CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
239 lines
14 KiB
YAML
239 lines
14 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942 -run-pass si-fold-operands %s -o - | FileCheck %s
|
|
# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942 -start-before=si-fold-operands -stop-after=register-coalescer %s -o - | FileCheck %s --check-prefixes=COALESCE
|
|
# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx908 -start-before=si-fold-operands -stop-after=register-coalescer %s -o - | FileCheck %s --check-prefixes=GFX908-COALESCE
|
|
|
|
...
|
|
---
|
|
name: test
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; CHECK-LABEL: name: test
|
|
; CHECK: bb.0:
|
|
; CHECK-NEXT: successors: %bb.1(0x80000000)
|
|
; CHECK-NEXT: liveins: $sgpr4_sgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
|
|
; CHECK-NEXT: [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
|
|
; CHECK-NEXT: S_BITCMP1_B32 killed [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
|
|
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]]:sgpr_32 = S_MOV_B32 0
|
|
; CHECK-NEXT: [[S_CSELECT_B64_:%[0-9]+]]:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit $scc
|
|
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:agpr_32 = COPY [[V_MOV_B32_e32_]]
|
|
; CHECK-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
|
|
; CHECK-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_CSELECT_B64_]], implicit $exec
|
|
; CHECK-NEXT: [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 [[V_CNDMASK_B32_e64_]], 1, implicit $exec
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.1:
|
|
; CHECK-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[PHI:%[0-9]+]]:agpr_32 = PHI [[COPY1]], %bb.0, %24, %bb.3
|
|
; CHECK-NEXT: [[PHI1:%[0-9]+]]:sreg_32 = PHI [[S_MOV_B32_]], %bb.0, %11, %bb.3
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[PHI]]
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:agpr_32 = COPY [[PHI]]
|
|
; CHECK-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
|
|
; CHECK-NEXT: $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_]], implicit-def $scc
|
|
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.3, implicit $vcc
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.2:
|
|
; CHECK-NEXT: successors: %bb.3(0x80000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[PHI1]], 1, implicit-def dead $scc
|
|
; CHECK-NEXT: [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[PHI1]], 31, implicit-def dead $scc
|
|
; CHECK-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 killed [[S_ASHR_I32_]], killed [[S_OR_B32_]], implicit-def dead $scc
|
|
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_128_align2 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[V_MOV_B32_e32_]], %subreg.sub1, [[V_MOV_B32_e32_]], %subreg.sub2, [[V_MOV_B32_e32_]], %subreg.sub3
|
|
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_]], %subreg.sub1
|
|
; CHECK-NEXT: [[COPY4:%[0-9]+]]:vreg_64_align2 = COPY [[REG_SEQUENCE1]]
|
|
; CHECK-NEXT: [[V_ACCVGPR_WRITE_B32_e64_:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
|
|
; CHECK-NEXT: [[V_ACCVGPR_WRITE_B32_e64_1:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
|
|
; CHECK-NEXT: [[V_ACCVGPR_WRITE_B32_e64_2:%[0-9]+]]:agpr_32 = V_ACCVGPR_WRITE_B32_e64 0, implicit $exec
|
|
; CHECK-NEXT: [[REG_SEQUENCE2:%[0-9]+]]:areg_128_align2 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[V_ACCVGPR_WRITE_B32_e64_]], %subreg.sub1, [[V_ACCVGPR_WRITE_B32_e64_1]], %subreg.sub2, [[V_ACCVGPR_WRITE_B32_e64_2]], %subreg.sub3
|
|
; CHECK-NEXT: [[V_MFMA_F32_16X16X16F16_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY4]], [[COPY4]], killed [[REG_SEQUENCE2]], 0, 0, 0, implicit $mode, implicit $exec
|
|
; CHECK-NEXT: [[S_MOV_B64_1:%[0-9]+]]:sreg_64 = S_MOV_B64 0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.3:
|
|
; CHECK-NEXT: successors: %bb.4(0x40000000), %bb.1(0x40000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[PHI2:%[0-9]+]]:sreg_32 = PHI [[DEF]], %bb.1, [[S_AND_B32_]], %bb.2
|
|
; CHECK-NEXT: [[PHI3:%[0-9]+]]:agpr_32 = PHI [[COPY3]], %bb.1, [[V_MFMA_F32_16X16X16F16_e64_]].sub0, %bb.2
|
|
; CHECK-NEXT: [[PHI4:%[0-9]+]]:sreg_64_xexec = PHI [[S_MOV_B64_]], %bb.1, [[S_MOV_B64_1]], %bb.2
|
|
; CHECK-NEXT: [[V_CNDMASK_B32_e64_1:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[PHI4]], implicit $exec
|
|
; CHECK-NEXT: [[V_CMP_NE_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 [[V_CNDMASK_B32_e64_1]], 1, implicit $exec
|
|
; CHECK-NEXT: $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_1]], implicit-def $scc
|
|
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
|
|
; CHECK-NEXT: S_BRANCH %bb.4
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.4:
|
|
; CHECK-NEXT: successors: %bb.5(0x80000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.5:
|
|
; CHECK-NEXT: S_ENDPGM 0
|
|
;
|
|
; COALESCE-LABEL: name: test
|
|
; COALESCE: bb.0:
|
|
; COALESCE-NEXT: successors: %bb.1(0x80000000)
|
|
; COALESCE-NEXT: liveins: $sgpr4_sgpr5
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
|
|
; COALESCE-NEXT: [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
|
|
; COALESCE-NEXT: S_BITCMP1_B32 [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
|
|
; COALESCE-NEXT: undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_64 = S_MOV_B32 0
|
|
; COALESCE-NEXT: [[S_CSELECT_B64_:%[0-9]+]]:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit killed $scc
|
|
; COALESCE-NEXT: undef [[AV_MOV_:%[0-9]+]].sub0:areg_128_align2 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
|
|
; COALESCE-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_CSELECT_B64_]], implicit $exec
|
|
; COALESCE-NEXT: [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_]], implicit $exec
|
|
; COALESCE-NEXT: undef [[AV_MOV_1:%[0-9]+]].sub1:areg_128_align2 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
|
|
; COALESCE-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 0
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: bb.1:
|
|
; COALESCE-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[AV_MOV_]].sub0
|
|
; COALESCE-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 -1
|
|
; COALESCE-NEXT: $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_]], implicit-def dead $scc
|
|
; COALESCE-NEXT: S_CBRANCH_VCCNZ %bb.3, implicit killed $vcc
|
|
; COALESCE-NEXT: S_BRANCH %bb.2
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: bb.2:
|
|
; COALESCE-NEXT: successors: %bb.3(0x80000000)
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[S_MOV_B32_1]], 1, implicit-def dead $scc
|
|
; COALESCE-NEXT: [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[S_MOV_B32_1]], 31, implicit-def dead $scc
|
|
; COALESCE-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_AND_B32 [[S_ASHR_I32_]], [[S_OR_B32_]], implicit-def dead $scc
|
|
; COALESCE-NEXT: [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_64 = COPY [[S_MOV_B32_]].sub0
|
|
; COALESCE-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY [[S_MOV_B32_]]
|
|
; COALESCE-NEXT: [[AV_MOV_1:%[0-9]+]].sub0:areg_128_align2 = COPY [[COPY1]]
|
|
; COALESCE-NEXT: [[AV_MOV_1:%[0-9]+]].sub2:areg_128_align2 = COPY [[AV_MOV_1]].sub1
|
|
; COALESCE-NEXT: [[AV_MOV_1:%[0-9]+]].sub3:areg_128_align2 = COPY [[AV_MOV_1]].sub1
|
|
; COALESCE-NEXT: [[AV_MOV_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY2]], [[COPY2]], [[AV_MOV_1]], 0, 0, 0, implicit $mode, implicit $exec
|
|
; COALESCE-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 0
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: bb.3:
|
|
; COALESCE-NEXT: successors: %bb.4(0x40000000), %bb.1(0x40000000)
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: [[V_CNDMASK_B32_e64_1:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_MOV_B64_]], implicit $exec
|
|
; COALESCE-NEXT: [[V_CMP_NE_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_1]], implicit $exec
|
|
; COALESCE-NEXT: $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_1]], implicit-def dead $scc
|
|
; COALESCE-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
|
|
; COALESCE-NEXT: S_BRANCH %bb.4
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: bb.4:
|
|
; COALESCE-NEXT: successors: %bb.5(0x80000000)
|
|
; COALESCE-NEXT: {{ $}}
|
|
; COALESCE-NEXT: bb.5:
|
|
; COALESCE-NEXT: S_ENDPGM 0
|
|
;
|
|
; GFX908-COALESCE-LABEL: name: test
|
|
; GFX908-COALESCE: bb.0:
|
|
; GFX908-COALESCE-NEXT: successors: %bb.1(0x80000000)
|
|
; GFX908-COALESCE-NEXT: liveins: $sgpr4_sgpr5
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: [[COPY:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr4_sgpr5
|
|
; GFX908-COALESCE-NEXT: [[S_LOAD_DWORD_IMM:%[0-9]+]]:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM [[COPY]](p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
|
|
; GFX908-COALESCE-NEXT: S_BITCMP1_B32 [[S_LOAD_DWORD_IMM]], 0, implicit-def $scc
|
|
; GFX908-COALESCE-NEXT: undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_64 = S_MOV_B32 0
|
|
; GFX908-COALESCE-NEXT: [[S_CSELECT_B64_:%[0-9]+]]:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit killed $scc
|
|
; GFX908-COALESCE-NEXT: undef [[AV_MOV_:%[0-9]+]].sub0:areg_128_align2 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
|
|
; GFX908-COALESCE-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_CSELECT_B64_]], implicit $exec
|
|
; GFX908-COALESCE-NEXT: [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_]], implicit $exec
|
|
; GFX908-COALESCE-NEXT: undef [[AV_MOV_1:%[0-9]+]].sub1:areg_128_align2 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
|
|
; GFX908-COALESCE-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 0
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: bb.1:
|
|
; GFX908-COALESCE-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[AV_MOV_]].sub0
|
|
; GFX908-COALESCE-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 -1
|
|
; GFX908-COALESCE-NEXT: $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_]], implicit-def dead $scc
|
|
; GFX908-COALESCE-NEXT: S_CBRANCH_VCCNZ %bb.3, implicit killed $vcc
|
|
; GFX908-COALESCE-NEXT: S_BRANCH %bb.2
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: bb.2:
|
|
; GFX908-COALESCE-NEXT: successors: %bb.3(0x80000000)
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[S_MOV_B32_1]], 1, implicit-def dead $scc
|
|
; GFX908-COALESCE-NEXT: [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[S_MOV_B32_1]], 31, implicit-def dead $scc
|
|
; GFX908-COALESCE-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_AND_B32 [[S_ASHR_I32_]], [[S_OR_B32_]], implicit-def dead $scc
|
|
; GFX908-COALESCE-NEXT: [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_64 = COPY [[S_MOV_B32_]].sub0
|
|
; GFX908-COALESCE-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY [[S_MOV_B32_]]
|
|
; GFX908-COALESCE-NEXT: [[AV_MOV_1:%[0-9]+]].sub0:areg_128_align2 = COPY [[COPY1]]
|
|
; GFX908-COALESCE-NEXT: [[AV_MOV_1:%[0-9]+]].sub2:areg_128_align2 = COPY [[AV_MOV_1]].sub1
|
|
; GFX908-COALESCE-NEXT: [[AV_MOV_1:%[0-9]+]].sub3:areg_128_align2 = COPY [[AV_MOV_1]].sub1
|
|
; GFX908-COALESCE-NEXT: [[AV_MOV_:%[0-9]+]]:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 [[COPY2]], [[COPY2]], [[AV_MOV_1]], 0, 0, 0, implicit $mode, implicit $exec
|
|
; GFX908-COALESCE-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 0
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: bb.3:
|
|
; GFX908-COALESCE-NEXT: successors: %bb.4(0x40000000), %bb.1(0x40000000)
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: [[V_CNDMASK_B32_e64_1:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_MOV_B64_]], implicit $exec
|
|
; GFX908-COALESCE-NEXT: [[V_CMP_NE_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_NE_U32_e64 1, [[V_CNDMASK_B32_e64_1]], implicit $exec
|
|
; GFX908-COALESCE-NEXT: $vcc = S_AND_B64 $exec, [[V_CMP_NE_U32_e64_1]], implicit-def dead $scc
|
|
; GFX908-COALESCE-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
|
|
; GFX908-COALESCE-NEXT: S_BRANCH %bb.4
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: bb.4:
|
|
; GFX908-COALESCE-NEXT: successors: %bb.5(0x80000000)
|
|
; GFX908-COALESCE-NEXT: {{ $}}
|
|
; GFX908-COALESCE-NEXT: bb.5:
|
|
; GFX908-COALESCE-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
successors: %bb.1
|
|
liveins: $sgpr4_sgpr5
|
|
|
|
%0:sgpr_64(p4) = COPY $sgpr4_sgpr5
|
|
%1:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0(p4), 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
|
|
S_BITCMP1_B32 killed %1, 0, implicit-def $scc
|
|
%2:sgpr_32 = S_MOV_B32 0
|
|
%3:sreg_64_xexec = S_CSELECT_B64 -1, 0, implicit $scc
|
|
%4:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
|
%5:sreg_32 = IMPLICIT_DEF
|
|
%6:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, %3, implicit $exec
|
|
%7:sreg_64_xexec = V_CMP_NE_U32_e64 %6, 1, implicit $exec
|
|
|
|
bb.1:
|
|
successors: %bb.2, %bb.3
|
|
|
|
%8:vgpr_32 = PHI %4, %bb.0, %9, %bb.3
|
|
%10:sreg_32 = PHI %2, %bb.0, %11, %bb.3
|
|
%12:agpr_32 = COPY %8
|
|
%13:sreg_64 = S_MOV_B64 -1
|
|
$vcc = S_AND_B64 $exec, %7, implicit-def $scc
|
|
S_CBRANCH_VCCNZ %bb.3, implicit $vcc
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
successors: %bb.3
|
|
|
|
%14:sreg_32 = S_OR_B32 %10, 1, implicit-def dead $scc
|
|
%15:sreg_32 = S_ASHR_I32 %10, 31, implicit-def dead $scc
|
|
%16:sreg_32 = S_AND_B32 killed %15, killed %14, implicit-def dead $scc
|
|
%17:vreg_128_align2 = REG_SEQUENCE %8, %subreg.sub0, %4, %subreg.sub1, %4, %subreg.sub2, %4, %subreg.sub3
|
|
%18:sreg_64 = REG_SEQUENCE %2, %subreg.sub0, %2, %subreg.sub1
|
|
%19:vreg_64_align2 = COPY %18
|
|
%20:areg_128_align2 = COPY %17
|
|
%21:areg_128_align2 = V_MFMA_F32_16X16X16F16_e64 %19, %19, killed %20, 0, 0, 0, implicit $mode, implicit $exec
|
|
%22:vgpr_32 = COPY %21.sub0
|
|
%23:sreg_64 = S_MOV_B64 0
|
|
|
|
bb.3:
|
|
successors: %bb.4, %bb.1
|
|
|
|
%11:sreg_32 = PHI %5, %bb.1, %16, %bb.2
|
|
%24:agpr_32 = PHI %12, %bb.1, %21.sub0, %bb.2
|
|
%25:sreg_64_xexec = PHI %13, %bb.1, %23, %bb.2
|
|
%9:vgpr_32 = COPY %24
|
|
%26:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, %25, implicit $exec
|
|
%27:sreg_64_xexec = V_CMP_NE_U32_e64 %26, 1, implicit $exec
|
|
$vcc = S_AND_B64 $exec, %27, implicit-def $scc
|
|
S_CBRANCH_VCCNZ %bb.1, implicit $vcc
|
|
S_BRANCH %bb.4
|
|
|
|
bb.4:
|
|
successors: %bb.5
|
|
|
|
bb.5:
|
|
S_ENDPGM 0
|
|
|
|
...
|