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
70 lines
2.7 KiB
LLVM
70 lines
2.7 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}const_load_no_shrink_dword_to_unaligned_byte:
|
|
; GCN: s_load_dword s{{[0-9]+}}
|
|
; GCN: s_load_dword [[LD:s[0-9]+]],
|
|
; GCN: s_bfe_i32 s{{[0-9]+}}, [[LD]], 0x10013
|
|
define amdgpu_kernel void @const_load_no_shrink_dword_to_unaligned_byte(ptr addrspace(1) %out, ptr addrspace(4) %in, i32 %x) {
|
|
%ptr = getelementptr i32, ptr addrspace(4) %in, i32 %x
|
|
%load = load i32, ptr addrspace(4) %ptr, align 4
|
|
%and = and i32 %load, 524288
|
|
%cmp = icmp eq i32 %and, 0
|
|
%sel = select i1 %cmp, i32 0, i32 -1
|
|
store i32 %sel, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: const_load_no_shrink_dword_to_aligned_byte:
|
|
; GCN: s_load_dword s{{[0-9]+}}
|
|
; GCN: s_load_dword [[LD:s[0-9]+]],
|
|
; GCN: s_bfe_i32 s{{[0-9]+}}, [[LD]], 0x10003
|
|
define amdgpu_kernel void @const_load_no_shrink_dword_to_aligned_byte(ptr addrspace(1) %out, ptr addrspace(4) %in, i32 %x) {
|
|
%ptr = getelementptr i32, ptr addrspace(4) %in, i32 %x
|
|
%load = load i32, ptr addrspace(4) %ptr, align 4
|
|
%and = and i32 %load, 8
|
|
%cmp = icmp eq i32 %and, 0
|
|
%sel = select i1 %cmp, i32 0, i32 -1
|
|
store i32 %sel, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: global_load_no_shrink_dword_to_unaligned_byte:
|
|
; GCN: s_load_dword s{{[0-9]+}}
|
|
; GCN: s_load_dword [[LD:s[0-9]+]],
|
|
; GCN: s_bfe_i32 s{{[0-9]+}}, [[LD]], 0x10013
|
|
define amdgpu_kernel void @global_load_no_shrink_dword_to_unaligned_byte(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in, i32 %x) {
|
|
%ptr = getelementptr i32, ptr addrspace(1) %in, i32 %x
|
|
%load = load i32, ptr addrspace(1) %ptr, align 4
|
|
%and = and i32 %load, 524288
|
|
%cmp = icmp eq i32 %and, 0
|
|
%sel = select i1 %cmp, i32 0, i32 -1
|
|
store i32 %sel, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: global_load_no_shrink_dword_to_aligned_byte:
|
|
; GCN: s_load_dword s{{[0-9]+}}
|
|
; GCN: s_load_dword [[LD:s[0-9]+]],
|
|
; GCN: s_bfe_i32 s{{[0-9]+}}, [[LD]], 0x10003
|
|
define amdgpu_kernel void @global_load_no_shrink_dword_to_aligned_byte(ptr addrspace(1) %out, ptr addrspace(1) %in, i32 %x) {
|
|
%ptr = getelementptr i32, ptr addrspace(1) %in, i32 %x
|
|
%load = load i32, ptr addrspace(1) %ptr, align 4
|
|
%and = and i32 %load, 8
|
|
%cmp = icmp eq i32 %and, 0
|
|
%sel = select i1 %cmp, i32 0, i32 -1
|
|
store i32 %sel, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: const_load_shrink_dword_to_unaligned_byte:
|
|
; GCN: global_load_ushort
|
|
define amdgpu_kernel void @const_load_shrink_dword_to_unaligned_byte(ptr addrspace(1) %out, ptr addrspace(4) %in, i32 %x) {
|
|
%ptr = getelementptr i32, ptr addrspace(4) %in, i32 %x
|
|
%load = load i32, ptr addrspace(4) %ptr, align 2
|
|
%and = and i32 %load, 524288
|
|
%cmp = icmp eq i32 %and, 0
|
|
%sel = select i1 %cmp, i32 0, i32 -1
|
|
store i32 %sel, ptr addrspace(1) %out
|
|
ret void
|
|
}
|