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
59 lines
2.4 KiB
LLVM
59 lines
2.4 KiB
LLVM
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx803 < %s | FileCheck -check-prefixes=GCN %s
|
|
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN %s
|
|
|
|
; The buffer_loads and buffer_stores all access the same location. Check they do
|
|
; not get reordered by the scheduler.
|
|
|
|
; GCN-LABEL: {{^}}test1:
|
|
; GCN: buffer_store_dword
|
|
; GCN: buffer_load_dword
|
|
; GCN: buffer_store_dword
|
|
define amdgpu_cs void @test1(<4 x i32> inreg %buf, i32 %off) {
|
|
.entry:
|
|
call void @llvm.amdgcn.raw.buffer.store.i32(i32 0, <4 x i32> %buf, i32 8, i32 0, i32 0)
|
|
%val = call i32 @llvm.amdgcn.raw.buffer.load.i32(<4 x i32> %buf, i32 %off, i32 0, i32 0)
|
|
call void @llvm.amdgcn.raw.buffer.store.i32(i32 %val, <4 x i32> %buf, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test1_ptrs:
|
|
; GCN: buffer_store_dword
|
|
; GCN: buffer_load_dword
|
|
; GCN: buffer_store_dword
|
|
define amdgpu_cs void @test1_ptrs(ptr addrspace(8) inreg %buf, i32 %off) {
|
|
.entry:
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 0, ptr addrspace(8) %buf, i32 8, i32 0, i32 0)
|
|
%val = call i32 @llvm.amdgcn.raw.ptr.buffer.load.i32(ptr addrspace(8) %buf, i32 %off, i32 0, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %val, ptr addrspace(8) %buf, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;; In the future, the stores should be reorderable because they'd be known to be
|
|
;; at distinct offsets.
|
|
; GCN-LABEL: {{^}}test1_ptrs_reorderable:
|
|
; GCN: buffer_store_dword
|
|
; GCN: buffer_load_dword
|
|
; GCN: buffer_store_dword
|
|
define amdgpu_cs void @test1_ptrs_reorderable(ptr addrspace(8) inreg %buf, i32 %off) {
|
|
.entry:
|
|
%shifted.off = shl i32 %off, 4
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 0, ptr addrspace(8) %buf, i32 8, i32 0, i32 0)
|
|
%val = call i32 @llvm.amdgcn.raw.ptr.buffer.load.i32(ptr addrspace(8) %buf, i32 %shifted.off, i32 0, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %val, ptr addrspace(8) %buf, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
|
|
declare i32 @llvm.amdgcn.raw.buffer.load.i32(<4 x i32>, i32, i32, i32) #2
|
|
|
|
declare void @llvm.amdgcn.raw.buffer.store.i32(i32, <4 x i32>, i32, i32, i32) #3
|
|
|
|
declare i32 @llvm.amdgcn.raw.ptr.buffer.load.i32(ptr addrspace(8) nocapture, i32, i32, i32) #4
|
|
|
|
declare void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32, ptr addrspace(8) nocapture, i32, i32, i32) #5
|
|
|
|
attributes #2 = { nounwind readonly }
|
|
attributes #3 = { nounwind writeonly }
|
|
attributes #4 = { nounwind memory(argmem: read) }
|
|
attributes #5 = { nounwind memory(argmem: write) }
|