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
46 lines
1.7 KiB
LLVM
46 lines
1.7 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; Interleave loads and stores to fit into 9 VGPR limit.
|
|
; This requires to avoid load/store clustering.
|
|
|
|
; Reschedule the second scheduling region without clustering while
|
|
; the first region is skipped.
|
|
|
|
; GCN: global_load_dwordx4
|
|
; GCN: global_store_dwordx4
|
|
; GCN: global_load_dwordx4
|
|
; GCN: global_store_dwordx4
|
|
; GCN: global_load_dwordx4
|
|
; GCN: global_store_dwordx4
|
|
; GCN: NumVgprs: {{[0-9]$}}
|
|
; GCN: ScratchSize: 0{{$}}
|
|
|
|
define amdgpu_kernel void @load_store_max_9vgprs(ptr addrspace(1) nocapture noalias readonly %arg, ptr addrspace(1) nocapture noalias %arg1, i1 %cnd) #1 {
|
|
bb:
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%base = getelementptr inbounds <4 x i32>, ptr addrspace(1) %arg, i32 %id
|
|
br i1 %cnd, label %bb1, label %bb2
|
|
|
|
bb1:
|
|
%tmp = getelementptr inbounds <4 x i32>, ptr addrspace(1) %base, i32 1
|
|
%tmp2 = load <4 x i32>, ptr addrspace(1) %tmp, align 4
|
|
%tmp3 = getelementptr inbounds <4 x i32>, ptr addrspace(1) %base, i32 3
|
|
%tmp4 = load <4 x i32>, ptr addrspace(1) %tmp3, align 4
|
|
%tmp5 = getelementptr inbounds <4 x i32>, ptr addrspace(1) %base, i32 5
|
|
%tmp6 = load <4 x i32>, ptr addrspace(1) %tmp5, align 4
|
|
store <4 x i32> %tmp2, ptr addrspace(1) %arg1, align 4
|
|
%tmp7 = getelementptr inbounds <4 x i32>, ptr addrspace(1) %arg1, i64 3
|
|
store <4 x i32> %tmp4, ptr addrspace(1) %tmp7, align 4
|
|
%tmp8 = getelementptr inbounds <4 x i32>, ptr addrspace(1) %arg1, i64 5
|
|
store <4 x i32> %tmp6, ptr addrspace(1) %tmp8, align 4
|
|
br label %bb2
|
|
|
|
bb2:
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
|
|
attributes #0 = { nounwind readnone }
|
|
attributes #1 = { "amdgpu-num-vgpr"="9" }
|