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
44 lines
1.7 KiB
LLVM
44 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
|
|
; RUN: opt -S < %s -p loop-vectorize -force-vector-width=4 | FileCheck %s
|
|
|
|
define void @preserve_trunc_flags(ptr %p) {
|
|
; CHECK-LABEL: define void @preserve_trunc_flags(
|
|
; CHECK-SAME: ptr [[P:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
|
|
; CHECK: [[VECTOR_PH]]:
|
|
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
|
|
; CHECK: [[VECTOR_BODY]]:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = trunc nuw i64 [[INDEX]] to i32
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr [8 x i8], ptr [[P]], i32 [[TMP0]]
|
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP1]], align 8
|
|
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i64> [[WIDE_LOAD]], splat (i64 42)
|
|
; CHECK-NEXT: store <4 x i64> [[TMP2]], ptr [[TMP1]], align 8
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 100
|
|
; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: [[MIDDLE_BLOCK]]:
|
|
; CHECK-NEXT: br label %[[EXIT:.*]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %header
|
|
|
|
header:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %header ]
|
|
; We can preserve nuw flags in the vectorized code:
|
|
%trunc = trunc nuw i64 %iv to i32
|
|
%gep = getelementptr [8 x i8], ptr %p, i32 %trunc
|
|
%load = load i64, ptr %gep, align 8
|
|
%add = add i64 %load, 42
|
|
store i64 %add, ptr %gep, align 8
|
|
%iv.next = add i64 %iv, 1
|
|
%ec = icmp eq i64 %iv.next, 100
|
|
br i1 %ec, label %exit, label %header
|
|
|
|
exit:
|
|
ret void
|
|
}
|