Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-select.mir
derek.holloway 7502bf64a4
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

125 lines
5.9 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 6
# RUN: llc -mtriple=amdgcn -verify-machineinstrs -mcpu=gfx1030 -run-pass prologepilog -o - %s | FileCheck %s
# s_cselect_b32 does not allow vreg & should use the sreg frameindex generated
# by v_readfirstlane_b32 in eliminateFrameIndex.
---
name: test_s_cselect_b32
tracksRegLiveness: true
stack:
- { id: 0, size: 12}
machineFunctionInfo:
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
body: |
; CHECK-LABEL: name: test_s_cselect_b32
; CHECK: bb.0:
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: liveins: $vgpr41
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_def_aspace_cfa $sgpr32, 0, 6
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr4
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr5
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $sgpr6
; CHECK-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr41, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, implicit $exec :: ("amdgpu-thread-private" store (s32) into %stack.1, addrspace 5)
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_vector_offset $vgpr41, 32, $exec_lo, 32, 0
; CHECK-NEXT: renamable $vgpr41 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: renamable $sgpr4 = S_MOV_B32 0
; CHECK-NEXT: renamable $sgpr5 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
; CHECK-NEXT: renamable $sgpr54 = S_ADD_I32 $sgpr5, 8, implicit-def dead $scc
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
; CHECK-NEXT: successors: %bb.2(0x80000000)
; CHECK-NEXT: liveins: $sgpr4, $sgpr54:0x000000000000000F
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: S_CMP_EQ_U32 killed renamable $sgpr4, 0, implicit-def $scc
; CHECK-NEXT: $vgpr0 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 4, killed $vgpr0, implicit $exec
; CHECK-NEXT: $sgpr5 = V_READFIRSTLANE_B32 $vgpr0, implicit $exec
; CHECK-NEXT: renamable $sgpr4 = S_CSELECT_B32 0, killed $sgpr5, implicit $scc
; CHECK-NEXT: $vgpr0 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
; CHECK-NEXT: $vgpr0 = V_ADD_U32_e32 4, killed $vgpr0, implicit $exec
; CHECK-NEXT: $sgpr4 = V_READFIRSTLANE_B32 $vgpr0, implicit $exec
; CHECK-NEXT: renamable $sgpr6 = S_CSELECT_B32 killed $sgpr4, 0, implicit $scc
; CHECK-NEXT: renamable $sgpr5 = S_CSELECT_B32 4, renamable $sgpr54, implicit $scc
; CHECK-NEXT: S_BRANCH %bb.2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2:
; CHECK-NEXT: $vgpr41 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, implicit $exec :: ("amdgpu-thread-private" load (s32) from %stack.1, addrspace 5)
; CHECK-NEXT: SI_RETURN
bb.0:
renamable $vgpr41 = V_MOV_B32_e32 0, implicit $exec
renamable $sgpr4 = S_MOV_B32 0
renamable $sgpr54 = S_ADD_I32 %stack.0, 4, implicit-def dead $scc
bb.1:
liveins: $sgpr4, $sgpr54:0x000000000000000F
S_CMP_EQ_U32 killed renamable $sgpr4, 0, implicit-def $scc
renamable $sgpr4 = S_CSELECT_B32 0, %stack.0, implicit $scc
renamable $sgpr6 = S_CSELECT_B32 %stack.0, 0, implicit $scc
renamable $sgpr5 = S_CSELECT_B32 4, renamable $sgpr54, implicit $scc
S_BRANCH %bb.2
bb.2:
SI_RETURN
...
# ensure register constraints of V_CNDMASK_B32_e32 are respected by
# eliminateFrameIndex.
---
name: test_v_cndmask_e32
tracksRegLiveness: true
stack:
- { id: 0, size: 12}
machineFunctionInfo:
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
liveins: $sgpr4
; CHECK-LABEL: name: test_v_cndmask_e32
; CHECK: liveins: $sgpr4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_def_aspace_cfa $sgpr32, 0, 6
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr2
; CHECK-NEXT: $vcc_lo = V_CMP_EQ_U32_e64 killed $sgpr4, 0, implicit $exec
; CHECK-NEXT: renamable $vgpr2 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: $vgpr1 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
; CHECK-NEXT: renamable $vgpr0 = V_CNDMASK_B32_e32 killed $vgpr1, killed $vgpr2, implicit $vcc_lo, implicit $vcc_lo, implicit $exec
; CHECK-NEXT: SI_RETURN
V_CMP_EQ_U32_e64 def $vcc_lo, killed $sgpr4, 0, implicit $exec
renamable $vgpr2 = V_MOV_B32_e32 0, implicit $exec
renamable $vgpr0 = V_CNDMASK_B32_e32 %stack.0, killed $vgpr2, implicit $vcc_lo, implicit $vcc, implicit $exec
SI_RETURN
...
# ensure register constraints of V_CNDMASK_B32_e64 are respected by
# eliminateFrameIndex.
---
name: test_v_cndmask_e64
tracksRegLiveness: true
stack:
- { id: 0, size: 12}
machineFunctionInfo:
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
frameOffsetReg: '$sgpr33'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
liveins: $sgpr4
; CHECK-LABEL: name: test_v_cndmask_e64
; CHECK: liveins: $sgpr4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_def_aspace_cfa $sgpr32, 0, 6
; CHECK-NEXT: frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr0
; CHECK-NEXT: frame-setup CFI_INSTRUCTION undefined $vgpr2
; CHECK-NEXT: renamable $vgpr2 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: $vgpr1 = V_LSHRREV_B32_e64 5, $sgpr32, implicit $exec
; CHECK-NEXT: renamable $vgpr0 = V_CNDMASK_B32_e64 0, killed $vgpr1, 0, killed $vgpr2, $sgpr4, implicit $exec
; CHECK-NEXT: SI_RETURN
renamable $vgpr2 = V_MOV_B32_e32 0, implicit $exec
renamable $vgpr0 = V_CNDMASK_B32_e64 0, %stack.0, 0, killed $vgpr2, $sgpr4, implicit $exec
SI_RETURN
...