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
84 lines
3.5 KiB
LLVM
84 lines
3.5 KiB
LLVM
; RUN: opt -S -aarch64-sve-intrinsic-opts < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
define void @pred_store_v2i8(<vscale x 16 x i1> %pred, ptr %addr) #0 {
|
|
; CHECK-LABEL: @pred_store_v2i8(
|
|
; CHECK-NEXT: store <vscale x 16 x i1> %pred, ptr %addr
|
|
; CHECK-NEXT: ret void
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <2 x i8> @llvm.vector.extract.v2i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 0)
|
|
store <2 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @pred_store_v4i8(<vscale x 16 x i1> %pred, ptr %addr) #1 {
|
|
; CHECK-LABEL: @pred_store_v4i8(
|
|
; CHECK-NEXT: store <vscale x 16 x i1> %pred, ptr %addr
|
|
; CHECK-NEXT: ret void
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <4 x i8> @llvm.vector.extract.v4i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 0)
|
|
store <4 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @pred_store_v8i8(<vscale x 16 x i1> %pred, ptr %addr) #2 {
|
|
; CHECK-LABEL: @pred_store_v8i8(
|
|
; CHECK-NEXT: store <vscale x 16 x i1> %pred, ptr %addr
|
|
; CHECK-NEXT: ret void
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <8 x i8> @llvm.vector.extract.v8i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 0)
|
|
store <8 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
|
|
; Check that too small of a vscale prevents optimization
|
|
define void @pred_store_neg1(<vscale x 16 x i1> %pred, ptr %addr) #0 {
|
|
; CHECK-LABEL: @pred_store_neg1(
|
|
; CHECK: call <4 x i8> @llvm.vector.extract
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <4 x i8> @llvm.vector.extract.v4i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 0)
|
|
store <4 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
; Check that too large of a vscale prevents optimization
|
|
define void @pred_store_neg2(<vscale x 16 x i1> %pred, ptr %addr) #2 {
|
|
; CHECK-LABEL: @pred_store_neg2(
|
|
; CHECK: call <4 x i8> @llvm.vector.extract
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <4 x i8> @llvm.vector.extract.v4i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 0)
|
|
store <4 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
; Check that a non-zero index prevents optimization
|
|
define void @pred_store_neg3(<vscale x 16 x i1> %pred, ptr %addr) #1 {
|
|
; CHECK-LABEL: @pred_store_neg3(
|
|
; CHECK: call <4 x i8> @llvm.vector.extract
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <4 x i8> @llvm.vector.extract.v4i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 4)
|
|
store <4 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
; Check that differing vscale min/max prevents optimization
|
|
define void @pred_store_neg4(<vscale x 16 x i1> %pred, ptr %addr) #3 {
|
|
; CHECK-LABEL: @pred_store_neg4(
|
|
; CHECK: call <4 x i8> @llvm.vector.extract
|
|
%bitcast = bitcast <vscale x 16 x i1> %pred to <vscale x 2 x i8>
|
|
%extract = tail call <4 x i8> @llvm.vector.extract.v4i8.nxv2i8(<vscale x 2 x i8> %bitcast, i64 0)
|
|
store <4 x i8> %extract, ptr %addr, align 4
|
|
ret void
|
|
}
|
|
|
|
declare <2 x i8> @llvm.vector.extract.v2i8.nxv2i8(<vscale x 2 x i8>, i64)
|
|
declare <4 x i8> @llvm.vector.extract.v4i8.nxv2i8(<vscale x 2 x i8>, i64)
|
|
declare <8 x i8> @llvm.vector.extract.v8i8.nxv2i8(<vscale x 2 x i8>, i64)
|
|
|
|
attributes #0 = { "target-features"="+sve" vscale_range(1,1) }
|
|
attributes #1 = { "target-features"="+sve" vscale_range(2,2) }
|
|
attributes #2 = { "target-features"="+sve" vscale_range(4,4) }
|
|
attributes #3 = { "target-features"="+sve" vscale_range(2,4) }
|