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
65 lines
5.3 KiB
LLVM
65 lines
5.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: opt < %s -passes=interleaved-access -mtriple=aarch64-linux-gnu -mattr=+sve -S | FileCheck %s
|
|
|
|
|
|
define void @interleave4(ptr %dst, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c, <vscale x 4 x i32> %d) {
|
|
; CHECK-LABEL: define void @interleave4
|
|
; CHECK-SAME: (ptr [[DST:%.*]], <vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]], <vscale x 4 x i32> [[C:%.*]], <vscale x 4 x i32> [[D:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: call void @llvm.aarch64.sve.st4.nxv4i32.p0(<vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]], <vscale x 4 x i32> [[D]], <vscale x 4 x i1> splat (i1 true), ptr [[DST]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%interleaved.vec = tail call <vscale x 16 x i32> @llvm.vector.interleave4.nxv16i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c, <vscale x 4 x i32> %d)
|
|
store <vscale x 16 x i32> %interleaved.vec, ptr %dst, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @wide_interleave4(ptr %dst, <vscale x 8 x i32> %a, <vscale x 8 x i32> %b, <vscale x 8 x i32> %c, <vscale x 8 x i32> %d) {
|
|
; CHECK-LABEL: define void @wide_interleave4
|
|
; CHECK-SAME: (ptr [[DST:%.*]], <vscale x 8 x i32> [[A:%.*]], <vscale x 8 x i32> [[B:%.*]], <vscale x 8 x i32> [[C:%.*]], <vscale x 8 x i32> [[D:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr <vscale x 4 x i32>, ptr [[DST]], i64 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[A]], i64 0)
|
|
; CHECK-NEXT: [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[B]], i64 0)
|
|
; CHECK-NEXT: [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[C]], i64 0)
|
|
; CHECK-NEXT: [[TMP5:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[D]], i64 0)
|
|
; CHECK-NEXT: call void @llvm.aarch64.sve.st4.nxv4i32.p0(<vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP3]], <vscale x 4 x i32> [[TMP4]], <vscale x 4 x i32> [[TMP5]], <vscale x 4 x i1> splat (i1 true), ptr [[TMP1]])
|
|
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr <vscale x 4 x i32>, ptr [[DST]], i64 4
|
|
; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[A]], i64 4)
|
|
; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[B]], i64 4)
|
|
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[C]], i64 4)
|
|
; CHECK-NEXT: [[TMP10:%.*]] = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[D]], i64 4)
|
|
; CHECK-NEXT: call void @llvm.aarch64.sve.st4.nxv4i32.p0(<vscale x 4 x i32> [[TMP7]], <vscale x 4 x i32> [[TMP8]], <vscale x 4 x i32> [[TMP9]], <vscale x 4 x i32> [[TMP10]], <vscale x 4 x i1> splat (i1 true), ptr [[TMP6]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%interleaved.vec = tail call <vscale x 32 x i32> @llvm.vector.interleave4.nxv32i32(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b, <vscale x 8 x i32> %c, <vscale x 8 x i32> %d)
|
|
store <vscale x 32 x i32> %interleaved.vec, ptr %dst, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @mix_interleave4_interleave2(ptr %dst1, ptr %dst2, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c, <vscale x 4 x i32> %d) {
|
|
; CHECK-LABEL: define void @mix_interleave4_interleave2
|
|
; CHECK-SAME: (ptr [[DST1:%.*]], ptr [[DST2:%.*]], <vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]], <vscale x 4 x i32> [[C:%.*]], <vscale x 4 x i32> [[D:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @llvm.aarch64.sve.st4.nxv4i32.p0(<vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[C]], <vscale x 4 x i32> [[D]], <vscale x 4 x i1> splat (i1 true), ptr [[DST1]])
|
|
; CHECK-NEXT: call void @llvm.aarch64.sve.st2.nxv4i32.p0(<vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[C]], <vscale x 4 x i1> splat (i1 true), ptr [[DST2]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%interleaved.vec = tail call <vscale x 16 x i32> @llvm.vector.interleave4.nxv16i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c, <vscale x 4 x i32> %d)
|
|
store <vscale x 16 x i32> %interleaved.vec, ptr %dst1, align 4
|
|
|
|
%interleaved = tail call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %c)
|
|
store <vscale x 8 x i32> %interleaved, ptr %dst2, align 4
|
|
ret void
|
|
}
|
|
|
|
; This case tests when the interleave is using same parameter twice,
|
|
; the dead parameter will not get deleted twice.
|
|
define void @duplicate_by_interleave(<vscale x 4 x i32> %A, <vscale x 4 x i32> %B, ptr writeonly %AB_duplicate) {
|
|
; CHECK-LABEL: define void @duplicate_by_interleave
|
|
; CHECK-SAME: (<vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[B:%.*]], ptr writeonly [[AB_DUPLICATE:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @llvm.aarch64.sve.st4.nxv4i32.p0(<vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[A]], <vscale x 4 x i32> [[B]], <vscale x 4 x i32> [[B]], <vscale x 4 x i1> splat (i1 true), ptr [[AB_DUPLICATE]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%interleave = tail call <vscale x 16 x i32> @llvm.vector.interleave4.nxv16i32(<vscale x 4 x i32> %A, <vscale x 4 x i32> %A, <vscale x 4 x i32> %B, <vscale x 4 x i32> %B)
|
|
store <vscale x 16 x i32> %interleave, ptr %AB_duplicate, align 4
|
|
ret void
|
|
}
|