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
141 lines
4.4 KiB
LLVM
141 lines
4.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
|
|
; RUN: -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-aix-xcoff \
|
|
; RUN: -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc-aix-xcoff \
|
|
; RUN: -mcpu=pwr8 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s
|
|
|
|
define void @test1(<16 x i8> %0) {
|
|
; CHECK-LABEL: test1:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> zeroinitializer)
|
|
ret void
|
|
}
|
|
|
|
define void @test2(<8 x i16> %0) {
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> zeroinitializer)
|
|
ret void
|
|
}
|
|
|
|
define void @test3(<16 x i8> %0) {
|
|
; CHECK-LABEL: test3:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> zeroinitializer)
|
|
ret void
|
|
}
|
|
|
|
define void @test4(<16 x i8> %0) {
|
|
; CHECK-LABEL: test4:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vspltisw v3, 1
|
|
; CHECK-NEXT: vsum4sbs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
|
|
ret void
|
|
}
|
|
|
|
define void @test5(<8 x i16> %0) {
|
|
; CHECK-LABEL: test5:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vspltisw v3, 1
|
|
; CHECK-NEXT: vsum4shs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
|
|
ret void
|
|
}
|
|
|
|
define void @test6(<16 x i8> %0) {
|
|
; CHECK-LABEL: test6:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vspltisw v3, 1
|
|
; CHECK-NEXT: vsum4ubs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
|
|
ret void
|
|
}
|
|
|
|
define <4 x i32> @test7(<16 x i8> %0) {
|
|
; CHECK-LABEL: test7:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xxlxor v3, v3, v3
|
|
; CHECK-NEXT: vsum4sbs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> zeroinitializer)
|
|
ret <4 x i32> %1
|
|
}
|
|
|
|
define <4 x i32> @test8(<8 x i16> %0) {
|
|
; CHECK-LABEL: test8:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xxlxor v3, v3, v3
|
|
; CHECK-NEXT: vsum4shs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> zeroinitializer)
|
|
ret <4 x i32> %1
|
|
}
|
|
|
|
define <4 x i32> @test9(<16 x i8> %0) {
|
|
; CHECK-LABEL: test9:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xxlxor v3, v3, v3
|
|
; CHECK-NEXT: vsum4ubs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%1 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> zeroinitializer)
|
|
ret <4 x i32> %1
|
|
}
|
|
|
|
define <4 x i32> @test10(<16 x i8> %0, <16 x i8> %1) {
|
|
; CHECK-LABEL: test10:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xxlxor v3, v3, v3
|
|
; CHECK-NEXT: vsum4sbs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%2 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %0, <4 x i32> zeroinitializer)
|
|
%3 = tail call <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8> %1, <4 x i32> zeroinitializer)
|
|
ret <4 x i32> %2
|
|
}
|
|
|
|
define <4 x i32> @test11(<8 x i16> %0, <8 x i16> %1) {
|
|
; CHECK-LABEL: test11:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xxlxor v3, v3, v3
|
|
; CHECK-NEXT: vsum4shs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%2 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %0, <4 x i32> zeroinitializer)
|
|
%3 = tail call <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16> %1, <4 x i32> zeroinitializer)
|
|
ret <4 x i32> %2
|
|
}
|
|
|
|
define <4 x i32> @test12(<16 x i8> %0, <16 x i8> %1) {
|
|
; CHECK-LABEL: test12:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xxlxor v3, v3, v3
|
|
; CHECK-NEXT: vsum4ubs v2, v2, v3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%2 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %0, <4 x i32> zeroinitializer)
|
|
%3 = tail call <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8> %1, <4 x i32> zeroinitializer)
|
|
ret <4 x i32> %2
|
|
}
|
|
|
|
declare <4 x i32> @llvm.ppc.altivec.vsum4sbs(<16 x i8>, <4 x i32>)
|
|
declare <4 x i32> @llvm.ppc.altivec.vsum4shs(<8 x i16>, <4 x i32>)
|
|
declare <4 x i32> @llvm.ppc.altivec.vsum4ubs(<16 x i8>, <4 x i32>)
|