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
53 lines
1.9 KiB
LLVM
53 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mattr=+sve -aarch64-sve-vector-bits-min=256 < %s | FileCheck %s
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
define <4 x i32> @test(ptr %arg1, ptr %arg2) {
|
|
; CHECK-LABEL: test:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.s, vl8
|
|
; CHECK-NEXT: mov x8, #8 // =0x8
|
|
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x0, x8, lsl #2]
|
|
; CHECK-NEXT: ld1w { z2.s }, p0/z, [x0]
|
|
; CHECK-NEXT: movprfx z0, z1
|
|
; CHECK-NEXT: ext z0.b, z0.b, z1.b, #16
|
|
; CHECK-NEXT: add z1.s, z1.s, z1.s
|
|
; CHECK-NEXT: add z2.s, z2.s, z2.s
|
|
; CHECK-NEXT: dup v0.4s, v0.s[2]
|
|
; CHECK-NEXT: st1w { z1.s }, p0, [x0, x8, lsl #2]
|
|
; CHECK-NEXT: st1w { z2.s }, p0, [x0]
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%0 = load <16 x i32>, ptr %arg1, align 256
|
|
%1 = load <16 x i32>, ptr %arg2, align 256
|
|
%shvec = shufflevector <16 x i32> %0, <16 x i32> %1, <4 x i32> <i32 14, i32 14, i32 14, i32 14>
|
|
%2 = add <16 x i32> %0, %0
|
|
store <16 x i32> %2, ptr %arg1, align 256
|
|
ret <4 x i32> %shvec
|
|
}
|
|
|
|
define <2 x i32> @test2(ptr %arg1, ptr %arg2) {
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.s, vl8
|
|
; CHECK-NEXT: mov x8, #8 // =0x8
|
|
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x0, x8, lsl #2]
|
|
; CHECK-NEXT: ld1w { z2.s }, p0/z, [x0]
|
|
; CHECK-NEXT: movprfx z0, z1
|
|
; CHECK-NEXT: ext z0.b, z0.b, z1.b, #24
|
|
; CHECK-NEXT: add z1.s, z1.s, z1.s
|
|
; CHECK-NEXT: add z2.s, z2.s, z2.s
|
|
; CHECK-NEXT: dup v0.2s, v0.s[0]
|
|
; CHECK-NEXT: st1w { z1.s }, p0, [x0, x8, lsl #2]
|
|
; CHECK-NEXT: st1w { z2.s }, p0, [x0]
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%0 = load <16 x i32>, ptr %arg1, align 256
|
|
%1 = load <16 x i32>, ptr %arg2, align 256
|
|
%shvec = shufflevector <16 x i32> %0, <16 x i32> %1, <2 x i32> <i32 14, i32 14>
|
|
%2 = add <16 x i32> %0, %0
|
|
store <16 x i32> %2, ptr %arg1, align 256
|
|
ret <2 x i32> %shvec
|
|
}
|