Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/X86/tuning-shuffle-permilps.ll
T
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

115 lines
5.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown --mattr=+avx,+no-bypass-delay-shuffle | FileCheck %s --check-prefixes=CHECK,CHECK-AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown --mattr=+avx | FileCheck %s --check-prefixes=CHECK,CHECK-AVX1-DELAY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown --mattr=+avx2,+no-bypass-delay-shuffle | FileCheck %s --check-prefixes=CHECK,CHECK-AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown --mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,CHECK-AVX2-DELAY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=icelake-server | FileCheck %s --check-prefixes=CHECK,CHECK-ICX,CHECK-ICX-NO-BYPASS-DELAY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=icelake-server -mattr=-no-bypass-delay-shuffle | FileCheck %s --check-prefixes=CHECK,CHECK-ICX,CHECK-ICX-BYPASS-DELAY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge -mattr=+no-bypass-delay-shuffle | FileCheck %s --check-prefixes=CHECK,CHECK-SNB,CHECK-SNB-NO-BYPASS-DELAY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge -mattr=-no-bypass-delay-shuffle | FileCheck %s --check-prefixes=CHECK,CHECK-SNB,CHECK-SNB-BYPASS-DELAY
define <8 x float> @transform_VPERMILPSYrr(<8 x float> %a) nounwind {
; CHECK-LABEL: transform_VPERMILPSYrr:
; CHECK: # %bb.0:
; CHECK-NEXT: vshufps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; CHECK-NEXT: retq
%shufp = shufflevector <8 x float> %a, <8 x float> poison, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shufp
}
define <4 x float> @transform_VPERMILPSrr(<4 x float> %a) nounwind {
; CHECK-LABEL: transform_VPERMILPSrr:
; CHECK: # %bb.0:
; CHECK-NEXT: vshufps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; CHECK-NEXT: retq
%shufp = shufflevector <4 x float> %a, <4 x float> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %shufp
}
define <8 x float> @transform_VPERMILPSYrm(ptr %ap) nounwind {
; CHECK-AVX1-LABEL: transform_VPERMILPSYrm:
; CHECK-AVX1: # %bb.0:
; CHECK-AVX1-NEXT: vpermilps {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-AVX1-NEXT: retq
;
; CHECK-AVX1-DELAY-LABEL: transform_VPERMILPSYrm:
; CHECK-AVX1-DELAY: # %bb.0:
; CHECK-AVX1-DELAY-NEXT: vpermilps {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-AVX1-DELAY-NEXT: retq
;
; CHECK-AVX2-LABEL: transform_VPERMILPSYrm:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: vpermilps {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-AVX2-NEXT: retq
;
; CHECK-AVX2-DELAY-LABEL: transform_VPERMILPSYrm:
; CHECK-AVX2-DELAY: # %bb.0:
; CHECK-AVX2-DELAY-NEXT: vpermilps {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-AVX2-DELAY-NEXT: retq
;
; CHECK-ICX-NO-BYPASS-DELAY-LABEL: transform_VPERMILPSYrm:
; CHECK-ICX-NO-BYPASS-DELAY: # %bb.0:
; CHECK-ICX-NO-BYPASS-DELAY-NEXT: vpshufd {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-ICX-NO-BYPASS-DELAY-NEXT: retq
;
; CHECK-ICX-BYPASS-DELAY-LABEL: transform_VPERMILPSYrm:
; CHECK-ICX-BYPASS-DELAY: # %bb.0:
; CHECK-ICX-BYPASS-DELAY-NEXT: vpermilps {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-ICX-BYPASS-DELAY-NEXT: retq
;
; CHECK-SNB-LABEL: transform_VPERMILPSYrm:
; CHECK-SNB: # %bb.0:
; CHECK-SNB-NEXT: vpermilps {{.*#+}} ymm0 = mem[3,2,1,0,7,6,5,4]
; CHECK-SNB-NEXT: retq
%a = load <8 x float>, ptr %ap
%shufp = shufflevector <8 x float> %a, <8 x float> poison, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shufp
}
define <4 x float> @transform_VPERMILPSrm(ptr %ap) nounwind {
; CHECK-AVX1-LABEL: transform_VPERMILPSrm:
; CHECK-AVX1: # %bb.0:
; CHECK-AVX1-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-AVX1-NEXT: retq
;
; CHECK-AVX1-DELAY-LABEL: transform_VPERMILPSrm:
; CHECK-AVX1-DELAY: # %bb.0:
; CHECK-AVX1-DELAY-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-AVX1-DELAY-NEXT: retq
;
; CHECK-AVX2-LABEL: transform_VPERMILPSrm:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-AVX2-NEXT: retq
;
; CHECK-AVX2-DELAY-LABEL: transform_VPERMILPSrm:
; CHECK-AVX2-DELAY: # %bb.0:
; CHECK-AVX2-DELAY-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-AVX2-DELAY-NEXT: retq
;
; CHECK-ICX-NO-BYPASS-DELAY-LABEL: transform_VPERMILPSrm:
; CHECK-ICX-NO-BYPASS-DELAY: # %bb.0:
; CHECK-ICX-NO-BYPASS-DELAY-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-ICX-NO-BYPASS-DELAY-NEXT: retq
;
; CHECK-ICX-BYPASS-DELAY-LABEL: transform_VPERMILPSrm:
; CHECK-ICX-BYPASS-DELAY: # %bb.0:
; CHECK-ICX-BYPASS-DELAY-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-ICX-BYPASS-DELAY-NEXT: retq
;
; CHECK-SNB-NO-BYPASS-DELAY-LABEL: transform_VPERMILPSrm:
; CHECK-SNB-NO-BYPASS-DELAY: # %bb.0:
; CHECK-SNB-NO-BYPASS-DELAY-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-SNB-NO-BYPASS-DELAY-NEXT: retq
;
; CHECK-SNB-BYPASS-DELAY-LABEL: transform_VPERMILPSrm:
; CHECK-SNB-BYPASS-DELAY: # %bb.0:
; CHECK-SNB-BYPASS-DELAY-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; CHECK-SNB-BYPASS-DELAY-NEXT: retq
%a = load <4 x float>, ptr %ap
%shufp = shufflevector <4 x float> %a, <4 x float> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %shufp
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; CHECK-ICX: {{.*}}