[llvm] [AMDGPU] Do not fold into v_accvpr_mov/write/read (PR #120475)

via llvm-commits llvm-commits at lists.llvm.org
Wed Dec 18 12:29:28 PST 2024


https://github.com/bcahoon created https://github.com/llvm/llvm-project/pull/120475

In SIFoldOperands, leave copies for moving between agpr and vgpr
registers. The register coalescer is able to handle the copies
more efficiently than v_accvgpr_mov, v_accvgpr_write, and
v_accvgpr_read. Otherwise, the compiler generates unneccesary
instructions such as v_accvgpr_mov a0, a0.


>From 0c5e40257d7ba46cde95c60afcdc8108ad54131b Mon Sep 17 00:00:00 2001
From: Brendon Cahoon <brendon.cahoon at amd.com>
Date: Wed, 18 Dec 2024 14:08:52 -0600
Subject: [PATCH] [AMDGPU] Do not fold into v_accvpr_mov/write/read

In SIFoldOperands, leave copies for moving between agpr and vgpr
registers. The register coalescer is able to handle the copies
more efficiently than v_accvgpr_mov, v_accvgpr_write, and
v_accvgpr_read. Otherwise, the compiler generates unneccesary
instructions such as v_accvgpr_mov a0, a0.
---
 llvm/lib/Target/AMDGPU/SIFoldOperands.cpp     |  13 -
 .../CodeGen/AMDGPU/no-fold-accvgpr-mov.mir    | 234 ++++++++++++++++++
 .../CodeGen/AMDGPU/no-fold-accvgpr-read.mir   | 181 ++++++++++++++
 3 files changed, 415 insertions(+), 13 deletions(-)
 create mode 100644 llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.mir
 create mode 100644 llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-read.mir

diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index 4fb5cb066be7c3..47e4afea6fa5f0 100644
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -1096,21 +1096,8 @@ void SIFoldOperandsImpl::foldOperand(
           B.addImm(Defs[I].second);
         }
         LLVM_DEBUG(dbgs() << "Folded " << *UseMI);
-        return;
       }
 
-      if (Size != 4)
-        return;
-
-      Register Reg0 = UseMI->getOperand(0).getReg();
-      Register Reg1 = UseMI->getOperand(1).getReg();
-      if (TRI->isAGPR(*MRI, Reg0) && TRI->isVGPR(*MRI, Reg1))
-        UseMI->setDesc(TII->get(AMDGPU::V_ACCVGPR_WRITE_B32_e64));
-      else if (TRI->isVGPR(*MRI, Reg0) && TRI->isAGPR(*MRI, Reg1))
-        UseMI->setDesc(TII->get(AMDGPU::V_ACCVGPR_READ_B32_e64));
-      else if (ST->hasGFX90AInsts() && TRI->isAGPR(*MRI, Reg0) &&
-               TRI->isAGPR(*MRI, Reg1))
-        UseMI->setDesc(TII->get(AMDGPU::V_ACCVGPR_MOV_B32));
       return;
     }
 
diff --git a/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.mir b/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.mir
new file mode 100644
index 00000000000000..15d6140b0206d4
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.mir
@@ -0,0 +1,234 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942  -verify-machineinstrs --run-pass si-fold-operands %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942  -verify-machineinstrs -start-before=si-fold-operands -stop-after=register-coalescer %s -o - | FileCheck %s --check-prefixes=COALESCE
+# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx908  -verify-machineinstrs -start-before=si-fold-operands -stop-after=register-coalescer %s -o - | FileCheck %s --check-prefixes=GFX908-COALESCE
+
+---
+name:            test
+tracksRegLiveness: true
+body:             |
+  ; CHECK-LABEL: name: test
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $sgpr4_sgpr5
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
+  ; CHECK-NEXT:   [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+  ; CHECK-NEXT:   S_BITCMP1_B32 killed [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
+  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sgpr_32 = S_MOV_B32 0
+  ; CHECK-NEXT:   [[S_CSELECT_B64_:%[0-9]+]]:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit $scc
+  ; CHECK-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:agpr_32 = COPY [[V_MOV_B32_e32_]]
+  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_CSELECT_B64_]], implicit $exec
+  ; CHECK-NEXT:   [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 [[V_CNDMASK_B32_e64_]], 1, implicit $exec
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.3(0x40000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[PHI:%[0-9]+]]:agpr_32 = PHI [[COPY1]], %bb.0, %24, %bb.3
+  ; CHECK-NEXT:   [[PHI1:%[0-9]+]]:sreg_32 = PHI [[S_MOV_B32_]], %bb.0, %11, %bb.3
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[PHI]]
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:agpr_32 = COPY [[PHI]]
+  ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
+  ; CHECK-NEXT:   $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_]], implicit-def $scc
+  ; CHECK-NEXT:   S_CBRANCH_VCCNZ %bb.3, implicit $vcc
+  ; CHECK-NEXT:   S_BRANCH %bb.2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   successors: %bb.3(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[PHI1]], 1, implicit-def dead $scc
+  ; CHECK-NEXT:   [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[PHI1]], 31, implicit-def dead $scc
+  ; CHECK-NEXT:   [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 killed [[S_ASHR_I32_]], killed [[S_OR_B32_]], implicit-def dead $scc
+  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_128_align2 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[V_MOV_B32_e32_]], %subreg.sub1, [[V_MOV_B32_e32_]], %subreg.sub2, [[V_MOV_B32_e32_]], %subreg.sub3
+  ; CHECK-NEXT:   [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_]], %subreg.sub1
+  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:vreg_64_align2 = COPY [[REG_SEQUENCE1]]
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:areg_128_align2 = COPY [[REG_SEQUENCE]]
+  ; CHECK-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY4]], [[COPY4]], killed [[COPY5]], 0, 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[S_MOV_B64_1:%[0-9]+]]:sreg_64 = S_MOV_B64 0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.3:
+  ; CHECK-NEXT:   successors: %bb.4(0x40000000), %bb.1(0x40000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[PHI2:%[0-9]+]]:sreg_32 = PHI [[DEF]], %bb.1, [[S_AND_B32_]], %bb.2
+  ; CHECK-NEXT:   [[PHI3:%[0-9]+]]:agpr_32 = PHI [[COPY3]], %bb.1, [[V_MFMA_F32_16X16X16F16_e64_]].sub0, %bb.2
+  ; CHECK-NEXT:   [[PHI4:%[0-9]+]]:sreg_64_xexec = PHI [[S_MOV_B64_]], %bb.1, [[S_MOV_B64_1]], %bb.2
+  ; CHECK-NEXT:   [[V_CNDMASK_B32_e64_1:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[PHI4]], implicit $exec
+  ; CHECK-NEXT:   [[V_CMP_NE_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 [[V_CNDMASK_B32_e64_1]], 1, implicit $exec
+  ; CHECK-NEXT:   $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_1]], implicit-def $scc
+  ; CHECK-NEXT:   S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+  ; CHECK-NEXT:   S_BRANCH %bb.4
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.4:
+  ; CHECK-NEXT:   successors: %bb.5(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.5:
+  ; CHECK-NEXT:   S_ENDPGM 0
+  ;
+  ; COALESCE-LABEL: name: test
+  ; COALESCE: bb.0:
+  ; COALESCE-NEXT:   successors: %bb.1(0x80000000)
+  ; COALESCE-NEXT:   liveins: $sgpr4_sgpr5
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
+  ; COALESCE-NEXT:   [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+  ; COALESCE-NEXT:   S_BITCMP1_B32 [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
+  ; COALESCE-NEXT:   undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_64 = S_MOV_B32 0
+  ; COALESCE-NEXT:   [[S_CSELECT_B64_:%[0-9]+]]:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit killed $scc
+  ; COALESCE-NEXT:   undef [[V_MOV_B32_e32_:%[0-9]+]].sub1:vreg_128_align2 = V_MOV_B32_e32 0, implicit $exec
+  ; COALESCE-NEXT:   undef [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]].sub0:areg_128_align2 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; COALESCE-NEXT:   [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_CSELECT_B64_]], implicit $exec
+  ; COALESCE-NEXT:   [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_]], implicit $exec
+  ; COALESCE-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 0
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.1:
+  ; COALESCE-NEXT:   successors: %bb.2(0x40000000), %bb.3(0x40000000)
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]].sub0:vreg_128_align2 = COPY [[V_ACCVGPR_WRITE_B32_e64_]].sub0
+  ; COALESCE-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 -1
+  ; COALESCE-NEXT:   $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_]], implicit-def dead $scc
+  ; COALESCE-NEXT:   S_CBRANCH_VCCNZ %bb.3, implicit killed $vcc
+  ; COALESCE-NEXT:   S_BRANCH %bb.2
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.2:
+  ; COALESCE-NEXT:   successors: %bb.3(0x80000000)
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[S_MOV_B32_1]], 1, implicit-def dead $scc
+  ; COALESCE-NEXT:   [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[S_MOV_B32_1]], 31, implicit-def dead $scc
+  ; COALESCE-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_AND_B32 [[S_ASHR_I32_]], [[S_OR_B32_]], implicit-def dead $scc
+  ; COALESCE-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]].sub2:vreg_128_align2 = COPY [[V_MOV_B32_e32_]].sub1
+  ; COALESCE-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]].sub3:vreg_128_align2 = COPY [[V_MOV_B32_e32_]].sub1
+  ; COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_64 = COPY [[S_MOV_B32_]].sub0
+  ; COALESCE-NEXT:   [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY [[S_MOV_B32_]]
+  ; COALESCE-NEXT:   [[COPY2:%[0-9]+]]:areg_128_align2 = COPY [[V_MOV_B32_e32_]]
+  ; COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[COPY2]], 0, 0, 0, implicit $mode, implicit $exec
+  ; COALESCE-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 0
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.3:
+  ; COALESCE-NEXT:   successors: %bb.4(0x40000000), %bb.1(0x40000000)
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   [[V_CNDMASK_B32_e64_1:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_MOV_B64_]], implicit $exec
+  ; COALESCE-NEXT:   [[V_CMP_NE_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_1]], implicit $exec
+  ; COALESCE-NEXT:   $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_1]], implicit-def dead $scc
+  ; COALESCE-NEXT:   S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
+  ; COALESCE-NEXT:   S_BRANCH %bb.4
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.4:
+  ; COALESCE-NEXT:   successors: %bb.5(0x80000000)
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.5:
+  ; COALESCE-NEXT:   S_ENDPGM 0
+  ;
+  ; GFX908-COALESCE-LABEL: name: test
+  ; GFX908-COALESCE: bb.0:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.1(0x80000000)
+  ; GFX908-COALESCE-NEXT:   liveins: $sgpr4_sgpr5
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
+  ; GFX908-COALESCE-NEXT:   [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+  ; GFX908-COALESCE-NEXT:   S_BITCMP1_B32 [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
+  ; GFX908-COALESCE-NEXT:   undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_64 = S_MOV_B32 0
+  ; GFX908-COALESCE-NEXT:   [[S_CSELECT_B64_:%[0-9]+]]:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit killed $scc
+  ; GFX908-COALESCE-NEXT:   undef [[V_MOV_B32_e32_:%[0-9]+]].sub1:vreg_128_align2 = V_MOV_B32_e32 0, implicit $exec
+  ; GFX908-COALESCE-NEXT:   undef [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]].sub0:areg_128_align2 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_CSELECT_B64_]], implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_]], implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 0
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.1:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.2(0x40000000), %bb.3(0x40000000)
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]].sub0:vreg_128_align2 = COPY [[V_ACCVGPR_WRITE_B32_e64_]].sub0
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 -1
+  ; GFX908-COALESCE-NEXT:   $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_]], implicit-def dead $scc
+  ; GFX908-COALESCE-NEXT:   S_CBRANCH_VCCNZ %bb.3, implicit killed $vcc
+  ; GFX908-COALESCE-NEXT:   S_BRANCH %bb.2
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.2:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.3(0x80000000)
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[S_MOV_B32_1]], 1, implicit-def dead $scc
+  ; GFX908-COALESCE-NEXT:   [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[S_MOV_B32_1]], 31, implicit-def dead $scc
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_AND_B32 [[S_ASHR_I32_]], [[S_OR_B32_]], implicit-def dead $scc
+  ; GFX908-COALESCE-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]].sub2:vreg_128_align2 = COPY [[V_MOV_B32_e32_]].sub1
+  ; GFX908-COALESCE-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]].sub3:vreg_128_align2 = COPY [[V_MOV_B32_e32_]].sub1
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_64 = COPY [[S_MOV_B32_]].sub0
+  ; GFX908-COALESCE-NEXT:   [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY [[S_MOV_B32_]]
+  ; GFX908-COALESCE-NEXT:   [[COPY2:%[0-9]+]]:areg_128_align2 = COPY [[V_MOV_B32_e32_]]
+  ; GFX908-COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[COPY2]], 0, 0, 0, implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 0
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.3:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.4(0x40000000), %bb.1(0x40000000)
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   [[V_CNDMASK_B32_e64_1:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_MOV_B64_]], implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_CMP_NE_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_1]], implicit $exec
+  ; GFX908-COALESCE-NEXT:   $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_1]], implicit-def dead $scc
+  ; GFX908-COALESCE-NEXT:   S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
+  ; GFX908-COALESCE-NEXT:   S_BRANCH %bb.4
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.4:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.5(0x80000000)
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.5:
+  ; GFX908-COALESCE-NEXT:   S_ENDPGM 0
+  bb.0:
+    successors: %bb.1
+    liveins: $sgpr4_sgpr5
+
+    %521:sgpr_64(p4) = COPY $sgpr4_sgpr5
+    %655:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %521(p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+    S_BITCMP1_B32 killed %655, 0, implicit-def $scc
+    %526:sgpr_32 = S_MOV_B32 0
+    %690:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit $scc
+    %815:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %658:sreg_32 = IMPLICIT_DEF
+    %660:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, %690, implicit $exec
+    %689:sreg_64_xexec = V_CMP_NE_U32_e64 %660, 1, implicit $exec
+
+  bb.1:
+    successors: %bb.2, %bb.3
+
+    %125:vgpr_32 = PHI %815, %bb.0, %384, %bb.3
+    %130:sreg_32 = PHI %526, %bb.0, %260, %bb.3
+    %820:agpr_32 = COPY %125
+    %659:sreg_64 = S_MOV_B64 -1
+    $vcc = S_AND_B64 $exec, %689, implicit-def $scc
+    S_CBRANCH_VCCNZ %bb.3, implicit $vcc
+    S_BRANCH %bb.2
+
+  bb.2:
+    successors: %bb.3
+
+    %665:sreg_32 = S_OR_B32 %130, 1, implicit-def dead $scc
+    %667:sreg_32 = S_ASHR_I32 %130, 31, implicit-def dead $scc
+    %131:sreg_32 = S_AND_B32 killed %667, killed %665, implicit-def dead $scc
+    %685:vreg_128_align2 = REG_SEQUENCE %125, %subreg.sub0, %815, %subreg.sub1, %815, %subreg.sub2, %815, %subreg.sub3
+    %671:sreg_64 = REG_SEQUENCE %526, %subreg.sub0, %526, %subreg.sub1
+    %673:vreg_64_align2 = COPY %671
+    %675:areg_128_align2 = COPY %685
+    %672:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 %673, %673, killed %675, 0, 0, 0, implicit $mode, implicit $exec
+    %255:vgpr_32 = COPY %672.sub0
+    %663:sreg_64 = S_MOV_B64 0
+
+  bb.3:
+    successors: %bb.4, %bb.1
+
+    %260:sreg_32 = PHI %658, %bb.1, %131, %bb.2
+    %821:agpr_32 = PHI %820, %bb.1, %672.sub0, %bb.2
+    %389:sreg_64_xexec = PHI %659, %bb.1, %663, %bb.2
+    %384:vgpr_32 = COPY %821
+    %676:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, %389, implicit $exec
+    %684:sreg_64_xexec = V_CMP_NE_U32_e64 %676, 1, implicit $exec
+    $vcc = S_AND_B64 $exec, %684, implicit-def $scc
+    S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+    S_BRANCH %bb.4
+
+  bb.4:
+    successors: %bb.5
+
+  bb.5:
+    S_ENDPGM 0
+
+...
diff --git a/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-read.mir b/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-read.mir
new file mode 100644
index 00000000000000..7ea4cf92c0d64a
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-read.mir
@@ -0,0 +1,181 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942 -verify-machineinstrs --run-pass si-fold-operands %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942  -verify-machineinstrs -start-before=si-fold-operands -stop-after=register-coalescer %s -o - | FileCheck %s --check-prefixes=COALESCE
+# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx908  -verify-machineinstrs -start-before=si-fold-operands -stop-after=register-coalescer %s -o - | FileCheck %s --check-prefixes=GFX908-COALESCE
+
+---
+name:            test
+tracksRegLiveness: true
+body:             |
+  ; CHECK-LABEL: name: test
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
+  ; CHECK-NEXT:   liveins: $sgpr4_sgpr5
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
+  ; CHECK-NEXT:   [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sgpr_32 = S_MOV_B32 0
+  ; CHECK-NEXT:   S_BITCMP0_B32 killed [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
+  ; CHECK-NEXT:   S_CBRANCH_SCC0 %bb.2, implicit $scc
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.3(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; CHECK-NEXT:   S_BRANCH %bb.3
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   successors: %bb.3(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sgpr_32 = S_MOV_B32 0
+  ; CHECK-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_1:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; CHECK-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_2:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; CHECK-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_3:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; CHECK-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_4:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:areg_128_align2 = REG_SEQUENCE [[V_ACCVGPR_WRITE_B32_e64_1]], %subreg.sub0, [[V_ACCVGPR_WRITE_B32_e64_2]], %subreg.sub1, [[V_ACCVGPR_WRITE_B32_e64_3]], %subreg.sub2, [[V_ACCVGPR_WRITE_B32_e64_4]], %subreg.sub3
+  ; CHECK-NEXT:   [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_1]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY [[REG_SEQUENCE1]]
+  ; CHECK-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], 0, 0, 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_1:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], killed [[V_MFMA_F32_16X16X16F16_e64_]], 0, 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_2:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], killed [[V_MFMA_F32_16X16X16F16_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_3:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], killed [[V_MFMA_F32_16X16X16F16_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[V_MFMA_F32_16X16X16F16_e64_3]].sub0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.3:
+  ; CHECK-NEXT:   [[PHI:%[0-9]+]]:agpr_32 = PHI [[V_ACCVGPR_WRITE_B32_e64_]], %bb.1, [[V_MFMA_F32_16X16X16F16_e64_3]].sub0, %bb.2
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[PHI]]
+  ; CHECK-NEXT:   [[V_CVT_F16_F32_e64_:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_F16_F32_e64 0, [[COPY3]], 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[V_PACK_B32_F16_e64_:%[0-9]+]]:vgpr_32 = nofpexcept V_PACK_B32_F16_e64 0, killed [[V_CVT_F16_F32_e64_]], 0, 0, 0, 0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+  ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[V_PACK_B32_F16_e64_]], %subreg.sub0, killed [[V_MOV_B32_e32_]], %subreg.sub1
+  ; CHECK-NEXT:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_]], %subreg.sub1, [[S_MOV_B32_]], %subreg.sub2, [[S_MOV_B32_]], %subreg.sub3
+  ; CHECK-NEXT:   BUFFER_STORE_DWORDX2_OFFSET_exact [[REG_SEQUENCE2]], killed [[REG_SEQUENCE3]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into `ptr addrspace(8) null`, align 1, addrspace 8)
+  ; CHECK-NEXT:   S_ENDPGM 0
+  ;
+  ; COALESCE-LABEL: name: test
+  ; COALESCE: bb.0:
+  ; COALESCE-NEXT:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
+  ; COALESCE-NEXT:   liveins: $sgpr4_sgpr5
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
+  ; COALESCE-NEXT:   [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+  ; COALESCE-NEXT:   undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_128 = S_MOV_B32 0
+  ; COALESCE-NEXT:   S_BITCMP0_B32 [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
+  ; COALESCE-NEXT:   S_CBRANCH_SCC0 %bb.2, implicit killed $scc
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.1:
+  ; COALESCE-NEXT:   successors: %bb.3(0x80000000)
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   undef [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]].sub0:areg_128_align2 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; COALESCE-NEXT:   S_BRANCH %bb.3
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.2:
+  ; COALESCE-NEXT:   successors: %bb.3(0x80000000)
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; COALESCE-NEXT:   [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY [[S_MOV_B32_]].sub0_sub1
+  ; COALESCE-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], 0, 0, 0, 0, implicit $mode, implicit $exec
+  ; COALESCE-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_1:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_MFMA_F32_16X16X16F16_e64_]], 0, 0, 0, implicit $mode, implicit $exec
+  ; COALESCE-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_2:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_MFMA_F32_16X16X16F16_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
+  ; COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_MFMA_F32_16X16X16F16_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
+  ; COALESCE-NEXT: {{  $}}
+  ; COALESCE-NEXT: bb.3:
+  ; COALESCE-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[V_ACCVGPR_WRITE_B32_e64_]].sub0
+  ; COALESCE-NEXT:   [[V_CVT_F16_F32_e32_:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_F16_F32_e32 [[COPY2]], implicit $mode, implicit $exec
+  ; COALESCE-NEXT:   undef [[V_PACK_B32_F16_e64_:%[0-9]+]].sub0:vreg_64_align2 = nofpexcept V_PACK_B32_F16_e64 0, [[V_CVT_F16_F32_e32_]], 0, 0, 0, 0, implicit $mode, implicit $exec
+  ; COALESCE-NEXT:   [[V_PACK_B32_F16_e64_:%[0-9]+]].sub1:vreg_64_align2 = V_MOV_B32_e32 0, implicit $exec
+  ; COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub2:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub3:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; COALESCE-NEXT:   BUFFER_STORE_DWORDX2_OFFSET_exact [[V_PACK_B32_F16_e64_]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into `ptr addrspace(8) null`, align 1, addrspace 8)
+  ; COALESCE-NEXT:   S_ENDPGM 0
+  ;
+  ; GFX908-COALESCE-LABEL: name: test
+  ; GFX908-COALESCE: bb.0:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
+  ; GFX908-COALESCE-NEXT:   liveins: $sgpr4_sgpr5
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
+  ; GFX908-COALESCE-NEXT:   [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+  ; GFX908-COALESCE-NEXT:   undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_128 = S_MOV_B32 0
+  ; GFX908-COALESCE-NEXT:   S_BITCMP0_B32 [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
+  ; GFX908-COALESCE-NEXT:   S_CBRANCH_SCC0 %bb.2, implicit killed $scc
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.1:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.3(0x80000000)
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   undef [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]].sub0:areg_128_align2 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; GFX908-COALESCE-NEXT:   S_BRANCH %bb.3
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.2:
+  ; GFX908-COALESCE-NEXT:   successors: %bb.3(0x80000000)
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT:   undef [[V_ACCVGPR_WRITE_B32_e64_1:%[0-9]+]].sub0:areg_128_align2 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_1:%[0-9]+]].sub1:areg_128_align2 = COPY [[V_ACCVGPR_WRITE_B32_e64_1]].sub0
+  ; GFX908-COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_1:%[0-9]+]].sub2:areg_128_align2 = COPY [[V_ACCVGPR_WRITE_B32_e64_1]].sub0
+  ; GFX908-COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_1:%[0-9]+]].sub3:areg_128_align2 = COPY [[V_ACCVGPR_WRITE_B32_e64_1]].sub0
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; GFX908-COALESCE-NEXT:   [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY [[S_MOV_B32_]].sub0_sub1
+  ; GFX908-COALESCE-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_ACCVGPR_WRITE_B32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_1:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_MFMA_F32_16X16X16F16_e64_]], 0, 0, 0, implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_MFMA_F32_16X16X16F16_e64_2:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_MFMA_F32_16X16X16F16_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY1]], [[COPY1]], [[V_MFMA_F32_16X16X16F16_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT: {{  $}}
+  ; GFX908-COALESCE-NEXT: bb.3:
+  ; GFX908-COALESCE-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[V_ACCVGPR_WRITE_B32_e64_]].sub0
+  ; GFX908-COALESCE-NEXT:   [[V_CVT_F16_F32_e32_:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_F16_F32_e32 [[COPY2]], implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT:   undef [[V_PACK_B32_F16_e64_:%[0-9]+]].sub0:vreg_64_align2 = nofpexcept V_PACK_B32_F16_e64 0, [[V_CVT_F16_F32_e32_]], 0, 0, 0, 0, implicit $mode, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[V_PACK_B32_F16_e64_:%[0-9]+]].sub1:vreg_64_align2 = V_MOV_B32_e32 0, implicit $exec
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub2:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; GFX908-COALESCE-NEXT:   [[S_MOV_B32_:%[0-9]+]].sub3:sgpr_128 = COPY [[S_MOV_B32_]].sub0
+  ; GFX908-COALESCE-NEXT:   BUFFER_STORE_DWORDX2_OFFSET_exact [[V_PACK_B32_F16_e64_]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into `ptr addrspace(8) null`, align 1, addrspace 8)
+  ; GFX908-COALESCE-NEXT:   S_ENDPGM 0
+  bb.0:
+    successors: %bb.1, %bb.3
+    liveins: $sgpr4_sgpr5
+
+    %259:sgpr_64(p4) = COPY $sgpr4_sgpr5
+    %392:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %259(p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
+    %264:sgpr_32 = S_MOV_B32 0
+    S_BITCMP0_B32 killed %392, 0, implicit-def $scc
+    S_CBRANCH_SCC0 %bb.1, implicit $scc
+
+  bb.3:
+    successors: %bb.2
+
+    %316:sgpr_32 = COPY %264
+    %484:vgpr_32 = COPY %316, implicit $exec
+    S_BRANCH %bb.2
+
+  bb.1:
+    successors: %bb.2
+
+    %396:sgpr_32 = S_MOV_B32 0
+    %424:vgpr_32 = COPY %396
+    %425:agpr_32 = V_ACCVGPR_WRITE_B32_e64 %424, implicit $exec
+    %427:agpr_32 = V_ACCVGPR_WRITE_B32_e64 %424, implicit $exec
+    %429:agpr_32 = V_ACCVGPR_WRITE_B32_e64 %424, implicit $exec
+    %431:agpr_32 = V_ACCVGPR_WRITE_B32_e64 %424, implicit $exec
+    %403:areg_128_align2 = REG_SEQUENCE %425, %subreg.sub0, %427, %subreg.sub1, %429, %subreg.sub2, %431, %subreg.sub3
+    %399:sreg_64 = REG_SEQUENCE %396, %subreg.sub0, %396, %subreg.sub1
+    %401:vreg_64_align2 = COPY %399
+    %400:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 %401, %401, killed %403, 0, 0, 0, implicit $mode, implicit $exec
+    %404:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 %401, %401, killed %400, 0, 0, 0, implicit $mode, implicit $exec
+    %407:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 %401, %401, killed %404, 0, 0, 0, implicit $mode, implicit $exec
+    %410:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 %401, %401, killed %407, 0, 0, 0, implicit $mode, implicit $exec
+    %48:vgpr_32 = COPY %410.sub0
+    %52:vgpr_32 = COPY %48
+
+  bb.2:
+    %180:vgpr_32 = PHI %484, %bb.3, %52, %bb.1
+    %413:vgpr_32 = nofpexcept V_CVT_F16_F32_e64 0, %180, 0, 0, implicit $mode, implicit $exec
+    %415:vgpr_32 = nofpexcept V_PACK_B32_F16_e64 0, killed %413, 0, %264, 0, 0, implicit $mode, implicit $exec
+    %423:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %422:vreg_64_align2 = REG_SEQUENCE %415, %subreg.sub0, killed %423, %subreg.sub1
+    %419:sgpr_128 = REG_SEQUENCE %264, %subreg.sub0, %264, %subreg.sub1, %264, %subreg.sub2, %264, %subreg.sub3
+    %420:vreg_64_align2 = COPY %422
+    BUFFER_STORE_DWORDX2_OFFSET_exact killed %420, killed %419, %264, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into `ptr addrspace(8) null`, align 1, addrspace 8)
+    S_ENDPGM 0
+
+...



More information about the llvm-commits mailing list