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
117 lines
4.4 KiB
LLVM
117 lines
4.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+vpclmulqdq,+avx512vl | FileCheck %s
|
|
; FIXME: actual vpclmulqdq operation should be eliminated
|
|
|
|
declare <2 x i64> @llvm.x86.pclmulqdq(<2 x i64>, <2 x i64>, i8) nounwind readnone
|
|
declare <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64>, <4 x i64>, i8) nounwind readnone
|
|
declare <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
define <2 x i64> @commute_xmm_v1(<2 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK-LABEL: commute_xmm_v1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, i8 0)
|
|
%2 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a1, <2 x i64> %a0, i8 0)
|
|
%3 = xor <2 x i64> %1, %2
|
|
ret <2 x i64> %3
|
|
}
|
|
|
|
define <2 x i64> @commute_xmm_v2(<2 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK-LABEL: commute_xmm_v2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $16, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, i8 16)
|
|
%2 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a1, <2 x i64> %a0, i8 1)
|
|
%3 = xor <2 x i64> %2, %1
|
|
ret <2 x i64> %3
|
|
}
|
|
|
|
define <2 x i64> @commute_xmm_v3(<2 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK-LABEL: commute_xmm_v3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $17, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, i8 17)
|
|
%2 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a1, <2 x i64> %a0, i8 17)
|
|
%3 = xor <2 x i64> %2, %1
|
|
ret <2 x i64> %3
|
|
}
|
|
|
|
define <4 x i64> @commute_ymm_v1(<4 x i64> %a0, <4 x i64> %a1) {
|
|
; CHECK-LABEL: commute_ymm_v1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $0, %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpxor %ymm0, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64> %a0, <4 x i64> %a1, i8 0)
|
|
%2 = call <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64> %a1, <4 x i64> %a0, i8 0)
|
|
%3 = xor <4 x i64> %1, %2
|
|
ret <4 x i64> %3
|
|
}
|
|
|
|
define <4 x i64> @commute_ymm_v2(<4 x i64> %a0, <4 x i64> %a1) {
|
|
; CHECK-LABEL: commute_ymm_v2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $16, %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpxor %ymm0, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64> %a0, <4 x i64> %a1, i8 16)
|
|
%2 = call <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64> %a1, <4 x i64> %a0, i8 1)
|
|
%3 = xor <4 x i64> %2, %1
|
|
ret <4 x i64> %3
|
|
}
|
|
|
|
define <4 x i64> @commute_ymm_v3(<4 x i64> %a0, <4 x i64> %a1) {
|
|
; CHECK-LABEL: commute_ymm_v3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $17, %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpxor %ymm0, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64> %a0, <4 x i64> %a1, i8 17)
|
|
%2 = call <4 x i64> @llvm.x86.pclmulqdq.256(<4 x i64> %a1, <4 x i64> %a0, i8 17)
|
|
%3 = xor <4 x i64> %2, %1
|
|
ret <4 x i64> %3
|
|
}
|
|
|
|
define <8 x i64> @commute_zmm_v1(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: commute_zmm_v1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $0, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpxorq %zmm0, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64> %a0, <8 x i64> %a1, i8 0)
|
|
%2 = call <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64> %a1, <8 x i64> %a0, i8 0)
|
|
%3 = xor <8 x i64> %1, %2
|
|
ret <8 x i64> %3
|
|
}
|
|
|
|
define <8 x i64> @commute_zmm_v2(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: commute_zmm_v2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $16, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpxorq %zmm0, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64> %a0, <8 x i64> %a1, i8 16)
|
|
%2 = call <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64> %a1, <8 x i64> %a0, i8 1)
|
|
%3 = xor <8 x i64> %2, %1
|
|
ret <8 x i64> %3
|
|
}
|
|
|
|
define <8 x i64> @commute_zmm_v3(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: commute_zmm_v3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpclmulqdq $17, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpxorq %zmm0, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = call <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64> %a0, <8 x i64> %a1, i8 17)
|
|
%2 = call <8 x i64> @llvm.x86.pclmulqdq.512(<8 x i64> %a1, <8 x i64> %a0, i8 17)
|
|
%3 = xor <8 x i64> %2, %1
|
|
ret <8 x i64> %3
|
|
}
|
|
|