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

215 lines
7.8 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
declare <2 x i64> @llvm.cttz.v2i64(<2 x i64>, i1)
declare <2 x i64> @llvm.ctlz.v2i64(<2 x i64>, i1)
declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>)
define <2 x i64> @footz(<2 x i64> %a) nounwind {
; CHECK-LABEL: footz:
; CHECK: # %bb.0:
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-NEXT: paddq %xmm0, %xmm1
; CHECK-NEXT: pandn %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $1, %xmm1
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; CHECK-NEXT: psubb %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlw $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddb %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $4, %xmm1
; CHECK-NEXT: paddb %xmm1, %xmm0
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> %a, i1 true)
ret <2 x i64> %c
}
define <2 x i64> @foolz(<2 x i64> %a) nounwind {
; CHECK-LABEL: foolz:
; CHECK: # %bb.0:
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $1, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $2, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $4, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $8, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $16, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlq $32, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-NEXT: pxor %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $1, %xmm1
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; CHECK-NEXT: psubb %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlw $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddb %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $4, %xmm1
; CHECK-NEXT: paddb %xmm1, %xmm0
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> %a, i1 true)
ret <2 x i64> %c
}
define <2 x i64> @foopop(<2 x i64> %a) nounwind {
; CHECK-LABEL: foopop:
; CHECK: # %bb.0:
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $1, %xmm1
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; CHECK-NEXT: psubb %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlw $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddb %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $4, %xmm1
; CHECK-NEXT: paddb %xmm1, %xmm0
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %a)
ret <2 x i64> %c
}
declare <2 x i32> @llvm.cttz.v2i32(<2 x i32>, i1)
declare <2 x i32> @llvm.ctlz.v2i32(<2 x i32>, i1)
declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32>)
define <2 x i32> @promtz(<2 x i32> %a) nounwind {
; CHECK-LABEL: promtz:
; CHECK: # %bb.0:
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-NEXT: paddd %xmm0, %xmm1
; CHECK-NEXT: pandn %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $1, %xmm1
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; CHECK-NEXT: psubb %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlw $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddb %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $4, %xmm1
; CHECK-NEXT: paddb %xmm1, %xmm0
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; CHECK-NEXT: psadbw %xmm1, %xmm2
; CHECK-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: packuswb %xmm2, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> %a, i1 false)
ret <2 x i32> %c
}
define <2 x i32> @promlz(<2 x i32> %a) nounwind {
; CHECK-LABEL: promlz:
; CHECK: # %bb.0:
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrld $1, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrld $2, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrld $4, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrld $8, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrld $16, %xmm1
; CHECK-NEXT: por %xmm1, %xmm0
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-NEXT: pxor %xmm1, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $1, %xmm1
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; CHECK-NEXT: psubb %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlw $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddb %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $4, %xmm1
; CHECK-NEXT: paddb %xmm1, %xmm0
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; CHECK-NEXT: psadbw %xmm1, %xmm2
; CHECK-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: packuswb %xmm2, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> %a, i1 false)
ret <2 x i32> %c
}
define <2 x i32> @prompop(<2 x i32> %a) nounwind {
; CHECK-LABEL: prompop:
; CHECK: # %bb.0:
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $1, %xmm1
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; CHECK-NEXT: psubb %xmm1, %xmm0
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pand %xmm1, %xmm2
; CHECK-NEXT: psrlw $2, %xmm0
; CHECK-NEXT: pand %xmm1, %xmm0
; CHECK-NEXT: paddb %xmm2, %xmm0
; CHECK-NEXT: movdqa %xmm0, %xmm1
; CHECK-NEXT: psrlw $4, %xmm1
; CHECK-NEXT: paddb %xmm1, %xmm0
; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; CHECK-NEXT: psadbw %xmm1, %xmm2
; CHECK-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT: psadbw %xmm1, %xmm0
; CHECK-NEXT: packuswb %xmm2, %xmm0
; CHECK-NEXT: retq
%c = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> %a)
ret <2 x i32> %c
}