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
71 lines
2.4 KiB
LLVM
71 lines
2.4 KiB
LLVM
; RUN: opt -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %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 [1024 x float] zeroinitializer, align 16
|
|
@B = common global [1024 x float] zeroinitializer, align 16
|
|
|
|
; Make sure we can vectorize in the presence of hoistable conditional loads.
|
|
; CHECK-LABEL: @hoist_cond_load(
|
|
; CHECK: load <2 x float>
|
|
|
|
define void @hoist_cond_load() {
|
|
entry:
|
|
br label %for.body
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
|
|
%arrayidx = getelementptr inbounds [1024 x float], ptr @A, i64 0, i64 %indvars.iv
|
|
%arrayidx2 = getelementptr inbounds [1024 x float], ptr @B, i64 0, i64 %indvars.iv
|
|
%0 = load float, ptr %arrayidx2, align 4
|
|
%cmp3 = fcmp oeq float %0, 0.000000e+00
|
|
br i1 %cmp3, label %if.end9, label %if.else
|
|
|
|
if.else:
|
|
%1 = load float, ptr %arrayidx, align 4
|
|
br label %if.end9
|
|
|
|
if.end9:
|
|
%tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
|
|
store float %tmp.0, ptr %arrayidx, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp ne i32 %lftr.wideiv, 1024
|
|
br i1 %exitcond, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
; However, we can't hoist loads whose address we have not seen unconditionally
|
|
; accessed. One wide load is fine, but not the second.
|
|
; CHECK-LABEL: @dont_hoist_cond_load(
|
|
; CHECK: load <2 x float>
|
|
; CHECK-NOT: load <2 x float>
|
|
|
|
define void @dont_hoist_cond_load(ptr %a) {
|
|
entry:
|
|
br label %for.body
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
|
|
%arrayidx = getelementptr inbounds [1024 x float], ptr %a, i64 0, i64 %indvars.iv
|
|
%arrayidx2 = getelementptr inbounds [1024 x float], ptr @B, i64 0, i64 %indvars.iv
|
|
%0 = load float, ptr %arrayidx2, align 4
|
|
%cmp3 = fcmp oeq float %0, 0.000000e+00
|
|
br i1 %cmp3, label %if.end9, label %if.else
|
|
|
|
if.else:
|
|
%1 = load float, ptr %arrayidx, align 4
|
|
br label %if.end9
|
|
|
|
if.end9:
|
|
%tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
|
|
store float %tmp.0, ptr %arrayidx2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp ne i32 %lftr.wideiv, 1024
|
|
br i1 %exitcond, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|