gcc: Fixes for ARC

A couple of fixes to be a part of 11.2 whenever it happens

1. https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=0061fabeb9393c362601486105202cfe837a5a68
   Fixes "harfbuzz" build, see https://github.com/foss-for-synopsys-dwc-arc-processors/toolchain/issues/382
   for all the gory details.

2. https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=4186b7e93be73f8d68dc0fcc00a4cc8cc83e99a8
   Fixes ext4 run-time issue:
   ------------------------->8---------------------------
   Path: /bin/busybox
   CPU: 0 PID: 1 Comm: init Not tainted 5.13.0-rc2-dirty #23
   Invalid Read @ 0x41c9e600 by insn @ __bio_try_merge_page+0x4e/0xfc
   ECR: 0x00050100 EFA: 0x41c9e600 ERET: 0x80159656
   STAT: 0x80080202 [IE K     ]   BTA: 0x80159648
    SP: 0x80821b88  FP: 0x00000008 BLK: bio_add_page+0x22/0x5c
   LPS: 0x801a6a94 LPE: 0x801a6a98 LPC: 0x00000000
   r00: 0x80823300 r01: 0xbfb85e38 r02: 0x00002000
   r03: 0x00000000 r04: 0x80821b9b r05: 0x80821bfc
   r06: 0x00000000 r07: 0x00000700 r08: 0x00000000
   r09: 0xffffffff r10: 0x00000000 r11: 0x00000000
   r12: 0x8080b300
   Stack Trace:
     __bio_try_merge_page+0x4e/0xfc
     bio_add_page+0x22/0x5c
     do_mpage_readpage+0x534/0x65c
     mpage_readahead+0x30/0xdc
     read_pages+0x34/0x194
     page_cache_ra_unbounded+0x56/0x154
     filemap_fault+0x25a/0x5d8
     __do_fault+0x94/0xe8
     handle_mm_fault+0x4de/0xbd4
     do_page_fault+0x108/0x21c
     ret_from_exception+0x0/0x8
   ------------------------->8---------------------------

3. https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=5a9b6a004f89fdd95b0470e1324dc4dee8c41d24
   Precautious fix for rare corner cases which we don't wnat to really end-up in.

(From OE-Core rev: 75110a9cc5e6840c65ed24bcca7d4cf1748ab67d)

Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

4 files changed, 525 insertions, 0 deletions

diff --git a/meta/recipes-devtools/gcc/gcc-11.1.inc b/meta/recipes-devtools/gcc/gcc-11.1.inc
index bf29879ded..69e4c8bacc 100644
--- a/meta/recipes-devtools/gcc/gcc-11.1.inc
+++ b/meta/recipes-devtools/gcc/gcc-11.1.inc
@@ -69,6 +69,9 @@ SRC_URI = "\
            file://0036-mingw32-Enable-operation_not_supported.patch \
            file://0037-libatomic-Do-not-enforce-march-on-aarch64.patch \
            file://0001-Revert-libstdc-Install-libstdc-gdb.py-more-robustly-.patch \
+           file://0038-arc-Update-64bit-move-split-patterns.patch \
+           file://0039-arc-Fix-u-maddhisi-patterns.patch \
+           file://0040-arc-Update-doloop_end-patterns.patch \
 "
 SRC_URI[sha256sum] = "4c4a6fb8a8396059241c2e674b85b351c26a5d678274007f076957afa1cc9ddf"
 SRC_URI[backports.sha256sum] = "69274bebd6c069a13443d4af61070e854740a639ec4d66eedf3e80070363587b"
diff --git a/meta/recipes-devtools/gcc/gcc/0038-arc-Update-64bit-move-split-patterns.patch b/meta/recipes-devtools/gcc/gcc/0038-arc-Update-64bit-move-split-patterns.patch
new file mode 100644
index 0000000000..37fe95d711
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc/0038-arc-Update-64bit-move-split-patterns.patch
@@ -0,0 +1,290 @@
+From 0061fabeb9393c362601486105202cfe837a5a68 Mon Sep 17 00:00:00 2001
+From: Claudiu Zissulescu <claziss@synopsys.com>
+Date: Wed, 9 Jun 2021 12:12:57 +0300
+Subject: [PATCH] arc: Update 64bit move split patterns.
+
+ARCv2HS can use a limited number of instructions to implement 64bit
+moves. The VADD2 is used as a 64bit move, the LDD/STD are 64 bit loads
+and stores. All those instructions are not baseline, hence we need to
+provide alternatives when they are not available or cannot be generate
+due to instruction restriction.
+
+This patch is cleaning up those move patterns, and updates splits
+instruction lengths.
+
+This is a backport from mainline gcc.
+
+gcc/
+2021-06-09  Claudiu Zissulescu  <claziss@synopsys.com>
+
+        * config/arc/arc-protos.h (arc_split_move_p): New prototype.
+        * config/arc/arc.c (arc_split_move_p): New function.
+        (arc_split_move): Clean up.
+        * config/arc/arc.md (movdi_insn): Clean up, use arc_split_move_p.
+        (movdf_insn): Likewise.
+        * config/arc/simdext.md (mov<VWH>_insn): Likewise.
+
+Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=0061fabeb9393c362601486105202cfe837a5a68]
+
+Signed-off-by: Claudiu Zissulescu <claziss@synopsys.com>
+(cherry picked from commit c0ba7a8af5366c37241f20e8be41e362f7260389)
+Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
+---
+ gcc/config/arc/arc-protos.h |  1 +
+ gcc/config/arc/arc.c        | 44 ++++++++++++----------
+ gcc/config/arc/arc.md       | 91 +++++++++------------------------------------
+ gcc/config/arc/simdext.md   | 38 ++++---------------
+ 4 files changed, 52 insertions(+), 122 deletions(-)
+
+diff --git a/gcc/config/arc/arc-protos.h b/gcc/config/arc/arc-protos.h
+index 1f56a0d82e4..62d7e45d29d 100644
+--- a/gcc/config/arc/arc-protos.h
++++ b/gcc/config/arc/arc-protos.h
+@@ -50,6 +50,7 @@ extern void arc_split_ior (rtx *);
+ extern bool arc_check_mov_const (HOST_WIDE_INT );
+ extern bool arc_split_mov_const (rtx *);
+ extern bool arc_can_use_return_insn (void);
++extern bool arc_split_move_p (rtx *);
+ #endif /* RTX_CODE */
+ 
+ extern bool arc_ccfsm_branch_deleted_p (void);
+diff --git a/gcc/config/arc/arc.c b/gcc/config/arc/arc.c
+index 3201c3fefd7..db541bc11f5 100644
+--- a/gcc/config/arc/arc.c
++++ b/gcc/config/arc/arc.c
+@@ -10129,6 +10129,31 @@ arc_process_double_reg_moves (rtx *operands)
+   return true;
+ }
+ 
++
++/* Check if we need to split a 64bit move.  We do not need to split it if we can
++   use vadd2 or ldd/std instructions.  */
++
++bool
++arc_split_move_p (rtx *operands)
++{
++  machine_mode mode = GET_MODE (operands[0]);
++
++  if (TARGET_LL64
++      && ((memory_operand (operands[0], mode)
++          && (even_register_operand (operands[1], mode)
++              || satisfies_constraint_Cm3 (operands[1])))
++         || (memory_operand (operands[1], mode)
++             && even_register_operand (operands[0], mode))))
++    return false;
++
++  if (TARGET_PLUS_QMACW
++      && even_register_operand (operands[0], mode)
++      && even_register_operand (operands[1], mode))
++    return false;
++
++  return true;
++}
++
+ /* operands 0..1 are the operands of a 64 bit move instruction.
+    split it into two moves with operands 2/3 and 4/5.  */
+ 
+@@ -10146,25 +10171,6 @@ arc_split_move (rtx *operands)
+       return;
+   }
+ 
+-  if (TARGET_LL64
+-      && ((memory_operand (operands[0], mode)
+-          && (even_register_operand (operands[1], mode)
+-              || satisfies_constraint_Cm3 (operands[1])))
+-         || (memory_operand (operands[1], mode)
+-             && even_register_operand (operands[0], mode))))
+-    {
+-      emit_move_insn (operands[0], operands[1]);
+-      return;
+-    }
+-
+-  if (TARGET_PLUS_QMACW
+-      && even_register_operand (operands[0], mode)
+-      && even_register_operand (operands[1], mode))
+-    {
+-      emit_move_insn (operands[0], operands[1]);
+-      return;
+-    }
+-
+   if (TARGET_PLUS_QMACW
+       && GET_CODE (operands[1]) == CONST_VECTOR)
+     {
+diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
+index 7a52551eef5..91a838a38e4 100644
+--- a/gcc/config/arc/arc.md
++++ b/gcc/config/arc/arc.md
+@@ -1329,47 +1329,20 @@ core_3, archs4x, archs4xd, archs4xd_slow"
+   "register_operand (operands[0], DImode)
+    || register_operand (operands[1], DImode)
+    || (satisfies_constraint_Cm3 (operands[1])
+-      && memory_operand (operands[0], DImode))"
+-  "*
+-{
+-  switch (which_alternative)
+-    {
+-    default:
+-      return \"#\";
+-
+-    case 0:
+-    if (TARGET_PLUS_QMACW
+-       && even_register_operand (operands[0], DImode)
+-       && even_register_operand (operands[1], DImode))
+-      return \"vadd2%?\\t%0,%1,0\";
+-    return \"#\";
+-
+-    case 2:
+-    if (TARGET_LL64
+-        && memory_operand (operands[1], DImode)
+-       && even_register_operand (operands[0], DImode))
+-      return \"ldd%U1%V1 %0,%1%&\";
+-    return \"#\";
+-
+-    case 3:
+-    if (TARGET_LL64
+-       && memory_operand (operands[0], DImode)
+-       && (even_register_operand (operands[1], DImode)
+-           || satisfies_constraint_Cm3 (operands[1])))
+-     return \"std%U0%V0 %1,%0\";
+-    return \"#\";
+-    }
+-}"
+-  "&& reload_completed"
++       && memory_operand (operands[0], DImode))"
++  "@
++   vadd2\\t%0,%1,0
++   #
++   ldd%U1%V1\\t%0,%1
++   std%U0%V0\\t%1,%0"
++  "&& reload_completed && arc_split_move_p (operands)"
+   [(const_int 0)]
+   {
+    arc_split_move (operands);
+    DONE;
+   }
+   [(set_attr "type" "move,move,load,store")
+-   ;; ??? The ld/st values could be 4 if it's [reg,bignum].
+-   (set_attr "length" "8,16,*,*")])
+-
++   (set_attr "length" "8,16,16,16")])
+ 
+ ;; Floating point move insns.
+ 
+@@ -1408,50 +1381,22 @@ core_3, archs4x, archs4xd, archs4xd_slow"
+ (define_insn_and_split "*movdf_insn"
+   [(set (match_operand:DF 0 "move_dest_operand"      "=D,r,r,r,r,m")
+        (match_operand:DF 1 "move_double_src_operand" "r,D,r,E,m,r"))]
+-  "register_operand (operands[0], DFmode)
+-   || register_operand (operands[1], DFmode)"
+-  "*
+-{
+- switch (which_alternative)
+-   {
+-    default:
+-      return \"#\";
+-
+-    case 2:
+-    if (TARGET_PLUS_QMACW
+-       && even_register_operand (operands[0], DFmode)
+-       && even_register_operand (operands[1], DFmode))
+-      return \"vadd2%?\\t%0,%1,0\";
+-    return \"#\";
+-
+-    case 4:
+-    if (TARGET_LL64
+-       && ((even_register_operand (operands[0], DFmode)
+-            && memory_operand (operands[1], DFmode))
+-           || (memory_operand (operands[0], DFmode)
+-               && even_register_operand (operands[1], DFmode))))
+-      return \"ldd%U1%V1 %0,%1%&\";
+-    return \"#\";
+-
+-    case 5:
+-    if (TARGET_LL64
+-       && ((even_register_operand (operands[0], DFmode)
+-            && memory_operand (operands[1], DFmode))
+-           || (memory_operand (operands[0], DFmode)
+-               && even_register_operand (operands[1], DFmode))))
+-     return \"std%U0%V0 %1,%0\";
+-    return \"#\";
+-   }
+-}"
+-  "reload_completed"
++  "(register_operand (operands[0], DFmode)
++    || register_operand (operands[1], DFmode))"
++  "@
++   #
++   #
++   vadd2\\t%0,%1,0
++   #
++   ldd%U1%V1\\t%0,%1
++   std%U0%V0\\t%1,%0"
++  "&& reload_completed && arc_split_move_p (operands)"
+   [(const_int 0)]
+   {
+    arc_split_move (operands);
+    DONE;
+   }
+   [(set_attr "type" "move,move,move,move,load,store")
+-   (set_attr "predicable" "no,no,no,yes,no,no")
+-   ;; ??? The ld/st values could be 16 if it's [reg,bignum].
+    (set_attr "length" "4,16,8,16,16,16")])
+ 
+ (define_insn_and_split "*movdf_insn_nolrsr"
+diff --git a/gcc/config/arc/simdext.md b/gcc/config/arc/simdext.md
+index f0900757452..36f41a5c3d0 100644
+--- a/gcc/config/arc/simdext.md
++++ b/gcc/config/arc/simdext.md
+@@ -1402,41 +1402,19 @@
+        (match_operand:VWH 1 "general_operand"    "i,r,m,r"))]
+   "(register_operand (operands[0], <MODE>mode)
+        || register_operand (operands[1], <MODE>mode))"
+-  "*
+-{
+-  switch (which_alternative)
+-    {
+-     default:
+-       return \"#\";
+-
+-     case 1:
+-       if (TARGET_PLUS_QMACW
+-           && even_register_operand (operands[0], <MODE>mode)
+-          && even_register_operand (operands[1], <MODE>mode))
+-         return \"vadd2%?\\t%0,%1,0\";
+-       return \"#\";
+-
+-     case 2:
+-       if (TARGET_LL64)
+-         return \"ldd%U1%V1 %0,%1\";
+-       return \"#\";
+-
+-     case 3:
+-       if (TARGET_LL64)
+-          return \"std%U0%V0 %1,%0\";
+-        return \"#\";
+-    }
+-}"
+-  "reload_completed"
++  "@
++   #
++   vadd2\\t%0,%1,0
++   ldd%U1%V1\\t%0,%1
++   std%U0%V0\\t%1,%0"
++  "&& reload_completed && arc_split_move_p (operands)"
+   [(const_int 0)]
+   {
+    arc_split_move (operands);
+    DONE;
+   }
+-  [(set_attr "type" "move,multi,load,store")
+-   (set_attr "predicable" "no,no,no,no")
+-   (set_attr "iscompact"  "false,false,false,false")
+-   ])
++  [(set_attr "type" "move,move,load,store")
++   (set_attr "length" "16,8,16,16")])
+ 
+ (define_expand "movmisalign<mode>"
+  [(set (match_operand:VWH 0 "general_operand" "")
+-- 
+2.16.2
+
diff --git a/meta/recipes-devtools/gcc/gcc/0039-arc-Fix-u-maddhisi-patterns.patch b/meta/recipes-devtools/gcc/gcc/0039-arc-Fix-u-maddhisi-patterns.patch
new file mode 100644
index 0000000000..9c5a2b8b33
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc/0039-arc-Fix-u-maddhisi-patterns.patch
@@ -0,0 +1,127 @@
+From 4186b7e93be73f8d68dc0fcc00a4cc8cc83e99a8 Mon Sep 17 00:00:00 2001
+From: Claudiu Zissulescu <claziss@synopsys.com>
+Date: Wed, 9 Jun 2021 12:12:57 +0300
+Subject: [PATCH] arc: Fix (u)maddhisi patterns
+
+Rework the (u)maddhisi4 patterns and use VMAC2H(U) instruction instead
+of the 64bit MAC(U) instruction.
+This fixes the next execute.exp failures:
+     arith-rand-ll.c   -O2  execution test
+     arith-rand-ll.c   -O3  execution test
+     pr78726.c   -O2  execution test
+     pr78726.c   -O3  execution test
+
+gcc/
+2021-06-09  Claudiu Zissulescu  <claziss@synopsys.com>
+
+        * config/arc/arc.md (maddhisi4): Use VMAC2H instruction.
+        (machi): New pattern.
+        (umaddhisi4): Use VMAC2HU instruction.
+        (umachi): New pattern.
+
+Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=4186b7e93be73f8d68dc0fcc00a4cc8cc83e99a8]
+
+Signed-off-by: Claudiu Zissulescu <claziss@synopsys.com>
+(cherry picked from commit dd4778a59b4693777c732075021375e19eee6a76)
+Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
+---
+ gcc/config/arc/arc.md | 66 ++++++++++++++++++++++++++++++++-------------------
+ 1 file changed, 41 insertions(+), 25 deletions(-)
+
+diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
+index 91a838a38e4..2a7e087ff72 100644
+--- a/gcc/config/arc/arc.md
++++ b/gcc/config/arc/arc.md
+@@ -6053,48 +6053,64 @@ core_3, archs4x, archs4xd, archs4xd_slow"
+ 
+ ;; MAC and DMPY instructions
+ 
+-; Use MAC instruction to emulate 16bit mac.
++; Use VMAC2H(U) instruction to emulate scalar 16bit mac.
+ (define_expand "maddhisi4"
+   [(match_operand:SI 0 "register_operand" "")
+    (match_operand:HI 1 "register_operand" "")
+    (match_operand:HI 2 "extend_operand"   "")
+    (match_operand:SI 3 "register_operand" "")]
+-  "TARGET_PLUS_DMPY"
++  "TARGET_PLUS_MACD"
+   "{
+-   rtx acc_reg = gen_rtx_REG (DImode, ACC_REG_FIRST);
+-   rtx tmp1 = gen_reg_rtx (SImode);
+-   rtx tmp2 = gen_reg_rtx (SImode);
+-   rtx accl = gen_lowpart (SImode, acc_reg);
+-
+-   emit_move_insn (accl, operands[3]);
+-   emit_insn (gen_rtx_SET (tmp1, gen_rtx_SIGN_EXTEND (SImode, operands[1])));
+-   emit_insn (gen_rtx_SET (tmp2, gen_rtx_SIGN_EXTEND (SImode, operands[2])));
+-   emit_insn (gen_mac (tmp1, tmp2));
+-   emit_move_insn (operands[0], accl);
++   rtx acc_reg = gen_rtx_REG (SImode, ACC_REG_FIRST);
++
++   emit_move_insn (acc_reg, operands[3]);
++   emit_insn (gen_machi (operands[1], operands[2]));
++   emit_move_insn (operands[0], acc_reg);
+    DONE;
+   }")
+ 
+-; The same for the unsigned variant, but using MACU instruction.
++(define_insn "machi"
++  [(set (reg:SI ARCV2_ACC)
++       (plus:SI
++        (mult:SI (sign_extend:SI (match_operand:HI 0 "register_operand" "%r"))
++                 (sign_extend:SI (match_operand:HI 1 "register_operand" "r")))
++        (reg:SI ARCV2_ACC)))]
++  "TARGET_PLUS_MACD"
++  "vmac2h\\t0,%0,%1"
++  [(set_attr "length" "4")
++   (set_attr "type" "multi")
++   (set_attr "predicable" "no")
++   (set_attr "cond" "nocond")])
++
++; The same for the unsigned variant, but using VMAC2HU instruction.
+ (define_expand "umaddhisi4"
+   [(match_operand:SI 0 "register_operand" "")
+    (match_operand:HI 1 "register_operand" "")
+-   (match_operand:HI 2 "extend_operand"   "")
++   (match_operand:HI 2 "register_operand" "")
+    (match_operand:SI 3 "register_operand" "")]
+-  "TARGET_PLUS_DMPY"
++  "TARGET_PLUS_MACD"
+   "{
+-   rtx acc_reg = gen_rtx_REG (DImode, ACC_REG_FIRST);
+-   rtx tmp1 = gen_reg_rtx (SImode);
+-   rtx tmp2 = gen_reg_rtx (SImode);
+-   rtx accl = gen_lowpart (SImode, acc_reg);
+-
+-   emit_move_insn (accl, operands[3]);
+-   emit_insn (gen_rtx_SET (tmp1, gen_rtx_ZERO_EXTEND (SImode, operands[1])));
+-   emit_insn (gen_rtx_SET (tmp2, gen_rtx_ZERO_EXTEND (SImode, operands[2])));
+-   emit_insn (gen_macu (tmp1, tmp2));
+-   emit_move_insn (operands[0], accl);
++   rtx acc_reg = gen_rtx_REG (SImode, ACC_REG_FIRST);
++
++   emit_move_insn (acc_reg, operands[3]);
++   emit_insn (gen_umachi (operands[1], operands[2]));
++   emit_move_insn (operands[0], acc_reg);
+    DONE;
+   }")
+ 
++(define_insn "umachi"
++  [(set (reg:SI ARCV2_ACC)
++       (plus:SI
++        (mult:SI (zero_extend:SI (match_operand:HI 0 "register_operand" "%r"))
++                 (zero_extend:SI (match_operand:HI 1 "register_operand" "r")))
++        (reg:SI ARCV2_ACC)))]
++  "TARGET_PLUS_MACD"
++  "vmac2hu\\t0,%0,%1"
++  [(set_attr "length" "4")
++   (set_attr "type" "multi")
++   (set_attr "predicable" "no")
++   (set_attr "cond" "nocond")])
++
+ (define_expand "maddsidi4"
+   [(match_operand:DI 0 "register_operand" "")
+    (match_operand:SI 1 "register_operand" "")
+-- 
+2.16.2
+
diff --git a/meta/recipes-devtools/gcc/gcc/0040-arc-Update-doloop_end-patterns.patch b/meta/recipes-devtools/gcc/gcc/0040-arc-Update-doloop_end-patterns.patch
new file mode 100644
index 0000000000..5f0bf8df8f
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc/0040-arc-Update-doloop_end-patterns.patch
@@ -0,0 +1,105 @@
+From 5a9b6a004f89fdd95b0470e1324dc4dee8c41d24 Mon Sep 17 00:00:00 2001
+From: Claudiu Zissulescu <claziss@synopsys.com>
+Date: Wed, 9 Jun 2021 12:12:57 +0300
+Subject: [PATCH] arc: Update doloop_end patterns
+
+ARC processor can use LP instruction to implement zero overlay loops.
+The current inplementation doesn't handle the unlikely situation when
+the loop iterator is located in memory.  Refurbish the loop_end insn
+pattern into a define_insn_and_split pattern.
+
+gcc/
+2021-07-09  Claudiu Zissulescu  <claziss@synopsys.com>
+
+        * config/arc/arc.md (loop_end): Change it to
+        define_insn_and_split.
+
+Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=5a9b6a004f89fdd95b0470e1324dc4dee8c41d24]
+
+Signed-off-by: Claudiu Zissulescu <claziss@synopsys.com>
+(cherry picked from commit 174e75a210753b68de0f2c398a13ace0f512e35b)
+Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
+---
+ gcc/config/arc/arc.md | 46 ++++++++++++++++++++--------------------------
+ 1 file changed, 20 insertions(+), 26 deletions(-)
+
+diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
+index 2a7e087ff72..d704044c13f 100644
+--- a/gcc/config/arc/arc.md
++++ b/gcc/config/arc/arc.md
+@@ -4986,7 +4986,7 @@ core_3, archs4x, archs4xd, archs4xd_slow"
+ (define_expand "doloop_end"
+   [(parallel [(set (pc)
+                   (if_then_else
+-                   (ne (match_operand 0 "" "")
++                   (ne (match_operand 0 "nonimmediate_operand")
+                        (const_int 1))
+                    (label_ref (match_operand 1 "" ""))
+                    (pc)))
+@@ -5012,44 +5012,38 @@ core_3, archs4x, archs4xd, archs4xd_slow"
+ 
+ ;; if by any chance the lp_count is not used, then use an 'r'
+ ;; register, instead of going to memory.
+-(define_insn "loop_end"
+-  [(set (pc)
+-       (if_then_else (ne (match_operand:SI 2 "nonimmediate_operand" "0,m")
+-                         (const_int 1))
+-                     (label_ref (match_operand 1 "" ""))
+-                     (pc)))
+-   (set (match_operand:SI 0 "nonimmediate_operand" "=r,m")
+-       (plus (match_dup 2) (const_int -1)))
+-   (unspec [(const_int 0)] UNSPEC_ARC_LP)
+-   (clobber (match_scratch:SI 3 "=X,&r"))]
+-  ""
+-  "; ZOL_END, begins @%l1"
+-  [(set_attr "length" "0")
+-   (set_attr "predicable" "no")
+-   (set_attr "type" "loop_end")])
+-
+ ;; split pattern for the very slim chance when the loop register is
+ ;; memory.
+-(define_split
++(define_insn_and_split "loop_end"
+   [(set (pc)
+-       (if_then_else (ne (match_operand:SI 0 "memory_operand")
++       (if_then_else (ne (match_operand:SI 0 "nonimmediate_operand" "+r,!m")
+                          (const_int 1))
+-                     (label_ref (match_operand 1 ""))
++                     (label_ref (match_operand 1 "" ""))
+                      (pc)))
+    (set (match_dup 0) (plus (match_dup 0) (const_int -1)))
+    (unspec [(const_int 0)] UNSPEC_ARC_LP)
+-   (clobber (match_scratch:SI 2))]
+-  "memory_operand (operands[0], SImode)"
++   (clobber (match_scratch:SI 2 "=X,&r"))]
++  ""
++  "@
++   ; ZOL_END, begins @%l1
++   #"
++  "reload_completed && memory_operand (operands[0], Pmode)"
+   [(set (match_dup 2) (match_dup 0))
+-   (set (match_dup 2) (plus:SI (match_dup 2) (const_int -1)))
++   (parallel
++    [(set (reg:CC_ZN CC_REG)
++         (compare:CC_ZN (plus:SI (match_dup 2) (const_int -1))
++                        (const_int 0)))
++     (set (match_dup 2) (plus:SI (match_dup 2) (const_int -1)))])
+    (set (match_dup 0) (match_dup 2))
+-   (set (reg:CC CC_REG) (compare:CC (match_dup 2) (const_int 0)))
+    (set (pc)
+-       (if_then_else (ne (reg:CC CC_REG)
++       (if_then_else (ne (reg:CC_ZN CC_REG)
+                          (const_int 0))
+                      (label_ref (match_dup 1))
+                      (pc)))]
+-  "")
++  ""
++  [(set_attr "length" "0,24")
++   (set_attr "predicable" "no")
++   (set_attr "type" "loop_end")])
+ 
+ (define_insn "loop_fail"
+   [(set (reg:SI LP_COUNT)
+-- 
+2.16.2
+