[llvm] AMDGPU: Add pseudoinstruction for agpr or vgpr constants (PR #130042)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Thu Mar 6 01:47:56 PST 2025


https://github.com/arsenm created https://github.com/llvm/llvm-project/pull/130042

AMDGPU: Add pseudoinstruction for agpr or vgpr constants

Currently constants are materialized with v_mov_b32, which
may fold into v_accvgpr_write_b32 if it happens to be copied
into an AGPR use. This is fine until the register allocator
wants to introduce temporary registers using the combined AV_
superclasses. Since each of these instructions is restricted to
writing the specific subclass, they block instances where
we could inflate the use register class. As v_accvgpr_write_b32 cannot
use a literal constant, only inline immediate values should be used
with the pseudo.

Introduce a pseudo with a flexible result register class. Alternatively
we would need to teach allocation about how to rewrite or rematerialize
with a change of opcode which would require a lot more machinery.

We may want a 64-bit variant, just in case we can make use of v_mov_b64.

This does not yet attempt to make use of it, and only adds the boilerplate
and tests on basic optimizations.

Add broken tests from preexisting failure

>From 6e0dcf534bf951883b23d59fac60c0f7a6713faf Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Tue, 25 Feb 2025 14:56:57 +0700
Subject: [PATCH 1/2] AMDGPU: Add pseudoinstruction for agpr or vgpr constants

Currently constants are materialized with v_mov_b32, which
may fold into v_accvgpr_write_b32 if it happens to be copied
into an AGPR use. This is fine until the register allocator
wants to introduce temporary registers using the combined AV_
superclasses. Since each of these instructions is restricted to
writing the specific subclass, they block instances where
we could inflate the use register class. As v_accvgpr_write_b32 cannot
use a literal constant, only inline immediate values should be used
with the pseudo.

Introduce a pseudo with a flexible result register class. Alternatively
we would need to teach allocation about how to rewrite or rematerialize
with a change of opcode which would require a lot more machinery.

We may want a 64-bit variant, just in case we can make use of v_mov_b64.

This does not yet attempt to make use of it, and only adds the boilerplate
and tests on basic optimizations.
---
 llvm/lib/Target/AMDGPU/SIInstrInfo.cpp        |  10 +-
 llvm/lib/Target/AMDGPU/SIInstructions.td      |  19 +++
 .../AMDGPU/av_movimm_pseudo_expansion.mir     |  56 +++++++
 llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir    |  75 +++++++++
 .../CodeGen/AMDGPU/inflate-av-remat-imm.mir   | 117 ++++++++++++++
 .../test/CodeGen/AMDGPU/peephole-fold-imm.mir |  65 ++++++++
 ...-do-not-undo-subclass-split-with-remat.mir | 143 ++++++++++++++++++
 llvm/test/CodeGen/AMDGPU/vgpr-remat.mir       |  45 ++++++
 .../AMDGPU/verify-av-mov-imm-pseudo.mir       |  15 ++
 9 files changed, 544 insertions(+), 1 deletion(-)
 create mode 100644 llvm/test/CodeGen/AMDGPU/av_movimm_pseudo_expansion.mir
 create mode 100644 llvm/test/CodeGen/AMDGPU/inflate-av-remat-imm.mir
 create mode 100644 llvm/test/MachineVerifier/AMDGPU/verify-av-mov-imm-pseudo.mir

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index e1fb4c9db0a84..ae285d069d876 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -1337,6 +1337,7 @@ bool SIInstrInfo::getConstValDefinedInReg(const MachineInstr &MI,
   case AMDGPU::S_MOV_B64:
   case AMDGPU::V_MOV_B64_e32:
   case AMDGPU::V_ACCVGPR_WRITE_B32_e64:
+  case AMDGPU::AV_MOV_B32_IMM_PSEUDO:
   case AMDGPU::S_MOV_B64_IMM_PSEUDO:
   case AMDGPU::V_MOV_B64_PSEUDO: {
     const MachineOperand &Src0 = MI.getOperand(1);
@@ -2186,7 +2187,13 @@ bool SIInstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
     MI.getMF()->getRegInfo().constrainRegClass(MI.getOperand(0).getReg(),
                                                &AMDGPU::SReg_32_XM0RegClass);
     break;
-
+  case AMDGPU::AV_MOV_B32_IMM_PSEUDO: {
+    Register Dst = MI.getOperand(0).getReg();
+    bool IsAGPR = SIRegisterInfo::isAGPRClass(RI.getPhysRegBaseClass(Dst));
+    MI.setDesc(
+        get(IsAGPR ? AMDGPU::V_ACCVGPR_WRITE_B32_e64 : AMDGPU::V_MOV_B32_e32));
+    break;
+  }
   case AMDGPU::V_MOV_B64_PSEUDO: {
     Register Dst = MI.getOperand(0).getReg();
     Register DstLo = RI.getSubReg(Dst, AMDGPU::sub0);
@@ -3423,6 +3430,7 @@ bool SIInstrInfo::isFoldableCopy(const MachineInstr &MI) {
   case AMDGPU::V_ACCVGPR_WRITE_B32_e64:
   case AMDGPU::V_ACCVGPR_READ_B32_e64:
   case AMDGPU::V_ACCVGPR_MOV_B32:
+  case AMDGPU::AV_MOV_B32_IMM_PSEUDO:
     return true;
   default:
     return false;
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 63f66023837a2..ea0c1ead1526b 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -140,6 +140,25 @@ def V_MOV_B64_PSEUDO : VPseudoInstSI <(outs VReg_64:$vdst),
   let UseNamedOperandTable = 1;
 }
 
+// 32-bit materialize immediate which supports AGPR or VGPR. Typically
+// this should just expand to V_MOV_B32, unless $vdst happens to be
+// allocated to an AGPR in which case it will lower to
+// V_ACCVGPR_WRITE_B32. This should always use an inline immediate
+// operand, as v_accvgpr_write_b32 does not support literal constants.
+def AV_MOV_B32_IMM_PSEUDO
+    : VPseudoInstSI<(outs AV_32:$vdst), (ins VCSrc_b32:$src0)> {
+  let isReMaterializable = 1;
+  let isAsCheapAsAMove = 1;
+
+  // Imprecise, technically if AGPR it's VOP3 and VOP1 for AGPR. But
+  // this tricks the rematerialize logic into working for it.
+  let VOP3 = 1;
+  let isMoveImm = 1;
+  let SchedRW = [Write32Bit];
+  let Size = 4;
+  let UseNamedOperandTable = 1;
+}
+
 // 64-bit vector move with dpp. Expanded post-RA.
 def V_MOV_B64_DPP_PSEUDO : VOP_DPP_Pseudo <"v_mov_b64_dpp", VOP_I64_I64> {
   let Size = 16; // Requires two 8-byte v_mov_b32_dpp to complete.
diff --git a/llvm/test/CodeGen/AMDGPU/av_movimm_pseudo_expansion.mir b/llvm/test/CodeGen/AMDGPU/av_movimm_pseudo_expansion.mir
new file mode 100644
index 0000000000000..1f9d49073da2c
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/av_movimm_pseudo_expansion.mir
@@ -0,0 +1,56 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx90a -run-pass=postrapseudos %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx942 -run-pass=postrapseudos %s -o - | FileCheck %s
+
+---
+name: av_mov_b32_imm_pseudo_agpr_0
+tracksRegLiveness: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: av_mov_b32_imm_pseudo_agpr_0
+    ; CHECK: $agpr0 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+    $agpr0 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+...
+
+---
+name: av_mov_b32_imm_pseudo_agpr_64
+tracksRegLiveness: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: av_mov_b32_imm_pseudo_agpr_64
+    ; CHECK: $agpr0 = V_ACCVGPR_WRITE_B32_e64 64, implicit $exec
+    $agpr0 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+...
+
+---
+name: av_mov_b32_imm_pseudo_vgpr_0
+tracksRegLiveness: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: av_mov_b32_imm_pseudo_vgpr_0
+    ; CHECK: $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+    $vgpr0 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+...
+
+---
+name: av_mov_b32_imm_pseudo_vgpr_64
+tracksRegLiveness: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: av_mov_b32_imm_pseudo_vgpr_64
+    ; CHECK: $vgpr0 = V_MOV_B32_e32 64, implicit $exec
+    $vgpr0 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+...
+
+---
+name: av_mov_b32_imm_pseudo_agpr_vgpr
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0
+    ; CHECK-LABEL: name: av_mov_b32_imm_pseudo_agpr_vgpr
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: $agpr1 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec
+    $agpr1 = AV_MOV_B32_IMM_PSEUDO $vgpr0, implicit $exec
+...
diff --git a/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir b/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
index 5d68c3135a026..90ccc30affe1a 100644
--- a/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
+++ b/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
@@ -109,3 +109,78 @@ body:             |
     S_ENDPGM 0
 
 ...
+
+---
+name: av_mov_b32_imm_pseudo_copy_av_32_to_physreg_agpr
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: av_mov_b32_imm_pseudo_copy_av_32_to_physreg_agpr
+    ; GCN: [[AV_MOV_:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    ; GCN-NEXT: $agpr0 = COPY [[AV_MOV_]]
+    ; GCN-NEXT: S_ENDPGM 0, implicit $agpr0
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    $agpr0 = COPY %0
+    S_ENDPGM 0, implicit $agpr0
+
+...
+
+---
+name: av_mov_b32_imm_pseudo_copy_av_32_to_physreg_vgpr
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: av_mov_b32_imm_pseudo_copy_av_32_to_physreg_vgpr
+    ; GCN: [[AV_MOV_:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    ; GCN-NEXT: $vgpr0 = COPY [[AV_MOV_]]
+    ; GCN-NEXT: S_ENDPGM 0, implicit $vgpr0
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    $vgpr0 = COPY %0
+    S_ENDPGM 0, implicit $vgpr0
+
+...
+
+---
+name: av_mov_b32_imm_pseudo_copy_av_32_to_virtreg_agpr
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: av_mov_b32_imm_pseudo_copy_av_32_to_virtreg_agpr
+    ; GCN: [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+    ; GCN-NEXT: S_ENDPGM 0, implicit [[V_ACCVGPR_WRITE_B32_e64_]]
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    %1:agpr_32 = COPY %0
+    S_ENDPGM 0, implicit %1
+
+...
+
+---
+name: av_mov_b32_imm_pseudo_copy_av_32_to_virtreg_vgpr
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: av_mov_b32_imm_pseudo_copy_av_32_to_virtreg_vgpr
+    ; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    ; GCN-NEXT: S_ENDPGM 0, implicit [[V_MOV_B32_e32_]]
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    %1:vgpr_32 = COPY %0
+    S_ENDPGM 0, implicit %1
+
+...
+
+---
+name: v_mov_b32_imm_literal_copy_v_to_agpr_32
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: v_mov_b32_imm_literal_copy_v_to_agpr_32
+    ; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:agpr_32 = COPY [[V_MOV_B32_e32_]]
+    ; GCN-NEXT: $agpr0 = COPY [[COPY]]
+    ; GCN-NEXT: S_ENDPGM 0
+    %0:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
+    %1:agpr_32 = COPY %0
+    $agpr0 = COPY %1
+    S_ENDPGM 0
+
+...
diff --git a/llvm/test/CodeGen/AMDGPU/inflate-av-remat-imm.mir b/llvm/test/CodeGen/AMDGPU/inflate-av-remat-imm.mir
new file mode 100644
index 0000000000000..eab5b1bb19057
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/inflate-av-remat-imm.mir
@@ -0,0 +1,117 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -simplify-mir -start-before=greedy,2 -stress-regalloc=3 -stop-after=postrapseudos -o - -verify-regalloc %s | FileCheck %s
+
+# Compare results of using V_MOV_B32 vs. AV_MOV_B32_IMM_PSEUDO during
+# allocation.
+
+---
+name: av_mov_b32_split
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+  scratchRSrcReg:  '$sgpr72_sgpr73_sgpr74_sgpr75'
+  stackPtrOffsetReg: '$sgpr32'
+  occupancy:       7
+  vgprForAGPRCopy: '$vgpr255'
+  sgprForEXECCopy: '$sgpr74_sgpr75'
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr4_sgpr5
+
+    ; CHECK-LABEL: name: av_mov_b32_split
+    ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $sgpr4_sgpr5
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: renamable $agpr0 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
+    ; CHECK-NEXT: renamable $agpr1 = V_ACCVGPR_WRITE_B32_e64 1, implicit $exec
+    ; CHECK-NEXT: renamable $agpr2 = V_ACCVGPR_WRITE_B32_e64 2, implicit $exec
+    ; CHECK-NEXT: $vgpr0 = V_ACCVGPR_READ_B32_e64 killed $agpr0, implicit $exec
+    ; CHECK-NEXT: renamable $agpr0 = V_ACCVGPR_WRITE_B32_e64 3, implicit $exec
+    ; CHECK-NEXT: $vgpr1 = V_ACCVGPR_READ_B32_e64 killed $agpr0, implicit $exec
+    ; CHECK-NEXT: renamable $agpr0 = V_ACCVGPR_WRITE_B32_e64 4, implicit $exec
+    ; CHECK-NEXT: $vgpr2 = V_ACCVGPR_READ_B32_e64 killed $agpr0, implicit $exec
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr1
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr2
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0
+    %0:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    %1:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 1, implicit $exec
+    %2:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 2, implicit $exec
+    %3:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 3, implicit $exec
+    %4:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 4, implicit $exec
+
+    %5:agpr_32 = COPY %0
+    %6:agpr_32 = COPY %1
+    %7:agpr_32 = COPY %2
+    %8:agpr_32 = COPY %3
+    %9:agpr_32 = COPY %4
+
+    S_NOP 0, implicit %5
+    S_NOP 0, implicit %6
+    S_NOP 0, implicit %7
+    S_NOP 0, implicit %8
+    S_NOP 0, implicit %9
+
+...
+
+---
+name: v_mov_b32_split
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+  scratchRSrcReg:  '$sgpr72_sgpr73_sgpr74_sgpr75'
+  stackPtrOffsetReg: '$sgpr32'
+  occupancy:       7
+  vgprForAGPRCopy: '$vgpr255'
+  sgprForEXECCopy: '$sgpr74_sgpr75'
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr4_sgpr5
+
+    ; CHECK-LABEL: name: v_mov_b32_split
+    ; CHECK: liveins: $vgpr0, $vgpr3, $vgpr4, $vgpr5, $sgpr4_sgpr5
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: renamable $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+    ; CHECK-NEXT: renamable $vgpr1 = V_MOV_B32_e32 1, implicit $exec
+    ; CHECK-NEXT: renamable $vgpr2 = V_MOV_B32_e32 2, implicit $exec
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr0, implicit $exec, implicit $exec
+    ; CHECK-NEXT: $vgpr3 = V_ACCVGPR_READ_B32_e64 killed $agpr0, implicit $exec
+    ; CHECK-NEXT: $agpr1 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1, implicit $exec, implicit $exec
+    ; CHECK-NEXT: $agpr2 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr2, implicit $exec, implicit $exec
+    ; CHECK-NEXT: renamable $vgpr0 = V_MOV_B32_e32 3, implicit $exec
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr0, implicit $exec, implicit $exec
+    ; CHECK-NEXT: $vgpr4 = V_ACCVGPR_READ_B32_e64 killed $agpr0, implicit $exec
+    ; CHECK-NEXT: renamable $vgpr0 = V_MOV_B32_e32 4, implicit $exec
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr0, implicit $exec, implicit $exec
+    ; CHECK-NEXT: $vgpr5 = V_ACCVGPR_READ_B32_e64 killed $agpr0, implicit $exec
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 $vgpr3, implicit $exec
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr1
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr2
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 $vgpr4, implicit $exec
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0
+    ; CHECK-NEXT: $agpr0 = V_ACCVGPR_WRITE_B32_e64 $vgpr5, implicit $exec
+    ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0
+    %0:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %1:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+    %2:vgpr_32 = V_MOV_B32_e32 2, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_e32 3, implicit $exec
+    %4:vgpr_32 = V_MOV_B32_e32 4, implicit $exec
+
+    %5:agpr_32 = COPY %0
+    %6:agpr_32 = COPY %1
+    %7:agpr_32 = COPY %2
+    %8:agpr_32 = COPY %3
+    %9:agpr_32 = COPY %4
+
+    S_NOP 0, implicit %5
+    S_NOP 0, implicit %6
+    S_NOP 0, implicit %7
+    S_NOP 0, implicit %8
+    S_NOP 0, implicit %9
+
+...
+
diff --git a/llvm/test/CodeGen/AMDGPU/peephole-fold-imm.mir b/llvm/test/CodeGen/AMDGPU/peephole-fold-imm.mir
index ddeb45a48a6ee..afbbb05bfc3a5 100644
--- a/llvm/test/CodeGen/AMDGPU/peephole-fold-imm.mir
+++ b/llvm/test/CodeGen/AMDGPU/peephole-fold-imm.mir
@@ -563,3 +563,68 @@ body:             |
     SI_RETURN_TO_EPILOG %1
 
 ...
+
+---
+name:            fold_v_mov_b32_e32_literal_to_agpr
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: fold_v_mov_b32_e32_literal_to_agpr
+    ; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:agpr_32 = COPY killed [[V_MOV_B32_e32_]]
+    ; GCN-NEXT: SI_RETURN_TO_EPILOG implicit [[COPY]]
+    %0:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
+    %1:agpr_32 = COPY killed %0
+    SI_RETURN_TO_EPILOG implicit %1
+...
+
+---
+name:            fold_v_mov_b32_e32_inlineimm_to_agpr
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: fold_v_mov_b32_e32_inlineimm_to_agpr
+    ; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 64, implicit $exec
+    ; GCN-NEXT: [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 64, implicit $exec
+    ; GCN-NEXT: SI_RETURN_TO_EPILOG implicit [[V_ACCVGPR_WRITE_B32_e64_]]
+    %0:vgpr_32 = V_MOV_B32_e32 64, implicit $exec
+    %1:agpr_32 = COPY killed %0
+    SI_RETURN_TO_EPILOG implicit %1
+...
+
+---
+name:            fold_av_mov_b32_imm_pseudo_inlineimm_to_vgpr
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: fold_av_mov_b32_imm_pseudo_inlineimm_to_vgpr
+    ; GCN: [[AV_MOV_:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+    ; GCN-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 64, implicit $exec
+    ; GCN-NEXT: SI_RETURN_TO_EPILOG implicit [[V_MOV_B32_e32_]]
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+    %1:vgpr_32 = COPY killed %0
+    SI_RETURN_TO_EPILOG implicit %1
+...
+
+---
+name:            fold_av_mov_b32_imm_pseudo_inlineimm_to_agpr
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: fold_av_mov_b32_imm_pseudo_inlineimm_to_agpr
+    ; GCN: [[AV_MOV_:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+    ; GCN-NEXT: [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 64, implicit $exec
+    ; GCN-NEXT: SI_RETURN_TO_EPILOG implicit [[V_ACCVGPR_WRITE_B32_e64_]]
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+    %1:agpr_32 = COPY killed %0
+    SI_RETURN_TO_EPILOG implicit %1
+...
+
+---
+name:            fold_av_mov_b32_imm_pseudo_inlineimm_to_av
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: fold_av_mov_b32_imm_pseudo_inlineimm_to_av
+    ; GCN: [[AV_MOV_:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:av_32 = COPY killed [[AV_MOV_]]
+    ; GCN-NEXT: SI_RETURN_TO_EPILOG implicit [[COPY]]
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 64, implicit $exec
+    %1:av_32 = COPY killed %0
+    SI_RETURN_TO_EPILOG implicit %1
+...
diff --git a/llvm/test/CodeGen/AMDGPU/splitkit-do-not-undo-subclass-split-with-remat.mir b/llvm/test/CodeGen/AMDGPU/splitkit-do-not-undo-subclass-split-with-remat.mir
index 9e2501a65c6e4..9b4031826dd22 100644
--- a/llvm/test/CodeGen/AMDGPU/splitkit-do-not-undo-subclass-split-with-remat.mir
+++ b/llvm/test/CodeGen/AMDGPU/splitkit-do-not-undo-subclass-split-with-remat.mir
@@ -153,3 +153,146 @@ body:             |
     S_ENDPGM 0
 
 ...
+
+# Same, except uses AV_MOV_B32_IMM_PSEUDO which is able to
+# rematerialize in the inflated register class.
+---
+name:            temp_vgpr_to_agpr_should_not_undo_split_with_remat_av_pseudo
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+  scratchRSrcReg:  '$sgpr96_sgpr97_sgpr98_sgpr99'
+  stackPtrOffsetReg: '$sgpr32'
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    kernargSegmentPtr: { reg: '$sgpr4_sgpr5' }
+    workGroupIDX:    { reg: '$sgpr6' }
+    privateSegmentWaveByteOffset: { reg: '$sgpr7' }
+    workItemIDX:     { reg: '$vgpr0' }
+  occupancy:       4
+  sgprForEXECCopy: '$sgpr100_sgpr101'
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr4_sgpr5
+
+    ; CHECK-LABEL: name: temp_vgpr_to_agpr_should_not_undo_split_with_remat_av_pseudo
+    ; CHECK: liveins: $vgpr0, $sgpr4_sgpr5
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: S_NOP 0, implicit-def $agpr0
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+    ; CHECK-NEXT: renamable $sgpr0_sgpr1 = S_LOAD_DWORDX2_IMM renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s64), align 16, addrspace 4)
+    ; CHECK-NEXT: [[V_LSHLREV_B32_e32_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e32 7, [[COPY]], implicit $exec
+    ; CHECK-NEXT: undef [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub28_sub29_sub30_sub31:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 112, 0, implicit $exec :: (load (s128), addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub24_sub25_sub26_sub27:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 96, 0, implicit $exec :: (load (s128), align 32, addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub20_sub21_sub22_sub23:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 80, 0, implicit $exec :: (load (s128), addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub16_sub17_sub18_sub19:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 64, 0, implicit $exec :: (load (s128), align 64, addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub12_sub13_sub14_sub15:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 48, 0, implicit $exec :: (load (s128), addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub8_sub9_sub10_sub11:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 32, 0, implicit $exec :: (load (s128), align 32, addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub4_sub5_sub6_sub7:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 16, 0, implicit $exec :: (load (s128), addrspace 1)
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub0_sub1_sub2_sub3:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, [[V_LSHLREV_B32_e32_]], 0, 0, implicit $exec :: (load (s128), align 128, addrspace 1)
+    ; CHECK-NEXT: [[AV_MOV_:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 1065353216, implicit $exec
+    ; CHECK-NEXT: [[AV_MOV_1:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 1073741824, implicit $exec
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]]:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_mac_vgprcd_e64 [[AV_MOV_]], [[AV_MOV_1]], [[GLOBAL_LOAD_DWORDX4_SADDR]], 0, 0, 0, implicit $mode, implicit $exec
+    ; CHECK-NEXT: [[AV_MOV_2:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 1073741824, implicit $exec
+    ; CHECK-NEXT: [[AV_MOV_3:%[0-9]+]]:av_32 = AV_MOV_B32_IMM_PSEUDO 1065353216, implicit $exec
+    ; CHECK-NEXT: early-clobber %5:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_vgprcd_e64 [[AV_MOV_3]], [[AV_MOV_2]], [[GLOBAL_LOAD_DWORDX4_SADDR]], 0, 0, 0, implicit $mode, implicit $exec, implicit $mode, implicit $exec
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub2:vreg_1024_align2 = COPY %5.sub0
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub3:vreg_1024_align2 = COPY %5.sub1
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub4:vreg_1024_align2 = COPY %5.sub2
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub5:vreg_1024_align2 = COPY %5.sub3
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub6:vreg_1024_align2 = COPY %5.sub4
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub7:vreg_1024_align2 = COPY %5.sub5
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub8:vreg_1024_align2 = COPY %5.sub6
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub9:vreg_1024_align2 = COPY %5.sub7
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub10:vreg_1024_align2 = COPY %5.sub8
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub11:vreg_1024_align2 = COPY %5.sub9
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub12:vreg_1024_align2 = COPY %5.sub10
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub13:vreg_1024_align2 = COPY %5.sub11
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub14:vreg_1024_align2 = COPY %5.sub12
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub15:vreg_1024_align2 = COPY %5.sub13
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub16:vreg_1024_align2 = COPY %5.sub14
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub17:vreg_1024_align2 = COPY %5.sub15
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub18:vreg_1024_align2 = COPY %5.sub16
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub19:vreg_1024_align2 = COPY %5.sub17
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub20:vreg_1024_align2 = COPY %5.sub18
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub21:vreg_1024_align2 = COPY %5.sub19
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub22:vreg_1024_align2 = COPY %5.sub20
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub23:vreg_1024_align2 = COPY %5.sub21
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub24:vreg_1024_align2 = COPY %5.sub22
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub25:vreg_1024_align2 = COPY %5.sub23
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub26:vreg_1024_align2 = COPY %5.sub24
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub27:vreg_1024_align2 = COPY %5.sub25
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub28:vreg_1024_align2 = COPY %5.sub26
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub29:vreg_1024_align2 = COPY %5.sub27
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub30:vreg_1024_align2 = COPY %5.sub28
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]].sub31:vreg_1024_align2 = COPY %5.sub29
+    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]]:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_mac_vgprcd_e64 [[AV_MOV_3]], [[AV_MOV_2]], [[GLOBAL_LOAD_DWORDX4_SADDR]], 0, 0, 0, implicit $mode, implicit $exec
+    ; CHECK-NEXT: [[AV_MOV_4:%[0-9]+]]:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub24_sub25_sub26_sub27, renamable $sgpr0_sgpr1, 96, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub28_sub29_sub30_sub31, renamable $sgpr0_sgpr1, 112, 0, implicit $exec :: (store (s128), addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub16_sub17_sub18_sub19, renamable $sgpr0_sgpr1, 64, 0, implicit $exec :: (store (s128), align 64, addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub20_sub21_sub22_sub23, renamable $sgpr0_sgpr1, 80, 0, implicit $exec :: (store (s128), addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub8_sub9_sub10_sub11, renamable $sgpr0_sgpr1, 32, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub12_sub13_sub14_sub15, renamable $sgpr0_sgpr1, 48, 0, implicit $exec :: (store (s128), addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub0_sub1_sub2_sub3, renamable $sgpr0_sgpr1, 0, 0, implicit $exec :: (store (s128), align 128, addrspace 1)
+    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[AV_MOV_4]], [[GLOBAL_LOAD_DWORDX4_SADDR]].sub4_sub5_sub6_sub7, killed renamable $sgpr0_sgpr1, 16, 0, implicit $exec :: (store (s128), addrspace 1)
+    ; CHECK-NEXT: S_ENDPGM 0
+    S_NOP 0, implicit-def $agpr0
+    %0:vgpr_32 = COPY $vgpr0
+    renamable $sgpr0_sgpr1 = S_LOAD_DWORDX2_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s64), align 16, addrspace 4)
+    %1:vgpr_32 = V_LSHLREV_B32_e32 7, %0, implicit $exec
+    undef %2.sub28_sub29_sub30_sub31:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 112, 0, implicit $exec :: (load (s128), addrspace 1)
+    %2.sub24_sub25_sub26_sub27:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 96, 0, implicit $exec :: (load (s128), align 32, addrspace 1)
+    %2.sub20_sub21_sub22_sub23:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 80, 0, implicit $exec :: (load (s128), addrspace 1)
+    %2.sub16_sub17_sub18_sub19:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 64, 0, implicit $exec :: (load (s128), align 64, addrspace 1)
+    %2.sub12_sub13_sub14_sub15:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 48, 0, implicit $exec :: (load (s128), addrspace 1)
+    %2.sub8_sub9_sub10_sub11:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 32, 0, implicit $exec :: (load (s128), align 32, addrspace 1)
+    %2.sub4_sub5_sub6_sub7:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 16, 0, implicit $exec :: (load (s128), addrspace 1)
+    %2.sub0_sub1_sub2_sub3:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4_SADDR renamable $sgpr0_sgpr1, %1, 0, 0, implicit $exec :: (load (s128), align 128, addrspace 1)
+    %3:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 1065353216, implicit $exec
+    %4:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 1073741824, implicit $exec
+    %2:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_mac_vgprcd_e64 %3, %4, %2, 0, 0, 0, implicit $mode, implicit $exec
+    early-clobber %5:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_vgprcd_e64 %3, %4, %2, 0, 0, 0, implicit $mode, implicit $exec, implicit $mode, implicit $exec
+    %2.sub2:vreg_1024_align2 = COPY %5.sub0
+    %2.sub3:vreg_1024_align2 = COPY %5.sub1
+    %2.sub4:vreg_1024_align2 = COPY %5.sub2
+    %2.sub5:vreg_1024_align2 = COPY %5.sub3
+    %2.sub6:vreg_1024_align2 = COPY %5.sub4
+    %2.sub7:vreg_1024_align2 = COPY %5.sub5
+    %2.sub8:vreg_1024_align2 = COPY %5.sub6
+    %2.sub9:vreg_1024_align2 = COPY %5.sub7
+    %2.sub10:vreg_1024_align2 = COPY %5.sub8
+    %2.sub11:vreg_1024_align2 = COPY %5.sub9
+    %2.sub12:vreg_1024_align2 = COPY %5.sub10
+    %2.sub13:vreg_1024_align2 = COPY %5.sub11
+    %2.sub14:vreg_1024_align2 = COPY %5.sub12
+    %2.sub15:vreg_1024_align2 = COPY %5.sub13
+    %2.sub16:vreg_1024_align2 = COPY %5.sub14
+    %2.sub17:vreg_1024_align2 = COPY %5.sub15
+    %2.sub18:vreg_1024_align2 = COPY %5.sub16
+    %2.sub19:vreg_1024_align2 = COPY %5.sub17
+    %2.sub20:vreg_1024_align2 = COPY %5.sub18
+    %2.sub21:vreg_1024_align2 = COPY %5.sub19
+    %2.sub22:vreg_1024_align2 = COPY %5.sub20
+    %2.sub23:vreg_1024_align2 = COPY %5.sub21
+    %2.sub24:vreg_1024_align2 = COPY %5.sub22
+    %2.sub25:vreg_1024_align2 = COPY %5.sub23
+    %2.sub26:vreg_1024_align2 = COPY %5.sub24
+    %2.sub27:vreg_1024_align2 = COPY %5.sub25
+    %2.sub28:vreg_1024_align2 = COPY %5.sub26
+    %2.sub29:vreg_1024_align2 = COPY %5.sub27
+    %2.sub30:vreg_1024_align2 = COPY %5.sub28
+    %2.sub31:vreg_1024_align2 = COPY %5.sub29
+    %2:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_mac_vgprcd_e64 %3, %4, %2, 0, 0, 0, implicit $mode, implicit $exec
+    %6:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub24_sub25_sub26_sub27, renamable $sgpr0_sgpr1, 96, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub28_sub29_sub30_sub31, renamable $sgpr0_sgpr1, 112, 0, implicit $exec :: (store (s128), addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub16_sub17_sub18_sub19, renamable $sgpr0_sgpr1, 64, 0, implicit $exec :: (store (s128), align 64, addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub20_sub21_sub22_sub23, renamable $sgpr0_sgpr1, 80, 0, implicit $exec :: (store (s128), addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub8_sub9_sub10_sub11, renamable $sgpr0_sgpr1, 32, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub12_sub13_sub14_sub15, renamable $sgpr0_sgpr1, 48, 0, implicit $exec :: (store (s128), addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub0_sub1_sub2_sub3, renamable $sgpr0_sgpr1, 0, 0, implicit $exec :: (store (s128), align 128, addrspace 1)
+    GLOBAL_STORE_DWORDX4_SADDR %6, %2.sub4_sub5_sub6_sub7, killed renamable $sgpr0_sgpr1, 16, 0, implicit $exec :: (store (s128), addrspace 1)
+    S_ENDPGM 0
+
+...
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-remat.mir b/llvm/test/CodeGen/AMDGPU/vgpr-remat.mir
index 0e7e4b9b10d44..9dad99f307c19 100644
--- a/llvm/test/CodeGen/AMDGPU/vgpr-remat.mir
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-remat.mir
@@ -90,3 +90,48 @@ body: |
     %4.sub2_sub3:vreg_192 = COPY %2:vreg_64_align2
     S_ENDPGM 0, implicit %4
 ...
+
+---
+name: av_mov_imm_b32
+tracksRegLiveness: true
+body: |
+  ; CHECK-LABEL: name: av_mov_imm_b32
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
+  ; CHECK-NEXT:   liveins: $sgpr0
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   undef [[AV_MOV_:%[0-9]+]].sub0:vreg_96 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+  ; CHECK-NEXT:   [[AV_MOV_:%[0-9]+]].sub1:vreg_96 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0
+  ; CHECK-NEXT:   $exec = S_MOV_B64_term [[COPY]]
+  ; CHECK-NEXT:   S_CBRANCH_EXECZ %bb.2, implicit $exec
+  ; CHECK-NEXT:   S_BRANCH %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.2(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[AV_MOV_:%[0-9]+]].sub0:vreg_96 = V_MUL_F32_e32 [[AV_MOV_]].sub0, [[AV_MOV_]].sub0, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   [[AV_MOV_:%[0-9]+]].sub1:vreg_96 = V_MUL_F32_e32 [[AV_MOV_]].sub1, [[AV_MOV_]].sub1, implicit $mode, implicit $exec
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   S_ENDPGM 0, implicit [[AV_MOV_]]
+  bb.0:
+    liveins: $sgpr0
+    %0:av_32 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    %1:vgpr_32 = COPY %0
+    %2:vgpr_32 = COPY %0
+    %3:sreg_64 = COPY $sgpr0
+    $exec = S_MOV_B64_term %3:sreg_64
+    S_CBRANCH_EXECZ %bb.2, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1:
+    %1:vgpr_32 = V_MUL_F32_e32 %1:vgpr_32, %1:vgpr_32, implicit $mode, implicit $exec
+    %2:vgpr_32 = V_MUL_F32_e32 %2:vgpr_32, %2:vgpr_32, implicit $mode, implicit $exec
+
+  bb.2:
+    undef %4.sub0:vreg_96 = COPY %1:vgpr_32
+    %4.sub1:vreg_96 = COPY %2:vgpr_32
+    S_ENDPGM 0, implicit %4
+
+...
diff --git a/llvm/test/MachineVerifier/AMDGPU/verify-av-mov-imm-pseudo.mir b/llvm/test/MachineVerifier/AMDGPU/verify-av-mov-imm-pseudo.mir
new file mode 100644
index 0000000000000..8973de09d9674
--- /dev/null
+++ b/llvm/test/MachineVerifier/AMDGPU/verify-av-mov-imm-pseudo.mir
@@ -0,0 +1,15 @@
+# RUN: not --crash llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -run-pass=none -o /dev/null %s 2>&1 | FileCheck %s
+---
+name: invalid_av_mov_b32_imm_pseudo
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    %0:vgpr_32 = IMPLICIT_DEF
+
+    ; CHECK: *** Bad machine code: Illegal immediate value for operand. ***
+    $agpr0 = AV_MOV_B32_IMM_PSEUDO 65, implicit $exec
+
+    ; CHECK: *** Bad machine code: Illegal immediate value for operand. ***
+    $vgpr0 = AV_MOV_B32_IMM_PSEUDO 65, implicit $exec
+
+...

>From 9081a0a886661267e03781b35ca6e89b3b7fc45b Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Thu, 6 Mar 2025 11:37:43 +0700
Subject: [PATCH 2/2] Add broken tests from preexisting failure

---
 llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir | 50 ++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir b/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
index 90ccc30affe1a..dce11209d0514 100644
--- a/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
+++ b/llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
@@ -184,3 +184,53 @@ body:             |
     S_ENDPGM 0
 
 ...
+
+# FIXME: Register class restrictions of av register not respected,
+# issue 130020
+
+# ---
+# name: s_mov_b32_inlineimm_copy_s_to_av_32
+# tracksRegLiveness: true
+# body:             |
+#   bb.0:
+#     %0:sreg_32 = S_MOV_B32 32
+#     %1:av_32 = COPY %0
+#     $agpr0 = COPY %1
+#     S_ENDPGM 0
+
+# ...
+
+# ---
+# name: v_mov_b32_inlineimm_copy_v_to_av_32
+# tracksRegLiveness: true
+# body:             |
+#  bb.0:
+#    %0:vgpr_32 = V_MOV_B32_e32 32, implicit $exec
+#    %1:av_32 = COPY %0
+#    $agpr0 = COPY %1
+#    S_ENDPGM 0
+# ...
+
+# ---
+# name: s_mov_b32_imm_literal_copy_s_to_av_32
+# tracksRegLiveness: true
+# body:             |
+#   bb.0:
+#     %0:sreg_32 = S_MOV_B32 999
+#     %1:av_32 = COPY %0
+#     $agpr0 = COPY %1
+#     S_ENDPGM 0
+
+# ...
+
+# ---
+# name: v_mov_b32_imm_literal_copy_v_to_av_32
+# tracksRegLiveness: true
+# body:             |
+#   bb.0:
+#     %0:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
+#     %1:av_32 = COPY %0
+#     $agpr0 = COPY %1
+#     S_ENDPGM 0
+
+# ...



More information about the llvm-commits mailing list