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
58 lines
2.5 KiB
LLVM
58 lines
2.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx10.2 | FileCheck %s --check-prefix=X86
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx10.2 | FileCheck %s --check-prefix=X64
|
|
|
|
; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: write)
|
|
declare void @llvm.masked.store.v8i8.p1(<8 x i8>, ptr addrspace(1) captures(none), <8 x i1>) #0
|
|
|
|
define void @foo(<8 x i16> %arg, ptr addrspace(1) %add.ptr) {
|
|
; X86-LABEL: foo:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: vmovw %xmm0, %ecx
|
|
; X86-NEXT: movb %ch, (%eax)
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: foo:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vmovw %xmm0, %eax
|
|
; X64-NEXT: movb %ah, (%rdi)
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%i3 = shufflevector <8 x i16> %arg, <8 x i16> <i16 poison, i16 257, i16 257, i16 257, i16 257, i16 257, i16 257, i16 257>, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%i4 = lshr <8 x i16> %i3, splat (i16 8)
|
|
%i5 = trunc <8 x i16> %i4 to <8 x i8>
|
|
call void @llvm.masked.store.v8i8.p1(<8 x i8> %i5, ptr addrspace(1) %add.ptr, <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false>)
|
|
ret void
|
|
}
|
|
|
|
define void @bar(<8 x i64> %arg, ptr addrspace(1) %add.ptr) {
|
|
; X86-LABEL: bar:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: vpbroadcastq {{.*#+}} zmm1 = [257,0,257,0,257,0,257,0,257,0,257,0,257,0,257,0]
|
|
; X86-NEXT: movb $2, %al
|
|
; X86-NEXT: kmovd %eax, %k1
|
|
; X86-NEXT: vmovdqa64 %zmm0, %zmm1 {%k1}
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: vpsrlq $16, %zmm1, %zmm0
|
|
; X86-NEXT: vpmovqb %zmm0, (%eax) {%k1}
|
|
; X86-NEXT: vzeroupper
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: bar:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vpextrq $1, %xmm0, %rax
|
|
; X64-NEXT: shrl $16, %eax
|
|
; X64-NEXT: movb %al, 1(%rdi)
|
|
; X64-NEXT: vzeroupper
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%i3 = shufflevector <8 x i64> %arg, <8 x i64> <i64 257, i64 poison, i64 257, i64 257, i64 257, i64 257, i64 257, i64 257>, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%i4 = lshr <8 x i64> %i3, splat (i64 16)
|
|
%i5 = trunc <8 x i64> %i4 to <8 x i8>
|
|
call void @llvm.masked.store.v8i8.p1(<8 x i8> %i5, ptr addrspace(1) %add.ptr, <8 x i1> <i1 false, i1 true, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false>)
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nocallback nofree nosync nounwind willreturn memory(argmem: write) }
|