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
58 lines
2.0 KiB
LLVM
58 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=fiji < %s | FileCheck -check-prefixes=GCN,W64 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 < %s | FileCheck -check-prefixes=GCN,W32 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GCN,W64 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-enable-vopd=0 < %s | FileCheck -check-prefixes=GCN,W32 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GCN,W64 %s
|
|
|
|
; GCN-LABEL: {{^}}fold_wavefrontsize:
|
|
|
|
; W32: v_mov_b32_e32 [[V:v[0-9]+]], 32
|
|
; W64: v_mov_b32_e32 [[V:v[0-9]+]], 64
|
|
; GCN: store_{{dword|b32}} v{{.+}}, [[V]]
|
|
|
|
|
|
define amdgpu_kernel void @fold_wavefrontsize(ptr addrspace(1) nocapture %arg) {
|
|
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.wavefrontsize() #0
|
|
store i32 %tmp, ptr addrspace(1) %arg, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}fold_and_optimize_wavefrontsize:
|
|
|
|
; W32: v_mov_b32_e32 [[V:v[0-9]+]], 1{{$}}
|
|
; W64: v_mov_b32_e32 [[V:v[0-9]+]], 2{{$}}
|
|
; GCN-NOT: cndmask
|
|
; GCN: store_{{dword|b32}} v{{.+}}, [[V]]
|
|
|
|
|
|
define amdgpu_kernel void @fold_and_optimize_wavefrontsize(ptr addrspace(1) nocapture %arg) {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.wavefrontsize() #0
|
|
%tmp1 = icmp ugt i32 %tmp, 32
|
|
%tmp2 = select i1 %tmp1, i32 2, i32 1
|
|
store i32 %tmp2, ptr addrspace(1) %arg
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}fold_and_optimize_if_wavefrontsize:
|
|
|
|
define amdgpu_kernel void @fold_and_optimize_if_wavefrontsize(ptr addrspace(1) nocapture %arg) {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.wavefrontsize() #0
|
|
%tmp1 = icmp ugt i32 %tmp, 32
|
|
br i1 %tmp1, label %bb2, label %bb3
|
|
|
|
bb2: ; preds = %bb
|
|
store i32 1, ptr addrspace(1) %arg, align 4
|
|
br label %bb3
|
|
|
|
bb3: ; preds = %bb2, %bb
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.wavefrontsize() #0
|
|
|
|
attributes #0 = { nounwind readnone speculatable }
|