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
46 lines
2.2 KiB
LLVM
46 lines
2.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^vector.ph:" --version 5
|
|
; RUN: opt -S -force-partial-aliasing-vectorization -force-target-supports-masked-memory-ops -tail-folding-policy=must-fold-tail -force-vector-width=4 -passes=loop-vectorize %s | FileCheck %s
|
|
|
|
target datalayout = "p0:64:64:64:16"
|
|
|
|
; Tests we correctly handle the extend for "NUM_ACTIVE_LANES" when the GEP index
|
|
; is smaller than the IV type.
|
|
define void @alias_mask(ptr noalias %a, ptr %b, ptr %c, i64 %n) {
|
|
; CHECK-LABEL: define void @alias_mask(
|
|
; CHECK-SAME: ptr noalias [[A:%.*]], ptr [[B:%.*]], ptr [[C:%.*]], i64 [[N:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[B2:%.*]] = ptrtoaddr ptr [[B]] to i16
|
|
; CHECK-NEXT: [[C1:%.*]] = ptrtoaddr ptr [[C]] to i16
|
|
; CHECK-NEXT: br label %[[VECTOR_CLAMPED_VF_CHECK:.*]]
|
|
; CHECK: [[VECTOR_CLAMPED_VF_CHECK]]:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = call <4 x i1> @llvm.loop.dependence.war.mask.v4i1.i16(i16 [[B2]], i16 [[C1]], i16 1)
|
|
; CHECK-NEXT: [[TMP1:%.*]] = zext <4 x i1> [[TMP0]] to <4 x i16>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> [[TMP1]])
|
|
; CHECK-NEXT: [[NUM_ACTIVE_LANES:%.*]] = zext i16 [[TMP2]] to i64
|
|
; CHECK-NEXT: [[VF_IS_SCALAR:%.*]] = icmp ule i64 [[NUM_ACTIVE_LANES]], 1
|
|
; CHECK-NEXT: [[TMP5:%.*]] = sub i64 -1, [[N]]
|
|
; CHECK-NEXT: [[VF_STEP_OVERFLOW:%.*]] = icmp ult i64 [[TMP5]], [[NUM_ACTIVE_LANES]]
|
|
; CHECK-NEXT: [[TMP6:%.*]] = or i1 [[VF_IS_SCALAR]], [[VF_STEP_OVERFLOW]]
|
|
; CHECK-NEXT: br i1 [[TMP6]], [[SCALAR_PH:label %.*]], label %[[VECTOR_PH:.*]]
|
|
; CHECK: [[VECTOR_PH]]:
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%gep.a = getelementptr inbounds i8, ptr %a, i64 %iv
|
|
%load.a = load i8, ptr %gep.a, align 1
|
|
%gep.b = getelementptr inbounds i8, ptr %b, i64 %iv
|
|
%load.b = load i8, ptr %gep.b, align 1
|
|
%add = add i8 %load.b, %load.a
|
|
%gep.c = getelementptr inbounds i8, ptr %c, i64 %iv
|
|
store i8 %add, ptr %gep.c, align 1
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv.next, %n
|
|
br i1 %exitcond.not, label %exit, label %for.body
|
|
|
|
exit:
|
|
ret void
|
|
}
|