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
214 lines
8.0 KiB
YAML
214 lines
8.0 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 -verify-machineinstrs -run-pass=si-optimize-exec-masking-pre-ra -o - %s | FileCheck %s
|
|
|
|
|
|
# Cannot fold this without moving the def of %7 after the and.
|
|
---
|
|
name: no_fold_andn2_select_condition_live_out_phi
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; CHECK-LABEL: name: no_fold_andn2_select_condition_live_out_phi
|
|
; CHECK: bb.0:
|
|
; CHECK-NEXT: successors: %bb.2(0x80000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 -1
|
|
; CHECK-NEXT: undef [[V_MOV_B32_e32_:%[0-9]+]].sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.1:
|
|
; CHECK-NEXT: S_ENDPGM 0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.2:
|
|
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, [[S_MOV_B64_]], implicit $exec
|
|
; CHECK-NEXT: V_CMP_NE_U32_e32 1, [[V_CNDMASK_B32_e64_]], implicit-def $vcc, implicit $exec
|
|
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]].sub1:vreg_64 = COPY [[V_MOV_B32_e32_]].sub0
|
|
; CHECK-NEXT: DS_WRITE_B64_gfx9 undef %3:vgpr_32, [[V_MOV_B32_e32_]], 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
; CHECK-NEXT: ATOMIC_FENCE 4, 2
|
|
; CHECK-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 0
|
|
; CHECK-NEXT: $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
|
|
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
bb.0:
|
|
successors: %bb.2
|
|
|
|
%7:sreg_64_xexec = S_MOV_B64 -1
|
|
undef %5.sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.1:
|
|
S_ENDPGM 0
|
|
|
|
bb.2:
|
|
successors: %bb.1, %bb.2
|
|
|
|
%4:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, %7, implicit $exec
|
|
V_CMP_NE_U32_e32 1, %4, implicit-def $vcc, implicit $exec
|
|
%5.sub1:vreg_64 = COPY %5.sub0
|
|
DS_WRITE_B64_gfx9 undef %6:vgpr_32, %5, 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
ATOMIC_FENCE 4, 2
|
|
%7:sreg_64_xexec = S_MOV_B64 0
|
|
$vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc
|
|
S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
|
|
S_BRANCH %bb.2
|
|
|
|
...
|
|
|
|
# It's OK to fold this, since the phi def is after the andn2 insert point.
|
|
---
|
|
name: fold_andn2_select_condition_live_out_phi_reorder
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; CHECK-LABEL: name: fold_andn2_select_condition_live_out_phi_reorder
|
|
; CHECK: bb.0:
|
|
; CHECK-NEXT: successors: %bb.2(0x80000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 -1
|
|
; CHECK-NEXT: undef [[V_MOV_B32_e32_:%[0-9]+]].sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.1:
|
|
; CHECK-NEXT: S_ENDPGM 0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.2:
|
|
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]].sub1:vreg_64 = COPY [[V_MOV_B32_e32_]].sub0
|
|
; CHECK-NEXT: DS_WRITE_B64_gfx9 undef %3:vgpr_32, [[V_MOV_B32_e32_]], 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
; CHECK-NEXT: ATOMIC_FENCE 4, 2
|
|
; CHECK-NEXT: $vcc = S_ANDN2_B64 $exec, [[S_MOV_B64_]], implicit-def dead $scc
|
|
; CHECK-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64_xexec = S_MOV_B64 0
|
|
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
bb.0:
|
|
successors: %bb.2
|
|
|
|
%7:sreg_64_xexec = S_MOV_B64 -1
|
|
undef %5.sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.1:
|
|
S_ENDPGM 0
|
|
|
|
bb.2:
|
|
successors: %bb.1, %bb.2
|
|
|
|
%4:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, %7, implicit $exec
|
|
V_CMP_NE_U32_e32 1, %4, implicit-def $vcc, implicit $exec
|
|
%5.sub1:vreg_64 = COPY %5.sub0
|
|
DS_WRITE_B64_gfx9 undef %6:vgpr_32, %5, 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
ATOMIC_FENCE 4, 2
|
|
$vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc
|
|
%7:sreg_64_xexec = S_MOV_B64 0
|
|
S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
|
|
S_BRANCH %bb.2
|
|
|
|
...
|
|
|
|
---
|
|
name: no_fold_andn2_select_condition_live_out_phi_physreg
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; CHECK-LABEL: name: no_fold_andn2_select_condition_live_out_phi_physreg
|
|
; CHECK: bb.0:
|
|
; CHECK-NEXT: successors: %bb.2(0x80000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: $sgpr4_sgpr5 = S_MOV_B64 -1
|
|
; CHECK-NEXT: undef [[V_MOV_B32_e32_:%[0-9]+]].sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.1:
|
|
; CHECK-NEXT: S_ENDPGM 0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.2:
|
|
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; CHECK-NEXT: liveins: $sgpr4_sgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, $sgpr4_sgpr5, implicit $exec
|
|
; CHECK-NEXT: V_CMP_NE_U32_e32 1, [[V_CNDMASK_B32_e64_]], implicit-def $vcc, implicit $exec
|
|
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]].sub1:vreg_64 = COPY [[V_MOV_B32_e32_]].sub0
|
|
; CHECK-NEXT: DS_WRITE_B64_gfx9 undef %2:vgpr_32, [[V_MOV_B32_e32_]], 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
; CHECK-NEXT: ATOMIC_FENCE 4, 2
|
|
; CHECK-NEXT: $sgpr4_sgpr5 = S_MOV_B64 0
|
|
; CHECK-NEXT: $vcc = S_AND_B64 $exec, $vcc, implicit-def dead $scc
|
|
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
bb.0:
|
|
successors: %bb.2
|
|
|
|
$sgpr4_sgpr5 = S_MOV_B64 -1
|
|
undef %5.sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.1:
|
|
S_ENDPGM 0
|
|
|
|
bb.2:
|
|
successors: %bb.1, %bb.2
|
|
liveins: $sgpr4_sgpr5
|
|
|
|
%4:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, $sgpr4_sgpr5, implicit $exec
|
|
V_CMP_NE_U32_e32 1, %4, implicit-def $vcc, implicit $exec
|
|
%5.sub1:vreg_64 = COPY %5.sub0
|
|
DS_WRITE_B64_gfx9 undef %6:vgpr_32, %5, 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
ATOMIC_FENCE 4, 2
|
|
$sgpr4_sgpr5 = S_MOV_B64 0
|
|
$vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc
|
|
S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
|
|
S_BRANCH %bb.2
|
|
|
|
...
|
|
|
|
---
|
|
name: fold_andn2_select_condition_live_out_phi_physreg_reorder
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; CHECK-LABEL: name: fold_andn2_select_condition_live_out_phi_physreg_reorder
|
|
; CHECK: bb.0:
|
|
; CHECK-NEXT: successors: %bb.2(0x80000000)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: $sgpr4_sgpr5 = S_MOV_B64 -1
|
|
; CHECK-NEXT: undef [[V_MOV_B32_e32_:%[0-9]+]].sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.1:
|
|
; CHECK-NEXT: S_ENDPGM 0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.2:
|
|
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; CHECK-NEXT: liveins: $sgpr4_sgpr5
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]].sub1:vreg_64 = COPY [[V_MOV_B32_e32_]].sub0
|
|
; CHECK-NEXT: DS_WRITE_B64_gfx9 undef %2:vgpr_32, [[V_MOV_B32_e32_]], 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
; CHECK-NEXT: ATOMIC_FENCE 4, 2
|
|
; CHECK-NEXT: $vcc = S_ANDN2_B64 $exec, $sgpr4_sgpr5, implicit-def dead $scc
|
|
; CHECK-NEXT: $sgpr4_sgpr5 = S_MOV_B64 0
|
|
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
|
|
; CHECK-NEXT: S_BRANCH %bb.2
|
|
bb.0:
|
|
successors: %bb.2
|
|
|
|
$sgpr4_sgpr5 = S_MOV_B64 -1
|
|
undef %5.sub0:vreg_64 = V_MOV_B32_e32 0, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.1:
|
|
S_ENDPGM 0
|
|
|
|
bb.2:
|
|
successors: %bb.1, %bb.2
|
|
liveins: $sgpr4_sgpr5
|
|
|
|
%4:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, $sgpr4_sgpr5, implicit $exec
|
|
V_CMP_NE_U32_e32 1, %4, implicit-def $vcc, implicit $exec
|
|
%5.sub1:vreg_64 = COPY %5.sub0
|
|
DS_WRITE_B64_gfx9 undef %6:vgpr_32, %5, 0, 0, implicit $exec :: (store (s64), addrspace 3)
|
|
ATOMIC_FENCE 4, 2
|
|
$vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc
|
|
$sgpr4_sgpr5 = S_MOV_B64 0
|
|
S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
|
|
S_BRANCH %bb.2
|
|
|
|
...
|