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
58 lines
2.0 KiB
LLVM
58 lines
2.0 KiB
LLVM
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s
|
|
|
|
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"
|
|
|
|
@a = common global [2048 x i32] zeroinitializer, align 16
|
|
@b = common global [2048 x i32] zeroinitializer, align 16
|
|
@c = common global [2048 x i32] zeroinitializer, align 16
|
|
|
|
;CHECK-LABEL: @example1(
|
|
;CHECK: load <4 x i32>
|
|
;CHECK: ret void
|
|
define void @example1() {
|
|
br label %1
|
|
|
|
; <label>:
|
|
%indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
|
|
%2 = getelementptr inbounds [2048 x i32], ptr @b, i64 0, i64 %indvars.iv
|
|
%3 = load i32, ptr %2, align 4
|
|
%4 = getelementptr inbounds [2048 x i32], ptr @c, i64 0, i64 %indvars.iv
|
|
%5 = load i32, ptr %4, align 4
|
|
%6 = add nsw i32 %5, %3
|
|
%7 = getelementptr inbounds [2048 x i32], ptr @a, i64 0, i64 %indvars.iv
|
|
store i32 %6, ptr %7, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 8 ; <----- A really small trip count
|
|
br i1 %exitcond, label %8, label %1 ; w/o scalar iteration overhead.
|
|
|
|
; <label>:
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: @bound1(
|
|
;CHECK-NOT: load <4 x i32>
|
|
;CHECK: ret void
|
|
define void @bound1(i32 %k) {
|
|
br label %1
|
|
|
|
; <label>:
|
|
%indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
|
|
%2 = getelementptr inbounds [2048 x i32], ptr @b, i64 0, i64 %indvars.iv
|
|
%3 = load i32, ptr %2, align 4
|
|
%4 = getelementptr inbounds [2048 x i32], ptr @c, i64 0, i64 %indvars.iv
|
|
%5 = load i32, ptr %4, align 4
|
|
%6 = add nsw i32 %5, %3
|
|
%7 = getelementptr inbounds [2048 x i32], ptr @a, i64 0, i64 %indvars.iv
|
|
store i32 %6, ptr %7, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%large = icmp sge i32 %lftr.wideiv, 8
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %k
|
|
%realexit = or i1 %large, %exitcond
|
|
br i1 %realexit, label %8, label %1
|
|
|
|
; <label>:
|
|
ret void
|
|
}
|