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
66 lines
1.8 KiB
LLVM
66 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-- -mattr=+sse2 | FileCheck %s --check-prefix=X86
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse2 | FileCheck %s --check-prefix=X64
|
|
|
|
define void @foo(ptr %P) {
|
|
; X86-LABEL: foo:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: xorps %xmm0, %xmm0
|
|
; X86-NEXT: addps (%eax), %xmm0
|
|
; X86-NEXT: movaps %xmm0, (%eax)
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: foo:
|
|
; X64: # %bb.0:
|
|
; X64-NEXT: xorps %xmm0, %xmm0
|
|
; X64-NEXT: addps (%rdi), %xmm0
|
|
; X64-NEXT: movaps %xmm0, (%rdi)
|
|
; X64-NEXT: retq
|
|
%T = load <4 x float>, ptr %P
|
|
%S = fadd <4 x float> zeroinitializer, %T
|
|
store <4 x float> %S, ptr %P
|
|
ret void
|
|
}
|
|
|
|
define void @bar(ptr %P) {
|
|
; X86-LABEL: bar:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: pxor %xmm0, %xmm0
|
|
; X86-NEXT: psubd (%eax), %xmm0
|
|
; X86-NEXT: movdqa %xmm0, (%eax)
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: bar:
|
|
; X64: # %bb.0:
|
|
; X64-NEXT: pxor %xmm0, %xmm0
|
|
; X64-NEXT: psubd (%rdi), %xmm0
|
|
; X64-NEXT: movdqa %xmm0, (%rdi)
|
|
; X64-NEXT: retq
|
|
%T = load <4 x i32>, ptr %P
|
|
%S = sub <4 x i32> zeroinitializer, %T
|
|
store <4 x i32> %S, ptr %P
|
|
ret void
|
|
}
|
|
|
|
; Without any type hints from operations, we fall back to the smaller xorps.
|
|
; The IR type <4 x i32> is ignored.
|
|
define void @untyped_zero(ptr %p) {
|
|
; X86-LABEL: untyped_zero:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: xorps %xmm0, %xmm0
|
|
; X86-NEXT: movaps %xmm0, (%eax)
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: untyped_zero:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: xorps %xmm0, %xmm0
|
|
; X64-NEXT: movaps %xmm0, (%rdi)
|
|
; X64-NEXT: retq
|
|
entry:
|
|
store <4 x i32> zeroinitializer, ptr %p, align 16
|
|
ret void
|
|
}
|