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
62 lines
1.9 KiB
LLVM
62 lines
1.9 KiB
LLVM
; RUN: opt -S -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck %s
|
|
target datalayout = "e-p:32:32:32-S128-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f16:16:16-f32:32:32-f64:32:64-f128:128:128-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32"
|
|
|
|
|
|
; We can vectorize this code because if the address computation would wrap then
|
|
; a load from 0 would take place which is undefined behaviour in address space 0
|
|
; according to LLVM IR semantics.
|
|
|
|
; PR16592
|
|
|
|
; CHECK-LABEL: @safe(
|
|
; CHECK: <4 x float>
|
|
|
|
define void @safe(ptr %A, ptr %B, float %K) {
|
|
entry:
|
|
br label %"<bb 3>"
|
|
|
|
"<bb 3>":
|
|
%i_15 = phi i32 [ 0, %entry ], [ %i_19, %"<bb 3>" ]
|
|
%pp3 = getelementptr float, ptr %A, i32 %i_15
|
|
%D.1396_10 = load float, ptr %pp3, align 4
|
|
%pp24 = getelementptr float, ptr %B, i32 %i_15
|
|
%D.1398_15 = load float, ptr %pp24, align 4
|
|
%D.1399_17 = fadd float %D.1398_15, %K
|
|
%D.1400_18 = fmul float %D.1396_10, %D.1399_17
|
|
store float %D.1400_18, ptr %pp3, align 4
|
|
%i_19 = add nsw i32 %i_15, 1
|
|
%exitcond = icmp ne i32 %i_19, 64
|
|
br i1 %exitcond, label %"<bb 3>", label %return
|
|
|
|
return:
|
|
ret void
|
|
}
|
|
|
|
; In a non-default address space we don't have this rule.
|
|
|
|
; CHECK-LABEL: @notsafe(
|
|
; CHECK-NOT: <4 x float>
|
|
|
|
define void @notsafe(ptr addrspace(5) %A, ptr %B, float %K) {
|
|
entry:
|
|
br label %"<bb 3>"
|
|
|
|
"<bb 3>":
|
|
%i_15 = phi i32 [ 0, %entry ], [ %i_19, %"<bb 3>" ]
|
|
%pp3 = getelementptr float, ptr addrspace(5) %A, i32 %i_15
|
|
%D.1396_10 = load float, ptr addrspace(5) %pp3, align 4
|
|
%pp24 = getelementptr float, ptr %B, i32 %i_15
|
|
%D.1398_15 = load float, ptr %pp24, align 4
|
|
%D.1399_17 = fadd float %D.1398_15, %K
|
|
%D.1400_18 = fmul float %D.1396_10, %D.1399_17
|
|
store float %D.1400_18, ptr addrspace(5) %pp3, align 4
|
|
%i_19 = add nsw i32 %i_15, 1
|
|
%exitcond = icmp ne i32 %i_19, 64
|
|
br i1 %exitcond, label %"<bb 3>", label %return
|
|
|
|
return:
|
|
ret void
|
|
}
|
|
|
|
|