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
94 lines
3.8 KiB
LLVM
94 lines
3.8 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; The bitcast should be pushed through the bitcasts so the vectors can
|
|
; be broken down and the shared components can be CSEd
|
|
|
|
; GCN-LABEL: {{^}}store_bitcast_constant_v8i32_to_v8f32:
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
define amdgpu_kernel void @store_bitcast_constant_v8i32_to_v8f32(ptr addrspace(1) %out, <8 x i32> %vec) {
|
|
%vec0.bc = bitcast <8 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 8> to <8 x float>
|
|
store volatile <8 x float> %vec0.bc, ptr addrspace(1) %out
|
|
|
|
%vec1.bc = bitcast <8 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 9> to <8 x float>
|
|
store volatile <8 x float> %vec1.bc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_bitcast_constant_v4i64_to_v8f32:
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
define amdgpu_kernel void @store_bitcast_constant_v4i64_to_v8f32(ptr addrspace(1) %out, <4 x i64> %vec) {
|
|
%vec0.bc = bitcast <4 x i64> <i64 7, i64 7, i64 7, i64 8> to <8 x float>
|
|
store volatile <8 x float> %vec0.bc, ptr addrspace(1) %out
|
|
|
|
%vec1.bc = bitcast <4 x i64> <i64 7, i64 7, i64 7, i64 9> to <8 x float>
|
|
store volatile <8 x float> %vec1.bc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_bitcast_constant_v4i64_to_v4f64:
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
define amdgpu_kernel void @store_bitcast_constant_v4i64_to_v4f64(ptr addrspace(1) %out, <4 x i64> %vec) {
|
|
%vec0.bc = bitcast <4 x i64> <i64 7, i64 7, i64 7, i64 8> to <4 x double>
|
|
store volatile <4 x double> %vec0.bc, ptr addrspace(1) %out
|
|
|
|
%vec1.bc = bitcast <4 x i64> <i64 7, i64 7, i64 7, i64 9> to <4 x double>
|
|
store volatile <4 x double> %vec1.bc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_bitcast_constant_v8i32_to_v16i16:
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: buffer_store_dwordx4
|
|
define amdgpu_kernel void @store_bitcast_constant_v8i32_to_v16i16(ptr addrspace(1) %out, <16 x i16> %vec) {
|
|
%vec0.bc = bitcast <16 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 8> to <8 x float>
|
|
store volatile <8 x float> %vec0.bc, ptr addrspace(1) %out
|
|
|
|
%vec1.bc = bitcast <16 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 9> to <8 x float>
|
|
store volatile <8 x float> %vec1.bc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_value_lowered_to_undef_bitcast_source:
|
|
; GCN-NOT: store_dword
|
|
define amdgpu_kernel void @store_value_lowered_to_undef_bitcast_source(ptr addrspace(1) %out, i64 %a, i64 %b) #0 {
|
|
%undef = call i64 @llvm.amdgcn.icmp.i64(i64 %a, i64 %b, i32 999) #1
|
|
%bc = bitcast i64 %undef to <2 x i32>
|
|
store <2 x i32> %bc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_value_lowered_to_undef_bitcast_source_extractelt:
|
|
; GCN-NOT: store_dword
|
|
define amdgpu_kernel void @store_value_lowered_to_undef_bitcast_source_extractelt(ptr addrspace(1) %out, i64 %a, i64 %b) #0 {
|
|
%undef = call i64 @llvm.amdgcn.icmp.i64(i64 %a, i64 %b, i32 9999) #1
|
|
%bc = bitcast i64 %undef to <2 x i32>
|
|
%elt1 = extractelement <2 x i32> %bc, i32 1
|
|
store i32 %elt1, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare i64 @llvm.amdgcn.icmp.i64(i64, i64, i32) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone convergent }
|