You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
944 lines
58 KiB
944 lines
58 KiB
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -march=amdgcn -mcpu=gfx908 -run-pass=regbankselect -regbankselect-fast -verify-machineinstrs %s -o - | FileCheck %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx908 -run-pass=regbankselect -regbankselect-greedy -verify-machineinstrs %s -o - | FileCheck %s
|
|
|
|
---
|
|
name: mfma_f32_32x32x1f32_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x1f32_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x1f32), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x1f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x1f32_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x1f32_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<32 x s32>) = COPY [[COPY2]](<32 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x1f32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x1f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x1f32_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x1f32_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x1f32), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x1f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x1f32_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x1f32_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x1f32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x1f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_4x4x1f32_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_4x4x1f32_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x1f32), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x1f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_4x4x1f32_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_4x4x1f32_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x1f32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x1f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x2f32_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x2f32_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2f32), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x2f32_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x2f32_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2f32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x4f32_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x4f32_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr1, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f32), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x4f32_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x4f32_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f32), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f32), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x4f16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x4f16_vva
|
|
; CHECK: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4f16), [[COPY]](<4 x s16>), [[COPY1]](<4 x s16>), [[COPY2]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
%2:_(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x4f16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x4f16_sss
|
|
; CHECK: liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY]](<4 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY1]](<4 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<32 x s32>) = COPY [[COPY2]](<32 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4f16), [[COPY3]](<4 x s16>), [[COPY4]](<4 x s16>), [[COPY5]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
%1:_(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
%2:_(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x4f16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x4f16_vva
|
|
; CHECK: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f16), [[COPY]](<4 x s16>), [[COPY1]](<4 x s16>), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x4f16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x4f16_sss
|
|
; CHECK: liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY]](<4 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY1]](<4 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f16), [[COPY3]](<4 x s16>), [[COPY4]](<4 x s16>), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
%1:_(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x4f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_4x4x4f16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_4x4x4f16_vva
|
|
; CHECK: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x4f16), [[COPY]](<4 x s16>), [[COPY1]](<4 x s16>), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x4f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_4x4x4f16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_4x4x4f16_sss
|
|
; CHECK: liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY]](<4 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY1]](<4 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x4f16), [[COPY3]](<4 x s16>), [[COPY4]](<4 x s16>), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
%1:_(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x4f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x8f16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x8f16_vva
|
|
; CHECK: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x8f16), [[COPY]](<4 x s16>), [[COPY1]](<4 x s16>), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x8f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x8f16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x8f16_sss
|
|
; CHECK: liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY]](<4 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY1]](<4 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x8f16), [[COPY3]](<4 x s16>), [[COPY4]](<4 x s16>), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
%1:_(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x8f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x16f16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x16f16_vva
|
|
; CHECK: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x16f16), [[COPY]](<4 x s16>), [[COPY1]](<4 x s16>), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x16f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x16f16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x16f16_sss
|
|
; CHECK: liveins: $sgpr32_sgpr33, $sgpr34_sgpr35, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY]](<4 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<4 x s16>) = COPY [[COPY1]](<4 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x16f16), [[COPY3]](<4 x s16>), [[COPY4]](<4 x s16>), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<4 x s16>) = COPY $sgpr32_sgpr33
|
|
%1:_(<4 x s16>) = COPY $sgpr34_sgpr35
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x16f16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_32x32x4i8_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
|
|
; CHECK-LABEL: name: mfma_i32_32x32x4i8_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x4i8), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr2
|
|
%2:_(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x4i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_32x32x4i8_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
|
|
; CHECK-LABEL: name: mfma_i32_32x32x4i8_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<32 x s32>) = COPY [[COPY2]](<32 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x4i8), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x4i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_16x16x4i8_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_i32_16x16x4i8_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x4i8), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr2
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x4i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_16x16x4i8_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_i32_16x16x4i8_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x4i8), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x4i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_4x4x4i8_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_i32_4x4x4i8_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.4x4x4i8), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr2
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.4x4x4i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_4x4x4i8_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_i32_4x4x4i8_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.4x4x4i8), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.4x4x4i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_32x32x8i8_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_i32_32x32x8i8_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x8i8), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr2
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x8i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_32x32x8i8_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_i32_32x32x8i8_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x8i8), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.32x32x8i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_16x16x16i8_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_i32_16x16x16i8_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x16i8), [[COPY]](s32), [[COPY1]](s32), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr2
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x16i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_i32_16x16x16i8_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_i32_16x16x16i8_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x16i8), [[COPY3]](s32), [[COPY4]](s32), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(s32) = COPY $sgpr32
|
|
%1:_(s32) = COPY $sgpr33
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.i32.16x16x16i8), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x2bf16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x2bf16_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2bf16), [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>), [[COPY2]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(<2 x s16>) = COPY $vgpr0
|
|
%1:_(<2 x s16>) = COPY $vgpr2
|
|
%2:_(<32 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x2bf16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x2bf16_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY]](<2 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY1]](<2 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<32 x s32>) = COPY [[COPY2]](<32 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2bf16), [[COPY3]](<2 x s16>), [[COPY4]](<2 x s16>), [[COPY5]](<32 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY [[INT]](<32 x s32>)
|
|
%0:_(<2 x s16>) = COPY $sgpr32
|
|
%1:_(<2 x s16>) = COPY $sgpr33
|
|
%2:_(<32 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31
|
|
%3:_(<32 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x2bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x2bf16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x2bf16_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x2bf16), [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<2 x s16>) = COPY $vgpr0
|
|
%1:_(<2 x s16>) = COPY $vgpr2
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x2bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x2bf16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x2bf16_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY]](<2 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY1]](<2 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x2bf16), [[COPY3]](<2 x s16>), [[COPY4]](<2 x s16>), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<2 x s16>) = COPY $sgpr32
|
|
%1:_(<2 x s16>) = COPY $sgpr33
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x2bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_4x4x2bf16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_4x4x2bf16_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x2bf16), [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<2 x s16>) = COPY $vgpr0
|
|
%1:_(<2 x s16>) = COPY $vgpr2
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x2bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_4x4x2bf16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_4x4x2bf16_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY]](<2 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY1]](<2 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x2bf16), [[COPY3]](<2 x s16>), [[COPY4]](<2 x s16>), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<2 x s16>) = COPY $sgpr32
|
|
%1:_(<2 x s16>) = COPY $sgpr33
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.4x4x2bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x4bf16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x4bf16_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4bf16), [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>), [[COPY2]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<2 x s16>) = COPY $vgpr0
|
|
%1:_(<2 x s16>) = COPY $vgpr2
|
|
%2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_32x32x4bf16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
|
|
; CHECK-LABEL: name: mfma_f32_32x32x4bf16_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY]](<2 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY1]](<2 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<16 x s32>) = COPY [[COPY2]](<16 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4bf16), [[COPY3]](<2 x s16>), [[COPY4]](<2 x s16>), [[COPY5]](<16 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
|
|
%0:_(<2 x s16>) = COPY $sgpr32
|
|
%1:_(<2 x s16>) = COPY $sgpr33
|
|
%2:_(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
%3:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.32x32x4bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x8bf16_vva
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x8bf16_vva
|
|
; CHECK: liveins: $vgpr0, $vgpr2, $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
|
|
; CHECK: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr2
|
|
; CHECK: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x8bf16), [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>), [[COPY2]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<2 x s16>) = COPY $vgpr0
|
|
%1:_(<2 x s16>) = COPY $vgpr2
|
|
%2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x8bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|
|
|
|
---
|
|
name: mfma_f32_16x16x8bf16_sss
|
|
legalized: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; CHECK-LABEL: name: mfma_f32_16x16x8bf16_sss
|
|
; CHECK: liveins: $sgpr32, $sgpr33, $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr32
|
|
; CHECK: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr33
|
|
; CHECK: [[COPY2:%[0-9]+]]:sgpr(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; CHECK: [[COPY3:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY]](<2 x s16>)
|
|
; CHECK: [[COPY4:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY1]](<2 x s16>)
|
|
; CHECK: [[COPY5:%[0-9]+]]:agpr(<4 x s32>) = COPY [[COPY2]](<4 x s32>)
|
|
; CHECK: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x8bf16), [[COPY3]](<2 x s16>), [[COPY4]](<2 x s16>), [[COPY5]](<4 x s32>), 0, 0, 0
|
|
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
|
|
%0:_(<2 x s16>) = COPY $sgpr32
|
|
%1:_(<2 x s16>) = COPY $sgpr33
|
|
%2:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%3:_(<4 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.mfma.f32.16x16x8bf16), %0, %1, %2, 0, 0, 0
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
|
|
...
|