In future changes we will have more AV_ virtual registers, which currently block the formation of write2. Most of the time these registers can simply be constrained to VGPR, so do that. Also relaxes the constraint in flat merging case. We already have the necessary code to insert copies to the original result registers, so there's no point in avoiding it. Addresses the easy half of #155769
211 lines
8.3 KiB
YAML
211 lines
8.3 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -run-pass=si-load-store-opt -o - %s | FileCheck %s
|
|
|
|
---
|
|
name: ds_write_b32__av32_x2
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; CHECK-LABEL: name: ds_write_b32__av32_x2
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; CHECK-NEXT: DS_WRITE2_B32_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 10, 24, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_32 = COPY $vgpr1
|
|
%2:av_32 = COPY $vgpr2
|
|
DS_WRITE_B32_gfx9 %0, %1, 40, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %2, 96, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b32__av32_x2_subregs_different_reg
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
|
|
; CHECK-LABEL: name: ds_write_b32__av32_x2_subregs_different_reg
|
|
; CHECK: liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY $vgpr2_vgpr3
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5
|
|
; CHECK-NEXT: DS_WRITE2_B32_gfx9 [[COPY]], [[COPY1]].sub0, [[COPY2]].sub1, 10, 24, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_64_align2 = COPY $vgpr2_vgpr3
|
|
%2:av_64_align2 = COPY $vgpr4_vgpr5
|
|
DS_WRITE_B32_gfx9 %0, %1.sub0, 40, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %2.sub1, 96, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b32__unaligned_av64_subregs
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
|
|
|
|
; CHECK-LABEL: name: ds_write_b32__unaligned_av64_subregs
|
|
; CHECK: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
|
|
; CHECK-NEXT: DS_WRITE2_B32_gfx9 [[COPY]], [[COPY1]].sub0, [[COPY2]].sub1, 10, 24, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_64 = COPY $vgpr1_vgpr2
|
|
%2:av_64 = COPY $vgpr3_vgpr4
|
|
DS_WRITE_B32_gfx9 %0, %1.sub0, 40, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %2.sub1, 96, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b32__av32_x2_subregs_same_reg
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
|
|
; CHECK-LABEL: name: ds_write_b32__av32_x2_subregs_same_reg
|
|
; CHECK: liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY $vgpr2_vgpr3
|
|
; CHECK-NEXT: DS_WRITE2_B32_gfx9 [[COPY]], [[COPY1]].sub0, [[COPY1]].sub1, 10, 24, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_64_align2 = COPY $vgpr2_vgpr3
|
|
DS_WRITE_B32_gfx9 %0, %1.sub0, 40, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %1.sub1, 96, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b32__av32__vgpr32
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; CHECK-LABEL: name: ds_write_b32__av32__vgpr32
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; CHECK-NEXT: DS_WRITE2_B32_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 10, 24, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_32 = COPY $vgpr1
|
|
%2:vgpr_32 = COPY $vgpr2
|
|
DS_WRITE_B32_gfx9 %0, %1, 40, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %2, 96, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b32__vgpr32__av32
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; CHECK-LABEL: name: ds_write_b32__vgpr32__av32
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; CHECK-NEXT: DS_WRITE2_B32_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 10, 24, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:vgpr_32 = COPY $vgpr1
|
|
%2:av_32 = COPY $vgpr2
|
|
DS_WRITE_B32_gfx9 %0, %1, 40, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %2, 96, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b64__av64_x2
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
|
|
; CHECK-LABEL: name: ds_write_b64__av64_x2
|
|
; CHECK: liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY $vgpr2_vgpr3
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5
|
|
; CHECK-NEXT: DS_WRITE2_B64_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 5, 12, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_64_align2 = COPY $vgpr2_vgpr3
|
|
%2:av_64_align2 = COPY $vgpr4_vgpr5
|
|
DS_WRITE_B64_gfx9 %0, %1, 40, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
DS_WRITE_B64_gfx9 %0, %2, 96, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_write_b64__av64_x2_subregs
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2_vgpr3_vgpr4_vgpr5, $vgpr6_vgpr7_vgpr8_vgpr9
|
|
|
|
; CHECK-LABEL: name: ds_write_b64__av64_x2_subregs
|
|
; CHECK: liveins: $vgpr0, $vgpr2_vgpr3_vgpr4_vgpr5, $vgpr6_vgpr7_vgpr8_vgpr9
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_128_align2 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_128_align2 = COPY $vgpr6_vgpr7_vgpr8_vgpr9
|
|
; CHECK-NEXT: DS_WRITE2_B64_gfx9 [[COPY]], [[COPY1]].sub2_sub3, [[COPY2]].sub2_sub3, 5, 12, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_128_align2 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
|
|
%2:av_128_align2 = COPY $vgpr6_vgpr7_vgpr8_vgpr9
|
|
DS_WRITE_B64_gfx9 %0, %1.sub2_sub3, 40, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
DS_WRITE_B64_gfx9 %0, %2.sub2_sub3, 96, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_writest64_b32__av32_x2
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2
|
|
|
|
; CHECK-LABEL: name: ds_writest64_b32__av32_x2
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
|
; CHECK-NEXT: DS_WRITE2ST64_B32_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 1, 3, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_32 = COPY $vgpr1
|
|
%2:av_32 = COPY $vgpr2
|
|
DS_WRITE_B32_gfx9 %0, %1, 256, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
DS_WRITE_B32_gfx9 %0, %2, 768, 0, implicit $exec :: (store (s32), addrspace 3)
|
|
|
|
...
|
|
|
|
---
|
|
name: ds_writest64_b64__av64_x2
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
|
|
; CHECK-LABEL: name: ds_writest64_b64__av64_x2
|
|
; CHECK: liveins: $vgpr0, $vgpr2_vgpr3, $vgpr4_vgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY $vgpr2_vgpr3
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5
|
|
; CHECK-NEXT: DS_WRITE2ST64_B64_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 1, 3, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%1:av_64_align2 = COPY $vgpr2_vgpr3
|
|
%2:av_64_align2 = COPY $vgpr4_vgpr5
|
|
DS_WRITE_B64_gfx9 %0, %1, 512, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
DS_WRITE_B64_gfx9 %0, %2, 1536, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
|
|
...
|