Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

39 lines
1.7 KiB
LLVM

; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}reduce_i64_load_align_4_width_to_i32:
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
; GCN: v_and_b32_e32 v{{[0-9]+}}, 0x12d687, [[VAL]]
; GCN: buffer_store_dwordx2
define amdgpu_kernel void @reduce_i64_load_align_4_width_to_i32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
%a = load i64, ptr addrspace(1) %in, align 4
%and = and i64 %a, 1234567
store i64 %and, ptr addrspace(1) %out, align 8
ret void
}
; GCN-LABEL: {{^}}reduce_i64_align_4_bitcast_v2i32_elt0:
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
; GCN: buffer_store_dword [[VAL]]
define amdgpu_kernel void @reduce_i64_align_4_bitcast_v2i32_elt0(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
%a = load i64, ptr addrspace(1) %in, align 4
%vec = bitcast i64 %a to <2 x i32>
%elt0 = extractelement <2 x i32> %vec, i32 0
store i32 %elt0, ptr addrspace(1) %out
ret void
}
; GCN-LABEL: {{^}}reduce_i64_align_4_bitcast_v2i32_elt1:
; GCN: buffer_load_dword [[VAL:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:4
; GCN: buffer_store_dword [[VAL]]
define amdgpu_kernel void @reduce_i64_align_4_bitcast_v2i32_elt1(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
%a = load i64, ptr addrspace(1) %in, align 4
%vec = bitcast i64 %a to <2 x i32>
%elt0 = extractelement <2 x i32> %vec, i32 1
store i32 %elt0, ptr addrspace(1) %out
ret void
}
attributes #0 = { nounwind }