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
39 lines
1.7 KiB
LLVM
39 lines
1.7 KiB
LLVM
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn < %s | FileCheck -check-prefix=FUNC -check-prefix=SI %s
|
|
|
|
; FIXME: This currently doesn't do a great job of clustering the
|
|
; loads, which end up with extra moves between them. Right now, it
|
|
; seems the only things areLoadsFromSameBasePtr is accomplishing is
|
|
; ordering the loads so that the lower address loads come first.
|
|
|
|
; FUNC-LABEL: {{^}}cluster_global_arg_loads:
|
|
; SI-DAG: buffer_load_dword [[REG0:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, 0{{$}}
|
|
; SI-DAG: buffer_load_dword [[REG1:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:8
|
|
; SI: buffer_store_dword [[REG0]]
|
|
; SI: buffer_store_dword [[REG1]]
|
|
define amdgpu_kernel void @cluster_global_arg_loads(ptr addrspace(1) %out0, ptr addrspace(1) %out1, ptr addrspace(1) %ptr) #0 {
|
|
%load0 = load i32, ptr addrspace(1) %ptr, align 4
|
|
%gep = getelementptr i32, ptr addrspace(1) %ptr, i32 2
|
|
%load1 = load i32, ptr addrspace(1) %gep, align 4
|
|
store i32 %load0, ptr addrspace(1) %out0, align 4
|
|
store i32 %load1, ptr addrspace(1) %out1, align 4
|
|
ret void
|
|
}
|
|
|
|
; Test for a crach in SIInstrInfo::areLoadsFromSameBasePtr() when checking
|
|
; an MUBUF load which does not have a vaddr operand.
|
|
; FUNC-LABEL: {{^}}same_base_ptr_crash:
|
|
; SI: buffer_load_dword
|
|
; SI: buffer_load_dword
|
|
define amdgpu_kernel void @same_base_ptr_crash(ptr addrspace(1) %out, ptr addrspace(1) %in, i32 %offset) {
|
|
entry:
|
|
%out1 = getelementptr i32, ptr addrspace(1) %out, i32 %offset
|
|
%tmp0 = load i32, ptr addrspace(1) %out
|
|
%tmp1 = load i32, ptr addrspace(1) %out1
|
|
%tmp2 = add i32 %tmp0, %tmp1
|
|
store i32 %tmp2, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|