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
48 lines
2.5 KiB
LLVM
48 lines
2.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
|
|
; RUN: opt -mtriple=riscv64 -cache-line-size=64 -prefetch-distance=64 \
|
|
; RUN: -passes=loop-data-prefetch -S < %s | FileCheck %s
|
|
|
|
define void @foo(ptr nocapture %a, ptr nocapture readonly %b) {
|
|
; CHECK-LABEL: define void @foo(
|
|
; CHECK-SAME: ptr captures(none) [[A:%.*]], ptr readonly captures(none) [[B:%.*]]) {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[TMP0]], 64
|
|
; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[A]], i64 [[TMP1]]
|
|
; CHECK-NEXT: [[TMP4:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
|
|
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[TMP4]], 64
|
|
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[B]], i64 [[TMP3]]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[B]], i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: call void @llvm.prefetch.p0(ptr [[SCEVGEP]], i32 0, i32 3, i32 1)
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load double, ptr [[ARRAYIDX]], align 8
|
|
; CHECK-NEXT: [[ADD:%.*]] = fadd double [[TMP2]], 1.000000e+00
|
|
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[A]], i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: call void @llvm.prefetch.p0(ptr [[SCEVGEP1]], i32 1, i32 3, i32 1)
|
|
; CHECK-NEXT: store double [[ADD]], ptr [[ARRAYIDX2]], align 8
|
|
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1600
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds double, ptr %b, i64 %indvars.iv
|
|
%0 = load double, ptr %arrayidx, align 8
|
|
%add = fadd double %0, 1.000000e+00
|
|
%arrayidx2 = getelementptr inbounds double, ptr %a, i64 %indvars.iv
|
|
store double %add, ptr %arrayidx2, align 8
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 1600
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|