From f1a24eeb89342186c6c718e02dd394775620799f Mon Sep 17 00:00:00 2001 From: haonanya Date: Wed, 28 Jul 2021 14:20:08 +0800 Subject: [PATCH 3/3] Support cl_ext_float_atomics Upstream-Status: Backport [Taken from opencl-clang patches; https://github.com/intel/opencl-clang/blob/ocl-open-120/patches/clang/0003-OpenCL-Support-cl_ext_float_atomics.patch] Signed-off-by: haonanya Signed-off-by: Naveen Saini --- clang/lib/Headers/opencl-c-base.h | 19 +++ clang/lib/Headers/opencl-c.h | 195 ++++++++++++++++++++++++++ clang/test/Headers/opencl-c-header.cl | 72 ++++++++++ 3 files changed, 286 insertions(+) diff --git a/clang/lib/Headers/opencl-c-base.h b/clang/lib/Headers/opencl-c-base.h index e8dcd70377e5..c8b6d36029ec 100644 --- a/clang/lib/Headers/opencl-c-base.h +++ b/clang/lib/Headers/opencl-c-base.h @@ -21,6 +21,25 @@ #define cl_khr_subgroup_shuffle 1 #define cl_khr_subgroup_shuffle_relative 1 #define cl_khr_subgroup_clustered_reduce 1 +#define cl_ext_float_atomics +#ifdef cl_khr_fp16 +#define __opencl_c_ext_fp16_global_atomic_load_store 1 +#define __opencl_c_ext_fp16_local_atomic_load_store 1 +#define __opencl_c_ext_fp16_global_atomic_add 1 +#define __opencl_c_ext_fp16_local_atomic_add 1 +#define __opencl_c_ext_fp16_global_atomic_min_max 1 +#define __opencl_c_ext_fp16_local_atomic_min_max 1 +#endif +#ifdef __opencl_c_fp64 +#define __opencl_c_ext_fp64_global_atomic_add 1 +#define __opencl_c_ext_fp64_local_atomic_add 1 +#define __opencl_c_ext_fp64_global_atomic_min_max 1 +#define __opencl_c_ext_fp64_local_atomic_min_max 1 +#endif +#define __opencl_c_ext_fp32_global_atomic_add 1 +#define __opencl_c_ext_fp32_local_atomic_add 1 +#define __opencl_c_ext_fp32_global_atomic_min_max 1 +#define __opencl_c_ext_fp32_local_atomic_min_max 1 #endif // defined(__SPIR__) #endif // (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200) diff --git a/clang/lib/Headers/opencl-c.h b/clang/lib/Headers/opencl-c.h index ab665628c8e1..6676da858d2a 100644 --- a/clang/lib/Headers/opencl-c.h +++ b/clang/lib/Headers/opencl-c.h @@ -13531,6 +13531,201 @@ intptr_t __ovld atomic_fetch_max_explicit(volatile atomic_intptr_t *object, uint intptr_t __ovld atomic_fetch_max_explicit(volatile atomic_intptr_t *object, uintptr_t opermax, memory_order minder, memory_scope scope); #endif +#if defined(cl_ext_float_atomics) + +#if defined(__opencl_c_ext_fp32_global_atomic_min_max) +float __ovld atomic_fetch_min(volatile __global atomic_float *object, + float operand); +float __ovld atomic_fetch_max(volatile __global atomic_float *object, + float operand); +float __ovld atomic_fetch_min_explicit(volatile __global atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_max_explicit(volatile __global atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_min_explicit(volatile __global atomic_float *object, + float operand, memory_order order, + memory_scope scope); +float __ovld atomic_fetch_max_explicit(volatile __global atomic_float *object, + float operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp32_local_atomic_min_max) +float __ovld atomic_fetch_min(volatile __local atomic_float *object, + float operand); +float __ovld atomic_fetch_max(volatile __local atomic_float *object, + float operand); +float __ovld atomic_fetch_min_explicit(volatile __local atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_max_explicit(volatile __local atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_min_explicit(volatile __local atomic_float *object, + float operand, memory_order order, + memory_scope scope); +float __ovld atomic_fetch_max_explicit(volatile __local atomic_float *object, + float operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp32_global_atomic_min_max) || \ + defined(__opencl_c_ext_fp32_local_atomic_min_max) +float __ovld atomic_fetch_min(volatile atomic_float *object, float operand); +float __ovld atomic_fetch_max(volatile atomic_float *object, float operand); +float __ovld atomic_fetch_min_explicit(volatile atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_max_explicit(volatile atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_min_explicit(volatile atomic_float *object, + float operand, memory_order order, + memory_scope scope); +float __ovld atomic_fetch_max_explicit(volatile atomic_float *object, + float operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp64_global_atomic_min_max) +double __ovld atomic_fetch_min(volatile __global atomic_double *object, + double operand); +double __ovld atomic_fetch_max(volatile __global atomic_double *object, + double operand); +double __ovld atomic_fetch_min_explicit(volatile __global atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_max_explicit(volatile __global atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_min_explicit(volatile __global atomic_double *object, + double operand, memory_order order, + memory_scope scope); +double __ovld atomic_fetch_max_explicit(volatile __global atomic_double *object, + double operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp64_local_atomic_min_max) +double __ovld atomic_fetch_min(volatile __local atomic_double *object, + double operand); +double __ovld atomic_fetch_max(volatile __local atomic_double *object, + double operand); +double __ovld atomic_fetch_min_explicit(volatile __local atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_max_explicit(volatile __local atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_min_explicit(volatile __local atomic_double *object, + double operand, memory_order order, + memory_scope scope); +double __ovld atomic_fetch_max_explicit(volatile __local atomic_double *object, + double operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp64_global_atomic_min_max) || \ + defined(__opencl_c_ext_fp64_local_atomic_min_max) +double __ovld atomic_fetch_min(volatile atomic_double *object, double operand); +double __ovld atomic_fetch_max(volatile atomic_double *object, double operand); +double __ovld atomic_fetch_min_explicit(volatile atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_max_explicit(volatile atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_min_explicit(volatile atomic_double *object, + double operand, memory_order order, + memory_scope scope); +double __ovld atomic_fetch_max_explicit(volatile atomic_double *object, + double operand, memory_order order, + memory_scope scope); +#endif + +#if defined(__opencl_c_ext_fp32_global_atomic_add) +float __ovld atomic_fetch_add(volatile __global atomic_float *object, + float operand); +float __ovld atomic_fetch_sub(volatile __global atomic_float *object, + float operand); +float __ovld atomic_fetch_add_explicit(volatile __global atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_sub_explicit(volatile __global atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_add_explicit(volatile __global atomic_float *object, + float operand, memory_order order, + memory_scope scope); +float __ovld atomic_fetch_sub_explicit(volatile __global atomic_float *object, + float operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp32_local_atomic_add) +float __ovld atomic_fetch_add(volatile __local atomic_float *object, + float operand); +float __ovld atomic_fetch_sub(volatile __local atomic_float *object, + float operand); +float __ovld atomic_fetch_add_explicit(volatile __local atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_sub_explicit(volatile __local atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_add_explicit(volatile __local atomic_float *object, + float operand, memory_order order, + memory_scope scope); +float __ovld atomic_fetch_sub_explicit(volatile __local atomic_float *object, + float operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp32_global_atomic_add) || \ + defined(__opencl_c_ext_fp32_local_atomic_add) +float __ovld atomic_fetch_add(volatile atomic_float *object, float operand); +float __ovld atomic_fetch_sub(volatile atomic_float *object, float operand); +float __ovld atomic_fetch_add_explicit(volatile atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_sub_explicit(volatile atomic_float *object, + float operand, memory_order order); +float __ovld atomic_fetch_add_explicit(volatile atomic_float *object, + float operand, memory_order order, + memory_scope scope); +float __ovld atomic_fetch_sub_explicit(volatile atomic_float *object, + float operand, memory_order order, + memory_scope scope); +#endif + +#if defined(__opencl_c_ext_fp64_global_atomic_add) +double __ovld atomic_fetch_add(volatile __global atomic_double *object, + double operand); +double __ovld atomic_fetch_sub(volatile __global atomic_double *object, + double operand); +double __ovld atomic_fetch_add_explicit(volatile __global atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_sub_explicit(volatile __global atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_add_explicit(volatile __global atomic_double *object, + double operand, memory_order order, + memory_scope scope); +double __ovld atomic_fetch_sub_explicit(volatile __global atomic_double *object, + double operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp64_local_atomic_add) +double __ovld atomic_fetch_add(volatile __local atomic_double *object, + double operand); +double __ovld atomic_fetch_sub(volatile __local atomic_double *object, + double operand); +double __ovld atomic_fetch_add_explicit(volatile __local atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_sub_explicit(volatile __local atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_add_explicit(volatile __local atomic_double *object, + double operand, memory_order order, + memory_scope scope); +double __ovld atomic_fetch_sub_explicit(volatile __local atomic_double *object, + double operand, memory_order order, + memory_scope scope); +#endif +#if defined(__opencl_c_ext_fp64_global_atomic_add) || \ + defined(__opencl_c_ext_fp64_local_atomic_add) +double __ovld atomic_fetch_add(volatile atomic_double *object, double operand); +double __ovld atomic_fetch_sub(volatile atomic_double *object, double operand); +double __ovld atomic_fetch_add_explicit(volatile atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_sub_explicit(volatile atomic_double *object, + double operand, memory_order order); +double __ovld atomic_fetch_add_explicit(volatile atomic_double *object, + double operand, memory_order order, + memory_scope scope); +double __ovld atomic_fetch_sub_explicit(volatile atomic_double *object, + double operand, memory_order order, + memory_scope scope); +#endif + +#endif // cl_ext_float_atomics + // atomic_store() void __ovld atomic_store(volatile atomic_int *object, int desired); diff --git a/clang/test/Headers/opencl-c-header.cl b/clang/test/Headers/opencl-c-header.cl index 13a3b62481ec..2c02d14f25c3 100644 --- a/clang/test/Headers/opencl-c-header.cl +++ b/clang/test/Headers/opencl-c-header.cl @@ -124,6 +124,36 @@ global atomic_int z = ATOMIC_VAR_INIT(99); #if cl_khr_subgroup_clustered_reduce != 1 #error "Incorrectly defined cl_khr_subgroup_clustered_reduce" #endif +#if __opencl_c_ext_fp16_global_atomic_load_store != 1 +#error "Incorrectly defined __opencl_c_ext_fp16_global_atomic_load_store" +#endif +#if __opencl_c_ext_fp16_local_atomic_load_store != 1 +#error "Incorrectly defined __opencl_c_ext_fp16_local_atomic_load_store" +#endif +#if __opencl_c_ext_fp16_global_atomic_add != 1 +#error "Incorrectly defined __opencl_c_ext_fp16_global_atomic_add" +#endif +#if __opencl_c_ext_fp32_global_atomic_add != 1 +#error "Incorrectly defined __opencl_c_ext_fp32_global_atomic_add" +#endif +#if __opencl_c_ext_fp16_local_atomic_add != 1 +#error "Incorrectly defined __opencl_c_ext_fp16_local_atomic_add" +#endif +#if __opencl_c_ext_fp32_local_atomic_add != 1 +#error "Incorrectly defined __opencl_c_ext_fp32_local_atomic_add" +#endif +#if __opencl_c_ext_fp16_global_atomic_min_max != 1 +#error "Incorrectly defined __opencl_c_ext_fp16_global_atomic_min_max" +#endif +#if __opencl_c_ext_fp32_global_atomic_min_max != 1 +#error "Incorrectly defined __opencl_c_ext_fp32_global_atomic_min_max" +#endif +#if __opencl_c_ext_fp16_local_atomic_min_max != 1 +#error "Incorrectly defined __opencl_c_ext_fp16_local_atomic_min_max" +#endif +#if __opencl_c_ext_fp32_local_atomic_min_max != 1 +#error "Incorrectly defined __opencl_c_ext_fp32_local_atomic_min_max" +#endif #else @@ -148,6 +178,48 @@ global atomic_int z = ATOMIC_VAR_INIT(99); #ifdef cl_khr_subgroup_clustered_reduce #error "Incorrect cl_khr_subgroup_clustered_reduce define" #endif +#ifdef __opencl_c_ext_fp16_global_atomic_load_store +#error "Incorrectly __opencl_c_ext_fp16_global_atomic_load_store defined" +#endif +#ifdef __opencl_c_ext_fp16_local_atomic_load_store +#error "Incorrectly __opencl_c_ext_fp16_local_atomic_load_store defined" +#endif +#ifdef __opencl_c_ext_fp16_global_atomic_add +#error "Incorrectly __opencl_c_ext_fp16_global_atomic_add defined" +#endif +#ifdef __opencl_c_ext_fp32_global_atomic_add +#error "Incorrectly __opencl_c_ext_fp32_global_atomic_add defined" +#endif +#ifdef __opencl_c_ext_fp64_global_atomic_add +#error "Incorrectly __opencl_c_ext_fp64_global_atomic_add defined" +#endif +#ifdef __opencl_c_ext_fp16_local_atomic_add +#error "Incorrectly __opencl_c_ext_fp16_local_atomic_add defined" +#endif +#ifdef __opencl_c_ext_fp32_local_atomic_add +#error "Incorrectly __opencl_c_ext_fp32_local_atomic_add defined" +#endif +#ifdef __opencl_c_ext_fp64_local_atomic_add +#error "Incorrectly __opencl_c_ext_fp64_local_atomic_add defined" +#endif +#ifdef __opencl_c_ext_fp16_global_atomic_min_max +#error "Incorrectly __opencl_c_ext_fp16_global_atomic_min_max defined" +#endif +#ifdef __opencl_c_ext_fp32_global_atomic_min_max +#error "Incorrectly __opencl_c_ext_fp32_global_atomic_min_max defined" +#endif +#ifdef __opencl_c_ext_fp64_global_atomic_min_max +#error "Incorrectly __opencl_c_ext_fp64_global_atomic_min_max defined" +#endif +#ifdef __opencl_c_ext_fp16_local_atomic_min_max +#error "Incorrectly __opencl_c_ext_fp16_local_atomic_min_max defined" +#endif +#ifdef __opencl_c_ext_fp32_local_atomic_min_max +#error "Incorrectly __opencl_c_ext_fp32_local_atomic_min_max defined" +#endif +#ifdef __opencl_c_ext_fp64_local_atomic_min_max +#error "Incorrectly __opencl_c_ext_fp64_local_atomic_min_max defined" +#endif #endif //(defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200) -- 2.17.1