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
52 lines
2.0 KiB
LLVM
52 lines
2.0 KiB
LLVM
; REQUIRES: asserts
|
|
; RUN: opt -passes=loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck %s
|
|
; RUN: opt -passes=loop-vectorize -enable-epilogue-vectorization -epilogue-vectorization-force-VF=2 -pass-remarks-analysis=loop-vectorize -S < %s 2>&1 | FileCheck --check-prefix=CHECK-EPILOGUE %s
|
|
|
|
; Make sure the unsafe user specified vectorization factor is clamped.
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
; void foo(int *a, int *b) {
|
|
; #pragma clang loop vectorize(enable) vectorize_width(4)
|
|
; for (int i=0; i < 1024; ++i) {
|
|
; a[i + 2] = a[i] + b[i];
|
|
; }
|
|
; }
|
|
|
|
; CHECK: LV: User VF=4 is unsafe, clamping to max safe VF=2.
|
|
; CHECK: remark: <unknown>:0:0: User-specified vectorization factor 4 is unsafe, clamping to maximum safe vectorization factor 2
|
|
; CHECK: remark: <unknown>:0:0: UserVF ignored because it may be larger than the maximal safe VF
|
|
; CHECK-LABEL: @foo
|
|
; CHECK: <2 x i32>
|
|
; CHECK-EPILOGUE: remark: <unknown>:0:0: UserVF ignored because it may be larger than the maximal safe VF
|
|
; CHECK-EPILOGUE-LABEL: @foo
|
|
; CHECK-EPILOGUE: <2 x i32>
|
|
define void @foo(ptr %a, ptr %b) {
|
|
entry:
|
|
br label %loop.ph
|
|
|
|
loop.ph:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %loop.ph ], [ %iv.next, %loop ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
|
|
%0 = load i32, ptr %arrayidx, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
|
|
%1 = load i32, ptr %arrayidx2, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%2 = add nuw nsw i64 %iv, 2
|
|
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
|
|
store i32 %add, ptr %arrayidx5, align 4
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv.next, 1024
|
|
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !0
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
!0 = !{!0, !1, !2}
|
|
!1 = !{!"llvm.loop.vectorize.width", i32 4}
|
|
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
|