blob: 4d8c011c64302870a13f5067f0dbf1121799a035 [file] [log] [blame]
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx90a -start-before=machine-scheduler -stop-after=postmisched %s -o - 2>&1 | FileCheck -check-prefix=DEFAULT %s
# RUN: llc -march=amdgcn -mcpu=gfx90a -start-before=machine-scheduler -stop-after=postmisched %s -o - -amdgpu-igrouplp=1 2>&1 | FileCheck -check-prefix=PIPELINE %s
---
name: no_pipeline
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0, $vgpr10_vgpr11
; DEFAULT-LABEL: name: no_pipeline
; DEFAULT: liveins: $sgpr0, $vgpr10_vgpr11
; DEFAULT-NEXT: {{ $}}
; DEFAULT-NEXT: $vgpr1 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr0 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr1 = V_ADD_F16_e32 killed $vgpr1, $vgpr0, implicit $mode, implicit $exec
; DEFAULT-NEXT: GLOBAL_STORE_DWORD killed $vgpr10_vgpr11, $vgpr1, 0, 0, implicit $exec
; DEFAULT-NEXT: $vgpr2 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr3 = DS_READ_U16_gfx9 killed $vgpr2, 0, 0, implicit $exec
; DEFAULT-NEXT: $vgpr5 = V_XOR_B32_e32 $vgpr1, killed $vgpr0, implicit $exec
; DEFAULT-NEXT: $vgpr6 = V_MUL_LO_U32_e64 killed $vgpr1, killed $sgpr0, implicit $exec
; DEFAULT-NEXT: $vgpr8 = V_MOV_B32_e32 0, implicit $exec
; DEFAULT-NEXT: $vgpr9 = V_MOV_B32_e32 9, implicit $exec
; PIPELINE-LABEL: name: no_pipeline
; PIPELINE: liveins: $sgpr0, $vgpr10_vgpr11
; PIPELINE-NEXT: {{ $}}
; PIPELINE-NEXT: $vgpr1 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr0 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr1 = V_ADD_F16_e32 killed $vgpr1, $vgpr0, implicit $mode, implicit $exec
; PIPELINE-NEXT: GLOBAL_STORE_DWORD killed $vgpr10_vgpr11, $vgpr1, 0, 0, implicit $exec
; PIPELINE-NEXT: $vgpr2 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr3 = DS_READ_U16_gfx9 killed $vgpr2, 0, 0, implicit $exec
; PIPELINE-NEXT: $vgpr5 = V_XOR_B32_e32 $vgpr1, killed $vgpr0, implicit $exec
; PIPELINE-NEXT: $vgpr6 = V_MUL_LO_U32_e64 killed $vgpr1, killed $sgpr0, implicit $exec
; PIPELINE-NEXT: $vgpr8 = V_MOV_B32_e32 0, implicit $exec
; PIPELINE-NEXT: $vgpr9 = V_MOV_B32_e32 9, implicit $exec
$vgpr1 = V_MOV_B32_e32 1, implicit $exec
$vgpr0 = V_MOV_B32_e32 1, implicit $exec
$vgpr8 = V_MOV_B32_e32 0, implicit $exec
$vgpr9 = V_MOV_B32_e32 9, implicit $exec
$vgpr1 = V_ADD_F16_e32 $vgpr1, $vgpr0, implicit $mode, implicit $exec
GLOBAL_STORE_DWORD $vgpr10_vgpr11, $vgpr1, 0, 0, implicit $exec
$vgpr2 = V_MOV_B32_e32 1, implicit $exec
$vgpr3 = DS_READ_U16_gfx9 $vgpr2, 0, 0, implicit $exec
$vgpr5 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
$vgpr6 = V_MUL_LO_U32_e64 $vgpr1, $sgpr0, implicit $exec
...
---
name: full_pipe
tracksRegLiveness: true
body: |
bb.0:
liveins: $agpr0_agpr1_agpr2_agpr3, $agpr4_agpr5_agpr6_agpr7, $agpr8_agpr9_agpr10_agpr11, $agpr12_agpr13_agpr14_agpr15, $agpr16_agpr17_agpr18_agpr19, $sgpr0, $vgpr10_vgpr11
; DEFAULT-LABEL: name: full_pipe
; DEFAULT: liveins: $sgpr0, $agpr0_agpr1_agpr2_agpr3, $agpr4_agpr5_agpr6_agpr7, $agpr8_agpr9_agpr10_agpr11, $agpr12_agpr13_agpr14_agpr15, $agpr16_agpr17_agpr18_agpr19, $vgpr10_vgpr11
; DEFAULT-NEXT: {{ $}}
; DEFAULT-NEXT: $vgpr0 = V_MOV_B32_e32 0, implicit $exec
; DEFAULT-NEXT: $vgpr1 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr2 = V_MOV_B32_e32 2, implicit $exec
; DEFAULT-NEXT: $vgpr3 = V_MOV_B32_e32 3, implicit $exec
; DEFAULT-NEXT: $vgpr6 = GLOBAL_LOAD_USHORT $vgpr0_vgpr1, 0, 0, implicit $exec
; DEFAULT-NEXT: $vgpr7 = GLOBAL_LOAD_USHORT $vgpr2_vgpr3, 0, 0, implicit $exec
; DEFAULT-NEXT: $vgpr4 = V_MOV_B32_e32 4, implicit $exec
; DEFAULT-NEXT: $vgpr5 = V_MOV_B32_e32 5, implicit $exec
; DEFAULT-NEXT: $vgpr8 = GLOBAL_LOAD_USHORT $vgpr4_vgpr5, 0, 0, implicit $exec
; DEFAULT-NEXT: $vgpr1 = V_ADD_F16_e32 killed $vgpr1, $vgpr0, implicit $mode, implicit $exec
; DEFAULT-NEXT: $vgpr26 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr27 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $agpr4_agpr5_agpr6_agpr7 = V_MFMA_F32_4X4X1F32_e64 $vgpr3, $vgpr4, killed $agpr4_agpr5_agpr6_agpr7, 0, 0, 0, implicit $mode, implicit $exec
; DEFAULT-NEXT: $vgpr23 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
; DEFAULT-NEXT: $vgpr9 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr24 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $agpr0_agpr1_agpr2_agpr3 = V_MFMA_F32_4X4X1F32_e64 $vgpr1, $vgpr0, killed $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
; DEFAULT-NEXT: $vgpr22 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
; DEFAULT-NEXT: $agpr8_agpr9_agpr10_agpr11 = V_MFMA_F32_4X4X1F32_e64 $vgpr3, killed $vgpr4, killed $agpr8_agpr9_agpr10_agpr11, 0, 0, 0, implicit $mode, implicit $exec
; DEFAULT-NEXT: $vgpr21 = V_MUL_LO_U32_e64 $vgpr1, killed $sgpr0, implicit $exec
; DEFAULT-NEXT: $agpr12_agpr13_agpr14_agpr15 = V_MFMA_F32_4X4X1F32_e64 $vgpr1, $vgpr0, killed $agpr12_agpr13_agpr14_agpr15, 0, 0, 0, implicit $mode, implicit $exec
; DEFAULT-NEXT: $vgpr30 = V_MOV_B32_e32 30, implicit $exec
; DEFAULT-NEXT: $vgpr17 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: $vgpr18 = V_MOV_B32_e32 1, implicit $exec
; DEFAULT-NEXT: BUNDLE implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr15, implicit-def $vgpr15_lo16, implicit-def $vgpr15_hi16, implicit-def $vgpr16, implicit-def $vgpr16_lo16, implicit-def $vgpr16_hi16, implicit $vgpr7, implicit $exec {
; DEFAULT-NEXT: $vgpr10 = DS_READ_U16_gfx9 $vgpr7, 0, 512, implicit $exec
; DEFAULT-NEXT: $vgpr11 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
; DEFAULT-NEXT: $vgpr12 = DS_READ_U16_gfx9 $vgpr7, 0, 1024, implicit $exec
; DEFAULT-NEXT: $vgpr15 = DS_READ_U16_gfx9 $vgpr7, 0, 4096, implicit $exec
; DEFAULT-NEXT: $vgpr16 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
; DEFAULT-NEXT: }
; DEFAULT-NEXT: DS_WRITE_B32 $vgpr3, killed $vgpr1, 0, 16, implicit $m0, implicit $exec
; DEFAULT-NEXT: BUNDLE implicit-def $vgpr19, implicit-def $vgpr19_lo16, implicit-def $vgpr19_hi16, implicit-def $vgpr20, implicit-def $vgpr20_lo16, implicit-def $vgpr20_hi16, implicit killed $vgpr26_vgpr27, implicit $exec {
; DEFAULT-NEXT: $vgpr19 = GLOBAL_LOAD_USHORT $vgpr26_vgpr27, 0, 0, implicit $exec
; DEFAULT-NEXT: $vgpr20 = GLOBAL_LOAD_USHORT killed $vgpr26_vgpr27, 0, 0, implicit $exec
; DEFAULT-NEXT: }
; DEFAULT-NEXT: $agpr4_agpr5_agpr6_agpr7 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr5, killed $vgpr6, killed $agpr4_agpr5_agpr6_agpr7, 0, 0, 0, implicit $mode, implicit $exec
; DEFAULT-NEXT: DS_WRITE_B32 killed $vgpr0, killed $vgpr7, 0, 16, implicit $m0, implicit $exec
; DEFAULT-NEXT: $agpr16_agpr17_agpr18_agpr19 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr10, killed $vgpr11, killed $agpr16_agpr17_agpr18_agpr19, 0, 0, 0, implicit $mode, implicit $exec
; DEFAULT-NEXT: DS_WRITE_B32 killed $vgpr23, killed $vgpr3, 0, 16, implicit $m0, implicit $exec
; DEFAULT-NEXT: DS_WRITE_B32 killed $vgpr9, killed $vgpr24, 0, 16, implicit $m0, implicit $exec
; PIPELINE-LABEL: name: full_pipe
; PIPELINE: liveins: $sgpr0, $agpr0_agpr1_agpr2_agpr3, $agpr4_agpr5_agpr6_agpr7, $agpr8_agpr9_agpr10_agpr11, $agpr12_agpr13_agpr14_agpr15, $agpr16_agpr17_agpr18_agpr19, $vgpr10_vgpr11
; PIPELINE-NEXT: {{ $}}
; PIPELINE-NEXT: $vgpr0 = V_MOV_B32_e32 0, implicit $exec
; PIPELINE-NEXT: $vgpr1 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr2 = V_MOV_B32_e32 2, implicit $exec
; PIPELINE-NEXT: $vgpr3 = V_MOV_B32_e32 3, implicit $exec
; PIPELINE-NEXT: $vgpr6 = GLOBAL_LOAD_USHORT $vgpr0_vgpr1, 0, 0, implicit $exec
; PIPELINE-NEXT: $vgpr7 = GLOBAL_LOAD_USHORT $vgpr2_vgpr3, 0, 0, implicit $exec
; PIPELINE-NEXT: $vgpr4 = V_MOV_B32_e32 4, implicit $exec
; PIPELINE-NEXT: $vgpr5 = V_MOV_B32_e32 5, implicit $exec
; PIPELINE-NEXT: $vgpr8 = GLOBAL_LOAD_USHORT $vgpr4_vgpr5, 0, 0, implicit $exec
; PIPELINE-NEXT: $vgpr1 = V_ADD_F16_e32 killed $vgpr1, $vgpr0, implicit $mode, implicit $exec
; PIPELINE-NEXT: $vgpr26 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr27 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr9 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr24 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr23 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
; PIPELINE-NEXT: $vgpr22 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
; PIPELINE-NEXT: $vgpr21 = V_MUL_LO_U32_e64 $vgpr1, killed $sgpr0, implicit $exec
; PIPELINE-NEXT: $vgpr30 = V_MOV_B32_e32 30, implicit $exec
; PIPELINE-NEXT: $vgpr17 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: $vgpr18 = V_MOV_B32_e32 1, implicit $exec
; PIPELINE-NEXT: BUNDLE implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr15, implicit-def $vgpr15_lo16, implicit-def $vgpr15_hi16, implicit-def $vgpr16, implicit-def $vgpr16_lo16, implicit-def $vgpr16_hi16, implicit $vgpr7, implicit $exec {
; PIPELINE-NEXT: $vgpr10 = DS_READ_U16_gfx9 $vgpr7, 0, 512, implicit $exec
; PIPELINE-NEXT: $vgpr11 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
; PIPELINE-NEXT: $vgpr12 = DS_READ_U16_gfx9 $vgpr7, 0, 1024, implicit $exec
; PIPELINE-NEXT: $vgpr15 = DS_READ_U16_gfx9 $vgpr7, 0, 4096, implicit $exec
; PIPELINE-NEXT: $vgpr16 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
; PIPELINE-NEXT: }
; PIPELINE-NEXT: DS_WRITE_B32 $vgpr3, $vgpr1, 0, 16, implicit $m0, implicit $exec
; PIPELINE-NEXT: BUNDLE implicit-def $vgpr19, implicit-def $vgpr19_lo16, implicit-def $vgpr19_hi16, implicit-def $vgpr20, implicit-def $vgpr20_lo16, implicit-def $vgpr20_hi16, implicit killed $vgpr26_vgpr27, implicit $exec {
; PIPELINE-NEXT: $vgpr19 = GLOBAL_LOAD_USHORT $vgpr26_vgpr27, 0, 0, implicit $exec
; PIPELINE-NEXT: $vgpr20 = GLOBAL_LOAD_USHORT killed $vgpr26_vgpr27, 0, 0, implicit $exec
; PIPELINE-NEXT: }
; PIPELINE-NEXT: $agpr4_agpr5_agpr6_agpr7 = V_MFMA_F32_4X4X1F32_e64 $vgpr3, $vgpr4, killed $agpr4_agpr5_agpr6_agpr7, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-NEXT: $agpr0_agpr1_agpr2_agpr3 = V_MFMA_F32_4X4X1F32_e64 $vgpr1, $vgpr0, killed $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-NEXT: $agpr8_agpr9_agpr10_agpr11 = V_MFMA_F32_4X4X1F32_e64 $vgpr3, killed $vgpr4, killed $agpr8_agpr9_agpr10_agpr11, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-NEXT: $agpr4_agpr5_agpr6_agpr7 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr5, killed $vgpr6, killed $agpr4_agpr5_agpr6_agpr7, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-NEXT: $agpr16_agpr17_agpr18_agpr19 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr10, killed $vgpr11, killed $agpr16_agpr17_agpr18_agpr19, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-NEXT: $agpr12_agpr13_agpr14_agpr15 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr1, $vgpr0, killed $agpr12_agpr13_agpr14_agpr15, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-NEXT: BUNDLE implicit killed $vgpr0, implicit killed $vgpr7, implicit $m0, implicit $exec, implicit killed $vgpr23, implicit killed $vgpr3 {
; PIPELINE-NEXT: DS_WRITE_B32 killed $vgpr0, killed $vgpr7, 0, 16, implicit $m0, implicit $exec
; PIPELINE-NEXT: DS_WRITE_B32 killed $vgpr23, killed $vgpr3, 0, 16, implicit $m0, implicit $exec
; PIPELINE-NEXT: }
; PIPELINE-NEXT: DS_WRITE_B32 killed $vgpr9, killed $vgpr24, 0, 16, implicit $m0, implicit $exec
$vgpr0 = V_MOV_B32_e32 0, implicit $exec
$vgpr1 = V_MOV_B32_e32 1, implicit $exec
$vgpr2 = V_MOV_B32_e32 2, implicit $exec
$vgpr3 = V_MOV_B32_e32 3, implicit $exec
$vgpr4 = V_MOV_B32_e32 4, implicit $exec
$vgpr5 = V_MOV_B32_e32 5, implicit $exec
$vgpr30 = V_MOV_B32_e32 30, implicit $exec
$vgpr6 = GLOBAL_LOAD_USHORT $vgpr0_vgpr1, 0, 0, implicit $exec
$vgpr7 = GLOBAL_LOAD_USHORT $vgpr2_vgpr3, 0, 0, implicit $exec
$vgpr8 = GLOBAL_LOAD_USHORT $vgpr4_vgpr5, 0, 0, implicit $exec
$vgpr9 = V_MOV_B32_e32 1, implicit $exec
$vgpr1 = V_ADD_F16_e32 $vgpr1, $vgpr0, implicit $mode, implicit $exec
$agpr0_agpr1_agpr2_agpr3 = V_MFMA_F32_4X4X1F32_e64 $vgpr1, $vgpr0, $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
$agpr4_agpr5_agpr6_agpr7 = V_MFMA_F32_4X4X1F32_e64 $vgpr3, $vgpr4, $agpr4_agpr5_agpr6_agpr7, 0, 0, 0, implicit $mode, implicit $exec
$vgpr23 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
$vgpr24 = V_MOV_B32_e32 1, implicit $exec
$agpr8_agpr9_agpr10_agpr11 = V_MFMA_F32_4X4X1F32_e64 $vgpr3, $vgpr4, $agpr8_agpr9_agpr10_agpr11, 0, 0, 0, implicit $mode, implicit $exec
$vgpr10 = DS_READ_U16_gfx9 $vgpr7, 0, 512, implicit $exec
$vgpr11 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
$vgpr26 = V_MOV_B32_e32 1, implicit $exec
$vgpr27 = V_MOV_B32_e32 1, implicit $exec
$vgpr12 = DS_READ_U16_gfx9 $vgpr7, 0, 1024, implicit $exec
$agpr4_agpr5_agpr6_agpr7 = V_MFMA_F32_4X4X1F32_e64 $vgpr5, $vgpr6, $agpr4_agpr5_agpr6_agpr7, 0, 0, 0, implicit $mode, implicit $exec
$vgpr22 = V_XOR_B32_e32 $vgpr1, $vgpr0, implicit $exec
$vgpr21 = V_MUL_LO_U32_e64 $vgpr1, $sgpr0, implicit $exec
$vgpr15 = DS_READ_U16_gfx9 $vgpr7, 0, 4096, implicit $exec
$vgpr16 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
DS_WRITE_B32 $vgpr3, $vgpr1, 0, 16, implicit $m0, implicit $exec
$vgpr19 = GLOBAL_LOAD_USHORT $vgpr26_vgpr27, 0, 0, implicit $exec
$vgpr17 = V_MOV_B32_e32 1, implicit $exec
$vgpr18 = V_MOV_B32_e32 1, implicit $exec
$vgpr20 = GLOBAL_LOAD_USHORT $vgpr26_vgpr27, 0, 0, implicit $exec
DS_WRITE_B32 $vgpr0, $vgpr7, 0, 16, implicit $m0, implicit $exec
$agpr16_agpr17_agpr18_agpr19 = V_MFMA_F32_4X4X1F32_e64 $vgpr10, $vgpr11, $agpr16_agpr17_agpr18_agpr19, 0, 0, 0, implicit $mode, implicit $exec
DS_WRITE_B32 $vgpr23, $vgpr3, 0, 16, implicit $m0, implicit $exec
$agpr12_agpr13_agpr14_agpr15 = V_MFMA_F32_4X4X1F32_e64 $vgpr1, $vgpr0, $agpr12_agpr13_agpr14_agpr15, 0, 0, 0, implicit $mode, implicit $exec
DS_WRITE_B32 $vgpr9, $vgpr24, 0, 16, implicit $m0, implicit $exec
...
---
name: block_ends_in_bundle
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr7, $agpr0_agpr1_agpr2_agpr3
; DEFAULT-LABEL: name: block_ends_in_bundle
; DEFAULT: liveins: $vgpr0, $vgpr1, $vgpr7, $agpr0_agpr1_agpr2_agpr3
; DEFAULT-NEXT: {{ $}}
; DEFAULT-NEXT: BUNDLE implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr15, implicit-def $vgpr15_lo16, implicit-def $vgpr15_hi16, implicit-def $vgpr16, implicit-def $vgpr16_lo16, implicit-def $vgpr16_hi16, implicit killed $vgpr7, implicit $exec {
; DEFAULT-NEXT: $vgpr10 = DS_READ_U16_gfx9 $vgpr7, 0, 512, implicit $exec
; DEFAULT-NEXT: $vgpr11 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
; DEFAULT-NEXT: $vgpr12 = DS_READ_U16_gfx9 $vgpr7, 0, 1024, implicit $exec
; DEFAULT-NEXT: $vgpr15 = DS_READ_U16_gfx9 $vgpr7, 0, 4096, implicit $exec
; DEFAULT-NEXT: $vgpr16 = DS_READ_U16_gfx9 killed $vgpr7, 0, 2048, implicit $exec
; DEFAULT-NEXT: }
; DEFAULT-NEXT: $agpr0_agpr1_agpr2_agpr3 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr1, killed $vgpr0, killed $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
; PIPELINE-LABEL: name: block_ends_in_bundle
; PIPELINE: liveins: $vgpr0, $vgpr1, $vgpr7, $agpr0_agpr1_agpr2_agpr3
; PIPELINE-NEXT: {{ $}}
; PIPELINE-NEXT: BUNDLE implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr15, implicit-def $vgpr15_lo16, implicit-def $vgpr15_hi16, implicit-def $vgpr16, implicit-def $vgpr16_lo16, implicit-def $vgpr16_hi16, implicit killed $vgpr7, implicit $exec {
; PIPELINE-NEXT: $vgpr10 = DS_READ_U16_gfx9 $vgpr7, 0, 512, implicit $exec
; PIPELINE-NEXT: $vgpr11 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
; PIPELINE-NEXT: $vgpr12 = DS_READ_U16_gfx9 $vgpr7, 0, 1024, implicit $exec
; PIPELINE-NEXT: $vgpr15 = DS_READ_U16_gfx9 $vgpr7, 0, 4096, implicit $exec
; PIPELINE-NEXT: $vgpr16 = DS_READ_U16_gfx9 killed $vgpr7, 0, 2048, implicit $exec
; PIPELINE-NEXT: }
; PIPELINE-NEXT: $agpr0_agpr1_agpr2_agpr3 = V_MFMA_F32_4X4X1F32_e64 killed $vgpr1, killed $vgpr0, killed $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
$agpr0_agpr1_agpr2_agpr3 = V_MFMA_F32_4X4X1F32_e64 $vgpr1, $vgpr0, $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
BUNDLE implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr15, implicit-def $vgpr15_lo16, implicit-def $vgpr15_hi16, implicit-def $vgpr16, implicit-def $vgpr16_lo16, implicit-def $vgpr16_hi16, implicit $vgpr7, implicit $exec {
$vgpr10 = DS_READ_U16_gfx9 $vgpr7, 0, 512, implicit $exec
$vgpr11 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
$vgpr12 = DS_READ_U16_gfx9 $vgpr7, 0, 1024, implicit $exec
$vgpr15 = DS_READ_U16_gfx9 $vgpr7, 0, 4096, implicit $exec
$vgpr16 = DS_READ_U16_gfx9 $vgpr7, 0, 2048, implicit $exec
}
...