Files
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

163 lines
5.3 KiB
YAML

# RUN: llc -mtriple=amdgcn -verify-machineinstrs -run-pass si-shrink-instructions -o - %s | FileCheck -check-prefix=GCN %s
# RUN: llc -mtriple=amdgcn -verify-machineinstrs -passes si-shrink-instructions -o - %s | FileCheck -check-prefix=GCN %s
--- |
define amdgpu_kernel void @fold_fi_vgpr() {
%alloca = alloca [4 x i32], addrspace(5)
ret void
}
define amdgpu_kernel void @fold_vgpr_fi() {
%alloca = alloca [4 x i32], addrspace(5)
ret void
}
define amdgpu_kernel void @fold_sgpr_fi() {
%alloca = alloca [4 x i32], addrspace(5)
ret void
}
define amdgpu_kernel void @fold_fi_sgpr() {
%alloca = alloca [4 x i32], addrspace(5)
ret void
}
define amdgpu_kernel void @fold_fi_imm() {
%alloca = alloca [4 x i32], addrspace(5)
ret void
}
define amdgpu_kernel void @fold_imm_fi() {
%alloca = alloca [4 x i32], addrspace(5)
ret void
}
...
# GCN-LABEL: name: fold_fi_vgpr{{$}}
# GCN: %1:vgpr_32 = IMPLICIT_DEF
# GCN: %2:vgpr_32 = V_ADD_CO_U32_e32 %stack.0.alloca, %1, implicit-def $vcc, implicit $exec
name: fold_fi_vgpr
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: vgpr_32 }
- { id: 2, class: vgpr_32 }
stack:
- { id: 0, name: alloca, type: default, offset: 0, size: 128, alignment: 8,
callee-saved-register: '', local-offset: 0, debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
%1 = IMPLICIT_DEF
%2, $vcc = V_ADD_CO_U32_e64 %0, %1, 0, implicit $exec
S_ENDPGM 0
...
# GCN-LABEL: name: fold_vgpr_fi{{$}}
# GCN: %1:vgpr_32 = IMPLICIT_DEF
# GCN: %2:vgpr_32 = V_ADD_CO_U32_e32 %stack.0.alloca, %1, implicit-def $vcc, implicit $exec
name: fold_vgpr_fi
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: vgpr_32 }
- { id: 2, class: vgpr_32 }
stack:
- { id: 0, name: alloca, type: default, offset: 0, size: 128, alignment: 8,
callee-saved-register: '', local-offset: 0, debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
%1 = IMPLICIT_DEF
%2, $vcc = V_ADD_CO_U32_e64 %1, %0, 0, implicit $exec
S_ENDPGM 0
...
# GCN-LABEL: name: fold_sgpr_fi{{$}}
# GCN: %0:vgpr_32 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
# GCN: %1:sgpr_32 = IMPLICIT_DEF
# GCN: %2:vgpr_32 = V_ADD_CO_U32_e32 %1, %0, implicit-def $vcc, implicit $exec
name: fold_sgpr_fi
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: sgpr_32 }
- { id: 2, class: vgpr_32 }
stack:
- { id: 0, name: alloca, type: default, offset: 0, size: 128, alignment: 8,
callee-saved-register: '', local-offset: 0, debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
%1 = IMPLICIT_DEF
%2, $vcc = V_ADD_CO_U32_e64 %1, %0, 0, implicit $exec
S_ENDPGM 0
...
# GCN-LABEL: name: fold_fi_sgpr{{$}}
# GCN: %0:vgpr_32 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
# GCN: %1:sgpr_32 = IMPLICIT_DEF
# GCN: %2:vgpr_32 = V_ADD_CO_U32_e32 %1, %0, implicit-def $vcc, implicit $exec
name: fold_fi_sgpr
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: sgpr_32 }
- { id: 2, class: vgpr_32 }
stack:
- { id: 0, name: alloca, type: default, offset: 0, size: 128, alignment: 8,
callee-saved-register: '', local-offset: 0, debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
%1 = IMPLICIT_DEF
%2, $vcc = V_ADD_CO_U32_e64 %0, %1, 0, implicit $exec
S_ENDPGM 0
...
# TODO: Should probably prefer folding immediate first
# GCN-LABEL: name: fold_fi_imm{{$}}
# GCN: %1:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
# GCN: %2:vgpr_32 = V_ADD_CO_U32_e32 %stack.0.alloca, %1, implicit-def $vcc, implicit $exec
name: fold_fi_imm
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: vgpr_32 }
- { id: 2, class: vgpr_32 }
stack:
- { id: 0, name: alloca, type: default, offset: 0, size: 128, alignment: 8,
callee-saved-register: '', local-offset: 0, debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
%1 = V_MOV_B32_e32 999, implicit $exec
%2, $vcc = V_ADD_CO_U32_e64 %0, %1, 0, implicit $exec
S_ENDPGM 0
...
# GCN-LABEL: name: fold_imm_fi{{$}}
# GCN: %0:vgpr_32 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
# GCN: %2:vgpr_32 = V_ADD_CO_U32_e32 999, %0, implicit-def $vcc, implicit $exec
name: fold_imm_fi
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: vgpr_32 }
- { id: 2, class: vgpr_32 }
stack:
- { id: 0, name: alloca, type: default, offset: 0, size: 128, alignment: 8,
callee-saved-register: '', local-offset: 0, debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 %stack.0.alloca, implicit $exec
%1 = V_MOV_B32_e32 999, implicit $exec
%2, $vcc = V_ADD_CO_U32_e64 %1, %0, 0, implicit $exec
S_ENDPGM 0