Files
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

87 lines
2.9 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 | FileCheck %s --check-prefixes=CHECK,SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse4.1 | FileCheck %s --check-prefixes=CHECK,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefixes=CHECK,AVX
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefixes=CHECK,AVX
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f | FileCheck %s --check-prefixes=CHECK,AVX
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512bw | FileCheck %s --check-prefixes=CHECK,AVX
declare i64 @llvm.vector.reduce.or.v2i64(<2 x i64>)
define i1 @parseHeaders(ptr %ptr) nounwind {
; SSE2-LABEL: parseHeaders:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqu (%rdi), %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm1
; SSE2-NEXT: movmskps %xmm1, %eax
; SSE2-NEXT: xorl $15, %eax
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: parseHeaders:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqu (%rdi), %xmm0
; SSE41-NEXT: ptest %xmm0, %xmm0
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX-LABEL: parseHeaders:
; AVX: # %bb.0:
; AVX-NEXT: vmovdqu (%rdi), %xmm0
; AVX-NEXT: vptest %xmm0, %xmm0
; AVX-NEXT: sete %al
; AVX-NEXT: retq
%vload = load <2 x i64>, ptr %ptr, align 8
%vreduce = call i64 @llvm.vector.reduce.or.v2i64(<2 x i64> %vload)
%vcheck = icmp eq i64 %vreduce, 0
ret i1 %vcheck
}
define i1 @parseHeaders2_scalar_or(ptr %ptr) nounwind {
; SSE2-LABEL: parseHeaders2_scalar_or:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqu (%rdi), %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm1
; SSE2-NEXT: movmskps %xmm1, %eax
; SSE2-NEXT: xorl $15, %eax
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: parseHeaders2_scalar_or:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqu (%rdi), %xmm0
; SSE41-NEXT: ptest %xmm0, %xmm0
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX-LABEL: parseHeaders2_scalar_or:
; AVX: # %bb.0:
; AVX-NEXT: vmovdqu (%rdi), %xmm0
; AVX-NEXT: vptest %xmm0, %xmm0
; AVX-NEXT: sete %al
; AVX-NEXT: retq
%vload = load <2 x i64>, ptr %ptr, align 8
%v1 = extractelement <2 x i64> %vload, i32 0
%v2 = extractelement <2 x i64> %vload, i32 1
%vreduce = or i64 %v1, %v2
%vcheck = icmp eq i64 %vreduce, 0
ret i1 %vcheck
}
define i1 @parseHeaders2_scalar_and(ptr %ptr) nounwind {
; CHECK-LABEL: parseHeaders2_scalar_and:
; CHECK: # %bb.0:
; CHECK-NEXT: movq (%rdi), %rax
; CHECK-NEXT: testq %rax, 8(%rdi)
; CHECK-NEXT: sete %al
; CHECK-NEXT: retq
%vload = load <2 x i64>, ptr %ptr, align 8
%v1 = extractelement <2 x i64> %vload, i32 0
%v2 = extractelement <2 x i64> %vload, i32 1
%vreduce = and i64 %v1, %v2
%vcheck = icmp eq i64 %vreduce, 0
ret i1 %vcheck
}