Google Git
Sign in
llvm / llvm-project / ec941a4a045106430bc643ea094f33eb03603090 / . / llvm / test / CodeGen / AMDGPU / splitkit-do-not-undo-subclass-split-with-remat.mir
blob: 9b4031826dd22e891bc1e86373efda1c43a20b75 [file] [log] [blame]
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -verify-regalloc -start-before=greedy,2 -stop-before=virtregrewriter,2 -o - %s | FileCheck %s
# FIXME: Assert if run to end
# The V_MFMA_F32_32X32X1F32_vgprcd_e64 as written requires 66 VGPRs
# to allocate, but the register budget (with a forced AGPR usage and
# occupancy 4) permits 64 VGPRs and 64 AGPRs, so we need to force a
# copy from VGPR to AGPR. The minimal copies required for this need to
# copy %3 and %4 V_MOV_B32s into temporary AGPRs for use by the MFMA.
# Previously we would attempt a register subclass based split, but
# immediately rematerialize the V_MOV_B32 into the new temporary
# register, defeating the point of introducing the split. The
# allocation would fail since it's 2 registers short.
---
name: temp_vgpr_to_agpr_should_not_undo_split_with_remat
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
; 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: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1065353216, implicit $exec
; CHECK-NEXT: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1073741824, implicit $exec
; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_SADDR:%[0-9]+]]:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_mac_vgprcd_e64 [[V_MOV_B32_e32_]], [[V_MOV_B32_e32_1]], [[GLOBAL_LOAD_DWORDX4_SADDR]], 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_32 = COPY [[V_MOV_B32_e32_1]]
; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_32 = COPY [[V_MOV_B32_e32_]]
; CHECK-NEXT: early-clobber %5:vreg_1024_align2 = V_MFMA_F32_32X32X1F32_vgprcd_e64 [[COPY2]], [[COPY1]], [[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 [[COPY2]], [[COPY1]], [[GLOBAL_LOAD_DWORDX4_SADDR]], 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: [[V_MOV_B32_e32_2:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 [[V_MOV_B32_e32_2]], [[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 = V_MOV_B32_e32 1065353216, implicit $exec
%4:vgpr_32 = V_MOV_B32_e32 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 = V_MOV_B32_e32 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 $exec :: (store (s128), addrspace 1)
S_ENDPGM 0
...
# Same, except uses AV_MOV_B32_IMM_PSEUDO which is able to
# rematerialize in the inflated register class.
---
name: temp_vgpr_to_agpr_should_not_undo_split_with_remat_av_pseudo
tracksRegLiveness: true
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$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
...