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
44 lines
2.0 KiB
LLVM
44 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mattr=+load-store-opt -enable-misched < %s | FileCheck %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=bonaire -mattr=+load-store-opt -enable-misched < %s | FileCheck %s
|
|
|
|
; This test is for a bug in the machine scheduler where stores without
|
|
; an underlying object would be moved across the barrier. In this
|
|
; test, the <2 x i8> store will be split into two i8 stores, so they
|
|
; won't have an underlying object.
|
|
|
|
; CHECK-LABEL: {{^}}test:
|
|
; CHECK: ds_write_b8
|
|
; CHECK: ds_write_b8
|
|
; CHECK: s_barrier
|
|
; CHECK: s_endpgm
|
|
; Function Attrs: nounwind
|
|
define amdgpu_kernel void @test(ptr addrspace(3) nocapture %arg, ptr addrspace(1) nocapture readonly %arg1, ptr addrspace(1) nocapture readonly %arg2, ptr addrspace(1) nocapture %arg3, i32 %arg4, i64 %tmp9) #0 {
|
|
bb:
|
|
%tmp10 = getelementptr inbounds i32, ptr addrspace(1) %arg2, i64 %tmp9
|
|
%tmp13 = load i32, ptr addrspace(1) %tmp10, align 2
|
|
%tmp14 = getelementptr inbounds <2 x i8>, ptr addrspace(3) %arg, i32 %tmp13
|
|
%tmp15 = load <2 x i8>, ptr addrspace(3) %tmp14, align 1
|
|
%tmp16 = add i32 %tmp13, 1
|
|
%tmp17 = getelementptr inbounds <2 x i8>, ptr addrspace(3) %arg, i32 %tmp16
|
|
store <2 x i8> %tmp15, ptr addrspace(3) %tmp17, align 1
|
|
tail call void @llvm.amdgcn.s.barrier()
|
|
%tmp25 = load i32, ptr addrspace(1) %tmp10, align 4
|
|
%tmp26 = sext i32 %tmp25 to i64
|
|
%tmp27 = sext i32 %arg4 to i64
|
|
%tmp28 = getelementptr inbounds <2 x i8>, ptr addrspace(3) %arg, i32 %tmp25, i32 %arg4
|
|
%tmp29 = load i8, ptr addrspace(3) %tmp28, align 1
|
|
%tmp30 = getelementptr inbounds <2 x i8>, ptr addrspace(1) %arg3, i64 %tmp26, i64 %tmp27
|
|
store i8 %tmp29, ptr addrspace(1) %tmp30, align 1
|
|
%tmp32 = getelementptr inbounds <2 x i8>, ptr addrspace(3) %arg, i32 %tmp25, i32 0
|
|
%tmp33 = load i8, ptr addrspace(3) %tmp32, align 1
|
|
%tmp35 = getelementptr inbounds <2 x i8>, ptr addrspace(1) %arg3, i64 %tmp26, i64 0
|
|
store i8 %tmp33, ptr addrspace(1) %tmp35, align 1
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: convergent nounwind
|
|
declare void @llvm.amdgcn.s.barrier() #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { convergent nounwind }
|