32 }>* %block to %struct.__opencl_block_literal_generic*
-+  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast %struct.__opencl_block_literal_generic* [[BL]] to i8 addrspace(4)*
-   // COMMON-LABEL: call i32 @__enqueue_kernel_basic(
-   // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* byval [[NDR]]{{([0-9]+)?}},
-   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVLK1:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
-@@ -95,8 +95,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
-   // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %event_wait_list to %opencl.clk_event_t{{.*}}* addrspace(4)*
-   // COMMON: [[EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)*
-   // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL2:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke
-  // COMMON: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()*
-  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* [[BL]] to i8 addrspace(4)*
-+  // COMMON: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to %struct.__opencl_block_literal_generic*
-+  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast %struct.__opencl_block_literal_generic* [[BL]] to i8 addrspace(4)*
-   // COMMON-LABEL: call i32 @__enqueue_kernel_basic_events
-   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]],
-   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVLK2:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
-@@ -300,13 +300,13 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
-   // Emits global block literal [[BLG8]] and invoke function [[INVG8]].
-   // The full type of these expressions are long (and repeated elsewhere), so we
-   // capture it as part of the regex for convenience and clarity.
-  // COMMON: store void () addrspace(4)* addrspacecast (void () addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to void () addrspace(1)*) to void () addrspace(4)*), void () addrspace(4)** %block_A
-+  // COMMON: store %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), %struct.__opencl_block_literal_generic addrspace(4)** %block_A
-   void (^const block_A)(void) = ^{
-     return;
-   };
- 
-   // Emits global block literal [[BLG9]] and invoke function [[INVG9]].
-  // COMMON: store void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG9]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*), void (i8 addrspace(3)*) addrspace(4)** %block_B
-+  // COMMON: store %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG9]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), %struct.__opencl_block_literal_generic addrspace(4)** %block_B
-   void (^const block_B)(local void *) = ^(local void *a) {
-     return;
-   };
-@@ -346,7 +346,7 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
-   // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL3:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke
-   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
-   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
-  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* {{.*}} to i8 addrspace(4)*
-+  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast %struct.__opencl_block_literal_generic* {{.*}} to i8 addrspace(4)*
-   // COMMON-LABEL: call i32 @__enqueue_kernel_basic(
-   // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* byval [[NDR]]{{([0-9]+)?}},
-   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVLK3:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
-- 
-1.8.3.1
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-Update-LowerOpenCL-pass-to-handle-new-blocks-represn.patch b/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-Update-LowerOpenCL-pass-to-handle-new-blocks-represn.patch
deleted file mode 100644
index 4a528674..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-Update-LowerOpenCL-pass-to-handle-new-blocks-represn.patch
+++ /dev/null
@@ -1,1119 +0,0 @@
-From 9ce0fe02fd6cda5fb29fbb0d5037a1798a810b8a Mon Sep 17 00:00:00 2001
-From: Alexey Sotkin <alexey.sotkin@intel.com>
-Date: Thu, 21 Feb 2019 17:14:36 +0300
-Subject: [PATCH 1/3] Update LowerOpenCL pass to handle new blocks
- represntation in LLVM IR
-Upstream-Status: Backport
-[https://github.com/KhronosGroup/SPIRV-LLVM-Translator/commit/bd6ddfaf7232cd81c7f2fe9877e66f286731bd8e]
-Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
---
- lib/SPIRV/SPIRVLowerOCLBlocks.cpp         | 413 ++++++++----------------------
- test/global_block.ll                      |  71 ++---
- test/literal-struct.ll                    |  31 ++-
- test/transcoding/block_w_struct_return.ll |  47 ++--
- test/transcoding/enqueue_kernel.ll        | 237 ++++++++++-------
- 5 files changed, 317 insertions(+), 482 deletions(-)
-diff --git a/lib/SPIRV/SPIRVLowerOCLBlocks.cpp b/lib/SPIRV/SPIRVLowerOCLBlocks.cpp
-index 50e1838..b42a4ec 100644
--- a/lib/SPIRV/SPIRVLowerOCLBlocks.cpp
-+++ b/lib/SPIRV/SPIRVLowerOCLBlocks.cpp
-@@ -1,303 +1,110 @@
-//===- SPIRVLowerOCLBlocks.cpp - OCL Utilities ----------------------------===//
-//
-//                     The LLVM/SPIRV Translator
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-// Copyright (c) 2018 Intel Corporation. All rights reserved.
-//
-// Permission is hereby granted, free of charge, to any person obtaining a
-// copy of this software and associated documentation files (the "Software"),
-// to deal with the Software without restriction, including without limitation
-// the rights to use, copy, modify, merge, publish, distribute, sublicense,
-// and/or sell copies of the Software, and to permit persons to whom the
-// Software is furnished to do so, subject to the following conditions:
-//
-// Redistributions of source code must retain the above copyright notice,
-// this list of conditions and the following disclaimers.
-// Redistributions in binary form must reproduce the above copyright notice,
-// this list of conditions and the following disclaimers in the documentation
-// and/or other materials provided with the distribution.
-// Neither the names of Intel Corporation, nor the names of its
-// contributors may be used to endorse or promote products derived from this
-// Software without specific prior written permission.
-// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-// CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS WITH
-// THE SOFTWARE.
-//
-//===----------------------------------------------------------------------===//
-//
-// SPIR-V specification doesn't allow function pointers, so SPIR-V translator
-// is designed to fail if a value with function type (except calls) is occured.
-// Currently there is only two cases, when function pointers are generating in
-// LLVM IR in OpenCL - block calls and device side enqueue built-in calls.
-//
-// In both cases values with function type used as intermediate representation
-// for block literal structure.
-//
-// This pass is designed to find such cases and simplify them to avoid any
-// function pointer types occurrences in LLVM IR in 4 steps.
-//
-// 1. Find all function pointer allocas, like
-//      %block = alloca void () *
-//
-//    Then find a single store to that alloca:
-//      %blockLit = alloca <{ i32, i32, ...}>, align 4
-//      %0 = bitcast <{ i32, i32, ... }>* %blockLit to void ()*
-//    > store void ()* %0, void ()** %block, align 4
-//
-//    And replace the alloca users by new instructions which used stored value
-//    %blockLit itself instead of function pointer alloca %block.
-//
-// 2. Find consecutive casts from block literal type to i8 addrspace(4)*
-//    used function pointers as an intermediate type:
-//      %0 = bitcast <{ i32, i32 }> %block to void() *
-//      %1 = addrspacecast void() * %0 to i8 addrspace(4)*
-//    And simplify them:
-//      %2 = addrspacecast <{ i32, i32 }> %block to i8 addrspace(4)*
-//
-// 3. Find all unused instructions with function pointer type occured after
-//    pp.1-2 and remove them.
-//
-// 4. Find unused globals with function pointer type, like
-//    @block = constant void ()*
-//             bitcast ({ i32, i32 }* @__block_literal_global to void ()*
-//
-//    And remove them.
-//
-//===----------------------------------------------------------------------===//
-#define DEBUG_TYPE "spv-lower-ocl-blocks"
-
-#include "OCLUtil.h"
-#include "SPIRVInternal.h"
-
-#include "llvm/ADT/SetVector.h"
-#include "llvm/Analysis/ValueTracking.h"
-#include "llvm/IR/GlobalVariable.h"
-#include "llvm/IR/InstIterator.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Pass.h"
-#include "llvm/PassSupport.h"
-#include "llvm/Support/Casting.h"
-
-using namespace llvm;
-
-namespace {
-
-static void
-removeUnusedFunctionPtrInst(Instruction *I,
-                            SmallSetVector<Instruction *, 16> &FuncPtrInsts) {
-  for (unsigned OpIdx = 0, Ops = I->getNumOperands(); OpIdx != Ops; ++OpIdx) {
-    Instruction *OpI = dyn_cast<Instruction>(I->getOperand(OpIdx));
-    I->setOperand(OpIdx, nullptr);
-    if (OpI && OpI != I && OpI->user_empty())
-      FuncPtrInsts.insert(OpI);
-  }
-  I->eraseFromParent();
-}
-
-static bool isFuncPtrAlloca(const AllocaInst *AI) {
-  auto *ET = dyn_cast<PointerType>(AI->getAllocatedType());
-  return ET && ET->getElementType()->isFunctionTy();
-}
-
-static bool hasFuncPtrType(const Value *V) {
-  auto *PT = dyn_cast<PointerType>(V->getType());
-  return PT && PT->getElementType()->isFunctionTy();
-}
-
-static bool isFuncPtrInst(const Instruction *I) {
-  if (auto *AI = dyn_cast<AllocaInst>(I))
-    return isFuncPtrAlloca(AI);
-
-  for (auto &Op : I->operands()) {
-    if (auto *AI = dyn_cast<AllocaInst>(Op))
-      return isFuncPtrAlloca(AI);
-
-    auto *OpI = dyn_cast<Instruction>(&Op);
-    if (OpI && OpI != I && hasFuncPtrType(OpI))
-      return true;
-  }
-  return false;
-}
-
-static StoreInst *findSingleStore(AllocaInst *AI) {
-  StoreInst *Store = nullptr;
-  for (auto *U : AI->users()) {
-    if (!isa<StoreInst>(U))
-      continue; // not a store
-    if (Store)
-      return nullptr; // there are more than one stores
-    Store = dyn_cast<StoreInst>(U);
-  }
-  return Store;
-}
-
-static void fixFunctionPtrAllocaUsers(AllocaInst *AI) {
-  // Find and remove a single store to alloca
-  auto *SingleStore = findSingleStore(AI);
-  assert(SingleStore && "More than one store to the function pointer alloca");
-  auto *StoredVal = SingleStore->getValueOperand();
-  SingleStore->eraseFromParent();
-
-  // Find loads from the alloca and replace thier users
-  for (auto *U : AI->users()) {
-    auto *LI = dyn_cast<LoadInst>(U);
-    if (!LI)
-      continue;
-
-    for (auto *U : LI->users()) {
-      auto *UInst = cast<Instruction>(U);
-      auto *Cast = CastInst::CreatePointerBitCastOrAddrSpaceCast(
-          StoredVal, UInst->getType(), "", UInst);
-      UInst->replaceAllUsesWith(Cast);
-    }
-  }
-}
-
-static int getBlockLiteralIdx(const Function &F) {
-  StringRef FName = F.getName();
-  if (isEnqueueKernelBI(FName))
-    return FName.contains("events") ? 7 : 4;
-  if (isKernelQueryBI(FName))
-    return FName.contains("for_ndrange") ? 2 : 1;
-  if (FName.startswith("__") && FName.contains("_block_invoke"))
-    return F.hasStructRetAttr() ? 1 : 0;
-
-  return -1; // No block literal argument
-}
-
-static bool hasBlockLiteralArg(const Function &F) {
-  return getBlockLiteralIdx(F) != -1;
-}
-
-static bool simplifyFunctionPtrCasts(Function &F) {
-  bool Changed = false;
-  int BlockLiteralIdx = getBlockLiteralIdx(F);
-  for (auto *U : F.users()) {
-    auto *Call = dyn_cast<CallInst>(U);
-    if (!Call)
-      continue;
-    if (Call->getFunction()->getName() == F.getName().str() + "_kernel")
-      continue; // Skip block invoke function calls inside block invoke kernels
-
-    const DataLayout &DL = F.getParent()->getDataLayout();
-    auto *BlockLiteral = Call->getOperand(BlockLiteralIdx);
-    auto *BlockLiteralVal = GetUnderlyingObject(BlockLiteral, DL);
-    if (isa<GlobalVariable>(BlockLiteralVal))
-      continue; // nothing to do with globals
-
-    auto *BlockLiteralAlloca = cast<AllocaInst>(BlockLiteralVal);
-    assert(!BlockLiteralAlloca->getAllocatedType()->isFunctionTy() &&
-           "Function type shouldn't be there");
-
-    auto *NewBlockLiteral = CastInst::CreatePointerBitCastOrAddrSpaceCast(
-        BlockLiteralAlloca, BlockLiteral->getType(), "", Call);
-    BlockLiteral->replaceAllUsesWith(NewBlockLiteral);
-    Changed |= true;
-  }
-  return Changed;
-}
-
-static void
-findFunctionPtrAllocas(Module &M,
-                       SmallVectorImpl<AllocaInst *> &FuncPtrAllocas) {
-  for (auto &F : M) {
-    if (F.isDeclaration())
-      continue;
-    for (auto &I : instructions(F)) {
-      auto *AI = dyn_cast<AllocaInst>(&I);
-      if (!AI || !isFuncPtrAlloca(AI))
-        continue;
-      FuncPtrAllocas.push_back(AI);
-    }
-  }
-}
-
-static void
-findUnusedFunctionPtrInsts(Module &M,
-                           SmallSetVector<Instruction *, 16> &FuncPtrInsts) {
-  for (auto &F : M) {
-    if (F.isDeclaration())
-      continue;
-    for (auto &I : instructions(F))
-      if (I.user_empty() && isFuncPtrInst(&I))
-        FuncPtrInsts.insert(&I);
-  }
-}
-
-static void
-findUnusedFunctionPtrGlbs(Module &M,
-                          SmallVectorImpl<GlobalVariable *> &FuncPtrGlbs) {
-  for (auto &GV : M.globals()) {
-    if (!GV.user_empty())
-      continue;
-    auto *GVType = dyn_cast<PointerType>(GV.getType()->getElementType());
-    if (GVType && GVType->getElementType()->isFunctionTy())
-      FuncPtrGlbs.push_back(&GV);
-  }
-}
-
-class SPIRVLowerOCLBlocks : public ModulePass {
-
-public:
-  SPIRVLowerOCLBlocks() : ModulePass(ID) {}
-
-  bool runOnModule(Module &M) {
-    bool Changed = false;
-
-    // 1. Find function pointer allocas and fix their users
-    SmallVector<AllocaInst *, 16> FuncPtrAllocas;
-    findFunctionPtrAllocas(M, FuncPtrAllocas);
-
-    Changed |= !FuncPtrAllocas.empty();
-    for (auto *AI : FuncPtrAllocas)
-      fixFunctionPtrAllocaUsers(AI);
-
-    // 2. Simplify consecutive casts which use function pointer types
-    for (auto &F : M)
-      if (hasBlockLiteralArg(F))
-        Changed |= simplifyFunctionPtrCasts(F);
-
-    // 3. Cleanup unused instructions with function pointer type
-    // which are occured after pp. 1-2
-    SmallSetVector<Instruction *, 16> FuncPtrInsts;
-    findUnusedFunctionPtrInsts(M, FuncPtrInsts);
-
-    Changed |= !FuncPtrInsts.empty();
-    while (!FuncPtrInsts.empty()) {
-      Instruction *I = FuncPtrInsts.pop_back_val();
-      removeUnusedFunctionPtrInst(I, FuncPtrInsts);
-    }
-
-    // 4. Find and remove unused global variables with function pointer type
-    SmallVector<GlobalVariable *, 16> FuncPtrGlbs;
-    findUnusedFunctionPtrGlbs(M, FuncPtrGlbs);
-
-    Changed |= !FuncPtrGlbs.empty();
-    for (auto *GV : FuncPtrGlbs)
-      GV->eraseFromParent();
-
-    return Changed;
-  }
-
-  static char ID;
-}; // class SPIRVLowerOCLBlocks
-
-char SPIRVLowerOCLBlocks::ID = 0;
-
-} // namespace
-
-INITIALIZE_PASS(
-    SPIRVLowerOCLBlocks, "spv-lower-ocl-blocks",
-    "Remove function pointers occured in case of using OpenCL blocks", false,
-    false)
-
-llvm::ModulePass *llvm::createSPIRVLowerOCLBlocks() {
-  return new SPIRVLowerOCLBlocks();
-}
-+//===- SPIRVLowerOCLBlocks.cpp - OCL Utilities ----------------------------===//
-+//
-+//                     The LLVM/SPIRV Translator
-+//
-+// This file is distributed under the University of Illinois Open Source
-+// License. See LICENSE.TXT for details.
-+//
-+// Copyright (c) 2018 Intel Corporation. All rights reserved.
-+//
-+// Permission is hereby granted, free of charge, to any person obtaining a
-+// copy of this software and associated documentation files (the "Software"),
-+// to deal with the Software without restriction, including without limitation
-+// the rights to use, copy, modify, merge, publish, distribute, sublicense,
-+// and/or sell copies of the Software, and to permit persons to whom the
-+// Software is furnished to do so, subject to the following conditions:
-+//
-+// Redistributions of source code must retain the above copyright notice,
-+// this list of conditions and the following disclaimers.
-+// Redistributions in binary form must reproduce the above copyright notice,
-+// this list of conditions and the following disclaimers in the documentation
-+// and/or other materials provided with the distribution.
-+// Neither the names of Intel Corporation, nor the names of its
-+// contributors may be used to endorse or promote products derived from this
-+// Software without specific prior written permission.
-+// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-+// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-+// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-+// CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-+// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-+// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS WITH
-+// THE SOFTWARE.
-+//
-+//===----------------------------------------------------------------------===//
-+//
-+// SPIR-V specification doesn't allow function pointers, so SPIR-V translator
-+// is designed to fail if a value with function type (except calls) is occured.
-+// Currently there is only two cases, when function pointers are generating in
-+// LLVM IR in OpenCL - block calls and device side enqueue built-in calls.
-+//
-+// In both cases values with function type used as intermediate representation
-+// for block literal structure.
-+//
-+// In LLVM IR produced by clang, blocks are represented with the following
-+// structure:
-+// %struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
-+// Pointers to block invoke functions are stored in the third field. Clang
-+// replaces inderect function calls in all cases except if block is passed as a
-+// function argument. Note that it is somewhat unclear if the OpenCL C spec
-+// should allow passing blocks as function argumernts. This pass is not supposed
-+// to work correctly with such functions.
-+// Clang though has to store function pointers to this structure. Purpose of
-+// this pass is to replace store of function pointers(not allowed in SPIR-V)
-+// with null pointers.
-+//
-+//===----------------------------------------------------------------------===//
-+#define DEBUG_TYPE "spv-lower-ocl-blocks"
-+
-+#include "SPIRVInternal.h"
-+
-+#include "llvm/IR/Module.h"
-+#include "llvm/Pass.h"
-+#include "llvm/Support/Regex.h"
-+
-+using namespace llvm;
-+
-+namespace {
-+
-+static bool isBlockInvoke(Function &F) {
-+  static Regex BlockInvokeRegex("_block_invoke_?[0-9]*$");
-+  return BlockInvokeRegex.match(F.getName());
-+}
-+
-+class SPIRVLowerOCLBlocks : public ModulePass {
-+
-+public:
-+  SPIRVLowerOCLBlocks() : ModulePass(ID) {}
-+
-+  bool runOnModule(Module &M) {
-+    bool Changed = false;
-+    for (Function &F : M) {
-+      if (!isBlockInvoke(F))
-+        continue;
-+      for (User *U : F.users()) {
-+        if (!isa<Constant>(U))
-+          continue;
-+        Constant *Null = Constant::getNullValue(U->getType());
-+        if (U != Null) {
-+          U->replaceAllUsesWith(Null);
-+          Changed = true;
-+        }
-+      }
-+    }
-+    return Changed;
-+  }
-+
-+  static char ID;
-+};
-+
-+char SPIRVLowerOCLBlocks::ID = 0;
-+
-+} // namespace
-+
-+INITIALIZE_PASS(
-+    SPIRVLowerOCLBlocks, "spv-lower-ocl-blocks",
-+    "Remove function pointers occured in case of using OpenCL blocks", false,
-+    false)
-+
-+llvm::ModulePass *llvm::createSPIRVLowerOCLBlocks() {
-+  return new SPIRVLowerOCLBlocks();
-+}
-diff --git a/test/global_block.ll b/test/global_block.ll
-index a9267d8..efb4cf3 100644
--- a/test/global_block.ll
-+++ b/test/global_block.ll
-@@ -16,7 +16,7 @@
- ; RUN: llvm-spirv %t.bc -o %t.spv
- ; RUN: llvm-spirv -r %t.spv -o - | llvm-dis | FileCheck %s --check-prefix=CHECK-LLVM
- 
-target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-n8:16:32:64"
-+target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
- target triple = "spir-unknown-unknown"
- 
- ; CHECK-SPIRV: Name [[block_invoke:[0-9]+]] "_block_invoke"
-@@ -26,71 +26,56 @@ target triple = "spir-unknown-unknown"
- ; CHECK-SPIRV: TypePointer [[int8Ptr:[0-9]+]] 8 [[int8]]
- ; CHECK-SPIRV: TypeFunction [[block_invoke_type:[0-9]+]] [[int]] [[int8Ptr]] [[int]]
- 
-;; This variable is not needed in SPIRV
-; CHECK-SPIRV-NOT: Name {{[0-9]+}} block_kernel.b1
-; CHECK-LLVM-NOT: @block_kernel.b1
-@block_kernel.b1 = internal addrspace(2) constant i32 (i32) addrspace(4)* addrspacecast (i32 (i32) addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to i32 (i32) addrspace(1)*) to i32 (i32) addrspace(4)*), align 8
-+%struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
- 
-@__block_literal_global = internal addrspace(1) constant { i32, i32 } { i32 8, i32 4 }, align 4
-+@block_kernel.b1 = internal addrspace(2) constant %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), align 4
-+@__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (i32 (i8 addrspace(4)*, i32)* @_block_invoke to i8*) to i8 addrspace(4)*) }, align 4
- 
-; Function Attrs: convergent nounwind
-define spir_kernel void @block_kernel(i32 addrspace(1)* %res) #0 !kernel_arg_addr_space !4 !kernel_arg_access_qual !5 !kernel_arg_type !6 !kernel_arg_base_type !6 !kernel_arg_type_qual !7 {
-+; Function Attrs: convergent noinline nounwind optnone
-+define spir_kernel void @block_kernel(i32 addrspace(1)* %res) #0 !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
- entry:
-  %res.addr = alloca i32 addrspace(1)*, align 8
-  store i32 addrspace(1)* %res, i32 addrspace(1)** %res.addr, align 8, !tbaa !10
-
-+  %res.addr = alloca i32 addrspace(1)*, align 4
-+  store i32 addrspace(1)* %res, i32 addrspace(1)** %res.addr, align 4
- ; CHECK-SPIRV: FunctionCall [[int]] {{[0-9]+}} [[block_invoke]] {{[0-9]+}} [[five]]
- ; CHECK-LLVM: %call = call spir_func i32 @_block_invoke(i8 addrspace(4)* {{.*}}, i32 5)
-  %call = call spir_func i32 @_block_invoke(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*), i32 5) #2
-
-  %0 = load i32 addrspace(1)*, i32 addrspace(1)** %res.addr, align 8, !tbaa !10
-  store i32 %call, i32 addrspace(1)* %0, align 4, !tbaa !14
-+  %call = call spir_func i32 @_block_invoke(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*), i32 5) #2
-+  %0 = load i32 addrspace(1)*, i32 addrspace(1)** %res.addr, align 4
-+  store i32 %call, i32 addrspace(1)* %0, align 4
-   ret void
- }
- 
-; CHECK-SPIRV: 5 Function [[int]] [[block_invoke]] 0 [[block_invoke_type]]
-+; CHECK-SPIRV: 5 Function [[int]] [[block_invoke]] 2 [[block_invoke_type]]
- ; CHECK-SPIRV-NEXT: 3 FunctionParameter [[int8Ptr]] {{[0-9]+}}
- ; CHECK-SPIRV-NEXT: 3 FunctionParameter [[int]] {{[0-9]+}}
- ; CHECK-LLVM: define internal spir_func i32 @_block_invoke(i8 addrspace(4)* {{.*}}, i32 %{{.*}})
-; Function Attrs: convergent nounwind
-+; Function Attrs: convergent noinline nounwind optnone
- define internal spir_func i32 @_block_invoke(i8 addrspace(4)* %.block_descriptor, i32 %i) #1 {
- entry:
-  %.block_descriptor.addr = alloca i8 addrspace(4)*, align 8
-+  %.block_descriptor.addr = alloca i8 addrspace(4)*, align 4
-   %i.addr = alloca i32, align 4
-  store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 8
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32 }> addrspace(4)*
-  store i32 %i, i32* %i.addr, align 4, !tbaa !14
-  %0 = load i32, i32* %i.addr, align 4, !tbaa !14
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*, align 4
-+  store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 4
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*
-+  store i32 %i, i32* %i.addr, align 4
-+  store <{ i32, i32, i8 addrspace(4)* }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)* }> addrspace(4)** %block.addr, align 4
-+  %0 = load i32, i32* %i.addr, align 4
-   %add = add nsw i32 %0, 1
-   ret i32 %add
- }
- 
-attributes #0 = { convergent nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #1 = { convergent nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #1 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
- attributes #2 = { convergent }
- 
- !llvm.module.flags = !{!0}
-!opencl.enable.FP_CONTRACT = !{}
- !opencl.ocl.version = !{!1}
- !opencl.spir.version = !{!1}
-!opencl.used.extensions = !{!2}
-!opencl.used.optional.core.features = !{!2}
-!opencl.compiler.options = !{!2}
-!llvm.ident = !{!3}
-+!llvm.ident = !{!2}
- 
- !0 = !{i32 1, !"wchar_size", i32 4}
- !1 = !{i32 2, i32 0}
-!2 = !{}
-!3 = !{!"clang version 7.0.0"}
-!4 = !{i32 1}
-!5 = !{!"none"}
-!6 = !{!"int*"}
-!7 = !{!""}
-!8 = !{i1 false}
-!9 = !{i32 0}
-!10 = !{!11, !11, i64 0}
-!11 = !{!"any pointer", !12, i64 0}
-!12 = !{!"omnipotent char", !13, i64 0}
-!13 = !{!"Simple C/C++ TBAA"}
-!14 = !{!15, !15, i64 0}
-!15 = !{!"int", !12, i64 0}
-+!2 = !{!"clang version 9.0.0 (https://llvm.org/git/clang 04fb8964a801a5c5d7baa5a22272243a7d183896) (https://llvm.org/git/llvm 384f64397f6ad95a361b72d62c07d7bac9f24163)"}
-+!3 = !{i32 1}
-+!4 = !{!"none"}
-+!5 = !{!"int*"}
-+!6 = !{!""}
-diff --git a/test/literal-struct.ll b/test/literal-struct.ll
-index c52170a..52a731a 100644
--- a/test/literal-struct.ll
-+++ b/test/literal-struct.ll
-@@ -2,7 +2,7 @@
- ; structs, i.e. structs whose type has no name. Typicaly clang generate such
- ; structs if the kernel contains OpenCL 2.0 blocks. The IR was produced with
- ; the following command:
-; clang -cc1 -triple spir -cl-std=cl2.0 -O0 -finclude-default-header literal-struct.cl -emit-llvm -o test/literal-struct.ll
-+; clang -cc1 -triple spir -cl-std=cl2.0 -O0 literal-struct.cl -emit-llvm -o test/literal-struct.ll
- 
- ; literal-struct.cl:
- ; void foo()
-@@ -14,25 +14,28 @@
- ; RUN: llvm-as < %s | llvm-spirv -spirv-text -o %t
- ; RUN: FileCheck < %t %s
- 
-; CHECK-DAG: TypeInt [[Int:[0-9]+]] 32 0
-; CHECK-DAG: TypeStruct [[StructType:[0-9]+]] [[Int]] [[Int]] {{$}}
-+; CHECK: TypeInt [[Int:[0-9]+]] 32 0
-+; CHECK: TypeInt [[Int8:[0-9]+]] 8 0
-+; CHECK: TypePointer [[Int8Ptr:[0-9]+]] 8 [[Int8]]
-+; CHECK: TypeStruct [[StructType:[0-9]+]] [[Int]] [[Int]] [[Int8Ptr]]
- 
- target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
- target triple = "spir"
- 
-@__block_literal_global = internal addrspace(1) constant { i32, i32 } { i32 8, i32 4 }, align 4
-+%struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
-+
-+@__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__foo_block_invoke to i8*) to i8 addrspace(4)*) }, align 4
- ; CHECK: ConstantComposite [[StructType]]
- 
-; This is artificial case is added to cover ConstantNull instrucitions with TypeStruct.
-@__block_literal_global.1 = internal addrspace(1) constant { i32, i32 } zeroinitializer, align 4
-+@__block_literal_global.1 = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } zeroinitializer, align 4
- ; CHECK: ConstantNull [[StructType]]
- 
- ; Function Attrs: convergent noinline nounwind optnone
- define spir_func void @foo() #0 {
- entry:
-  %myBlock = alloca void () addrspace(4)*, align 4
-  store void () addrspace(4)* addrspacecast (void () addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to void () addrspace(1)*) to void () addrspace(4)*), void () addrspace(4)** %myBlock, align 4
-  call spir_func void @__foo_block_invoke(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*)) #1
-+  %myBlock = alloca %struct.__opencl_block_literal_generic addrspace(4)*, align 4
-+  store %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), %struct.__opencl_block_literal_generic addrspace(4)** %myBlock, align 4
-+  call spir_func void @__foo_block_invoke(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*)) #1
-   ret void
- }
- 
-@@ -40,14 +43,14 @@ entry:
- define internal spir_func void @__foo_block_invoke(i8 addrspace(4)* %.block_descriptor) #0 {
- entry:
-   %.block_descriptor.addr = alloca i8 addrspace(4)*, align 4
-  %block.addr = alloca <{ i32, i32 }> addrspace(4)*, align 4
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*, align 4
-   store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 4
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32 }> addrspace(4)*
-  store <{ i32, i32 }> addrspace(4)* %block, <{ i32, i32 }> addrspace(4)** %block.addr, align 4
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*
-+  store <{ i32, i32, i8 addrspace(4)* }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)* }> addrspace(4)** %block.addr, align 4
-   ret void
- }
- 
-attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
- attributes #1 = { convergent }
- 
- !llvm.module.flags = !{!0}
-@@ -57,4 +60,4 @@ attributes #1 = { convergent }
- 
- !0 = !{i32 1, !"wchar_size", i32 4}
- !1 = !{i32 2, i32 0}
-!2 = !{!"clang version 8.0.0 "}
-+!2 = !{!"clang version 9.0.0 (https://llvm.org/git/clang 04fb8964a801a5c5d7baa5a22272243a7d183896) (https://llvm.org/git/llvm 384f64397f6ad95a361b72d62c07d7bac9f24163)"}
-diff --git a/test/transcoding/block_w_struct_return.ll b/test/transcoding/block_w_struct_return.ll
-index 76e29f0..df89b13 100644
--- a/test/transcoding/block_w_struct_return.ll
-+++ b/test/transcoding/block_w_struct_return.ll
-@@ -16,6 +16,8 @@
- ;   res[tid] = kernelBlock(aa).a - 6;
- ; }
- 
-+; clang -cc1 -triple spir -cl-std=cl2.0 -disable-llvm-passes -finclude-default-header block_w_struct_return.cl -emit-llvm -o test/transcoding/block_w_struct_return.ll
-+
- ; RUN: llvm-as %s -o %t.bc
- ; RUN: llvm-spirv %t.bc -spirv-text -o %t.spv.txt
- ; RUN: FileCheck < %t.spv.txt %s --check-prefix=CHECK-SPIRV
-@@ -27,12 +29,14 @@
- ; CHECK-SPIRV: Name [[BlockInv:[0-9]+]] "__block_ret_struct_block_invoke"
- 
- ; CHECK-SPIRV: 4 TypeInt [[IntTy:[0-9]+]] 32
-+; CHECK-SPIRV: 4 TypeInt [[Int8Ty:[0-9]+]] 8
-+; CHECK-SPIRV: 4 TypePointer [[Int8Ptr:[0-9]+]] 8 [[Int8Ty]]
- ; CHECK-SPIRV: 3 TypeStruct [[StructTy:[0-9]+]] [[IntTy]]
- ; CHECK-SPIRV: 4 TypePointer [[StructPtrTy:[0-9]+]] 7 [[StructTy]]
- 
- ; CHECK-SPIRV: 4 Variable [[StructPtrTy]] [[StructArg:[0-9]+]] 7
- ; CHECK-SPIRV: 4 Variable [[StructPtrTy]] [[StructRet:[0-9]+]] 7
-; CHECK-SPIRV: 4 PtrCastToGeneric {{[0-9]+}} [[BlockLit:[0-9]+]] {{[0-9]+}}
-+; CHECK-SPIRV: 4 PtrCastToGeneric [[Int8Ptr]] [[BlockLit:[0-9]+]] {{[0-9]+}}
- ; CHECK-SPIRV: 7 FunctionCall {{[0-9]+}} {{[0-9]+}} [[BlockInv]] [[StructRet]] [[BlockLit]] [[StructArg]]
- 
- ; CHECK-LLVM: %[[StructA:.*]] = type { i32 }
-@@ -41,20 +45,21 @@
- target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
- target triple = "spir64-unknown-unknown"
- 
-+%struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
- %struct.A = type { i32 }
- 
-@__block_literal_global = internal addrspace(1) constant { i32, i32 } { i32 8, i32 4 }, align 4
-+@__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 16, i32 8, i8 addrspace(4)* addrspacecast (i8* bitcast (void (%struct.A*, i8 addrspace(4)*, %struct.A*)* @__block_ret_struct_block_invoke to i8*) to i8 addrspace(4)*) }, align 8
- 
- ; Function Attrs: convergent noinline nounwind optnone
-define spir_kernel void @block_ret_struct(i32 addrspace(1)* %res) #0 !kernel_arg_addr_space !4 !kernel_arg_access_qual !5 !kernel_arg_type !6 !kernel_arg_base_type !6 !kernel_arg_type_qual !7 !kernel_arg_host_accessible !8 !kernel_arg_pipe_depth !9 !kernel_arg_pipe_io !7 !kernel_arg_buffer_location !7 {
-+define spir_kernel void @block_ret_struct(i32 addrspace(1)* %res) #0 !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
- entry:
-   %res.addr = alloca i32 addrspace(1)*, align 8
-  %kernelBlock = alloca void (%struct.A*, %struct.A*) addrspace(4)*, align 8
-+  %kernelBlock = alloca %struct.__opencl_block_literal_generic addrspace(4)*, align 8
-   %tid = alloca i64, align 8
-   %aa = alloca %struct.A, align 4
-   %tmp = alloca %struct.A, align 4
-   store i32 addrspace(1)* %res, i32 addrspace(1)** %res.addr, align 8
-  store void (%struct.A*, %struct.A*) addrspace(4)* addrspacecast (void (%struct.A*, %struct.A*) addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to void (%struct.A*, %struct.A*) addrspace(1)*) to void (%struct.A*, %struct.A*) addrspace(4)*), void (%struct.A*, %struct.A*) addrspace(4)** %kernelBlock, align 8
-+  store %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), %struct.__opencl_block_literal_generic addrspace(4)** %kernelBlock, align 8
-   %call = call spir_func i64 @_Z13get_global_idj(i32 0) #4
-   store i64 %call, i64* %tid, align 8
-   %0 = load i32 addrspace(1)*, i32 addrspace(1)** %res.addr, align 8
-@@ -63,7 +68,7 @@ entry:
-   store i32 -1, i32 addrspace(1)* %arrayidx, align 4
-   %a = getelementptr inbounds %struct.A, %struct.A* %aa, i32 0, i32 0
-   store i32 5, i32* %a, align 4
-  call spir_func void @__block_ret_struct_block_invoke(%struct.A* sret %tmp, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*), %struct.A* byval align 4 %aa) #5
-+  call spir_func void @__block_ret_struct_block_invoke(%struct.A* sret %tmp, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*), %struct.A* byval align 4 %aa) #5
-   %a1 = getelementptr inbounds %struct.A, %struct.A* %tmp, i32 0, i32 0
-   %2 = load i32, i32* %a1, align 4
-   %sub = sub nsw i32 %2, 6
-@@ -78,10 +83,10 @@ entry:
- define internal spir_func void @__block_ret_struct_block_invoke(%struct.A* noalias sret %agg.result, i8 addrspace(4)* %.block_descriptor, %struct.A* byval align 4 %a) #1 {
- entry:
-   %.block_descriptor.addr = alloca i8 addrspace(4)*, align 8
-  %block.addr = alloca <{ i32, i32 }> addrspace(4)*, align 8
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*, align 8
-   store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 8
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32 }> addrspace(4)*
-  store <{ i32, i32 }> addrspace(4)* %block, <{ i32, i32 }> addrspace(4)** %block.addr, align 8
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*
-+  store <{ i32, i32, i8 addrspace(4)* }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)* }> addrspace(4)** %block.addr, align 8
-   %a1 = getelementptr inbounds %struct.A, %struct.A* %a, i32 0, i32 0
-   store i32 6, i32* %a1, align 4
-   %0 = bitcast %struct.A* %agg.result to i8*
-@@ -96,30 +101,22 @@ declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture r
- ; Function Attrs: convergent nounwind readnone
- declare spir_func i64 @_Z13get_global_idj(i32) #3
- 
-attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #1 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #1 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
- attributes #2 = { argmemonly nounwind }
- attributes #3 = { convergent nounwind readnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
- attributes #4 = { convergent nounwind readnone }
- attributes #5 = { convergent }
- 
- !llvm.module.flags = !{!0}
-!opencl.enable.FP_CONTRACT = !{}
- !opencl.ocl.version = !{!1}
- !opencl.spir.version = !{!1}
-!opencl.used.extensions = !{!2}
-!opencl.used.optional.core.features = !{!2}
-!opencl.compiler.options = !{!2}
-!llvm.ident = !{!3}
-+!llvm.ident = !{!2}
- 
- !0 = !{i32 1, !"wchar_size", i32 4}
- !1 = !{i32 2, i32 0}
-!2 = !{}
-!3 = !{!"clang version 7.0.0"}
-!4 = !{i32 1}
-!5 = !{!"none"}
-!6 = !{!"int*"}
-!7 = !{!""}
-!8 = !{i1 false}
-!9 = !{i32 0}
-
-+!2 = !{!"clang version 9.0.0 (https://llvm.org/git/clang 04fb8964a801a5c5d7baa5a22272243a7d183896) (https://llvm.org/git/llvm 384f64397f6ad95a361b72d62c07d7bac9f24163)"}
-+!3 = !{i32 1}
-+!4 = !{!"none"}
-+!5 = !{!"int*"}
-+!6 = !{!""}
-diff --git a/test/transcoding/enqueue_kernel.ll b/test/transcoding/enqueue_kernel.ll
-index 0d29c71..435871d 100644
--- a/test/transcoding/enqueue_kernel.ll
-+++ b/test/transcoding/enqueue_kernel.ll
-@@ -51,11 +51,12 @@
- ; ModuleID = 'enqueue_kernel.cl'
- source_filename = "enqueue_kernel.cl"
- target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
-target triple = "spir-unknown-unknown"
-+target triple = "spir"
- 
- %opencl.queue_t = type opaque
- %struct.ndrange_t = type { i32 }
- %opencl.clk_event_t = type opaque
-+%struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
- 
- ; CHECK-SPIRV: EntryPoint {{[0-9]+}} [[BlockKer1:[0-9]+]] "__device_side_enqueue_block_invoke_kernel"
- ; CHECK-SPIRV: EntryPoint {{[0-9]+}} [[BlockKer2:[0-9]+]] "__device_side_enqueue_block_invoke_2_kernel"
-@@ -66,89 +67,123 @@ target triple = "spir-unknown-unknown"
- 
- ; CHECK-SPIRV: TypeInt [[Int32Ty:[0-9]+]] 32
- ; CHECK-SPIRV: TypeInt [[Int8Ty:[0-9]+]] 8
-; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt8:[0-9]+]] 8
- ; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt0:[0-9]+]] 0
-; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt17:[0-9]+]] 17
-+; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt17:[0-9]+]] 21
- ; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt2:[0-9]+]] 2
-; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt20:[0-9]+]] 20
-; CHECK-SPIRV: TypeVoid [[VoidTy:[0-9]+]]
-+; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt8:[0-9]+]] 8
-+; CHECK-SPIRV: Constant [[Int32Ty]] [[ConstInt20:[0-9]+]] 24
- 
- ; CHECK-SPIRV: TypePointer {{[0-9]+}} 7 {{[0-9]+}}
-+; CHECK-SPIRV: TypePointer [[Int8PtrGenTy:[0-9]+]] 8 [[Int8Ty]]
-+; CHECK-SPIRV: TypeVoid [[VoidTy:[0-9]+]]
- ; CHECK-SPIRV: TypePointer [[Int32LocPtrTy:[0-9]+]] 7 [[Int32Ty]]
- ; CHECK-SPIRV: TypeDeviceEvent [[EventTy:[0-9]+]]
-; CHECK-SPIRV: TypePointer [[Int8PtrGenTy:[0-9]+]] 8 [[Int8Ty]]
- ; CHECK-SPIRV: TypePointer [[EventPtrTy:[0-9]+]] 8 [[EventTy]]
- ; CHECK-SPIRV: TypeFunction [[BlockTy1:[0-9]+]] [[VoidTy]] [[Int8PtrGenTy]]
- ; CHECK-SPIRV: TypeFunction [[BlockTy2:[0-9]+]] [[VoidTy]] [[Int8PtrGenTy]]
- ; CHECK-SPIRV: TypeFunction [[BlockTy3:[0-9]+]] [[VoidTy]] [[Int8PtrGenTy]]
- ; CHECK-SPIRV: ConstantNull [[EventPtrTy]] [[EventNull:[0-9]+]]
- 
-; CHECK-LLVM: [[BlockTy1:%[0-9]+]] = type { i32, i32 }
-; CHECK-LLVM: [[BlockTy2:%[0-9]+]] = type <{ i32, i32, i32 addrspace(1)*, i32, i8 }>
-; CHECK-LLVM: [[BlockTy3:%[0-9]+]] = type <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>
-; CHECK-LLVM: [[BlockTy4:%[0-9]+]] = type <{ i32, i32 }>
-+; CHECK-LLVM: [[BlockTy1:%[0-9]+]] = type { i32, i32, i8 addrspace(4)* }
-+; CHECK-LLVM: [[BlockTy2:%[0-9]+]] = type <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>
-+; CHECK-LLVM: [[BlockTy3:%[0-9]+]] = type <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>
-+; CHECK-LLVM: [[BlockTy4:%[0-9]+]] = type <{ i32, i32, i8 addrspace(4)* }>
- 
-; CHECK-LLVM: @__block_literal_global = internal addrspace(1) constant [[BlockTy1]] { i32 8, i32 4 }, align 4
-; CHECK-LLVM: @__block_literal_global.1 = internal addrspace(1) constant [[BlockTy1]] { i32 8, i32 4 }, align 4
-+; CHECK-LLVM: @__block_literal_global = internal addrspace(1) constant [[BlockTy1]] { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* null to i8 addrspace(4)*) }, align 4
-+; CHECK-LLVM: @__block_literal_global.1 = internal addrspace(1) constant [[BlockTy1]] { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* null to i8 addrspace(4)*) }, align 4
- 
-@__block_literal_global = internal addrspace(1) constant { i32, i32 } { i32 8, i32 4 }, align 4
-@__block_literal_global.1 = internal addrspace(1) constant { i32, i32 } { i32 8, i32 4 }, align 4
-+@__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_3 to i8*) to i8 addrspace(4)*) }, align 4
-+@__block_literal_global.1 = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_4 to i8*) to i8 addrspace(4)*) }, align 4
- 
- ; Function Attrs: convergent noinline nounwind optnone
-define spir_kernel void @device_side_enqueue(i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 %i, i8 signext %c0) #0 !kernel_arg_addr_space !4 !kernel_arg_access_qual !5 !kernel_arg_type !6 !kernel_arg_base_type !6 !kernel_arg_type_qual !7 {
-+define spir_kernel void @device_side_enqueue(i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 %i, i8 signext %c0) #0 !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
- entry:
-+  %a.addr = alloca i32 addrspace(1)*, align 4
-+  %b.addr = alloca i32 addrspace(1)*, align 4
-+  %i.addr = alloca i32, align 4
-+  %c0.addr = alloca i8, align 1
-   %default_queue = alloca %opencl.queue_t*, align 4
-   %flags = alloca i32, align 4
-   %ndrange = alloca %struct.ndrange_t, align 4
-   %clk_event = alloca %opencl.clk_event_t*, align 4
-   %event_wait_list = alloca %opencl.clk_event_t*, align 4
-   %event_wait_list2 = alloca [1 x %opencl.clk_event_t*], align 4
-  %block = alloca <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, align 4
-  %block3 = alloca <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, align 4
-+  %block = alloca <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, align 4
-+  %tmp = alloca %struct.ndrange_t, align 4
-+  %block3 = alloca <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, align 4
-+  %tmp4 = alloca %struct.ndrange_t, align 4
-   %c = alloca i8, align 1
-+  %tmp11 = alloca %struct.ndrange_t, align 4
-+  %block_sizes = alloca [1 x i32], align 4
-+  %tmp12 = alloca %struct.ndrange_t, align 4
-+  %block_sizes13 = alloca [3 x i32], align 4
-+  store i32 addrspace(1)* %a, i32 addrspace(1)** %a.addr, align 4
-+  store i32 addrspace(1)* %b, i32 addrspace(1)** %b.addr, align 4
-+  store i32 %i, i32* %i.addr, align 4
-+  store i8 %c0, i8* %c0.addr, align 1
-   store i32 0, i32* %flags, align 4
-   %arrayinit.begin = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0
-   %0 = load %opencl.clk_event_t*, %opencl.clk_event_t** %clk_event, align 4
-   store %opencl.clk_event_t* %0, %opencl.clk_event_t** %arrayinit.begin, align 4
-   %1 = load %opencl.queue_t*, %opencl.queue_t** %default_queue, align 4
-   %2 = load i32, i32* %flags, align 4
-  %block.size = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 0
-  store i32 17, i32* %block.size, align 4
-  %block.align = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 1
-+  %3 = bitcast %struct.ndrange_t* %tmp to i8*
-+  %4 = bitcast %struct.ndrange_t* %ndrange to i8*
-+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %3, i8* align 4 %4, i32 4, i1 false)
-+  %block.size = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 0
-+  store i32 21, i32* %block.size, align 4
-+  %block.align = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 1
-   store i32 4, i32* %block.align, align 4
-  %block.captured = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 2
-  store i32 addrspace(1)* %a, i32 addrspace(1)** %block.captured, align 4
-  %block.captured1 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 3
-  store i32 %i, i32* %block.captured1, align 4
-  %block.captured2 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 4
-  store i8 %c0, i8* %block.captured2, align 4
-  %3 = bitcast <{ i32, i32, i32 addrspace(1)*, i32, i8 }>* %block to void ()*
-  %4 = addrspacecast void ()* %3 to i8 addrspace(4)*
-+  %block.invoke = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 2
-+  store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke, align 4
-+  %block.captured = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 3
-+  %5 = load i32 addrspace(1)*, i32 addrspace(1)** %a.addr, align 4
-+  store i32 addrspace(1)* %5, i32 addrspace(1)** %block.captured, align 4
-+  %block.captured1 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 4
-+  %6 = load i32, i32* %i.addr, align 4
-+  store i32 %6, i32* %block.captured1, align 4
-+  %block.captured2 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block, i32 0, i32 5
-+  %7 = load i8, i8* %c0.addr, align 1
-+  store i8 %7, i8* %block.captured2, align 4
-+  %8 = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>* %block to %struct.__opencl_block_literal_generic*
-+  %9 = addrspacecast %struct.__opencl_block_literal_generic* %8 to i8 addrspace(4)*
- 
- ; CHECK-SPIRV: PtrCastToGeneric [[Int8PtrGenTy]] [[BlockLit1:[0-9]+]]
- ; CHECK-SPIRV: EnqueueKernel [[Int32Ty]] {{[0-9]+}} {{[0-9]+}} {{[0-9]+}} {{[0-9]+}}
- ;                            [[ConstInt0]] [[EventNull]] [[EventNull]]
- ;                            [[BlockKer1]] [[BlockLit1]] [[ConstInt17]] [[ConstInt8]]
- 
-; CHECK-LLVM: [[Block2:%[0-9]+]] = addrspacecast [[BlockTy2]]* %block to i8 addrspace(4)*
-+; CHECK-LLVM: [[Block2:%[0-9]+]] = bitcast [[BlockTy2]]* %block to %struct.__opencl_block_literal_generic*
-+; CHECK-LLVM: [[Block2Ptr:%[0-9]+]] = addrspacecast %struct.__opencl_block_literal_generic* [[Block2]] to i8 addrspace(4)*
- ; CHECK-LLVM: [[BlockInv2:%[0-9]+]] = addrspacecast void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_kernel to i8 addrspace(4)*
-; CHECK-LLVM: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* {{.*}}, i32 {{.*}}, %struct.ndrange_t* {{.*}}, i32 0, %opencl.clk_event_t* addrspace(4)* null, %opencl.clk_event_t* addrspace(4)* null, i8 addrspace(4)* [[BlockInv2]], i8 addrspace(4)* [[Block2]])
-
-  %5 = call i32 @__enqueue_kernel_basic(%opencl.queue_t* %1, i32 %2, %struct.ndrange_t* byval %ndrange, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* %4)
-  %6 = addrspacecast %opencl.clk_event_t** %event_wait_list to %opencl.clk_event_t* addrspace(4)*
-  %7 = addrspacecast %opencl.clk_event_t** %clk_event to %opencl.clk_event_t* addrspace(4)*
-  %block.size5 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 0
-  store i32 20, i32* %block.size5, align 4
-  %block.align6 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 1
-+; CHECK-LLVM: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* {{.*}}, i32 {{.*}}, %struct.ndrange_t* {{.*}}, i32 0, %opencl.clk_event_t* addrspace(4)* null, %opencl.clk_event_t* addrspace(4)* null, i8 addrspace(4)* [[BlockInv2]], i8 addrspace(4)* [[Block2Ptr]])
-+
-+  %10 = call i32 @__enqueue_kernel_basic(%opencl.queue_t* %1, i32 %2, %struct.ndrange_t* byval %tmp, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* %9)
-+  %11 = load %opencl.queue_t*, %opencl.queue_t** %default_queue, align 4
-+  %12 = load i32, i32* %flags, align 4
-+  %13 = bitcast %struct.ndrange_t* %tmp4 to i8*
-+  %14 = bitcast %struct.ndrange_t* %ndrange to i8*
-+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %13, i8* align 4 %14, i32 4, i1 false)
-+  %15 = addrspacecast %opencl.clk_event_t** %event_wait_list to %opencl.clk_event_t* addrspace(4)*
-+  %16 = addrspacecast %opencl.clk_event_t** %clk_event to %opencl.clk_event_t* addrspace(4)*
-+  %block.size5 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 0
-+  store i32 24, i32* %block.size5, align 4
-+  %block.align6 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 1
-   store i32 4, i32* %block.align6, align 4
-  %block.captured7 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 2
-  store i32 addrspace(1)* %a, i32 addrspace(1)** %block.captured7, align 4
-  %block.captured8 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 3
-  store i32 %i, i32* %block.captured8, align 4
-  %block.captured9 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 4
-  store i32 addrspace(1)* %b, i32 addrspace(1)** %block.captured9, align 4
-  %8 = bitcast <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3 to void ()*
-  %9 = addrspacecast void ()* %8 to i8 addrspace(4)*
-+  %block.invoke7 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 2
-+  store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_2 to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke7, align 4
-+  %block.captured8 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 3
-+  %17 = load i32 addrspace(1)*, i32 addrspace(1)** %a.addr, align 4
-+  store i32 addrspace(1)* %17, i32 addrspace(1)** %block.captured8, align 4
-+  %block.captured9 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 4
-+  %18 = load i32, i32* %i.addr, align 4
-+  store i32 %18, i32* %block.captured9, align 4
-+  %block.captured10 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3, i32 0, i32 5
-+  %19 = load i32 addrspace(1)*, i32 addrspace(1)** %b.addr, align 4
-+  store i32 addrspace(1)* %19, i32 addrspace(1)** %block.captured10, align 4
-+  %20 = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block3 to %struct.__opencl_block_literal_generic*
-+  %21 = addrspacecast %struct.__opencl_block_literal_generic* %20 to i8 addrspace(4)*
-+
- 
- ; CHECK-SPIRV: PtrCastToGeneric [[EventPtrTy]] [[Event1:[0-9]+]]
- ; CHECK-SPIRV: PtrCastToGeneric [[EventPtrTy]] [[Event2:[0-9]+]]
-@@ -158,16 +193,24 @@ entry:
- ;                            [[ConstInt2]] [[Event1]] [[Event2]]
- ;                            [[BlockKer2]] [[BlockLit2]] [[ConstInt20]] [[ConstInt8]]
- 
-; CHECK-LLVM: [[Block3:%[0-9]+]] = addrspacecast [[BlockTy3]]* %block3 to i8 addrspace(4)*
-+; CHECK-LLVM: [[Block3:%[0-9]+]] = bitcast [[BlockTy3]]* %block3 to %struct.__opencl_block_literal_generic*
-+; CHECK-LLVM: [[Block3Ptr:%[0-9]+]] = addrspacecast %struct.__opencl_block_literal_generic* [[Block3]] to i8 addrspace(4)
- ; CHECK-LLVM: [[BlockInv3:%[0-9]+]] = addrspacecast void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_2_kernel to i8 addrspace(4)*
-; CHECK-LLVM: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* {{.*}}, i32 {{.*}}, %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t* addrspace(4)* {{.*}}, %opencl.clk_event_t* addrspace(4)* {{.*}}, i8 addrspace(4)* [[BlockInv3]], i8 addrspace(4)* [[Block3]])
-
-  %10 = call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* %1, i32 %2, %struct.ndrange_t* %ndrange, i32 2, %opencl.clk_event_t* addrspace(4)* %6, %opencl.clk_event_t* addrspace(4)* %7, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_2_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* %9)
-  %11 = alloca [1 x i32]
-  %12 = getelementptr [1 x i32], [1 x i32]* %11, i32 0, i32 0
-  %13 = load i8, i8* %c, align 1
-  %14 = zext i8 %13 to i32
-  store i32 %14, i32* %12, align 4
-+; CHECK-LLVM: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* {{.*}}, i32 {{.*}}, %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t* addrspace(4)* {{.*}}, %opencl.clk_event_t* addrspace(4)* {{.*}}, i8 addrspace(4)* [[BlockInv3]], i8 addrspace(4)* [[Block3Ptr]])
-+
-+  %22 = call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* %11, i32 %12, %struct.ndrange_t* %tmp4, i32 2, %opencl.clk_event_t* addrspace(4)* %15, %opencl.clk_event_t* addrspace(4)* %16, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* @__device_side_enqueue_block_invoke_2_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* %21)
-+  %23 = load %opencl.queue_t*, %opencl.queue_t** %default_queue, align 4
-+  %24 = load i32, i32* %flags, align 4
-+  %25 = bitcast %struct.ndrange_t* %tmp11 to i8*
-+  %26 = bitcast %struct.ndrange_t* %ndrange to i8*
-+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %25, i8* align 4 %26, i32 4, i1 false)
-+  %arraydecay = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0
-+  %27 = addrspacecast %opencl.clk_event_t** %arraydecay to %opencl.clk_event_t* addrspace(4)*
-+  %28 = addrspacecast %opencl.clk_event_t** %clk_event to %opencl.clk_event_t* addrspace(4)*
-+  %29 = getelementptr [1 x i32], [1 x i32]* %block_sizes, i32 0, i32 0
-+  %30 = load i8, i8* %c, align 1
-+  %31 = zext i8 %30 to i32
-+  store i32 %31, i32* %29, align 4
- 
- ; CHECK-SPIRV: PtrAccessChain [[Int32LocPtrTy]] [[LocalBuf31:[0-9]+]]
- ; CHECK-SPIRV: Bitcast {{[0-9]+}} [[BlockLit3Tmp:[0-9]+]] [[BlockGlb1:[0-9]+]]
-@@ -182,14 +225,18 @@ entry:
- ; CHECK-LLVM: [[BlockInv0:%[0-9]+]] = addrspacecast void (i8 addrspace(4)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_3_kernel to i8 addrspace(4)*
- ; CHECK-LLVM: call i32 @__enqueue_kernel_events_varargs(%opencl.queue_t* {{.*}}, i32 {{.*}}, %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t* addrspace(4)* {{.*}}, %opencl.clk_event_t* addrspace(4)* {{.*}}, i8 addrspace(4)* [[BlockInv0]], i8 addrspace(4)* [[Block0]], i32 1, i32* {{.*}})
- 
-  %15 = call i32 @__enqueue_kernel_events_varargs(%opencl.queue_t* %1, i32 %2, %struct.ndrange_t* %ndrange, i32 2, %opencl.clk_event_t* addrspace(4)* %6, %opencl.clk_event_t* addrspace(4)* %7, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_3_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %12)
-  %16 = alloca [3 x i32]
-  %17 = getelementptr [3 x i32], [3 x i32]* %16, i32 0, i32 0
-  store i32 1, i32* %17, align 4
-  %18 = getelementptr [3 x i32], [3 x i32]* %16, i32 0, i32 1
-  store i32 2, i32* %18, align 4
-  %19 = getelementptr [3 x i32], [3 x i32]* %16, i32 0, i32 2
-  store i32 4, i32* %19, align 4
-+  %32 = call i32 @__enqueue_kernel_events_varargs(%opencl.queue_t* %23, i32 %24, %struct.ndrange_t* %tmp11, i32 2, %opencl.clk_event_t* addrspace(4)* %27, %opencl.clk_event_t* addrspace(4)* %28, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_3_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %29)
-+  %33 = load %opencl.queue_t*, %opencl.queue_t** %default_queue, align 4
-+  %34 = load i32, i32* %flags, align 4
-+  %35 = bitcast %struct.ndrange_t* %tmp12 to i8*
-+  %36 = bitcast %struct.ndrange_t* %ndrange to i8*
-+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %35, i8* align 4 %36, i32 4, i1 false)
-+  %37 = getelementptr [3 x i32], [3 x i32]* %block_sizes13, i32 0, i32 0
-+  store i32 1, i32* %37, align 4
-+  %38 = getelementptr [3 x i32], [3 x i32]* %block_sizes13, i32 0, i32 1
-+  store i32 2, i32* %38, align 4
-+  %39 = getelementptr [3 x i32], [3 x i32]* %block_sizes13, i32 0, i32 2
-+  store i32 4, i32* %39, align 4
- 
- ; CHECK-SPIRV: PtrAccessChain [[Int32LocPtrTy]] [[LocalBuf41:[0-9]+]]
- ; CHECK-SPIRV: PtrAccessChain [[Int32LocPtrTy]] [[LocalBuf42:[0-9]+]]
-@@ -206,24 +253,27 @@ entry:
- ; CHECK-LLVM: [[BlockInv1:%[0-9]+]] = addrspacecast void (i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_4_kernel to i8 addrspace(4)*
- ; CHECK-LLVM: call i32 @__enqueue_kernel_events_varargs(%opencl.queue_t* {{.*}}, i32 {{.*}}, %struct.ndrange_t* {{.*}}, i32 0, %opencl.clk_event_t* addrspace(4)* null, %opencl.clk_event_t* addrspace(4)* null, i8 addrspace(4)* [[BlockInv1]], i8 addrspace(4)* [[Block1]], i32 3, i32* {{.*}})
- 
-  %20 = call i32 @__enqueue_kernel_varargs(%opencl.queue_t* %1, i32 %2, %struct.ndrange_t* %ndrange, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_4_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* @__block_literal_global.1 to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3, i32* %17)
-+  %40 = call i32 @__enqueue_kernel_varargs(%opencl.queue_t* %33, i32 %34, %struct.ndrange_t* %tmp12, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*)* @__device_side_enqueue_block_invoke_4_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global.1 to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3, i32* %37)
-   ret void
- }
- 
-+; Function Attrs: argmemonly nounwind
-+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1) #1
-+
- ; Function Attrs: convergent noinline nounwind optnone
- define internal spir_func void @__device_side_enqueue_block_invoke(i8 addrspace(4)* %.block_descriptor) #2 {
- entry:
-   %.block_descriptor.addr = alloca i8 addrspace(4)*, align 4
-  %block.addr = alloca <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)*, align 4
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)*, align 4
-   store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 4
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)*
-  store <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)** %block.addr, align 4
-  %block.capture.addr = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, i32 0, i32 4
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)*
-+  store <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)** %block.addr, align 4
-+  %block.capture.addr = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, i32 0, i32 5
-   %0 = load i8, i8 addrspace(4)* %block.capture.addr, align 4
-   %conv = sext i8 %0 to i32
-  %block.capture.addr1 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, i32 0, i32 2
-+  %block.capture.addr1 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, i32 0, i32 3
-   %1 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %block.capture.addr1, align 4
-  %block.capture.addr2 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, i32 0, i32 3
-+  %block.capture.addr2 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i8 }> addrspace(4)* %block, i32 0, i32 4
-   %2 = load i32, i32 addrspace(4)* %block.capture.addr2, align 4
-   %arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %1, i32 %2
-   store i32 %conv, i32 addrspace(1)* %arrayidx, align 4
-@@ -243,19 +293,19 @@ declare i32 @__enqueue_kernel_basic(%opencl.queue_t*, i32, %struct.ndrange_t*, i
- define internal spir_func void @__device_side_enqueue_block_invoke_2(i8 addrspace(4)* %.block_descriptor) #2 {
- entry:
-   %.block_descriptor.addr = alloca i8 addrspace(4)*, align 4
-  %block.addr = alloca <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)*, align 4
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)*, align 4
-   store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 4
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)*
-  store <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)** %block.addr, align 4
-  %block.capture.addr = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 4
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)*
-+  store <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)** %block.addr, align 4
-+  %block.capture.addr = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 5
-   %0 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %block.capture.addr, align 4
-  %block.capture.addr1 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 3
-+  %block.capture.addr1 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 4
-   %1 = load i32, i32 addrspace(4)* %block.capture.addr1, align 4
-   %arrayidx = getelementptr inbounds i32, i32 addrspace(1)* %0, i32 %1
-   %2 = load i32, i32 addrspace(1)* %arrayidx, align 4
-  %block.capture.addr2 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 2
-+  %block.capture.addr2 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 3
-   %3 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %block.capture.addr2, align 4
-  %block.capture.addr3 = getelementptr inbounds <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 3
-+  %block.capture.addr3 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>, <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }> addrspace(4)* %block, i32 0, i32 4
-   %4 = load i32, i32 addrspace(4)* %block.capture.addr3, align 4
-   %arrayidx4 = getelementptr inbounds i32, i32 addrspace(1)* %3, i32 %4
-   store i32 %2, i32 addrspace(1)* %arrayidx4, align 4
-@@ -276,11 +326,11 @@ define internal spir_func void @__device_side_enqueue_block_invoke_3(i8 addrspac
- entry:
-   %.block_descriptor.addr = alloca i8 addrspace(4)*, align 4
-   %p.addr = alloca i8 addrspace(3)*, align 4
-  %block.addr = alloca <{ i32, i32 }> addrspace(4)*, align 4
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*, align 4
-   store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 4
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32 }> addrspace(4)*
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*
-   store i8 addrspace(3)* %p, i8 addrspace(3)** %p.addr, align 4
-  store <{ i32, i32 }> addrspace(4)* %block, <{ i32, i32 }> addrspace(4)** %block.addr, align 4
-+  store <{ i32, i32, i8 addrspace(4)* }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)* }> addrspace(4)** %block.addr, align 4
-   ret void
- }
- 
-@@ -300,13 +350,13 @@ entry:
-   %p1.addr = alloca i8 addrspace(3)*, align 4
-   %p2.addr = alloca i8 addrspace(3)*, align 4
-   %p3.addr = alloca i8 addrspace(3)*, align 4
-  %block.addr = alloca <{ i32, i32 }> addrspace(4)*, align 4
-+  %block.addr = alloca <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*, align 4
-   store i8 addrspace(4)* %.block_descriptor, i8 addrspace(4)** %.block_descriptor.addr, align 4
-  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32 }> addrspace(4)*
-+  %block = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)* }> addrspace(4)*
-   store i8 addrspace(3)* %p1, i8 addrspace(3)** %p1.addr, align 4
-   store i8 addrspace(3)* %p2, i8 addrspace(3)** %p2.addr, align 4
-   store i8 addrspace(3)* %p3, i8 addrspace(3)** %p3.addr, align 4
-  store <{ i32, i32 }> addrspace(4)* %block, <{ i32, i32 }> addrspace(4)** %block.addr, align 4
-+  store <{ i32, i32, i8 addrspace(4)* }> addrspace(4)* %block, <{ i32, i32, i8 addrspace(4)* }> addrspace(4)** %block.addr, align 4
-   ret void
- }
- 
-@@ -329,27 +379,20 @@ declare i32 @__enqueue_kernel_varargs(%opencl.queue_t*, i32, %struct.ndrange_t*,
- ; CHECK-LLVM-DAG: define spir_kernel void @__device_side_enqueue_block_invoke_3_kernel(i8 addrspace(4)*, i8 addrspace(3)*)
- ; CHECK-LLVM-DAG: define spir_kernel void @__device_side_enqueue_block_invoke_4_kernel(i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*)
- 
-attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
- attributes #1 = { argmemonly nounwind }
-attributes #2 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-+attributes #2 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
- attributes #3 = { nounwind }
- 
- !llvm.module.flags = !{!0}
-!opencl.enable.FP_CONTRACT = !{}
- !opencl.ocl.version = !{!1}
- !opencl.spir.version = !{!1}
-!opencl.used.extensions = !{!2}
-!opencl.used.optional.core.features = !{!2}
-!opencl.compiler.options = !{!2}
-!llvm.ident = !{!3}
-+!llvm.ident = !{!2}
- 
- !0 = !{i32 1, !"wchar_size", i32 4}
- !1 = !{i32 2, i32 0}
-!2 = !{}
-!3 = !{!"clang version 7.0.0"}
-!4 = !{i32 1, i32 1, i32 0, i32 0}
-!5 = !{!"none", !"none", !"none", !"none"}
-!6 = !{!"int*", !"int*", !"int", !"char"}
-!7 = !{!"", !"", !"", !""}
-!8 = !{i1 false, i1 false, i1 false, i1 false}
-!9 = !{i32 0, i32 0, i32 0, i32 0}
-+!2 = !{!"clang version 9.0.0 (https://llvm.org/git/clang 04fb8964a801a5c5d7baa5a22272243a7d183896) (https://llvm.org/git/llvm 384f64397f6ad95a361b72d62c07d7bac9f24163)"}
-+!3 = !{i32 1, i32 1, i32 0, i32 0}
-+!4 = !{!"none", !"none", !"none", !"none"}
-+!5 = !{!"int*", !"int*", !"int", !"char"}
-+!6 = !{!"", !"", !"", !""}
-- 
-1.8.3.1
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-dont-export-targets-for-binaries.patch b/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-dont-export-targets-for-binaries.patch
deleted file mode 100644
index 9d25bbad..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-dont-export-targets-for-binaries.patch
+++ /dev/null
@@ -1,66 +0,0 @@
-From 7bbd0058362ac3bb5edd7a82d43e1785810776b3 Mon Sep 17 00:00:00 2001
-From: Anuj Mittal <anuj.mittal@intel.com>
-Date: Fri, 29 Mar 2019 08:56:53 +0800
-Subject: [PATCH] dont export targets for binaries
-The projects using LLVM cmake modules look for target binaries in
-sysroot as a result which isn't desirable in this case and isn't needed
-either.
-Upstream-Status: Inappropriate [cross-compile specific] 
-Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
---
- llvm/cmake/modules/AddLLVM.cmake  | 9 ---------
- llvm/cmake/modules/TableGen.cmake | 6 ------
- 2 files changed, 15 deletions(-)
-diff --git a/llvm/cmake/modules/AddLLVM.cmake b/llvm/cmake/modules/AddLLVM.cmake
-index 0df6845..b79f4fa 100644
--- a/llvm/cmake/modules/AddLLVM.cmake
-+++ b/llvm/cmake/modules/AddLLVM.cmake
-@@ -866,12 +866,6 @@ macro(add_llvm_tool name)
- 
-   if ( ${name} IN_LIST LLVM_TOOLCHAIN_TOOLS OR NOT LLVM_INSTALL_TOOLCHAIN_ONLY)
-     if( LLVM_BUILD_TOOLS )
-      if(${name} IN_LIST LLVM_DISTRIBUTION_COMPONENTS OR
-          NOT LLVM_DISTRIBUTION_COMPONENTS)
-        set(export_to_llvmexports EXPORT LLVMExports)
-        set_property(GLOBAL PROPERTY LLVM_HAS_EXPORTS True)
-      endif()
-
-       install(TARGETS ${name}
-               ${export_to_llvmexports}
-               RUNTIME DESTINATION ${LLVM_TOOLS_INSTALL_DIR}
-@@ -884,9 +878,6 @@ macro(add_llvm_tool name)
-       endif()
-     endif()
-   endif()
-  if( LLVM_BUILD_TOOLS )
-    set_property(GLOBAL APPEND PROPERTY LLVM_EXPORTS ${name})
-  endif()
-   set_target_properties(${name} PROPERTIES FOLDER "Tools")
- endmacro(add_llvm_tool name)
- 
-diff --git a/llvm/cmake/modules/TableGen.cmake b/llvm/cmake/modules/TableGen.cmake
-index 3c84ae7..141219f 100644
--- a/llvm/cmake/modules/TableGen.cmake
-+++ b/llvm/cmake/modules/TableGen.cmake
-@@ -164,14 +164,8 @@ macro(add_tablegen target project)
-   endif()
- 
-   if (${project} STREQUAL LLVM AND NOT LLVM_INSTALL_TOOLCHAIN_ONLY)
-    if(${target} IN_LIST LLVM_DISTRIBUTION_COMPONENTS OR
-        NOT LLVM_DISTRIBUTION_COMPONENTS)
-      set(export_to_llvmexports EXPORT LLVMExports)
-    endif()
-
-     install(TARGETS ${target}
-             ${export_to_llvmexports}
-             RUNTIME DESTINATION ${LLVM_TOOLS_INSTALL_DIR})
-   endif()
-  set_property(GLOBAL APPEND PROPERTY LLVM_EXPORTS ${target})
- endmacro()
-- 
-2.7.4
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-point-to-correct-clang.patch b/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-point-to-correct-clang.patch
deleted file mode 100644
index 0dfc537b..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0001-point-to-correct-clang.patch
+++ /dev/null
@@ -1,59 +0,0 @@
-From 6c33fb58869ffb17106047c45ab8d3856966eaf7 Mon Sep 17 00:00:00 2001
-From: Anuj Mittal <anuj.mittal@intel.com>
-Date: Tue, 26 Mar 2019 14:11:29 +0800
-Subject: [PATCH] point to correct clang project and tblgen
-Point to correct path for clang project as per the way we unpack. Also
-let llvm-tblgen path be passed from recipe itself.
-Also since we're going to do the patching ourselves, no need to look for
-git through cmake.
-Upstream-Status: Inappropriate [OE specific]
---
- CMakeLists.txt | 8 ++++----
- 1 file changed, 4 insertions(+), 4 deletions(-)
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index 174133b..c769f08 100644
--- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -53,7 +53,7 @@ endif(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)
- include(AddLLVM)
- include(TableGen)
- 
-find_package(Git REQUIRED)
-+#find_package(Git REQUIRED)
- 
- if (NOT WIN32)
-     add_subdirectory( linux_linker )
-@@ -80,7 +80,7 @@ set(TARGET_NAME ${COMMON_CLANG_LIBRARY_NAME}${BUILD_PLATFORM} )
- 
- if(NOT USE_PREBUILT_LLVM)
-     set(TARGET_BRANCH "ocl-open-80")
-    set(CLANG_SOURCE_DIR ${LLVM_SOURCE_DIR}/tools/clang)
-+    set(CLANG_SOURCE_DIR ${LLVM_SOURCE_DIR}/../clang)
-     set(CLANG_BASE_REVISION a03da8be08a208122e292016cb6cea1f30229677)
- 
-     set(SPIRV_SOURCE_DIR ${LLVM_SOURCE_DIR}/projects/llvm-spirv)
-@@ -102,7 +102,7 @@ endif(NOT USE_PREBUILT_LLVM)
- set (COMPILE_OPTIONS_TD  opencl_clang_options.td)
- set (COMPILE_OPTIONS_INC opencl_clang_options.inc)
- 
-set(LLVM_TABLEGEN_EXE "llvm-tblgen")
-+#set(LLVM_TABLEGEN_EXE "llvm-tblgen")
- set(LLVM_TARGET_DEFINITIONS ${COMPILE_OPTIONS_TD})
- if(USE_PREBUILT_LLVM)
-   set(TABLEGEN_ADDITIONAL -I ${LLVM_INCLUDE_DIRS})
-@@ -153,7 +153,7 @@ endif()
- 
- if(NOT USE_PREBUILT_LLVM)
-     set(CLANG_BINARY_DIR ${LLVM_BINARY_DIR}/tools/clang/)
-    set(CLANG_SOURCE_DIR ${LLVM_MAIN_SRC_DIR}/tools/clang/)
-+    set(CLANG_SOURCE_DIR ${LLVM_MAIN_SRC_DIR}/../clang/)
-     include_directories(
-         ${CLANG_BINARY_DIR}/include # for tablegened includes
-         ${CLANG_SOURCE_DIR}/include # for basic headers
-- 
-2.19.1
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0002-OpenCL-Simplify-LLVM-IR-generated-for-OpenCL-blocks.patch b/dynamic-layers/clang-layer/recipes-devtools/clang/files/0002-OpenCL-Simplify-LLVM-IR-generated-for-OpenCL-blocks.patch
deleted file mode 100644
index 2e935a13..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0002-OpenCL-Simplify-LLVM-IR-generated-for-OpenCL-blocks.patch
+++ /dev/null
@@ -1,294 +0,0 @@
-From c94ec28600255098ffb9d73d1b386a7c8a535590 Mon Sep 17 00:00:00 2001
-From: Andrew Savonichev <andrew.savonichev@intel.com>
-Date: Thu, 21 Feb 2019 11:02:10 +0000
-Subject: [PATCH 2/2] [OpenCL] Simplify LLVM IR generated for OpenCL blocks
-Summary:
-Emit direct call of block invoke functions when possible, i.e. in case the
-block is not passed as a function argument.
-Also doing some refactoring of `CodeGenFunction::EmitBlockCallExpr()`
-Reviewers: Anastasia, yaxunl, svenvh
-Reviewed By: Anastasia
-Subscribers: cfe-commits
-Tags: #clang
-Differential Revision: https://reviews.llvm.org/D58388
-git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@354568 91177308-0d34-0410-b5e6-96231b3b80d8
-Upstream-Status: Backport
-[https://github.com/llvm-mirror/clang/commit/eae71f8d05ce550c4e2595c9b7082cc2c7882c58]
-Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
---
- lib/CodeGen/CGBlocks.cpp                       | 77 +++++++++++++-------------
- lib/CodeGen/CGOpenCLRuntime.cpp                | 30 +++++++---
- lib/CodeGen/CGOpenCLRuntime.h                  |  4 ++
- test/CodeGenOpenCL/blocks.cl                   | 10 +---
- test/CodeGenOpenCL/cl20-device-side-enqueue.cl | 34 +++++++++---
- 5 files changed, 91 insertions(+), 64 deletions(-)
-diff --git a/lib/CodeGen/CGBlocks.cpp b/lib/CodeGen/CGBlocks.cpp
-index fa3c3ee..10a0238 100644
--- a/lib/CodeGen/CGBlocks.cpp
-+++ b/lib/CodeGen/CGBlocks.cpp
-@@ -1261,52 +1261,49 @@ RValue CodeGenFunction::EmitBlockCallExpr(const CallExpr *E,
-                                           ReturnValueSlot ReturnValue) {
-   const BlockPointerType *BPT =
-     E->getCallee()->getType()->getAs<BlockPointerType>();
-
-   llvm::Value *BlockPtr = EmitScalarExpr(E->getCallee());
-
-  // Get a pointer to the generic block literal.
-  // For OpenCL we generate generic AS void ptr to be able to reuse the same
-  // block definition for blocks with captures generated as private AS local
-  // variables and without captures generated as global AS program scope
-  // variables.
-  unsigned AddrSpace = 0;
-  if (getLangOpts().OpenCL)
-    AddrSpace = getContext().getTargetAddressSpace(LangAS::opencl_generic);
-
-  llvm::Type *BlockLiteralTy =
-      llvm::PointerType::get(CGM.getGenericBlockLiteralType(), AddrSpace);
-
-  // Bitcast the callee to a block literal.
-  BlockPtr =
-      Builder.CreatePointerCast(BlockPtr, BlockLiteralTy, "block.literal");
-
-  // Get the function pointer from the literal.
-  llvm::Value *FuncPtr =
-      Builder.CreateStructGEP(CGM.getGenericBlockLiteralType(), BlockPtr,
-                              CGM.getLangOpts().OpenCL ? 2 : 3);
-
-  // Add the block literal.
-+  llvm::Type *GenBlockTy = CGM.getGenericBlockLiteralType();
-+  llvm::Value *Func = nullptr;
-+  QualType FnType = BPT->getPointeeType();
-+  ASTContext &Ctx = getContext();
-   CallArgList Args;
- 
-  QualType VoidPtrQualTy = getContext().VoidPtrTy;
-  llvm::Type *GenericVoidPtrTy = VoidPtrTy;
-   if (getLangOpts().OpenCL) {
-    GenericVoidPtrTy = CGM.getOpenCLRuntime().getGenericVoidPointerType();
-    VoidPtrQualTy =
-        getContext().getPointerType(getContext().getAddrSpaceQualType(
-            getContext().VoidTy, LangAS::opencl_generic));
-  }
-
-  BlockPtr = Builder.CreatePointerCast(BlockPtr, GenericVoidPtrTy);
-  Args.add(RValue::get(BlockPtr), VoidPtrQualTy);
-
-  QualType FnType = BPT->getPointeeType();
-+    // For OpenCL, BlockPtr is already casted to generic block literal.
-+
-+    // First argument of a block call is a generic block literal casted to
-+    // generic void pointer, i.e. i8 addrspace(4)*
-+    llvm::Value *BlockDescriptor = Builder.CreatePointerCast(
-+        BlockPtr, CGM.getOpenCLRuntime().getGenericVoidPointerType());
-+    QualType VoidPtrQualTy = Ctx.getPointerType(
-+        Ctx.getAddrSpaceQualType(Ctx.VoidTy, LangAS::opencl_generic));
-+    Args.add(RValue::get(BlockDescriptor), VoidPtrQualTy);
-+    // And the rest of the arguments.
-+    EmitCallArgs(Args, FnType->getAs<FunctionProtoType>(), E->arguments());
-+
-+    // We *can* call the block directly unless it is a function argument.
-+    if (!isa<ParmVarDecl>(E->getCalleeDecl()))
-+      Func = CGM.getOpenCLRuntime().getInvokeFunction(E->getCallee());
-+    else {
-+      llvm::Value *FuncPtr = Builder.CreateStructGEP(GenBlockTy, BlockPtr, 2);
-+      Func = Builder.CreateAlignedLoad(FuncPtr, getPointerAlign());
-+    }
-+  } else {
-+    // Bitcast the block literal to a generic block literal.
-+    BlockPtr = Builder.CreatePointerCast(
-+        BlockPtr, llvm::PointerType::get(GenBlockTy, 0), "block.literal");
-+    // Get pointer to the block invoke function
-+    llvm::Value *FuncPtr = Builder.CreateStructGEP(GenBlockTy, BlockPtr, 3);
- 
-  // And the rest of the arguments.
-  EmitCallArgs(Args, FnType->getAs<FunctionProtoType>(), E->arguments());
-+    // First argument is a block literal casted to a void pointer
-+    BlockPtr = Builder.CreatePointerCast(BlockPtr, VoidPtrTy);
-+    Args.add(RValue::get(BlockPtr), Ctx.VoidPtrTy);
-+    // And the rest of the arguments.
-+    EmitCallArgs(Args, FnType->getAs<FunctionProtoType>(), E->arguments());
- 
-  // Load the function.
-  llvm::Value *Func = Builder.CreateAlignedLoad(FuncPtr, getPointerAlign());
-+    // Load the function.
-+    Func = Builder.CreateAlignedLoad(FuncPtr, getPointerAlign());
-+  }
- 
-   const FunctionType *FuncTy = FnType->castAs<FunctionType>();
-   const CGFunctionInfo &FnInfo =
-diff --git a/lib/CodeGen/CGOpenCLRuntime.cpp b/lib/CodeGen/CGOpenCLRuntime.cpp
-index 7f6f595..75003e5 100644
--- a/lib/CodeGen/CGOpenCLRuntime.cpp
-+++ b/lib/CodeGen/CGOpenCLRuntime.cpp
-@@ -123,6 +123,23 @@ llvm::PointerType *CGOpenCLRuntime::getGenericVoidPointerType() {
-       CGM.getContext().getTargetAddressSpace(LangAS::opencl_generic));
- }
- 
-+// Get the block literal from an expression derived from the block expression.
-+// OpenCL v2.0 s6.12.5:
-+// Block variable declarations are implicitly qualified with const. Therefore
-+// all block variables must be initialized at declaration time and may not be
-+// reassigned.
-+static const BlockExpr *getBlockExpr(const Expr *E) {
-+  const Expr *Prev = nullptr; // to make sure we do not stuck in infinite loop.
-+  while(!isa<BlockExpr>(E) && E != Prev) {
-+    Prev = E;
-+    E = E->IgnoreCasts();
-+    if (auto DR = dyn_cast<DeclRefExpr>(E)) {
-+      E = cast<VarDecl>(DR->getDecl())->getInit();
-+    }
-+  }
-+  return cast<BlockExpr>(E);
-+}
-+
- /// Record emitted llvm invoke function and llvm block literal for the
- /// corresponding block expression.
- void CGOpenCLRuntime::recordBlockInfo(const BlockExpr *E,
-@@ -137,20 +154,17 @@ void CGOpenCLRuntime::recordBlockInfo(const BlockExpr *E,
-   EnqueuedBlockMap[E].Kernel = nullptr;
- }
- 
-+llvm::Function *CGOpenCLRuntime::getInvokeFunction(const Expr *E) {
-+  return EnqueuedBlockMap[getBlockExpr(E)].InvokeFunc;
-+}
-+
- CGOpenCLRuntime::EnqueuedBlockInfo
- CGOpenCLRuntime::emitOpenCLEnqueuedBlock(CodeGenFunction &CGF, const Expr *E) {
-   CGF.EmitScalarExpr(E);
- 
-   // The block literal may be assigned to a const variable. Chasing down
-   // to get the block literal.
-  if (auto DR = dyn_cast<DeclRefExpr>(E)) {
-    E = cast<VarDecl>(DR->getDecl())->getInit();
-  }
-  E = E->IgnoreImplicit();
-  if (auto Cast = dyn_cast<CastExpr>(E)) {
-    E = Cast->getSubExpr();
-  }
-  auto *Block = cast<BlockExpr>(E);
-+  const BlockExpr *Block = getBlockExpr(E);
- 
-   assert(EnqueuedBlockMap.find(Block) != EnqueuedBlockMap.end() &&
-          "Block expression not emitted");
-diff --git a/lib/CodeGen/CGOpenCLRuntime.h b/lib/CodeGen/CGOpenCLRuntime.h
-index 750721f..4effc7e 100644
--- a/lib/CodeGen/CGOpenCLRuntime.h
-+++ b/lib/CodeGen/CGOpenCLRuntime.h
-@@ -92,6 +92,10 @@ public:
-   /// \param Block block literal emitted for the block expression.
-   void recordBlockInfo(const BlockExpr *E, llvm::Function *InvokeF,
-                        llvm::Value *Block);
-+
-+  /// \return LLVM block invoke function emitted for an expression derived from
-+  /// the block expression.
-+  llvm::Function *getInvokeFunction(const Expr *E);
- };
- 
- }
-diff --git a/test/CodeGenOpenCL/blocks.cl b/test/CodeGenOpenCL/blocks.cl
-index 19aacc3..ab5a2c6 100644
--- a/test/CodeGenOpenCL/blocks.cl
-+++ b/test/CodeGenOpenCL/blocks.cl
-@@ -39,11 +39,8 @@ void foo(){
-   // SPIR: %[[blk_gen_ptr:.*]] = addrspacecast %struct.__opencl_block_literal_generic* %[[blk_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
-   // SPIR: store %struct.__opencl_block_literal_generic addrspace(4)* %[[blk_gen_ptr]], %struct.__opencl_block_literal_generic addrspace(4)** %[[block_B:.*]],
-   // SPIR: %[[block_literal:.*]] = load %struct.__opencl_block_literal_generic addrspace(4)*, %struct.__opencl_block_literal_generic addrspace(4)** %[[block_B]]
-  // SPIR: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 2
-   // SPIR: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)*
-  // SPIR: %[[invoke_func_ptr:.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* %[[invoke_addr]]
-  // SPIR: %[[invoke_func:.*]] = addrspacecast i8 addrspace(4)* %[[invoke_func_ptr]] to i32 (i8 addrspace(4)*)*
-  // SPIR: call {{.*}}i32 %[[invoke_func]](i8 addrspace(4)* %[[blk_gen_ptr]])
-+  // SPIR: call {{.*}}i32 @__foo_block_invoke(i8 addrspace(4)* %[[blk_gen_ptr]])
-   // AMDGCN: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block:.*]], i32 0, i32 2
-   // AMDGCN: store i8* bitcast (i32 (i8*)* @__foo_block_invoke to i8*), i8* addrspace(5)* %[[block_invoke]]
-   // AMDGCN: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]], i32 0, i32 3
-@@ -53,11 +50,8 @@ void foo(){
-   // AMDGCN: %[[blk_gen_ptr:.*]] = addrspacecast %struct.__opencl_block_literal_generic addrspace(5)* %[[blk_ptr]] to %struct.__opencl_block_literal_generic*
-   // AMDGCN: store %struct.__opencl_block_literal_generic* %[[blk_gen_ptr]], %struct.__opencl_block_literal_generic* addrspace(5)* %[[block_B:.*]],
-   // AMDGCN: %[[block_literal:.*]] = load %struct.__opencl_block_literal_generic*, %struct.__opencl_block_literal_generic* addrspace(5)* %[[block_B]]
-  // AMDGCN: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic* %[[block_literal]], i32 0, i32 2
-   // AMDGCN: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic* %[[block_literal]] to i8*
-  // AMDGCN: %[[invoke_func_ptr:.*]] = load i8*, i8** %[[invoke_addr]]
-  // AMDGCN: %[[invoke_func:.*]] = bitcast i8* %[[invoke_func_ptr]] to i32 (i8*)*
-  // AMDGCN: call {{.*}}i32 %[[invoke_func]](i8* %[[blk_gen_ptr]])
-+  // AMDGCN: call {{.*}}i32 @__foo_block_invoke(i8* %[[blk_gen_ptr]])
- 
-   int (^ block_B)(void) = ^{
-     return i;
-diff --git a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
-index 8445016..1566912 100644
--- a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
-+++ b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
-@@ -312,9 +312,7 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
-   };
- 
-   // Uses global block literal [[BLG8]] and invoke function [[INVG8]].
-  // COMMON: [[r1:%.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* getelementptr inbounds (%struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), i32 0, i32 2)
-  // COMMON: [[r2:%.*]] = addrspacecast i8 addrspace(4)* [[r1]] to void (i8 addrspace(4)*)*
-  // COMMON: call spir_func void [[r2]](i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*))
-+  // COMMON: call spir_func void @__device_side_enqueue_block_invoke_11(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*))
-   block_A();
- 
-   // Emits global block literal [[BLG8]] and block kernel [[INVGK8]]. [[INVGK8]] calls [[INVG8]].
-@@ -333,15 +331,35 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
-   unsigned size = get_kernel_work_group_size(block_A);
- 
-   // Uses global block literal [[BLG8]] and invoke function [[INVG8]]. Make sure no redundant block literal and invoke functions are emitted.
-  // COMMON: [[r1:%.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* getelementptr inbounds (%struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), i32 0, i32 2)
-  // COMMON: [[r2:%.*]] = addrspacecast i8 addrspace(4)* [[r1]] to void (i8 addrspace(4)*)*
-  // COMMON: call spir_func void [[r2]](i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*))
-+  // COMMON: call spir_func void @__device_side_enqueue_block_invoke_11(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*))
-   block_A();
- 
-+  // Make sure that block invoke function is resolved correctly after sequence of assignements.
-+  // COMMON: store %struct.__opencl_block_literal_generic addrspace(4)*
-+  // COMMON-SAME: addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)*
-+  // COMMON-SAME: bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to %struct.__opencl_block_literal_generic addrspace(1)*)
-+  // COMMON-SAME: to %struct.__opencl_block_literal_generic addrspace(4)*),
-+  // COMMON-SAME: %struct.__opencl_block_literal_generic addrspace(4)** %b1,
-+  bl_t b1 = block_G;
-+  // COMMON: store %struct.__opencl_block_literal_generic addrspace(4)*
-+  // COMMON-SAME: addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)*
-+  // COMMON-SAME: bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to %struct.__opencl_block_literal_generic addrspace(1)*)
-+  // COMMON-SAME: to %struct.__opencl_block_literal_generic addrspace(4)*),
-+  // COMMON-SAME: %struct.__opencl_block_literal_generic addrspace(4)** %b2,
-+  bl_t b2 = b1;
-+  // COMMON: call spir_func void @block_G_block_invoke(i8 addrspace(4)* addrspacecast (i8 addrspace(1)*
-+  // COMMON-SAME: bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*)
-+  // COOMON-SAME: to i8 addrspace(4)*), i8 addrspace(3)* null)
-+  b2(0);
-+  // Uses global block literal [[BL_GLOBAL]] and block kernel [[INV_G_K]]. [[INV_G_K]] calls [[INV_G]].
-+  // COMMON: call i32 @__get_kernel_preferred_work_group_size_multiple_impl(
-+  // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INV_G_K:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
-+  // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*) to i8 addrspace(4)*))
-+  size = get_kernel_preferred_work_group_size_multiple(b2);
-+
-   void (^block_C)(void) = ^{
-     callee(i, a);
-   };
-
-   // Emits block literal on stack and block kernel [[INVLK3]].
-   // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL3:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke
-   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
-@@ -404,8 +422,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
- // COMMON: define internal spir_func void [[INVG8]](i8 addrspace(4)*{{.*}})
- // COMMON: define internal spir_func void [[INVG9]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)* %{{.*}})
- // COMMON: define internal spir_kernel void [[INVGK8]](i8 addrspace(4)*{{.*}})
-+// COMMON: define internal spir_kernel void [[INV_G_K]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
- // COMMON: define internal spir_kernel void [[INVLK3]](i8 addrspace(4)*{{.*}})
- // COMMON: define internal spir_kernel void [[INVGK9]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
-// COMMON: define internal spir_kernel void [[INV_G_K]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
- // COMMON: define internal spir_kernel void [[INVGK10]](i8 addrspace(4)*{{.*}})
- // COMMON: define internal spir_kernel void [[INVGK11]](i8 addrspace(4)*{{.*}})
-- 
-1.8.3.1
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0003-OpenCL-Fix-assertion-due-to-blocks.patch b/dynamic-layers/clang-layer/recipes-devtools/clang/files/0003-OpenCL-Fix-assertion-due-to-blocks.patch
deleted file mode 100644
index 510c7c6e..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/files/0003-OpenCL-Fix-assertion-due-to-blocks.patch
+++ /dev/null
@@ -1,61 +0,0 @@
-From 29e2813a2ab7d5569860bb07892dfef7b5374d96 Mon Sep 17 00:00:00 2001
-From: Yaxun Liu <Yaxun.Liu@amd.com>
-Date: Tue, 26 Feb 2019 16:20:41 +0000
-Subject: [PATCH] [OpenCL] Fix assertion due to blocks
-A recent change caused assertion in CodeGenFunction::EmitBlockCallExpr when a block is called.
-There is code
-  Func = CGM.getOpenCLRuntime().getInvokeFunction(E->getCallee());
-getCalleeDecl calls Expr::getReferencedDeclOfCallee, which does not handle
-BlockExpr and returns nullptr, which causes isa to assert.
-This patch fixes that.
-Differential Revision: https://reviews.llvm.org/D58658
-git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@354893 91177308-0d34-0410-b5e6-96231b3b80d8
-Upstream-Status: Backport
-[https://github.com/llvm-mirror/clang/commit/29e2813a2ab7d5569860bb07892dfef7b5374d96]
-Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
---
- lib/AST/Expr.cpp             | 2 ++
- test/CodeGenOpenCL/blocks.cl | 6 ++++++
- 2 files changed, 8 insertions(+)
-diff --git a/lib/AST/Expr.cpp b/lib/AST/Expr.cpp
-index aef1eab..85690c7 100644
--- a/lib/AST/Expr.cpp
-+++ b/lib/AST/Expr.cpp
-@@ -1358,6 +1358,8 @@ Decl *Expr::getReferencedDeclOfCallee() {
-     return DRE->getDecl();
-   if (MemberExpr *ME = dyn_cast<MemberExpr>(CEE))
-     return ME->getMemberDecl();
-+  if (auto *BE = dyn_cast<BlockExpr>(CEE))
-+    return BE->getBlockDecl();
- 
-   return nullptr;
- }
-diff --git a/test/CodeGenOpenCL/blocks.cl b/test/CodeGenOpenCL/blocks.cl
-index ab5a2c6..c3e2685 100644
--- a/test/CodeGenOpenCL/blocks.cl
-+++ b/test/CodeGenOpenCL/blocks.cl
-@@ -90,6 +90,12 @@ int get42() {
-   return blockArgFunc(^{return 42;});
- }
- 
-+// COMMON-LABEL: define {{.*}}@call_block
-+// call {{.*}}@__call_block_block_invoke
-+int call_block() {
-+  return ^int(int num) { return num; } (11);
-+}
-+
- // CHECK-DEBUG: !DIDerivedType(tag: DW_TAG_member, name: "__size"
- // CHECK-DEBUG: !DIDerivedType(tag: DW_TAG_member, name: "__align"
- 
-- 
-1.8.3.1
diff --git a/dynamic-layers/clang-layer/recipes-devtools/clang/llvm-project-source.bbappend b/dynamic-layers/clang-layer/recipes-devtools/clang/llvm-project-source.bbappend
deleted file mode 100644
index f536f0f2..00000000
--- a/dynamic-layers/clang-layer/recipes-devtools/clang/llvm-project-source.bbappend
+++ /dev/null
@@ -1,16 +0,0 @@
-FILESEXTRAPATHS_prepend_intel-x86-common := "${THISDIR}/files:"
-SRC_URI_append_intel-x86-common = " \
-                                    git://github.com/intel/opencl-clang.git;protocol=https;branch=ocl-open-80;destsuffix=git/llvm/projects/opencl-clang;name=opencl-clang \
-                                    git://github.com/KhronosGroup/SPIRV-LLVM-Translator.git;protocol=https;branch=llvm_release_80;destsuffix=git/llvm/projects/llvm-spirv;name=spirv \
-                                    file://0001-point-to-correct-clang.patch;patchdir=llvm/projects/opencl-clang \
-                                    file://0001-OpenCL-Change-type-of-block-pointer-for-OpenCL.patch;patchdir=clang \
-                                    file://0002-OpenCL-Simplify-LLVM-IR-generated-for-OpenCL-blocks.patch;patchdir=clang \
-                                    file://0003-OpenCL-Fix-assertion-due-to-blocks.patch;patchdir=clang \
-                                    file://0001-dont-export-targets-for-binaries.patch \
-                                    file://0001-Update-LowerOpenCL-pass-to-handle-new-blocks-represn.patch;patchdir=llvm/projects/llvm-spirv \
-                                    "
-SRCREV_opencl-clang = "daf5e4dd718477ae8cf89a283c653939d9182f15"
-SRCREV_spirv = "bd0f28fb92061d49c0f120b4dac3fd8956006745"
diff --git a/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime/0002-Build-not-able-to-locate-cpp_generation_tool.patch b/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime/0002-Build-not-able-to-locate-cpp_generation_tool.patch
new file mode 100644
index 00000000..45288ce1
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime/0002-Build-not-able-to-locate-cpp_generation_tool.patch
@@ -0,0 +1,41 @@
+From 8c330d0cb5167612296801f0202b0de35e9ca88d Mon Sep 17 00:00:00 2001
+From: Dongwon Kim <dongwon.kim@intel.com>
+Date: Sat, 21 Aug 2021 16:09:39 -0700
+Subject: [PATCH 2/5] Build not able to locate cpp_generation_tool.
+Upstream-Status: Inappropriate [oe specific]
+Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
+Signed-off-by: Dongwon Kim <dongwon.kim@intel.com>
+---
+ shared/source/built_ins/kernels/CMakeLists.txt | 10 +++++-----
+ 1 file changed, 5 insertions(+), 5 deletions(-)
+Index: git/shared/source/built_ins/kernels/CMakeLists.txt
+===================================================================
+--- git.orig/shared/source/built_ins/kernels/CMakeLists.txt
+++ git/shared/source/built_ins/kernels/CMakeLists.txt
+@@ -122,9 +122,9 @@ function(compile_builtin core_type platf
+       endif()
+       add_custom_command(
+                          OUTPUT ${OUTPUT_FILE_CPP}
+-                         COMMAND $<TARGET_FILE:cpp_generate_tool> --file ${BINARY_OUTPUT}.bin --output ${OUTPUT_FILE_CPP} --array ${mode}_${BASENAME} --device ${RELEASE_FILENAME}
+                         COMMAND cpp_generate_tool --file ${BINARY_OUTPUT}.bin --output ${OUTPUT_FILE_CPP} --array ${mode}_${BASENAME} --device ${RELEASE_FILENAME}
+                          WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+-                         DEPENDS ${OUTPUT_FILES_BINARIES} $<TARGET_FILE:cpp_generate_tool>
+                         DEPENDS ${OUTPUT_FILES_BINARIES} cpp_generate_tool
+       )
+       list(APPEND BUILTINS_COMMANDS "${OUTPUT_FILE_CPP}")
+     else()
+@@ -176,9 +176,9 @@ function(generate_cpp_spirv builtin)
+     endif()
+     add_custom_command(
+                        OUTPUT ${OUTPUT_FILE_CPP}
+-                       COMMAND $<TARGET_FILE:cpp_generate_tool> --file ${GENERATED_SPV_INPUT} --output ${OUTPUT_FILE_CPP} --array ${BASENAME}
+                       COMMAND cpp_generate_tool --file ${GENERATED_SPV_INPUT} --output ${OUTPUT_FILE_CPP} --array ${BASENAME}
+                        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+-                       DEPENDS ${GENERATED_SPV_INPUT} $<TARGET_FILE:cpp_generate_tool>
+                       DEPENDS ${GENERATED_SPV_INPUT} cpp_generate_tool
+     )
+     set(OUTPUT_LIST_CPP_FILES ${OUTPUT_LIST_CPP_FILES} ${OUTPUT_FILE_CPP} PARENT_SCOPE)
+   else()
diff --git a/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime/0003-external-ocloc.patch b/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime/0003-external-ocloc.patch
new file mode 100644
index 00000000..2001d839
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime/0003-external-ocloc.patch
@@ -0,0 +1,38 @@
+From 0006db5f55a9f08bd3452558a53704cd3bbb790f Mon Sep 17 00:00:00 2001
+From: Dongwon Kim <dongwon.kim@intel.com>
+Date: Wed, 2 Mar 2022 15:52:45 -0800
+Subject: [PATCH 3/5] external ocloc
+Upstream-Status: Inappropriate
+Signed-off-by: Dongwon Kim <dongwon.kim@intel.com>
+---
+ cmake/ocloc_cmd_prefix.cmake | 14 ++++++++------
+ 1 file changed, 8 insertions(+), 6 deletions(-)
+Index: git/cmake/ocloc_cmd_prefix.cmake
+===================================================================
+--- git.orig/cmake/ocloc_cmd_prefix.cmake
+++ git/cmake/ocloc_cmd_prefix.cmake
+@@ -4,13 +4,15 @@
+ # SPDX-License-Identifier: MIT
+ #
+ 
+-if(WIN32)
+-  set(ocloc_cmd_prefix ocloc)
+-else()
+-  if(DEFINED NEO__IGC_LIBRARY_PATH)
+-    set(ocloc_cmd_prefix ${CMAKE_COMMAND} -E env "LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${NEO__IGC_LIBRARY_PATH}:$<TARGET_FILE_DIR:ocloc_lib>" $<TARGET_FILE:ocloc>)
+if(NOT DEFINED ocloc_cmd_prefix)
+  if(WIN32)
+    set(ocloc_cmd_prefix ocloc)
+   else()
+-    set(ocloc_cmd_prefix ${CMAKE_COMMAND} -E env "LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$<TARGET_FILE_DIR:ocloc_lib>" $<TARGET_FILE:ocloc>)
+    if(DEFINED NEO__IGC_LIBRARY_PATH)
+      set(ocloc_cmd_prefix LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${NEO__IGC_LIBRARY_PATH}:$<TARGET_FILE_DIR:ocloc_lib> $<TARGET_FILE:ocloc>)
+    else()
+      set(ocloc_cmd_prefix LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$<TARGET_FILE_DIR:ocloc_lib> $<TARGET_FILE:ocloc>)
+    endif()
+   endif()
+ endif()
+ 
diff --git a/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime_25.13.33276.16.bb b/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime_25.13.33276.16.bb
new file mode 100644
index 00000000..b13daaa8
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/compute-runtime/intel-compute-runtime_25.13.33276.16.bb
@@ -0,0 +1,61 @@
+SUMMARY = "The Intel(R) Graphics Compute Runtime for OpenCL(TM)"
+DESCRIPTION = "The Intel(R) Graphics Compute Runtime for OpenCL(TM) \
+is an open source project to converge Intel's development efforts \
+on OpenCL(TM) compute stacks supporting the GEN graphics hardware \
+architecture."
+LICENSE = "MIT & Apache-2.0"
+LIC_FILES_CHKSUM = "file://LICENSE.md;md5=eca6ec6997e18db166db7109cdbe611c \
+                    file://third_party/opencl_headers/LICENSE;md5=3b83ef96387f14655fc854ddc3c6bd57"
+SRC_URI = "git://github.com/intel/compute-runtime.git;protocol=https;branch=releases/25.13 \
+           file://0002-Build-not-able-to-locate-cpp_generation_tool.patch \
+           file://0003-external-ocloc.patch \
+           "
+SRCREV = "a9961bdfaa07250fd52ff930bf8f31fb4e3b7799"
+DEPENDS += " intel-graphics-compiler gmmlib libva qemu-native"
+RDEPENDS:${PN} += " intel-graphics-compiler gmmlib"
+inherit cmake pkgconfig qemu
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+EXTRA_OECMAKE = " \
+                 -DIGC_DIR=${STAGING_INCDIR}/igc \
+                 -DBUILD_TYPE=Release \
+                 -DSKIP_UNIT_TESTS=1 \
+                 -DCCACHE_ALLOWED=FALSE \
+                 -DNEO_DISABLE_LD_LLD=ON \
+                 -DNEO_DISABLE_LD_GOLD=ON \
+                 "
+EXTRA_OECMAKE:append:class-target = " \
+                                     -Docloc_cmd_prefix=ocloc \
+                                     -DCMAKE_CROSSCOMPILING_EMULATOR=${WORKDIR}/qemuwrapper \
+                                     "
+PACKAGECONFIG ??= ""
+PACKAGECONFIG[levelzero] = "-DBUILD_WITH_L0=ON, -DBUILD_WITH_L0=OFF, level-zero"
+do_configure:prepend:class-target () {
+    # Write out a qemu wrapper that will be used by cmake.
+    qemu_binary="${@qemu_wrapper_cmdline(d, d.getVar('STAGING_DIR_HOST'), [d.expand('${B}/bin'),d.expand('${STAGING_DIR_HOST}${libdir}'),d.expand('${STAGING_DIR_HOST}${base_libdir}')])}"
+    cat > ${WORKDIR}/qemuwrapper << EOF
+#!/bin/sh
+$qemu_binary "\$@"
+EOF
+    chmod +x ${WORKDIR}/qemuwrapper
+}
+FILES:${PN} += " \
+                 ${libdir}/intel-opencl/libigdrcl.so \
+                 ${libdir}/libocloc.so \
+                 "
+FILES:${PN}-dev = "${includedir}"
+UPSTREAM_CHECK_GITTAGREGEX = "(?P<pver>\d+(\.\d+)+)"
diff --git a/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-BiF-CMakeLists.txt-remove-opt-from-DEPENDS.patch b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-BiF-CMakeLists.txt-remove-opt-from-DEPENDS.patch
new file mode 100644
index 00000000..456a8c65
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-BiF-CMakeLists.txt-remove-opt-from-DEPENDS.patch
@@ -0,0 +1,32 @@
+From 1b98a931c3bf8daccc48cd618335ff35e3d382da Mon Sep 17 00:00:00 2001
+From: Anuj Mittal <anuj.mittal@intel.com>
+Date: Tue, 12 Oct 2021 23:46:42 +0800
+Subject: [PATCH] BiF/CMakeLists.txt: remove opt from DEPENDS
+Otherwise it starts failing with:
+| ninja: error: 'IGC/VectorCompiler/lib/BiF/opt', needed by 'IGC/VectorCompiler/lib/BiF/VCBiFPrintfOCL32.opt.bc', missing and no known rule to make it
+We don't need to explicitly make sure opt is built when
+using prebuilt binaries.
+Upstream-Status: Inappropriate
+Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
+---
+ IGC/VectorCompiler/lib/BiF/cmake/Functions.cmake | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+Index: git/IGC/VectorCompiler/lib/BiF/cmake/Functions.cmake
+===================================================================
+--- git.orig/IGC/VectorCompiler/lib/BiF/cmake/Functions.cmake
+++ git/IGC/VectorCompiler/lib/BiF/cmake/Functions.cmake
+@@ -121,7 +121,7 @@ function(vc_build_bif RES_FILE CMCL_SRC_
+     COMMENT "vc_build_bif: Translating CMCL builtins:  ${BIF_CLANG_BC_NAME_FINAL} -> ${BIF_OPT_BC_NAME}"
+     COMMAND CMCLTranslatorTool ${OPT_OPAQUE_ARG} -o ${BIF_CMCL_BC_PATH} ${BIF_CLANG_BC_PATH_FINAL}
+     COMMAND ${LLVM_OPT_EXE} ${OPT_OPAQUE_ARG} --O2 -o ${BIF_OPT_BC_PATH} ${BIF_CMCL_BC_PATH}
+-    DEPENDS CMCLTranslatorTool ${LLVM_OPT_EXE} ${OPT_BC_DEPENDS})
+    DEPENDS CMCLTranslatorTool ${BIF_CLANG_BC_PATH_FINAL})
+ 
+   add_custom_target(${TARGET_NAME}
+     DEPENDS ${BIF_OPT_BC_PATH}
diff --git a/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-Build-not-able-to-locate-BiFManager-bin.patch b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-Build-not-able-to-locate-BiFManager-bin.patch
new file mode 100644
index 00000000..87b094aa
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-Build-not-able-to-locate-BiFManager-bin.patch
@@ -0,0 +1,27 @@
+From 048512728eea53b3772a3f80ac9743bfc462487e Mon Sep 17 00:00:00 2001
+From: Yogesh Tyagi <yogesh.tyagi@intel.com>
+Date: Thu, 2 Jan 2025 15:59:27 +0530
+Subject: [PATCH] Build not able to locate BiFManager-bin
+Upstream-Status: Inappropriate [oe specific]
+Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
+---
+ IGC/BiFModule/CMakeLists.txt | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+Index: git/IGC/BiFModule/CMakeLists.txt
+===================================================================
+--- git.orig/IGC/BiFModule/CMakeLists.txt
+++ git/IGC/BiFModule/CMakeLists.txt
+@@ -655,8 +655,8 @@ set(IGC_BUILD__PROJ__BiFModuleCache_OCL
+ 
+ add_custom_command(
+     OUTPUT "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.h" "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bifbc"
+-    COMMAND $<TARGET_FILE:BiFManager-bin> "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_32.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_64.bc" "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bifbc" "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.h"
+-    DEPENDS "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_32.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_64.bc"$<TARGET_FILE:BiFManager-bin>
+    COMMAND BiFManager-bin "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_32.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_64.bc" "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bifbc" "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.h"
+    DEPENDS "${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_32.bc" "${IGC_BUILD__BIF_DIR}/IGCsize_t_64.bc" BiFManager-bin
+     COMMENT "BiF: ${IGC_BUILD__BIF_DIR}/OCLBiFImpl.bc: Spliting output .bc."
+     COMMAND_EXPAND_LISTS
+ )
diff --git a/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-external-SPIRV-Tools-change-path-to-tools-and-header.patch b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-external-SPIRV-Tools-change-path-to-tools-and-header.patch
new file mode 100644
index 00000000..fc66b71d
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-external-SPIRV-Tools-change-path-to-tools-and-header.patch
@@ -0,0 +1,30 @@
+From 251e2854dd206ebf66e5908d3277e4585fe2a63b Mon Sep 17 00:00:00 2001
+From: Anuj Mittal <anuj.mittal@intel.com>
+Date: Mon, 9 Jan 2023 11:43:05 +0800
+Subject: [PATCH] external/SPIRV-Tools: change path to tools and headers
+We clone the SPIRV headers and tools in a different directory to ensure
+file path substitutions take place.
+Upstream-Status: Inappropriate
+Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
+---
+ external/SPIRV-Tools/CMakeLists.txt | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+Index: git/external/SPIRV-Tools/CMakeLists.txt
+===================================================================
+--- git.orig/external/SPIRV-Tools/CMakeLists.txt
+++ git/external/SPIRV-Tools/CMakeLists.txt
+@@ -45,8 +45,8 @@ else() #By default use build from source
+  message(STATUS "[SPIRV-Tools] : Building from source")
+  message(STATUS "[SPIRV-Tools] : Current source dir: ${CMAKE_CURRENT_SOURCE_DIR}")
+ 
+- set(SPIRV-Headers_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../../SPIRV-Headers") # used in subdirectory
+- set(SPIRV-Tools_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../../SPIRV-Tools")
+ set(SPIRV-Headers_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../SPIRV-Headers") # used in subdirectory
+ set(SPIRV-Tools_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../SPIRV-Tools")
+ 
+  set(SPIRV-Tools_OUTPUT_DIR "${IGC_OPTION__OUTPUT_DIR}/external/SPIRV-Tools/build")
+  set(IGC_BUILD__SPIRV-Headers_DIR "${SPIRV-Headers_SOURCE_DIR}")
diff --git a/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-fix-tblgen.patch b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-fix-tblgen.patch
new file mode 100644
index 00000000..3d9ae02f
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0001-fix-tblgen.patch
@@ -0,0 +1,23 @@
+From 1641dc87b2ed6b6b87b2cef824e4d66da65b0b30 Mon Sep 17 00:00:00 2001
+From: Anuj Mittal <anuj.mittal@intel.com>
+Date: Thu, 19 May 2022 22:50:09 +0800
+Subject: [PATCH] fix tblgen
+Upstream-Status: Inappropriate [OE specific]
+---
+ IGC/cmake/igc_llvm.cmake | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+diff --git a/IGC/cmake/igc_llvm.cmake b/IGC/cmake/igc_llvm.cmake
+index b708cc904..fe4668890 100644
+--- a/IGC/cmake/igc_llvm.cmake
+++ b/IGC/cmake/igc_llvm.cmake
+@@ -53,7 +53,7 @@ else()
+   set(LLVM_OPT_EXE "opt" CACHE STRING "")
+ 
+   set(LLVM_TABLEGEN_EXE "llvm-tblgen")
+-  if(CMAKE_CROSSCOMPILING)
+  if(TRUE)
+     if(DEFINED LLVM_TABLEGEN)
+       set(LLVM_TABLEGEN_EXE ${LLVM_TABLEGEN})
+     else()
diff --git a/dynamic-layers/clang-layer/recipes-opencl/igc/files/0003-Improve-Reproducibility-for-src-package.patch b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0003-Improve-Reproducibility-for-src-package.patch
new file mode 100644
index 00000000..4269fadf
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/igc/files/0003-Improve-Reproducibility-for-src-package.patch
@@ -0,0 +1,33 @@
+From ca136c04d4ac60e3febc8ea2b9c4d4736365a424 Mon Sep 17 00:00:00 2001
+From: Lee Chee Yang <chee.yang.lee@intel.com>
+Date: Wed, 2 Sep 2020 08:28:35 +0800
+Subject: [PATCH] Improve Reproducibility for src package
+Improve reproducibility for intel-graphics-compiler-src package.
+needs to pass build path as environment variable to the build.
+this only works on bison 3.7 onward, hence check for bison version
+before adding the flags.
+Upstream-Status: Inappropriate [applying --file-prefix-map in such way does not work for upstream]
+Signed-off-by: Lee Chee Yang <chee.yang.lee@intel.com>
+---
+ visa/CMakeLists.txt | 7 +++++--
+ 1 file changed, 5 insertions(+), 2 deletions(-)
+Index: git/visa/CMakeLists.txt
+===================================================================
+--- git.orig/visa/CMakeLists.txt
+++ git/visa/CMakeLists.txt
+@@ -135,8 +135,11 @@ endif()
+ set(bison_output_file ${CMAKE_CURRENT_BINARY_DIR}/CISA.tab.cpp)
+ set(flex_output_file ${CMAKE_CURRENT_BINARY_DIR}/lex.CISA.cpp)
+ 
+-BISON_TARGET(CISAParser CISA.y ${bison_output_file} COMPILE_FLAGS "-vt -p CISA")
+-FLEX_TARGET(CISAScanner CISA.l ${flex_output_file} COMPILE_FLAGS "-PCISA ${WIN_FLEX_FLAG}")
+if(BISON_VERSION VERSION_GREATER_EQUAL "3.7.0")
+    set(BISON_EXTRA_FLAGS " --file-prefix-map=$ENV{B}=/igc/ ")
+endif()
+BISON_TARGET(CISAParser CISA.y ${bison_output_file} COMPILE_FLAGS "-l -vt -p CISA ${BISON_EXTRA_FLAGS} ")
+FLEX_TARGET(CISAScanner CISA.l ${flex_output_file} COMPILE_FLAGS "-PCISA -L ${WIN_FLEX_FLAG} ")
+ ADD_FLEX_BISON_DEPENDENCY(CISAScanner CISAParser)
+ set(CISAScanner_dependencies)
+ 
diff --git a/dynamic-layers/clang-layer/recipes-opencl/igc/intel-graphics-compiler_2.10.10.bb b/dynamic-layers/clang-layer/recipes-opencl/igc/intel-graphics-compiler_2.10.10.bb
new file mode 100644
index 00000000..05611cbf
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/igc/intel-graphics-compiler_2.10.10.bb
@@ -0,0 +1,77 @@
+SUMMARY = "The Intel(R) Graphics Compiler for OpenCL(TM)"
+DESCRIPTION = "The Intel(R) Graphics Compiler for OpenCL(TM) is an \
+llvm based compiler for OpenCL(TM) targeting Intel Gen graphics \
+hardware architecture."
+LICENSE = "MIT & Apache-2.0"
+LIC_FILES_CHKSUM = "file://IGC/BiFModule/Implementation/ExternalLibraries/libclc/LICENSE.TXT;md5=311cfc1a5b54bab8ed34a0b5fba4373e \
+                    file://LICENSE.md;md5=488d74376edf2765f6e78d271543dde3 \
+                    file://NOTICES.txt;md5=b81a52411c84df3419f20bad4d755880"
+SRC_URI = "git://github.com/intel/intel-graphics-compiler.git;protocol=https;name=igc;branch=releases/2.10.x \
+           git://github.com/intel/vc-intrinsics.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/vc-intrinsics;name=vc;nobranch=1 \
+           git://github.com/KhronosGroup/SPIRV-Tools.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/SPIRV-Tools;name=spirv-tools;branch=main \
+           git://github.com/KhronosGroup/SPIRV-Headers.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/SPIRV-Headers;name=spirv-headers;branch=main \
+           file://0003-Improve-Reproducibility-for-src-package.patch \
+           file://0001-BiF-CMakeLists.txt-remove-opt-from-DEPENDS.patch \
+           file://0001-external-SPIRV-Tools-change-path-to-tools-and-header.patch \
+           file://0001-Build-not-able-to-locate-BiFManager-bin.patch \
+           "
+SRC_URI:append:class-native = " file://0001-fix-tblgen.patch"
+SRCREV_igc = "83925314d4fc32b017fcbfcd73e0667ba833fb8f"
+SRCREV_vc = "9d255266e1df8f1dc5d11e1fbb03213acfaa4fc7"
+SRCREV_spirv-tools = "f289d047f49fb60488301ec62bafab85573668cc"
+SRCREV_spirv-headers = "0e710677989b4326ac974fd80c5308191ed80965"
+SRCREV_FORMAT = "igc_vc_spirv-tools_spirv-headers"
+# Used to replace with relative path in reproducibility patch
+export B
+inherit cmake pkgconfig qemu python3native
+CXXFLAGS:append = " -Wno-error=nonnull"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+DEPENDS += " flex-native bison-native clang clang-cross-x86_64 opencl-clang qemu-native python3-mako-native \
+             python3-pyyaml-native \
+           "
+RDEPENDS:${PN} += "opencl-clang"
+PACKAGECONFIG ??= "vc"
+PACKAGECONFIG[vc] = "-DIGC_BUILD__VC_ENABLED=ON -DIGC_OPTION__LINK_KHRONOS_SPIRV_TRANSLATOR=ON -DIGC_OPTION__SPIRV_TRANSLATOR_MODE=Prebuilds,-DIGC_BUILD__VC_ENABLED=OFF,"
+EXTRA_OECMAKE = " \
+                  -DIGC_OPTION__LLVM_PREFERRED_VERSION=${LLVMVERSION} \
+                  -DVC_INTRINSICS_SRC="${S}/vc-intrinsics" \
+                  -DIGC_OPTION__LLVM_MODE=Prebuilds \
+                  -DLLVM_TABLEGEN=${STAGING_BINDIR_NATIVE}/llvm-tblgen \
+                  -DLLVM_LINK_EXE=${STAGING_BINDIR_NATIVE}/llvm-link \
+                  -DCLANG_EXE=${STAGING_BINDIR_NATIVE}/clang \
+                  -DCMAKE_CROSSCOMPILING_EMULATOR=${WORKDIR}/qemuwrapper \
+                  "
+do_configure:prepend:class-target () {
+    # Write out a qemu wrapper that will be used by cmake.
+    qemu_binary="${@qemu_wrapper_cmdline(d, d.getVar('STAGING_DIR_HOST'), [d.expand('${STAGING_DIR_HOST}${libdir}'),d.expand('${STAGING_DIR_HOST}${base_libdir}')])}"
+    cat > ${WORKDIR}/qemuwrapper << EOF
+#!/bin/sh
+$qemu_binary "\$@"
+EOF
+    chmod +x ${WORKDIR}/qemuwrapper
+}
+UPSTREAM_CHECK_GITTAGREGEX = "^v(?P<pver>\d+(\.\d+)+)$"
+FILES:${PN} += " \
+                 ${libdir}/igc2/NOTICES.txt \
+                 "
+# libigc.so contains buildpaths
+INSANE_SKIP:${PN} += "buildpaths"
diff --git a/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/files/0001-cl_headers-CMakeLists.txt-use-clang-from-native-sysr.patch b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/files/0001-cl_headers-CMakeLists.txt-use-clang-from-native-sysr.patch
new file mode 100644
index 00000000..031a77c7
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/files/0001-cl_headers-CMakeLists.txt-use-clang-from-native-sysr.patch
@@ -0,0 +1,49 @@
+From 5aea653e611b59c70e529a1bd71885a509831557 Mon Sep 17 00:00:00 2001
+From: Anuj Mittal <anuj.mittal@intel.com>
+Date: Tue, 1 Aug 2023 11:15:31 +0800
+Subject: [PATCH] cl_headers/CMakeLists.txt: use clang from native sysroot
+Allow clang to be found in target sysroot for target builds and dont try
+to compile cross binaries, we do that ourselves.
+Upstream-Status: Inappropriate [oe-specific]
+Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
+---
+ CMakeLists.txt            | 8 ++++----
+ cl_headers/CMakeLists.txt | 2 +-
+ 2 files changed, 5 insertions(+), 5 deletions(-)
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 5864009..60ba39e 100644
+--- a/CMakeLists.txt
+++ b/CMakeLists.txt
+@@ -35,10 +35,10 @@ set(CMAKE_MODULE_PATH
+ 
+ include(CMakeFunctions)
+ 
+-if(CMAKE_CROSSCOMPILING AND OPENCL_CLANG_BUILD_EXTERNAL)
+-  include(CrossCompile)
+-  llvm_create_cross_target(${PROJECT_NAME} NATIVE "" Release)
+-endif()
+#if(CMAKE_CROSSCOMPILING AND OPENCL_CLANG_BUILD_EXTERNAL)
+#  include(CrossCompile)
+#  llvm_create_cross_target(${PROJECT_NAME} NATIVE "" Release)
+#endif()
+ 
+ if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)
+     set(USE_PREBUILT_LLVM ON)
+diff --git a/cl_headers/CMakeLists.txt b/cl_headers/CMakeLists.txt
+index 16cabb7..4423536 100644
+--- a/cl_headers/CMakeLists.txt
+++ b/cl_headers/CMakeLists.txt
+@@ -1,6 +1,6 @@
+ set(CL_HEADERS_LIB cl_headers)
+ if(USE_PREBUILT_LLVM)
+-    find_program(CLANG_COMMAND clang PATHS ${LLVM_TOOLS_BINARY_DIR} NO_DEFAULT_PATH)
+    find_program(CLANG_COMMAND clang PATHS ${LLVM_TOOLS_BINARY_DIR})
+ else()
+     set(CLANG_COMMAND $<TARGET_FILE:clang>)
+ endif()
+-- 
+2.37.3
diff --git a/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/files/0002-Request-native-clang-only-when-cross-compiling-464.patch b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/files/0002-Request-native-clang-only-when-cross-compiling-464.patch
new file mode 100644
index 00000000..2f1814f8
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/files/0002-Request-native-clang-only-when-cross-compiling-464.patch
@@ -0,0 +1,60 @@
+From 43c806ef321b1f677a49d28c89fb7ffecf539c2d Mon Sep 17 00:00:00 2001
+From: Tim Creech <timothy.m.creech@intel.com>
+Date: Wed, 28 Jun 2023 03:45:51 -0400
+Subject: [PATCH 2/2] Request native clang only when cross-compiling (#464)
+* Request native clang only when cross-compiling
+LLVM_USE_HOST_TOOLS may be set if LLVM is configured with
+LLVM_OPTIMIZED_TABLEGEN, which does not necessarily indicate
+cross-compilation or that clang will only execute on the target.
+By checking that CMAKE_CROSSCOMPILING is set, we ensure that we only
+build/use clang again if necessary for host execution.
+* fixup: CMAKE_CROSSCOMPILING implies LLVM_USE_HOST_TOOLS
+Co-authored-by: Wenju He <wenju.he@intel.com>
+* fixup: also use CMAKE_CROSSCOMPILING in top-level CMakeLists.txt
+---------
+Co-authored-by: Wenju He <wenju.he@intel.com>
+Upstream-Status: Backport [https://github.com/intel/opencl-clang/commit/53843eee13cfb2357919ee02714a43bef1af0f86]
+Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
+---
+ CMakeLists.txt            | 2 +-
+ cl_headers/CMakeLists.txt | 2 +-
+ 2 files changed, 2 insertions(+), 2 deletions(-)
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index e772de9..5864009 100644
+--- a/CMakeLists.txt
+++ b/CMakeLists.txt
+@@ -35,7 +35,7 @@ set(CMAKE_MODULE_PATH
+ 
+ include(CMakeFunctions)
+ 
+-if(LLVM_USE_HOST_TOOLS AND OPENCL_CLANG_BUILD_EXTERNAL)
+if(CMAKE_CROSSCOMPILING AND OPENCL_CLANG_BUILD_EXTERNAL)
+   include(CrossCompile)
+   llvm_create_cross_target(${PROJECT_NAME} NATIVE "" Release)
+ endif()
+diff --git a/cl_headers/CMakeLists.txt b/cl_headers/CMakeLists.txt
+index 18296c2..16cabb7 100644
+--- a/cl_headers/CMakeLists.txt
+++ b/cl_headers/CMakeLists.txt
+@@ -4,7 +4,7 @@ if(USE_PREBUILT_LLVM)
+ else()
+     set(CLANG_COMMAND $<TARGET_FILE:clang>)
+ endif()
+-if(LLVM_USE_HOST_TOOLS AND NOT OPENCL_CLANG_BUILD_EXTERNAL)
+if(CMAKE_CROSSCOMPILING AND NOT OPENCL_CLANG_BUILD_EXTERNAL)
+   build_native_tool(clang CLANG_COMMAND)
+ endif()
+ 
+-- 
+2.37.3
diff --git a/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/opencl-clang.inc b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/opencl-clang.inc
new file mode 100644
index 00000000..726b035d
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/opencl-clang.inc
@@ -0,0 +1,33 @@
+SUMMARY = "Common clang is a thin wrapper library around clang"
+DESCRIPTION = "Common clang has OpenCL-oriented API and is capable \
+ to compile OpenCL C kernels to SPIR-V modules."
+LICENSE = "NCSA"
+LIC_FILES_CHKSUM = "file://LICENSE;md5=e8a15bf1416762a09ece07e44c79118c"
+SRC_URI = "git://github.com/intel/opencl-clang.git;branch=${BRANCH};protocol=https \
+           file://0002-Request-native-clang-only-when-cross-compiling-464.patch \
+           file://0001-cl_headers-CMakeLists.txt-use-clang-from-native-sysr.patch \
+           "
+inherit cmake
+DEPENDS += "clang"
+DEPENDS:append:class-target = " opencl-clang-native"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+DEPENDS += " spirv-llvm-translator"
+EXTRA_OECMAKE += "\
+                  -DLLVM_TABLEGEN_EXE=${STAGING_BINDIR_NATIVE}/llvm-tblgen \
+                  -DCMAKE_SKIP_RPATH=TRUE \
+                  -DPREFERRED_LLVM_VERSION=${LLVMVERSION} \
+                  "
+do_install:append:class-native() {
+        install -d ${D}${bindir}
+        install -m 0755 ${B}/bin/linux_resource_linker ${D}${bindir}/
+}
+BBCLASSEXTEND = "native nativesdk"
diff --git a/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/opencl-clang_15.0.0.bb b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/opencl-clang_15.0.0.bb
new file mode 100644
index 00000000..e946c31c
--- /dev/null
+++ b/dynamic-layers/clang-layer/recipes-opencl/opencl-clang/opencl-clang_15.0.0.bb
@@ -0,0 +1,5 @@
+require opencl-clang.inc
+SRCREV = "60fd799cc58755c16d951f9ebfde6d0f9b8554dd"
+BRANCH = "ocl-open-150"
diff --git a/dynamic-layers/openembedded-layer/recipes-bsp/amt/files/0001-LMS-fix-build-issue-with-gcc-15.patch b/dynamic-layers/openembedded-layer/recipes-bsp/amt/files/0001-LMS-fix-build-issue-with-gcc-15.patch
new file mode 100644
index 00000000..751c7973
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-bsp/amt/files/0001-LMS-fix-build-issue-with-gcc-15.patch
@@ -0,0 +1,32 @@
+From 439af27f7641185933d7810b6c4eb17086438df3 Mon Sep 17 00:00:00 2001
+From: Yogesh Tyagi <yogesh.tyagi@intel.com>
+Date: Mon, 19 May 2025 17:50:40 +0530
+Subject: [PATCH] LMS : fix build issue with gcc 15
+include cstdint header to resolve the below error with gcc 15
+| In file included from /lms/2406.0.0.0/git/MEIClient/src/MEICommand.cpp:11:
+| /lms/2406.0.0.0/git/MEIClient/Include/MEICommand.h:40:54: error: 'uint8_t' was not declared in this scope
+Upstream-Status: Submitted [https://github.com/intel/lms/pull/23]
+Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
+---
+ MEIClient/Include/MEICommand.h | 1 +
+ 1 file changed, 1 insertion(+)
+diff --git a/MEIClient/Include/MEICommand.h b/MEIClient/Include/MEICommand.h
+index 6192d26..5332e44 100644
+--- a/MEIClient/Include/MEICommand.h
+++ b/MEIClient/Include/MEICommand.h
+@@ -12,6 +12,7 @@
+ #define __MEI_COMMAND_H__
+ #include "heci.h"
+ #include "MEIClientException.h"
+#include <cstdint>
+ #include <memory>
+ #include <vector>
+ 
+-- 
+2.43.0
diff --git a/dynamic-layers/openembedded-layer/recipes-bsp/amt/files/lms_drop_rpath_1921.0.0.0.diff b/dynamic-layers/openembedded-layer/recipes-bsp/amt/files/lms_drop_rpath_1921.0.0.0.diff
deleted file mode 100644
index b68924a5..00000000
--- a/dynamic-layers/openembedded-layer/recipes-bsp/amt/files/lms_drop_rpath_1921.0.0.0.diff
+++ /dev/null
@@ -1,31 +0,0 @@
-From b92a5bda8015454a570990a3d9c4fba87010f1af Mon Sep 17 00:00:00 2001
-From: Alexander Usyskin <alexander.usyskin@intel.com>
-Date: Mon, 17 Jun 2019 13:27:33 +0300
-Subject: [PATCH] lms: drop rpath definitions
-Yocto fail to compile with this definitions.
-Upstream-Status: Inappropriate [configuration]
-Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
---
- CMakeLists.txt | 4 ----
- 1 file changed, 4 deletions(-)
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index 04257fb..85d0445 100644
--- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -107,10 +107,6 @@ install (DIRECTORY Docs/Licenses
-   FILES_MATCHING PATTERN "LICENSE.*"
- )
- 
-list (APPEND CMAKE_INSTALL_RPATH "${PROJECT_BINARY_DIR}/UNS/GMS_COMMON")
-list (APPEND CMAKE_INSTALL_RPATH "${PROJECT_BINARY_DIR}/WsmanClient")
-list (APPEND CMAKE_INSTALL_RPATH "${PROJECT_BINARY_DIR}/UNS/StatusEventHandler")
-
- if (BUILD_TESTS)
-   include (gtest.cmake)
- endif (BUILD_TESTS)
-- 
-2.7.4
diff --git a/dynamic-layers/openembedded-layer/recipes-bsp/amt/lms_1921.0.0.0.bb b/dynamic-layers/openembedded-layer/recipes-bsp/amt/lms_1921.0.0.0.bb
deleted file mode 100644
index 8ed74486..00000000
--- a/dynamic-layers/openembedded-layer/recipes-bsp/amt/lms_1921.0.0.0.bb
+++ /dev/null
@@ -1,39 +0,0 @@
-SUMMARY = "Intel(R) Local Managability Service"
-DESCRIPTION = "Intel Local Manageability Service allows applications \
-to access the Intel Active Management Technology (AMT) firmware via \
-the Intel Management Engine Interface (MEI)."
-LICENSE = "Apache-2.0"
-LIC_FILES_CHKSUM = "file://COPYING;md5=2ee41112a44fe7014dce33e26468ba93"
-COMPATIBLE_HOST = '(i.86|x86_64).*-linux'
-inherit cmake systemd
-DEPENDS = "metee ace xerces-c libnl libxml2 glib-2.0 glib-2.0-native connman"
-EXTRA_OECMAKE += "-DPYTHON_EXECUTABLE=${HOSTTOOLS_DIR}/python3"
-REQUIRED_DISTRO_FEATURES= "systemd"
-FILES_${PN} += "${datadir}/dbus-1/system-services/*.service"
-FILES_${PN} += "${libdir}/libLms*.so"
-FILES_SOLIBSDEV = ""
-INSANE_SKIP_${PN} += "dev-so"
-S = "${WORKDIR}/git"
-SYSTEMD_SERVICE_${PN} = "lms.service"
-SRC_URI = "git://github.com/intel/lms.git"
-SRCREV = "f7c374745ae7efb3ed7860fdc3f8abbb52dc9f8f"
-SRC_URI_append = " file://lms_drop_rpath_${PV}.diff"
-do_install_append() {
-    install -d ${D}${systemd_system_unitdir}
-    install -m 0644 ${B}/UNS/lms.service ${D}${systemd_system_unitdir}
-}
-RDEPENDS_${PN} += "ace"
diff --git a/dynamic-layers/openembedded-layer/recipes-bsp/amt/lms_2406.0.0.0.bb b/dynamic-layers/openembedded-layer/recipes-bsp/amt/lms_2406.0.0.0.bb
new file mode 100644
index 00000000..0a5a57ed
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-bsp/amt/lms_2406.0.0.0.bb
@@ -0,0 +1,43 @@
+SUMMARY = "Intel(R) Local Managability Service"
+DESCRIPTION = "Intel Local Manageability Service allows applications \
+to access the Intel Active Management Technology (AMT) firmware via \
+the Intel Management Engine Interface (MEI)."
+LICENSE = "Apache-2.0"
+LIC_FILES_CHKSUM = "file://COPYING;md5=2ee41112a44fe7014dce33e26468ba93"
+COMPATIBLE_HOST = '(i.86|x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+inherit cmake systemd features_check python3native
+DEPENDS = "metee ace xerces-c libnl libxml2 glib-2.0 glib-2.0-native pkgconfig-native python3-packaging-native"
+# Enable either connman or networkmanager or none but not both.
+PACKAGECONFIG ??= "connman"
+PACKAGECONFIG[connman]        = "-DNETWORK_CN=ON, -DNETWORK_CN=OFF, connman"
+PACKAGECONFIG[networkmanager] = "-DNETWORK_NM=ON, -DNETWORK_NM=OFF, networkmanager"
+REQUIRED_DISTRO_FEATURES = "systemd"
+FILES:${PN} += "${datadir}/dbus-1/system-services/*.service"
+SYSTEMD_SERVICE:${PN} = "lms.service"
+SRC_URI = "git://github.com/intel/lms.git;branch=master;protocol=https \
+           file://0001-LMS-fix-build-issue-with-gcc-15.patch \
+           "
+SRCREV = "388f115b2aeb3ea11499971c65f828daefd32c47"
+do_install:append() {
+    install -d ${D}${sysconfdir}/lms
+    install -d ${D}${systemd_system_unitdir}
+    install -m 0644 ${B}/UNS/lms.service ${D}${systemd_system_unitdir}
+    install -d ${D}${sysconfdir}/udev/rules.d
+    install -m 0644 ${S}/UNS/linux_scripts/70-mei-wdt.rules ${D}${sysconfdir}/udev/rules.d/70-mei-wdt.rules
+}
+RDEPENDS:${PN} += "ace"
+CVE_STATUS[CVE-2018-1000535] = "cpe-incorrect: This CVE is for a different LMS - Lan Management System."
diff --git a/dynamic-layers/openembedded-layer/recipes-bsp/thermald/thermald_2.5.8.bb b/dynamic-layers/openembedded-layer/recipes-bsp/thermald/thermald_2.5.8.bb
new file mode 100644
index 00000000..575a00e8
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-bsp/thermald/thermald_2.5.8.bb
@@ -0,0 +1,43 @@
+SUMMARY = "Linux thermal daemon"
+DESCRIPTION = "Thermal Daemon is a Linux daemon used to prevent the \
+overheating of platforms. This daemon monitors temperature and applies \
+compensation using available cooling methods."
+HOMEPAGE = "https://github.com/01org/thermal_daemon"
+DEPENDS = "dbus dbus-glib dbus-glib-native libxml2 glib-2.0 glib-2.0-native upower libevdev"
+DEPENDS += "autoconf-archive-native"
+LICENSE = "GPL-2.0-only"
+LIC_FILES_CHKSUM = "file://COPYING;md5=ea8831610e926e2e469075b52bf08848"
+SRC_URI = "git://github.com/intel/thermal_daemon/;branch=master;protocol=https \
+           "
+SRCREV = "df3b9ab0ffe780c4fbad7750987eff76f659cfd5"
+inherit pkgconfig autotools systemd gtk-doc
+# gtkdocsize runs before autotools do_configure and it copies gtk-doc.m4 and fails
+# to copy becuase there is no m4 dir yet.
+do_configure:prepend () {
+        mkdir -p ${S}/m4
+}
+EXTRA_OECONF = " \
+                 --with-systemdsystemunitdir=${systemd_system_unitdir} \
+                 "
+FILES:${PN} += "${datadir}/dbus-1"
+SYSTEMD_SERVICE:${PN} = "thermald.service"
+COMPATIBLE_HOST = '(i.86|x86_64).*-linux'
+CONFFILES:${PN} = " \
+                   ${sysconfdir}/thermald/thermal-conf.xml \
+                   ${sysconfdir}/thermald/thermal-cpu-cdev-order.xml \
+                  "
+UPSTREAM_CHECK_URI = "https://github.com/01org/thermal_daemon/releases"
diff --git a/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0001-Add-print-function-to-print-test-run-status-in-ptest.patch b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0001-Add-print-function-to-print-test-run-status-in-ptest.patch
new file mode 100644
index 00000000..4d583657
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0001-Add-print-function-to-print-test-run-status-in-ptest.patch
@@ -0,0 +1,53 @@
+From deccc0c69c2c8759c52885be8bdda54d3cee481c Mon Sep 17 00:00:00 2001
+From: Yogesh Tyagi <yogesh.tyagi@intel.com>
+Date: Sun, 11 Dec 2022 22:34:15 +0800
+Subject: [PATCH] Add print function to print test run status in ptest format
+Upstream-Status: Inappropriate [OE ptest specific]
+Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
+---
+ run_tests.py | 16 ++++++++++++++++
+ 1 file changed, 16 insertions(+)
+diff --git a/run_tests.py b/run_tests.py
+index 1cd796dd..e3ffd1ab 100755
+--- a/run_tests.py
+++ b/run_tests.py
+@@ -327,6 +327,9 @@ def run_test(testname, host, target):
+     else:
+         ispc_exe_rel = add_prefix(host.ispc_cmd, host, target)
+ 
+    # to reslove the error '.rodata' can not be used when making a PIE object
+    ispc_exe_rel = ispc_exe_rel + " --pic"
+
+     # is this a test to make sure an error is issued?
+     want_error = (filename.find("tests_errors") != -1)
+     if want_error == True:
+@@ -795,6 +798,17 @@ def check_compiler_exists(compiler_exe):
+             return
+     error("missing the required compiler: %s \n" % compiler_exe, 1)
+ 
+def print_test_run_status(results):
+    for fstatus in results:
+       if (fstatus[1]  ==  Status.Success):
+          print( "%s: %s" % ("PASS", fstatus[0]))
+       elif (fstatus[1] ==  Status.Compfail):
+          print( "%s: %s" % ("FAIL", fstatus[0]))
+       elif (fstatus[1] ==  Status.Runfail):
+          print( "%s: %s" % ("FAIL", fstatus[0]))
+       elif (fstatus[1] ==  Status.Skip):
+          print( "%s: %s" % ("SKIP", fstatus[0]))
+
+ def print_result(status, results, s, run_tests_log, csv):
+     title = StatusStr[status]
+     file_list = [fname for fname, fstatus in results if status == fstatus]
+@@ -938,6 +952,8 @@ def run_tests(options1, args, print_version):
+         pass_rate = -1
+     print_debug("PASSRATE (%d/%d) = %d%% \n\n" % (len(run_succeed_files), total_tests_executed, pass_rate), s, run_tests_log)
+ 
+    print_test_run_status(results)
+
+     for status in Status:
+         print_result(status, results, s, run_tests_log, options.csv)
+     fails = [status != Status.Compfail and status != Status.Runfail for _, status in results]
diff --git a/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0001-Fix-QA-Issues.patch b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0001-Fix-QA-Issues.patch
new file mode 100644
index 00000000..b0a76ff9
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0001-Fix-QA-Issues.patch
@@ -0,0 +1,36 @@
+From 7beff95c11071170eb27b6fa7d0cc77588caee8e Mon Sep 17 00:00:00 2001
+From: Yogesh Tyagi <yogesh.tyagi@intel.com>
+Date: Tue, 26 Jul 2022 15:25:10 +0800
+Subject: [PATCH] Fix QA Issues
+Stop ispc from inserting host file path in generated headers which leads to reproducibility problems.
+Upstream-Status: Inappropriate [OE build specific]
+Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
+---
+ src/module.cpp | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+diff --git a/src/module.cpp b/src/module.cpp
+index e2084d2e..e2626865 100644
+--- a/src/module.cpp
+++ b/src/module.cpp
+@@ -2555,7 +2555,7 @@ bool Module::writeHeader(const char *fn) {
+         perror("fopen");
+         return false;
+     }
+-    fprintf(f, "//\n// %s\n// (Header automatically generated by the ispc compiler.)\n", fn);
+    fprintf(f, "//\n// \n// (Header automatically generated by the ispc compiler.)\n");
+     fprintf(f, "// DO NOT EDIT THIS FILE.\n//\n\n");
+ 
+     // Create a nice guard string from the filename, turning any
+@@ -2677,7 +2677,7 @@ bool Module::writeDispatchHeader(DispatchHeaderInfo *DHI) {
+     FILE *f = DHI->file;
+ 
+     if (DHI->EmitFrontMatter) {
+-        fprintf(f, "//\n// %s\n// (Header automatically generated by the ispc compiler.)\n", DHI->fn);
+        fprintf(f, "//\n// \n// (Header automatically generated by the ispc compiler.)\n");
+         fprintf(f, "// DO NOT EDIT THIS FILE.\n//\n\n");
+     }
+     // Create a nice guard string from the filename, turning any
diff --git a/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0002-cmake-don-t-build-for-32-bit-targets.patch b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0002-cmake-don-t-build-for-32-bit-targets.patch
new file mode 100644
index 00000000..f452dc50
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/0002-cmake-don-t-build-for-32-bit-targets.patch
@@ -0,0 +1,52 @@
+From 16a2c22339287122d2c25d8bb33a5a51b4e6ee51 Mon Sep 17 00:00:00 2001
+From: Naveen Saini <naveen.kumar.saini@intel.com>
+Date: Thu, 24 Feb 2022 20:01:11 +0530
+Subject: [PATCH] cmake: don't build for 32-bit targets
+Error log:
+| tmp/work/corei7-64-poky-linux/ispc/1.16.0-r0/recipe-sysroot/usr/include/bits/long-double.h:23:10: fatal error: 'bits/long-double-32.h' file not found
+| #include <bits/long-double-32.h>
+|          ^~~~~~~~~~~~~~~~~~~~~~~
+| 1 error generated.
+Remove SYSTEM include search path and set -isysroot dir path
+for root dir for cross compilation.
+Upstream-Status: Inappropriate
+Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
+---
+ cmake/GenerateBuiltins.cmake | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+diff --git a/cmake/GenerateBuiltins.cmake b/cmake/GenerateBuiltins.cmake
+index f84494ed..d90cb1ec 100644
+--- a/cmake/GenerateBuiltins.cmake
+++ b/cmake/GenerateBuiltins.cmake
+@@ -253,7 +253,7 @@ function(builtin_to_cpp bit os_name arch supported_archs supported_oses resultFi
+             #   In this case headers will be installed in /usr/arm-linux-gnueabihf/include and will not be picked up
+             #   by clang by default. So the following line adds such path explicitly. If this path doesn't exist and
+             #   the headers can be found in other locations, this should not be a problem.
+-            set(includePath -isystem/usr/${debian_triple}/include)
+            set(includePath -isysroot${SYSROOT_DIR})
+         endif()
+     endif()
+ 
+@@ -339,7 +339,7 @@ function (generate_target_builtins resultList)
+     set(regular_targets ${ARGN})
+     list(FILTER regular_targets EXCLUDE REGEX wasm)
+     foreach (ispc_target ${regular_targets})
+-        foreach (bit 32 64)
+        foreach (bit 64)
+             foreach (os_name ${TARGET_OS_LIST_FOR_LL})
+                 target_ll_to_cpp(target-${ispc_target} ${bit} ${os_name} output${os_name}${bit})
+                 list(APPEND tmpList ${output${os_name}${bit}})
+@@ -405,7 +405,7 @@ function (generate_common_builtins resultList)
+     endif()
+ 
+     message (STATUS "ISPC will be built with support of ${supported_oses} for ${supported_archs}")
+-    foreach (bit 32 64)
+    foreach (bit 64)
+         foreach (os_name "windows" "linux" "freebsd" "macos" "android" "ios" "ps4" "web")
+             foreach (arch "x86" "arm" "wasm")
+                 builtin_to_cpp(${bit} ${os_name} ${arch} "${supported_archs}" "${supported_oses}" res${bit}${os_name}${arch})
diff --git a/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/run-ptest b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/run-ptest
new file mode 100644
index 00000000..77d13bb4
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc/run-ptest
@@ -0,0 +1,2 @@
+#!/bin/sh
+python3 run_tests.py
diff --git a/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc_1.24.0.bb b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc_1.24.0.bb
new file mode 100644
index 00000000..f40e445c
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/ispc/ispc_1.24.0.bb
@@ -0,0 +1,62 @@
+SUMMARY  = "Intel(R) Implicit SPMD Program Compiler"
+DESCRIPTION = "ispc is a compiler for a variant of the C programming language, \
+with extensions for single program, multiple data programming."
+HOMEPAGE = "https://github.com/ispc/ispc"
+LICENSE  = "BSD-3-Clause & Apache-2.0-with-LLVM-exception"
+LIC_FILES_CHKSUM = "file://LICENSE.txt;md5=da5ecffdd210b3cf776b32b41c182e87 \
+                    file://third-party-programs.txt;md5=2061218c7be521556719c8b504bf9ddd"
+inherit cmake python3native ptest
+SRC_URI = "git://github.com/ispc/ispc.git;protocol=https;branch=main \
+           file://0002-cmake-don-t-build-for-32-bit-targets.patch \
+           file://0001-Fix-QA-Issues.patch \
+           file://0001-Add-print-function-to-print-test-run-status-in-ptest.patch \
+           file://run-ptest \
+           "
+SRCREV = "d394222aef59e4759b06e39ec160e4aba6ee5f40"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+DEPENDS += " clang-native bison-native flex-native"
+DEPENDS:append:class-target = " clang"
+RDEPENDS:${PN}-ptest += " python3-multiprocessing"
+PACKAGECONFIG ??= "tbb"
+PACKAGECONFIG[tbb] = "-DISPCRT_BUILD_TASK_MODEL=TBB, -DISPCRT_BUILD_TASK_MODEL=OpenMP, tbb"
+YFLAGS = '-d -t -v -y --file-prefix-map=${WORKDIR}=/usr/src/debug/${PN}/${EXTENDPE}${PV}-${PR}'
+do_configure:prepend() {
+        sed -i -e 's#\${BISON_EXECUTABLE}.*#\${BISON_EXECUTABLE} ${YFLAGS} #g' ${S}/CMakeLists.txt
+        sed -i -e 's#\${FLEX_EXECUTABLE}.*#\${FLEX_EXECUTABLE} \-L #g' ${S}/CMakeLists.txt
+}
+do_install_ptest() {
+        cp -rf ${S}/run_tests.py ${D}${PTEST_PATH}
+        cp -rf ${S}/common.py ${D}${PTEST_PATH}
+        cp -rf ${S}/tests ${D}${PTEST_PATH}
+        cp -rf ${S}/test_static.isph ${D}${PTEST_PATH}
+        cp -rf ${S}/fail_db.txt ${D}${PTEST_PATH}
+        cp -rf ${S}/test_static.cpp ${D}${PTEST_PATH}
+}
+EXTRA_OECMAKE += " \
+                  -DISPC_INCLUDE_TESTS=OFF  \
+                  -DISPC_INCLUDE_EXAMPLES=OFF  \
+                  -DARM_ENABLED=OFF  \
+                  -DISPC_CROSS=ON  \
+                  -DISPC_ANDROID_TARGET=OFF  \
+                  -DISPC_FREEBSD_TARGET=OFF  \
+                  -DISPC_WINDOWS_TARGET=OFF  \
+                  -DISPC_IOS_TARGET=OFF  \
+                  -DISPC_PS_TARGET=OFF  \
+                  -DSYSROOT_DIR=${STAGING_DIR} \
+                  -DCLANG_EXECUTABLE=${STAGING_BINDIR_NATIVE}/clang \
+                  -DCLANGPP_EXECUTABLE=${STAGING_BINDIR_NATIVE}/clang++ \
+                  -DLLVM_AS_EXECUTABLE=${STAGING_BINDIR_NATIVE}/llvm-as \
+                  "
+BBCLASSEXTEND = "native nativesdk"
diff --git a/dynamic-layers/openembedded-layer/recipes-core/levelzero/level-zero_1.21.1.bb b/dynamic-layers/openembedded-layer/recipes-core/levelzero/level-zero_1.21.1.bb
new file mode 100644
index 00000000..21b3956f
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/levelzero/level-zero_1.21.1.bb
@@ -0,0 +1,32 @@
+SUMMARY = "oneAPI Level Zero Specification Headers and Loader"
+HOMEPAGE = "https://github.com/oneapi-src/level-zero"
+LICENSE = "MIT"
+LIC_FILES_CHKSUM = "file://LICENSE;md5=97957beb2f7808ffa247e5d93e6442cc"
+SRC_URI = "git://github.com/oneapi-src/level-zero.git;protocol=https;branch=master"
+SRCREV = "9536683855b17a21508e5b54ba358225d6a976da"
+inherit cmake
+DEPENDS += "opencl-headers"
+UPSTREAM_CHECK_GITTAGREGEX = "^v(?P<pver>(\d+(\.\d+)+))$"
+PACKAGES =+ "${PN}-headers ${PN}-samples ${PN}-loader"
+do_install:append () {
+        install -d ${D}${bindir} ${D}${libdir}
+        install -m 755 ${B}/bin/zello* ${D}${bindir}
+        oe_libinstall -C lib libze_null ${D}${libdir}
+}
+FILES:${PN}-headers = "${includedir}"
+FILES:${PN}-samples = "${bindir} ${libdir}/libze_null* ${libdir}/libze_validation*"
+FILES:${PN}-loader = "${libdir}"
+# PN-loader (non -dev/-dbg/nativesdk- package) contains symlink .so
+INSANE_SKIP:${PN}-loader = "dev-so"
+INSANE_SKIP:${PN}-samples = "dev-so"
+ALLOW_EMPTY:${PN} = "1"
+BBCLASSEXTEND = "native nativesdk"
diff --git a/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0001-Fix-the-compilation-warning-when-using-gcc-13-25.patch b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0001-Fix-the-compilation-warning-when-using-gcc-13-25.patch
new file mode 100644
index 00000000..2748d7ab
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0001-Fix-the-compilation-warning-when-using-gcc-13-25.patch
@@ -0,0 +1,99 @@
+From b57297c14d94dac9bdef7570b7b33d70b10171f3 Mon Sep 17 00:00:00 2001
+From: Jozef Wludzik <jozef.wludzik@intel.com>
+Date: Tue, 26 Mar 2024 14:43:29 +0100
+Subject: [PATCH 1/2] Fix the compilation warning when using gcc-13 (#25)
+Added missing headers. Fixed compilation error about casting from
+unsigned to signed int.
+Upstream-Status: Backport [https://github.com/intel/linux-npu-driver/commit/4bcbf2abe94eb4d9c083bd616b58e309a82d008a]
+Signed-off-by: Jozef Wludzik <jozef.wludzik@intel.com>
+Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
+---
+ umd/level_zero_driver/ext/source/graph/vcl_symbols.hpp | 7 ++++---
+ umd/vpu_driver/include/umd_common.hpp                  | 1 +
+ validation/umd-test/umd_prime_buffers.h                | 9 +++++++--
+ validation/umd-test/utilities/data_handle.h            | 1 +
+ 4 files changed, 13 insertions(+), 5 deletions(-)
+diff --git a/umd/level_zero_driver/ext/source/graph/vcl_symbols.hpp b/umd/level_zero_driver/ext/source/graph/vcl_symbols.hpp
+index f206ebe..682e5b4 100644
+--- a/umd/level_zero_driver/ext/source/graph/vcl_symbols.hpp
+++ b/umd/level_zero_driver/ext/source/graph/vcl_symbols.hpp
+@@ -5,12 +5,13 @@
+  *
+  */
+ 
+-#include <dlfcn.h>
+-#include <memory>
+-
+ #include "vpux_driver_compiler.h"
+ #include "vpu_driver/source/utilities/log.hpp"
+ 
+#include <array>
+#include <dlfcn.h>
+#include <memory>
+
+ class Vcl {
+   public:
+     static Vcl &sym() {
+diff --git a/umd/vpu_driver/include/umd_common.hpp b/umd/vpu_driver/include/umd_common.hpp
+index 0c874a3..5ad9be2 100644
+--- a/umd/vpu_driver/include/umd_common.hpp
+++ b/umd/vpu_driver/include/umd_common.hpp
+@@ -7,6 +7,7 @@
+ 
+ #pragma once
+ 
+#include <cstdint>
+ #include <limits>
+ #include <linux/kernel.h>
+ #include <stdexcept>
+diff --git a/validation/umd-test/umd_prime_buffers.h b/validation/umd-test/umd_prime_buffers.h
+index 6f7c7de..ab4814c 100644
+--- a/validation/umd-test/umd_prime_buffers.h
+++ b/validation/umd-test/umd_prime_buffers.h
+@@ -6,12 +6,17 @@
+  */
+ 
+ #pragma once
+
+#include "umd_test.h"
+
+ #include <fcntl.h>
+-#include <linux/kernel.h>
+ #include <linux/dma-buf.h>
+ #include <linux/dma-heap.h>
+#include <linux/kernel.h>
+#include <stdint.h>
+ #include <sys/ioctl.h>
+ #include <sys/mman.h>
+#include <unistd.h>
+ 
+ #define ALLIGN_TO_PAGE(x) __ALIGN_KERNEL((x), (UmdTest::PAGE_SIZE))
+ 
+@@ -60,7 +65,7 @@ class PrimeBufferHelper {
+             return false;
+ 
+         bufferFd = heapAlloc.fd;
+-        buffers.insert({heapAlloc.fd, {size, nullptr}});
+        buffers.insert({static_cast<int>(heapAlloc.fd), {size, nullptr}});
+         return true;
+     }
+ 
+diff --git a/validation/umd-test/utilities/data_handle.h b/validation/umd-test/utilities/data_handle.h
+index d6e0ec0..5d937b2 100644
+--- a/validation/umd-test/utilities/data_handle.h
+++ b/validation/umd-test/utilities/data_handle.h
+@@ -6,6 +6,7 @@
+  */
+ 
+ #include <linux/kernel.h>
+#include <stdint.h>
+ #include <string>
+ #include <vector>
+ 
+-- 
+2.43.0
diff --git a/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0001-linux-npu-driver-fix-multilib-install-issue.patch b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0001-linux-npu-driver-fix-multilib-install-issue.patch
new file mode 100644
index 00000000..71a60b20
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0001-linux-npu-driver-fix-multilib-install-issue.patch
@@ -0,0 +1,28 @@
+From 561e3b5edc0ec3d8835aaf8ef8e5c9e8f9b53061 Mon Sep 17 00:00:00 2001
+From: Yogesh Tyagi <yogesh.tyagi@intel.com>
+Date: Wed, 28 May 2025 13:35:18 +0800
+Subject: [PATCH] linux-npu-driver : fix multilib install issue
+Upstream-Status: Inappropriate [oe specific]
+Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
+---
+ firmware/CMakeLists.txt | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+diff --git a/firmware/CMakeLists.txt b/firmware/CMakeLists.txt
+index 0c093ca..ba346a0 100644
+--- a/firmware/CMakeLists.txt
+++ b/firmware/CMakeLists.txt
+@@ -12,7 +12,7 @@ target_include_directories(${PROJECT_NAME} INTERFACE include)
+ file(GLOB FIRMWARE_BINARIES ${CMAKE_CURRENT_SOURCE_DIR}/bin/*.bin)
+ if (FIRMWARE_BINARIES)
+   install(FILES ${FIRMWARE_BINARIES}
+-    DESTINATION /lib/firmware/updates/intel/vpu/
+    DESTINATION ${CMAKE_INSTALL_FIRMWARE_DIR}/firmware/updates/intel/vpu/
+     PERMISSIONS OWNER_READ
+     COMPONENT fw-npu)
+ endif()
+-- 
+2.37.3
diff --git a/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0002-Fix-compilation-failure-with-GCC-14.patch b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0002-Fix-compilation-failure-with-GCC-14.patch
new file mode 100644
index 00000000..9fb97354
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver/0002-Fix-compilation-failure-with-GCC-14.patch
@@ -0,0 +1,110 @@
+From a9f51fd88effb7d324609e692ca7da576d6dad2e Mon Sep 17 00:00:00 2001
+From: Naveen Saini <naveen.kumar.saini@intel.com>
+Date: Tue, 28 May 2024 10:23:42 +0800
+Subject: [PATCH 2/2] Fix compilation failure with GCC-14
+umd/level_zero_driver/core/source/event/event.cpp:65:31: error: 'remove_if' is not a member of 'std'; did you mean 'remove_cv'?
+|    65 |     associatedJobs.erase(std::remove_if(associatedJobs.begin(),
+|       |                               ^~~~~~~~~
+|       |                               remove_cv
+| umd/vpu_driver/source/command/vpu_command.cpp: In member function 'void VPU::VPUCommand::appendAssociateBufferObject(VPU::VPUBufferObject*)':
+| umd/vpu_driver/source/command/vpu_command.cpp:126:20: error: 'find' is not a member of 'std'; did you mean 'bind'?
+|   126 |     auto it = std::find(bufferObjects.begin(), bufferObjects.end(), bo);
+|       |                    ^~~~
+|       |                    bind
+| umd/vpu_driver/source/command/vpu_command_buffer.cpp: In member function 'bool VPU::VPUCommandBuffer::addCommand(VPU::VPUCommand*, uint64_t&, uint64_t&)':
+| umd/vpu_driver/source/command/vpu_command_buffer.cpp:185:24: error: 'find' is not a member of 'std'; did you mean 'bind'?
+|   185 |         auto it = std::find(bufferHandles.begin(), bufferHandles.end(), bo->getHandle());
+|       |                        ^~~~
+|       |                        bind
+| umd/level_zero_driver/ext/source/graph/elf_parser.cpp:301:32: error: 'max_element' is not a member of 'std'; did you mean 'tuple_element'?
+|   301 |                           std::max_element(stride_begin + TENSOR_5D_STRIDE_C, stride_end));
+|       |                                ^~~~~~~~~~~
+|       |                                tuple_element
+| umd/level_zero_driver/ext/source/graph/elf_parser.cpp:315:37: error: 'max_element' is not a member of 'std'; did you mean 'tuple_element'?
+|   315 |         auto max_stride_val = *std::max_element(stride_begin + TENSOR_4D_STRIDE_C, stride_end);
+|       |                                     ^~~~~~~~~~~
+| umd/level_zero_driver/tools/source/metrics/metric.cpp: In member function 'void L0::MetricContext::deactivateMetricGroups(int)':
+| umd/level_zero_driver/tools/source/metrics/metric.cpp:275:38: error: 'remove_if' is not a member of 'std'; did you mean 'remove_cv'?
+|   275 |     activatedMetricGroups.erase(std::remove_if(activatedMetricGroups.begin(),
+|       |                                      ^~~~~~~~~
+|       |                                      remove_cv
+Upstream-Status: Submitted [https://github.com/intel/linux-npu-driver/pull/30]
+Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
+---
+ umd/level_zero_driver/core/source/event/event.cpp     | 1 +
+ umd/level_zero_driver/ext/source/graph/elf_parser.cpp | 1 +
+ umd/level_zero_driver/tools/source/metrics/metric.cpp | 1 +
+ umd/vpu_driver/source/command/vpu_command.cpp         | 1 +
+ umd/vpu_driver/source/command/vpu_command_buffer.cpp  | 1 +
+ 5 files changed, 5 insertions(+)
+diff --git a/umd/level_zero_driver/core/source/event/event.cpp b/umd/level_zero_driver/core/source/event/event.cpp
+index a92248f..196d176 100644
+--- a/umd/level_zero_driver/core/source/event/event.cpp
+++ b/umd/level_zero_driver/core/source/event/event.cpp
+@@ -14,6 +14,7 @@
+ 
+ #include <level_zero/ze_api.h>
+ #include <thread>
+#include <algorithm>
+ 
+ namespace L0 {
+ 
+diff --git a/umd/level_zero_driver/ext/source/graph/elf_parser.cpp b/umd/level_zero_driver/ext/source/graph/elf_parser.cpp
+index a1c8e14..dfbd61d 100644
+--- a/umd/level_zero_driver/ext/source/graph/elf_parser.cpp
+++ b/umd/level_zero_driver/ext/source/graph/elf_parser.cpp
+@@ -21,6 +21,7 @@
+ #include <vpux_headers/metadata.hpp>
+ #include <vpux_elf/types/vpu_extensions.hpp>
+ #include <vpux_elf/utils/error.hpp>
+#include <algorithm>
+ 
+ namespace L0 {
+ 
+diff --git a/umd/level_zero_driver/tools/source/metrics/metric.cpp b/umd/level_zero_driver/tools/source/metrics/metric.cpp
+index b67750f..9497311 100644
+--- a/umd/level_zero_driver/tools/source/metrics/metric.cpp
+++ b/umd/level_zero_driver/tools/source/metrics/metric.cpp
+@@ -7,6 +7,7 @@
+ 
+ #include "level_zero_driver/tools/source/metrics/metric.hpp"
+ #include "vpu_driver/source/utilities/log.hpp"
+#include <algorithm>
+ 
+ namespace L0 {
+ 
+diff --git a/umd/vpu_driver/source/command/vpu_command.cpp b/umd/vpu_driver/source/command/vpu_command.cpp
+index f4ca23f..75331d9 100644
+--- a/umd/vpu_driver/source/command/vpu_command.cpp
+++ b/umd/vpu_driver/source/command/vpu_command.cpp
+@@ -14,6 +14,7 @@
+ #include <cstdint>
+ #include <vector>
+ #include <map>
+#include <algorithm>
+ 
+ namespace VPU {
+ 
+diff --git a/umd/vpu_driver/source/command/vpu_command_buffer.cpp b/umd/vpu_driver/source/command/vpu_command_buffer.cpp
+index c4ad052..bbb80ec 100644
+--- a/umd/vpu_driver/source/command/vpu_command_buffer.cpp
+++ b/umd/vpu_driver/source/command/vpu_command_buffer.cpp
+@@ -11,6 +11,7 @@
+ #include "vpu_driver/source/command/vpu_command_buffer.hpp"
+ #include "vpu_driver/source/command/vpu_copy_command.hpp"
+ #include "vpu_driver/source/utilities/log.hpp"
+#include <algorithm>
+ 
+ namespace VPU {
+ 
+-- 
+2.43.0
diff --git a/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver_1.17.0.bb b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver_1.17.0.bb
new file mode 100644
index 00000000..852bc0c1
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-core/linux-npu-driver/linux-npu-driver_1.17.0.bb
@@ -0,0 +1,43 @@
+SUMMARY = "User Mode Driver for Intel® NPU device"
+HOMEPAGE = "https://github.com/intel/linux-npu-driver"
+LICENSE = "MIT & Apache-2.0"
+LIC_FILES_CHKSUM = "file://LICENSE.md;md5=7b256470048be42466f7d10e1d6482e6 \
+                    file://third-party-programs.txt;md5=0ae40d7f1ef3bbd509197e427fdd7e70 \
+                    file://third_party/vpux_elf/LICENSE;md5=a7a2dfa2b52a22cf2257893ee87ba11c"
+SRC_URI = "git://github.com/intel/linux-npu-driver.git;protocol=https;name=linux-npu-driver;branch=main;lfs=1 \
+            git://github.com/openvinotoolkit/npu_plugin_elf.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/third_party/vpux_elf;name=vpux-elf;nobranch=1 \
+            git://github.com/jbeder/yaml-cpp.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/third_party/yaml-cpp;name=yaml-cpp;nobranch=1 \
+            git://github.com/intel/level-zero-npu-extensions.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/third_party/level-zero-npu-extensions;name=lzvext;nobranch=1 \
+            git://github.com/google/googletest.git;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/third_party/googletest;name=googletest;nobranch=1 \
+            file://0001-linux-npu-driver-fix-multilib-install-issue.patch \
+        "
+SRCREV_linux-npu-driver = "0fe92dd0720448fb571f0ac4e5e64ef9f2ec3bd7"
+SRCREV_vpux-elf = "50f2b13dbb6dd435c3e2ef6f8abb7393633bfcdd"
+SRCREV_yaml-cpp = "f7320141120f720aecc4c32be25586e7da9eb978"
+SRCREV_lzvext = "c7d8f849d6a8195c1db38cbaca8d431cbabf3a6e"
+SRCREV_googletest = "b514bdc898e2951020cbdca1304b75f5950d1f59"
+SRCREV_FORMAT = "linux-npu-driver_vpux-elf_yaml-cpp_lzvext_googletest"
+inherit cmake
+# Fix warning _FORTIFY_SOURCE requires compiling with optimization (-O)
+EXTRA_OECMAKE += " -DCMAKE_BUILD_TYPE=Release "
+EXTRA_OECMAKE += " -DCMAKE_CXX_FLAGS_RELEASE=-O2 "
+EXTRA_OECMAKE += " -DCMAKE_CXX_FLAGS='-I${RECIPE_SYSROOT}/usr/include/level_zero'"
+EXTRA_OECMAKE += " -DCMAKE_INSTALL_FIRMWARE_DIR=${nonarch_base_libdir}"
+DEPENDS = "level-zero dpkg-native pkgconfig-native"
+PACKAGES =+ "${PN}-firmware ${PN}-tests"
+FILES:${PN}-firmware = "${nonarch_base_libdir}/firmware/updates/intel/vpu/*"
+FILES:${PN}-tests = "${bindir}"
+INSANE_SKIP:${PN} += "buildpaths"
+INSANE_SKIP:${PN}-dbg += "buildpaths"
+INSANE_SKIP:${PN}-tests += "buildpaths"
+INSANE_SKIP:${PN}-firmware += "buildpaths"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/dpcpp-compiler/intel-oneapi-dpcpp-cpp-runtime_2024.0.0-49819.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/dpcpp-compiler/intel-oneapi-dpcpp-cpp-runtime_2024.0.0-49819.bb
new file mode 100644
index 00000000..106b3ad5
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/dpcpp-compiler/intel-oneapi-dpcpp-cpp-runtime_2024.0.0-49819.bb
@@ -0,0 +1,54 @@
+SUMMARY = "Intel® oneAPI DPC++/C++ Compiler runtime files"
+DESCRIPTION = "The Intel® oneAPI DPC++/C++ Compiler provides optimizations \
+that help your applications run faster on Intel® 64 architectures with support \
+for the latest C, C++, and SYCL language standards. This compiler produces \
+optimized code that can run significantly faster by taking advantage of the \
+ever-increasing core count and vector register width in Intel® Xeon® processors \
+and compatible processors."
+HOMEPAGE = "https://www.intel.com/content/www/us/en/developer/tools/oneapi/dpc-compiler.html"
+LICENSE = "EULA"
+COMPILERMAINVER = "2024.0"
+LIC_FILES_CHKSUM = " \
+                     file://opt/intel/oneapi/licensing/${COMPILERMAINVER}/licensing/${COMPILERMAINVER}/license.htm;md5=5ff64c6ff3ef98089ed69360e7a84c39 \
+                     "
+COMPILERDOTVER = "2024.0.0-49406"
+DEVUTILITVERSION = "2024.0-2024.0.0-49320"
+SRC_URI = " \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-compiler-dpcpp-cpp-runtime-${COMPILERMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=dpcpp-runtime \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-compiler-dpcpp-cpp-common-${COMPILERMAINVER}-${PV}_all.deb;subdir=${BPN};name=dpcpp-common \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-compiler-shared-runtime-${COMPILERMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=compiler-shared-runtime \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-common-vars-${COMPILERDOTVER}_all.deb;subdir=${BPN};name=common-vars \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-openmp-${COMPILERMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=openmp \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-openmp-common-${COMPILERMAINVER}-${PV}_all.deb;subdir=${BPN};name=openmp-common \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-common-licensing-${COMPILERMAINVER}-${COMPILERDOTVER}_all.deb;subdir=${BPN};name=license \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-dev-utilities-${DEVUTILITVERSION}_amd64.deb;subdir=${BPN};name=dev-utils \
+            "
+SRC_URI[dpcpp-runtime.sha256sum] = "e24f0ba69daf3f66ceaf23d5e632f183cdb90bac69f65407fdb4407fc9034f33"
+SRC_URI[dpcpp-common.sha256sum] = "f5a3db6a725598224edf1099260955aee3e36beadcaed2af5b8b453e873a82fa"
+SRC_URI[compiler-shared-runtime.sha256sum] = "bce010cbe076259ddd3feb8e69792869e22fccd5b4e2c9af9e815826f2c1a394"
+SRC_URI[common-vars.sha256sum] = "368553c99db1b52060b8225355336778be0b00e5991d0f769c42f891c6328750"
+SRC_URI[openmp.sha256sum] = "154ff1e81adfdc872ba1d47bd860de70d62188417c7128422435dfd0ceca62fe"
+SRC_URI[openmp-common.sha256sum] = "8217001d78311cbef97dd139e684c6767932b532309c3843ba57d7894d15c07d"
+SRC_URI[license.sha256sum] = "9f9c8a12fc0bc82ab5b71e118e66745eff23f42224eba304068225b366cd74b6"
+SRC_URI[dev-utils.sha256sum] = "c675d960a5abca361cead9217d6e74adee499ee0a095c4e44092bd710b304d50"
+S = "${UNPACKDIR}/${BPN}"
+inherit bin_package
+RDEPENDS:${PN} += "virtual-opencl-icd zlib tbb level-zero-loader bash tcsh"
+SKIP_FILEDEPS:${PN} = '1'
+INHIBIT_PACKAGE_STRIP = "1"
+INHIBIT_PACKAGE_DEBUG_SPLIT  = "1"
+# doesn't have GNU_HASH (didn't pass LDFLAGS?)
+INSANE_SKIP:${PN} += "textrel dev-so dev-elf ldflags already-stripped staticdev rpaths arch useless-rpaths file-rdeps"
+FILES_SOLIBSDEV = ""
+BBCLASSEXTEND = "native nativesdk"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/dpcpp-compiler/intel-oneapi-dpcpp-cpp_2024.0.0-49819.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/dpcpp-compiler/intel-oneapi-dpcpp-cpp_2024.0.0-49819.bb
new file mode 100644
index 00000000..d2bd72a3
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/dpcpp-compiler/intel-oneapi-dpcpp-cpp_2024.0.0-49819.bb
@@ -0,0 +1,45 @@
+SUMMARY = "Intel® oneAPI DPC++/C++ Compiler"
+DESCRIPTION = "The Intel® oneAPI DPC++/C++ Compiler provides optimizations \
+that help your applications run faster on Intel® 64 architectures with support \
+for the latest C, C++, and SYCL language standards. This compiler produces \
+optimized code that can run significantly faster by taking advantage of the \
+ever-increasing core count and vector register width in Intel® Xeon® processors \
+and compatible processors."
+HOMEPAGE = "https://www.intel.com/content/www/us/en/developer/tools/oneapi/dpc-compiler.html"
+LICENSE = "EULA"
+COMPILERMAINVER = "2024.0"
+LIC_FILES_CHKSUM = " \
+                     file://opt/intel/oneapi/compiler/${COMPILERMAINVER}/share/doc/compiler/credist.txt;md5=b41f55af9f479b9570fc35b955d5ba1a \
+                     "
+SRC_URI = " \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-dpcpp-cpp-${COMPILERMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=icx-compiler \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-compiler-shared-${COMPILERMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=compiler-linker \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-compiler-shared-common-${COMPILERMAINVER}-${PV}_all.deb;subdir=${BPN};name=shared-common \
+            "
+SRC_URI[icx-compiler.sha256sum] = "0dcbac766d5a1519d4cf393f5a85e71d19024fef65f77638f3f849796b62cd82"
+SRC_URI[compiler-linker.sha256sum] = "e00faea6d797934d62143e4aa70b727ce30f80fdf30769d22122b3051140c236"
+SRC_URI[shared-common.sha256sum] = "cf490a4a790f349da79e618359598d3b32312ca3b2639e5d4c84e1cfa2745558"
+S = "${UNPACKDIR}/${BPN}"
+inherit bin_package
+RDEPENDS:${PN} += "intel-oneapi-dpcpp-cpp-runtime"
+SKIP_FILEDEPS:${PN} = '1'
+INHIBIT_PACKAGE_STRIP = "1"
+INHIBIT_PACKAGE_DEBUG_SPLIT  = "1"
+# doesn't have GNU_HASH (didn't pass LDFLAGS?)
+INSANE_SKIP:${PN} += "textrel dev-so dev-elf ldflags already-stripped file-rdeps staticdev rpaths arch useless-rpaths"
+FILES_SOLIBSDEV = ""
+EXCLUDE_FROM_SHLIBS = "1"
+BBCLASSEXTEND = "native nativesdk"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/embree/embree_4.3.3.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/embree/embree_4.3.3.bb
new file mode 100644
index 00000000..77549479
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/embree/embree_4.3.3.bb
@@ -0,0 +1,30 @@
+SUMMARY  = "Collection of high-performance ray tracing kernels"
+DESCRIPTION = "A collection of high-performance ray tracing kernels \
+intended to graphics application engineers that want to improve the \
+performance of their application."
+HOMEPAGE = "https://github.com/embree/embree"
+LICENSE  = "Apache-2.0 & BSD-3-Clause"
+LIC_FILES_CHKSUM = "file://LICENSE.txt;md5=3b83ef96387f14655fc854ddc3c6bd57 \
+                    file://third-party-programs.txt;md5=f989f5b74cfff0d45d3ccf0e1366cbdc \
+                    file://common/math/transcendental.h;beginline=6;endline=8;md5=73380bb2ab6613b30b8464f114bd0ca8"
+inherit pkgconfig cmake
+SRC_URI = "git://github.com/embree/embree.git;protocol=https;branch=master"
+SRCREV = "5730b150471602d6dc02d9b7d8a4a6ce9ceffe16"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+DEPENDS = "tbb jpeg libpng glfw ispc-native"
+EXTRA_OECMAKE += " \
+                  -DEMBREE_IGNORE_CMAKE_CXX_FLAGS=OFF  \
+                  -DEMBREE_MAX_ISA=DEFAULT  \
+                  -DEMBREE_TUTORIALS=OFF  \
+                  -DEMBREE_ISPC_SUPPORT=ON  \
+                  -DEMBREE_ZIP_MODE=OFF  \
+                  "
+UPSTREAM_CHECK_GITTAGREGEX = "^v(?P<pver>(\d+(\.\d+)+))$"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/ipp/intel-oneapi-ipp_2021.10.0-653.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/ipp/intel-oneapi-ipp_2021.10.0-653.bb
new file mode 100644
index 00000000..d10f50f9
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/ipp/intel-oneapi-ipp_2021.10.0-653.bb
@@ -0,0 +1,35 @@
+DESCRIPTION = "Intel® Integrated Performance Primitives are production-ready \
+ building blocks for cross-platform performance. Develop high-performance vision, \
+ signal, security, and storage applications with this multithreaded software library."
+HOMEPAGE = "https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/ipp.html"
+LICENSE = "ISSL"
+MAXVER = "2021.10"
+LIC_FILES_CHKSUM = " \
+                     file://opt/intel/oneapi/ipp/${MAXVER}/share/doc/ipp/licensing/license.txt;md5=d7cdc92ed6c4de1263da879599ddc3e2 \
+                     file://opt/intel/oneapi/ipp/${MAXVER}/share/doc/ipp/licensing/third-party-programs.txt;md5=22bd13987911dcf790907041b43081f3 \
+                     "
+SRC_URI = " \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-ipp-${MAXVER}-${PV}_amd64.deb;subdir=${BPN};name=ipp \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-ipp-common-devel-${MAXVER}-${PV}_all.deb;subdir=${BPN};name=headers \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-ipp-common-${MAXVER}-${PV}_all.deb;subdir=${BPN};name=env \
+            "
+SRC_URI[ipp.sha256sum] = "b51e45c6e691aa46c7136b0ab61f5abe346388433e017a30cf53fd23e92bea07"
+SRC_URI[headers.sha256sum] = "342f37ab2f82bc9f4498435f848ee660591c2488b44d988bf6ee96b2a71fd005"
+SRC_URI[env.sha256sum] = "731e8c28a3b8b757730cd874d0941de2eb744856128f24ade59d36c12b415bf6"
+S = "${UNPACKDIR}/${BPN}"
+COMPATIBLE_HOST:libc-musl = "null"
+inherit bin_package
+INHIBIT_PACKAGE_STRIP = "1"
+INHIBIT_PACKAGE_DEBUG_SPLIT  = "1"
+INHIBIT_DEFAULT_DEPS = ""
+RDEPENDS:${PN} += "tbb setup-intel-oneapi-env"
+INSANE_SKIP:${PN} += "ldflags dev-so"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/mkl/intel-oneapi-mkl_2024.0.0-49656.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/mkl/intel-oneapi-mkl_2024.0.0-49656.bb
new file mode 100644
index 00000000..e77ac588
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/mkl/intel-oneapi-mkl_2024.0.0-49656.bb
@@ -0,0 +1,74 @@
+SUMMARY = "Intel® oneAPI Math Kernel Library (oneMKL)"
+DESCRIPTION = "The Intel® oneAPI Math Kernel Library (oneMKL) is a computing \
+ math library of highly optimized and extensively parallelized routines \
+ for applications that require maximum performance. oneMKL contains \
+ the high-performance optimizations from the full Intel® Math Kernel Library \
+ for CPU architectures (with C/Fortran programming language interfaces)\
+ and adds to them a set of DPC++ programming language interfaces for \
+ achieving performance on various CPU architectures \
+ and Intel Graphics Technology for certain key functionalities."
+HOMEPAGE = "https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl.html"
+LICENSE = "ISSL"
+MKLMAINVER = "2024.0"
+LIC_FILES_CHKSUM = " \
+                     file://opt/intel/oneapi/mkl/${MKLMAINVER}/share/doc/mkl/licensing/license.txt;md5=8510d21bf355a76e378c3216c3929ccd  \
+                     file://opt/intel/oneapi/mkl/${MKLMAINVER}/share/doc/mkl/licensing/third-party-programs-benchmarks.txt;md5=cb98e1a1f14c05ea85a979ea8982e7a4 \
+                     file://opt/intel/oneapi/mkl/${MKLMAINVER}/share/doc/mkl/licensing/third-party-programs-ipp.txt;md5=a4b2bf15e38f5c1267cdafed18bc0b09 \
+                     file://opt/intel/oneapi/mkl/${MKLMAINVER}/share/doc/mkl/licensing/third-party-programs-openmp.txt;md5=6b3c1aa2a11393060074c0346ce21e49 \
+                     file://opt/intel/oneapi/mkl/${MKLMAINVER}/share/doc/mkl/licensing/third-party-programs-safestring.txt;md5=c3aeee91c6d35a0f0753aed6c2633b82 \
+                     file://opt/intel/oneapi/mkl/${MKLMAINVER}/share/doc/mkl/licensing/third-party-programs.txt;md5=27de873e4084d62530fe828406b33ca9 \
+                     "
+SRC_URI = " \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-mkl-${MKLMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=runtime \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-mkl-common-devel-${MKLMAINVER}-${PV}_all.deb;subdir=${BPN};name=common-devel \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-mkl-devel-${MKLMAINVER}-${PV}_amd64.deb;subdir=${BPN};name=devel \
+            https://apt.repos.intel.com/oneapi/pool/main/intel-oneapi-mkl-common-${MKLMAINVER}-${PV}_all.deb;subdir=${BPN};name=common-vars \
+            "
+SRC_URI[runtime.sha256sum] = "10a86e24051d6ef4a80fd839c570e629190638a3c0ac9bcca99ab855f534b959"
+SRC_URI[common-devel.sha256sum] = "adbf0ea946f63946d29b7f9c750c38a42ea7a65d8c81655b268aa2c7bb908192"
+SRC_URI[devel.sha256sum] = "fab2a6f15e18bfd9b4d425f2703e4e98928c57f52c4feebc9ed886f097062e84"
+SRC_URI[common-vars.sha256sum] = "ec2b67813739fa4a2895f63479a41acba2174afe2d0cb8a0c1c9119d1317d8ef"
+S = "${UNPACKDIR}/${BPN}"
+inherit bin_package
+do_install:append () {
+        install -d ${D}${bindir}
+        (cd ${D}${bindir} ; ln -s ../../opt/intel/oneapi/mkl/${MKLMAINVER}/bin/* .)
+        install -d ${D}${libdir}
+        (cd ${D}${libdir} ; ln -s ../../opt/intel/oneapi/mkl/${MKLMAINVER}/lib/intel64/*.so* .)
+        (cd ${D}${libdir} ; ln -s ../../opt/intel/oneapi/mkl/${MKLMAINVER}/lib/intel64/*.a* .)
+        install -d ${D}${libdir}/pkgconfig
+        (cd ${D}${libdir}/pkgconfig ; ln -s ../../../opt/intel/oneapi/mkl/${MKLMAINVER}/lib/pkgconfig/* .)
+        install -d ${D}${libdir}/cmake
+        (cd ${D}${libdir}/cmake ; ln -s ../../../opt/intel/oneapi/mkl/${MKLMAINVER}/lib/cmake/* .)
+        install -d ${D}${includedir}
+        find ${D}/opt/intel/oneapi/mkl/${MKLMAINVER}/include/ -mindepth 1 -maxdepth 1 -type d -printf '%f\n' | while read srcdir; do
+            install -d ${D}${includedir}/$srcdir
+            (cd ${D}${includedir} ; ln -s ../../opt/intel/oneapi/mkl/${MKLMAINVER}/include/$srcdir/* ./$srcdir/)
+        done
+        find ${D}/opt/intel/oneapi/mkl/${MKLMAINVER}/include/ -mindepth 1 -maxdepth 1 -type f -printf '%f\n' | while read srcfile; do
+            (cd ${D}${includedir} ; ln -s ../../opt/intel/oneapi/mkl/${MKLMAINVER}/include/$srcfile .)
+        done
+}
+AUTO_LIBNAME_PKGS = ""
+INHIBIT_PACKAGE_STRIP = "1"
+INHIBIT_PACKAGE_DEBUG_SPLIT  = "1"
+RDEPENDS:${PN} += "bash tbb intel-oneapi-dpcpp-cpp-runtime setup-intel-oneapi-env virtual-opencl-icd"
+INSANE_SKIP:${PN} = "ldflags textrel dev-so staticdev arch already-stripped"
+FILES:${PN}-staticdev += "/opt/intel/oneapi/mkl/${MKLMAINVER}/lib/*.a*"
+SKIP_FILEDEPS:${PN} = '1'
+SYSROOT_DIRS += "/opt"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/oidn/oidn_2.1.0.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/oidn/oidn_2.1.0.bb
new file mode 100644
index 00000000..8005f544
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/oidn/oidn_2.1.0.bb
@@ -0,0 +1,27 @@
+SUMMARY = "Intel® Open Image Denoise"
+DESCRIPTION = "Intel Open Image Denoise is an open source library of \
+high-performance, high-quality denoising filters for images \
+rendered with ray tracing. Intel Open Image Denoise is part \
+of the Intel® oneAPI Rendering Toolkit"
+HOMEPAGE = "https://www.openimagedenoise.org/"
+LICENSE = "Apache-2.0 & BSD-3-Clause"
+LIC_FILES_CHKSUM = "file://LICENSE.txt;md5=3b83ef96387f14655fc854ddc3c6bd57 \
+                    file://external/mkl-dnn/LICENSE;md5=b48e3de3bfd47c27882a0d85b20823f5 \
+                    file://external/mkl-dnn/src/cpu/x64/xbyak/COPYRIGHT;md5=3b9bf048d063d54cdb28964db558bcc7 \
+                    file://external/mkl-dnn/src/common/ittnotify/LICENSE.BSD;md5=e671ff178b24a95a382ba670503c66fb \
+                    file://weights/LICENSE.txt;md5=3b83ef96387f14655fc854ddc3c6bd57"
+SRC_URI = "https://github.com/OpenImageDenoise/${BPN}/releases/download/v${PV}/${BP}.src.tar.gz\
+           "
+SRC_URI[sha256sum] = "ce144ba582ff36563d9442ee07fa2a4d249bc85aa93e5b25fc527ff4ee755ed6"
+inherit cmake
+DEPENDS += "tbb ispc-native"
+do_install:append() {
+        chrpath -d ${D}${bindir}/* ${D}${libdir}/*${SOLIBS}
+}
+UPSTREAM_CHECK_URI = "https://github.com/OpenImageDenoise/oidn/releases"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/openvkl/openvkl_2.0.1.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/openvkl/openvkl_2.0.1.bb
new file mode 100644
index 00000000..1b0b32ed
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/openvkl/openvkl_2.0.1.bb
@@ -0,0 +1,40 @@
+SUMMARY  = "Intel(R) Open Volume Kernel Library"
+DESCRIPTION = "Intel(R) Open Volume Kernel Library (Intel(R) Open VKL) is a \
+collection of high-performance volume computation kernels. The target users \
+of Open VKL are graphics application engineers who want to improve the \
+performance of their volume rendering applications by leveraging Open VKL’s \
+performance-optimized kernels, which include volume traversal and sampling \
+functionality for a variety of volumetric data formats. The kernels are optimized \
+for the latest Intel(R) processors with support for SSE, AVX, AVX2, and AVX-512 \
+instructions."
+HOMEPAGE = "https://www.openvkl.org/"
+LICENSE  = "Apache-2.0 & BSD-3-Clause & MIT & Zlib"
+LIC_FILES_CHKSUM = "file://LICENSE.txt;md5=3b83ef96387f14655fc854ddc3c6bd57 \
+                    file://third-party-programs.txt;md5=69ec7caf49616c471161b921f53d5ec0 \
+                    file://testing/external/half.hpp;beginline=1;endline=17;md5=4b60058493630c3bd0ef145470f04a7b"
+inherit pkgconfig cmake
+SRC_URI = "git://github.com/openvkl/openvkl.git;protocol=https;branch=master \
+           "
+SRCREV = "8c6ba526813b871a624cb9d73d4cbb689ac7f4ce"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+DEPENDS = "ispc ispc-native rkcommon embree"
+EXTRA_OECMAKE += " \
+                  -DISPC_EXECUTABLE=${STAGING_BINDIR_NATIVE}/ispc  \
+                  "
+EXTRA_OECMAKE:intel-corei7-64 += " \
+                  -DOPENVKL_ISA_AVX=OFF  \
+                  -DOPENVKL_ISA_AVX2=OFF  \
+                  -DOPENVKL_ISA_AVX512SKX=OFF  \
+                  "
+PACKAGES =+ "${PN}-examples"
+FILES:${PN}-examples = "\
+                     ${bindir} \
+                     "
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/ospray/ospray/0001-Fix-GCC11-Compile-Error-in-benchmark_register.h.patch b/dynamic-layers/openembedded-layer/recipes-oneapi/ospray/ospray/0001-Fix-GCC11-Compile-Error-in-benchmark_register.h.patch
new file mode 100644
index 00000000..c2136321
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/ospray/ospray/0001-Fix-GCC11-Compile-Error-in-benchmark_register.h.patch
@@ -0,0 +1,28 @@
+From 09e6b6615d9a16e9555eff9d569356e32bd26aa4 Mon Sep 17 00:00:00 2001
+From: benradel <86351445+benradel@users.noreply.github.com>
+Date: Wed, 23 Jun 2021 11:56:03 +0200
+Subject: [PATCH] Fix GCC11 Compile Error in benchmark_register.h
+Fix GCC11 compilation error due to missing header "limits" in benchmark_register.h
+Upstream-Status: Submitted [https://github.com/ospray/ospray/pull/484/files]
+Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
+---
+ apps/common/external/benchmark/src/benchmark_register.h | 1 +
+ 1 file changed, 1 insertion(+)
+diff --git a/apps/common/external/benchmark/src/benchmark_register.h b/apps/common/external/benchmark/src/benchmark_register.h
+index 61377d742..8f1bb7795 100644
+--- a/apps/common/external/benchmark/src/benchmark_register.h
+++ b/apps/common/external/benchmark/src/benchmark_register.h
+@@ -2,6 +2,7 @@
+ #define BENCHMARK_REGISTER_H
+ 
+ #include <vector>
+#include <limits>
+ 
+ #include "check.h"
+ 
+-- 
+2.32.0
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/ospray/ospray_3.2.0.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/ospray/ospray_3.2.0.bb
new file mode 100644
index 00000000..d4e85cbc
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/ospray/ospray_3.2.0.bb
@@ -0,0 +1,36 @@
+SUMMARY  = "Intel OSPray, Ray Tracing based Rendering Engine"
+DESCRIPTION = "Intel OSPRay is an open source, scalable, and portable ray \
+tracing engine for high-performance, high-fidelity visualization on \
+Intel Architecture CPUs."
+HOMEPAGE = "https://www.ospray.org/"
+LICENSE  = "Apache-2.0 & BSD-3-Clause & MIT & Zlib"
+LIC_FILES_CHKSUM = "file://LICENSE.txt;md5=1dece7821bf3fd70fe1309eaa37d52a2 \
+                    file://third-party-programs.txt;md5=e37b77e3bd997abccc359c710fb1f1db \
+                    "
+inherit pkgconfig cmake
+SRC_URI = "git://github.com/ospray/ospray.git;protocol=https;branch=master \
+           git://github.com/nothings/stb;protocol=https;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/apps/common/external/stb_image/stb;name=stb;nobranch=1 \
+          "
+SRCREV = "85af2929937d516997451cbd52d352cf93125ed2"
+COMPATIBLE_HOST = '(x86_64).*-linux'
+COMPATIBLE_HOST:libc-musl = "null"
+DEPENDS = "rkcommon ispc ispc-native openvkl embree"
+EXTRA_OECMAKE += " \
+                  -DISPC_EXECUTABLE=${STAGING_BINDIR_NATIVE}/ispc \
+                  -DOSPRAY_ENABLE_APPS_BENCHMARK=OFF \
+                  -DOSPRAY_ENABLE_APPS_TESTING=OFF \
+                  -DOSPRAY_ENABLE_APPS_EXAMPLES=OFF \
+                  "
+PACKAGES =+ "${PN}-apps"
+FILES:${PN}-apps = "\
+                     ${bindir} \
+                     "
+UPSTREAM_CHECK_GITTAGREGEX = "^v(?P<pver>(\d+(\.\d+)+))$"
diff --git a/dynamic-layers/openembedded-layer/recipes-oneapi/rkcommon/rkcommon_1.14.0.bb b/dynamic-layers/openembedded-layer/recipes-oneapi/rkcommon/rkcommon_1.14.0.bb
new file mode 100644
index 00000000..5289e9eb
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-oneapi/rkcommon/rkcommon_1.14.0.bb
@@ -0,0 +1,17 @@
+SUMMARY  = "rkcommon - C++/CMake infrastructure"
+DESCRIPTION = "A common set of C++ infrastructure and CMake utilities \
+used by various components of Intel® oneAPI Rendering Toolkit."
+HOMEPAGE = "https://github.com/ospray/rkcommon"
+LICENSE  = "Apache-2.0"
+LIC_FILES_CHKSUM = "file://LICENSE.txt;md5=3b83ef96387f14655fc854ddc3c6bd57"
+inherit pkgconfig cmake
+SRC_URI = "git://github.com/ospray/rkcommon.git;protocol=https;branch=master \
+            "
+SRCREV = "4a00047ae5a3ac705b6b33b4a7574588d91e7953"
+DEPENDS = "tbb"
+EXTRA_OECMAKE += " -DBUILD_TESTING=OFF"
diff --git a/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl/0001-CMakeLists-disable-Werror.patch b/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl/0001-CMakeLists-disable-Werror.patch
new file mode 100644
index 00000000..4474aa3c
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl/0001-CMakeLists-disable-Werror.patch
@@ -0,0 +1,38 @@
+From ef56be8e6bf2ea273cbeb960f3131164e7b517b6 Mon Sep 17 00:00:00 2001
+From: Anuj Mittal <anuj.mittal@intel.com>
+Date: Wed, 18 May 2022 12:24:03 +0800
+Subject: [PATCH] CMakeLists: disable Werror
+gcc12 highlights minor warnings that cause the build to fail. Ignore
+those until they aren't fixed upstream.
+Upstream-Status: Inappropriate
+Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
+---
+ CMakeLists.txt | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 418483f7..c019fea0 100644
+--- a/CMakeLists.txt
+++ b/CMakeLists.txt
+@@ -146,7 +146,7 @@ else()
+   set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O2 -fno-strict-aliasing -D_FORTIFY_SOURCE=2")
+   if(LNX_BUILD)
+     #A few warnings yet to resolve under esx
+-    set(CMAKE_C_FLAGS_RELEASE "${CMAKE_C_FLAGS_RELEASE} -Werror")
+    #set(CMAKE_C_FLAGS_RELEASE "${CMAKE_C_FLAGS_RELEASE} -Werror")
+     set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -Werror")
+   endif()
+   set(CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -O0 -ggdb")
+@@ -791,4 +791,4 @@ if(ESX_BUILD)
+   include(CMake/esx.cmake)
+ endif()
+ 
+-add_subdirectory(src/os/nvm_api_sample)
+\ No newline at end of file
+add_subdirectory(src/os/nvm_api_sample)
+-- 
+2.35.3
diff --git a/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl/0001-Ignore-STATIC_ASSERTs-and-NULL-define-for-os-and-ut-builds.patch b/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl/0001-Ignore-STATIC_ASSERTs-and-NULL-define-for-os-and-ut-builds.patch
new file mode 100644
index 00000000..8a734ed2
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl/0001-Ignore-STATIC_ASSERTs-and-NULL-define-for-os-and-ut-builds.patch
@@ -0,0 +1,62 @@
+Subject: [PATCH] [PATCH]: ignore static asserts and null define for os and ut
+ builds
+Upstream-Status: Backport
+Signed-off-by: Teoh Suh Haw <suh.haw.teoh@intel.com>
+---
+ MdePkg/Include/Base.h | 12 ++++++++++++
+ 1 file changed, 12 insertions(+)
+Index: edk2/MdePkg/Include/Base.h
+===================================================================
+--- edk2.orig/MdePkg/Include/Base.h
+++ edk2/MdePkg/Include/Base.h
+@@ -316,8 +316,12 @@ struct _LIST_ENTRY {
+ #define NULL  __null
+   #endif
+ #else
+#ifndef OS_BUILD
+#ifndef UNIT_TEST_UEFI_BUILD
+ #define NULL  ((VOID *) 0)
+ #endif
+#endif
+#endif
+ 
+ //
+ // Null character
+@@ -813,6 +817,8 @@ typedef UINTN *BASE_LIST;
+ // Section 2.3.1 of the UEFI 2.3 Specification.
+ //
+ 
+#ifndef OS_BUILD
+#ifndef UNIT_TEST_UEFI_BUILD
+ STATIC_ASSERT (sizeof (BOOLEAN) == 1, "sizeof (BOOLEAN) does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (sizeof (INT8)    == 1, "sizeof (INT8) does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (sizeof (UINT8)   == 1, "sizeof (UINT8) does not meet UEFI Specification Data Type requirements");
+@@ -841,7 +847,8 @@ STATIC_ASSERT (ALIGNOF (CHAR16)  == size
+ STATIC_ASSERT (ALIGNOF (INTN)    == sizeof (INTN), "Alignment of INTN does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (ALIGNOF (UINTN)   == sizeof (UINTN), "Alignment of UINTN does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (ALIGNOF (VOID *)  == sizeof (VOID *), "Alignment of VOID * does not meet UEFI Specification Data Type requirements");
+-
+#endif
+#endif
+ //
+ // The following three enum types are used to verify that the compiler
+ // configuration for enum types is compliant with Section 2.3.1 of the
+@@ -861,6 +868,8 @@ typedef enum {
+   __VerifyInt32EnumValue = 0x7fffffff
+ } __VERIFY_INT32_ENUM_SIZE;
+ 
+#ifndef OS_BUILD
+#ifndef UNIT_TEST_UEFI_BUILD
+ STATIC_ASSERT (sizeof (__VERIFY_UINT8_ENUM_SIZE) == 4, "Size of enum does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (sizeof (__VERIFY_UINT16_ENUM_SIZE) == 4, "Size of enum does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (sizeof (__VERIFY_INT32_ENUM_SIZE) == 4, "Size of enum does not meet UEFI Specification Data Type requirements");
+@@ -868,6 +877,8 @@ STATIC_ASSERT (sizeof (__VERIFY_INT32_EN
+ STATIC_ASSERT (ALIGNOF (__VERIFY_UINT8_ENUM_SIZE)  == sizeof (__VERIFY_UINT8_ENUM_SIZE), "Alignment of enum does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (ALIGNOF (__VERIFY_UINT16_ENUM_SIZE) == sizeof (__VERIFY_UINT16_ENUM_SIZE), "Alignment of enum does not meet UEFI Specification Data Type requirements");
+ STATIC_ASSERT (ALIGNOF (__VERIFY_INT32_ENUM_SIZE) == sizeof (__VERIFY_INT32_ENUM_SIZE), "Alignment of enum does not meet UEFI Specification Data Type requirements");
+#endif
+#endif
+ 
+ /**
+   Macro that returns a pointer to the data structure that contains a specified field of
diff --git a/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl_03.00.00.0499.bb b/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl_03.00.00.0499.bb
new file mode 100644
index 00000000..7b95ffe4
--- /dev/null
+++ b/dynamic-layers/openembedded-layer/recipes-support/ipmctl/ipmctl_03.00.00.0499.bb
@@ -0,0 +1,45 @@
+SUMMARY = "Utility for managing Intel Optane DC persistent memory modules"
+DESCRIPTION = "Utility for configuring and managing Intel Optane Persistent \
+Memory modules (PMem). It supports functionality to: \
+Discover DCPMMs on the platform. \
+Provision the platform memory configuration. \
+View and update the firmware on DCPMMs. \
+Configure data-at-rest security on DCPMMs. \
+Track health and performance of DCPMMs. \
+Debug and troubleshoot DCPMMs."
+HOMEPAGE = "https://github.com/intel/ipmctl"
+BUGTRACKER = "https://github.com/intel/ipmctl/issues"
+LICENSE = "BSD-3-Clause | BSD-2-Clause"
+LIC_FILES_CHKSUM = "file://LICENSE;md5=72b9da60da6219d612ce30b746a0fe71  \
+                    file://edk2/License.txt;md5=6123e5bf044a66db96c4ce88a36b2d08"
+SRC_URI = "git://github.com/intel/ipmctl.git;protocol=https;branch=master_3_0;name=ipmctl; \
+        git://github.com/tianocore/edk2.git;protocol=https;name=edk2;destsuffix=${BB_GIT_DEFAULT_DESTSUFFIX}/edk2;branch=master \
+        file://0001-Ignore-STATIC_ASSERTs-and-NULL-define-for-os-and-ut-builds.patch;patchdir=edk2 \
+        file://0001-CMakeLists-disable-Werror.patch \
+"
+SRCREV_ipmctl = "a71f2fb1c90dd07f9862b71c789881132193e8f9"
+#tag edk2-stable202408
+SRCREV_edk2 = "b158dad150bf02879668f72ce306445250838201"
+SRCREV_FORMAT = "ipmctl_edk2"
+inherit cmake dos2unix
+DEPENDS = "ndctl pkgconfig-native"
+EXTRA_OECMAKE = "-DRELEASE=ON"
+do_configure:prepend() {
+    for dir in BaseTools MdeModulePkg MdePkg ShellPkg ; do
+        ln -sf edk2/${dir} ${S}
+    done
+}
+do_install:append() {
+    # Remove /var/log/ipmctl as anything created in /var/log will not be
+    # available when tmpfs is mounted at /var/volatile/log.
+    rm -rf ${D}${localstatedir}/log
+}