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
69 lines
3.3 KiB
LLVM
69 lines
3.3 KiB
LLVM
; RUN: opt -force-vector-interleave=2 -force-vector-width=4 -passes=loop-vectorize -pass-remarks-analysis=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s
|
|
|
|
; CHECK: remark: mixed-precision.c:3:26: floating point conversion changes vector width. Mixed floating point precision requires an up/down cast that will negatively impact performance.
|
|
define void @f(ptr noalias nocapture %X, i64 %N) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
|
|
for.body:
|
|
%i = phi i64 [ %inc, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds float, ptr %X, i64 %i
|
|
%0 = load float, ptr %arrayidx, align 4
|
|
%conv = fpext float %0 to double, !dbg !9
|
|
%mul = fmul double %conv, 0x3FD5555555555555
|
|
%conv3 = fptrunc double %mul to float
|
|
store float %conv3, ptr %arrayidx, align 4
|
|
%inc = add nuw i64 %i, 1
|
|
%exitcond.not = icmp eq i64 %inc, %N
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
}
|
|
|
|
; CHECK: remark: mixed-precision.c:8:8: floating point conversion changes vector width. Mixed floating point precision requires an up/down cast that will negatively impact performance.
|
|
; CHECK: remark: mixed-precision.c:7:16: floating point conversion changes vector width. Mixed floating point precision requires an up/down cast that will negatively impact performance.
|
|
; CHECK-NOT: remark: mixed-precision.c:7:16: floating point conversion changes vector width. Mixed floating point precision requires an up/down cast that will negatively impact performance.
|
|
define void @g(ptr noalias nocapture %X, ptr noalias nocapture %Y, i64 %N) {
|
|
entry:
|
|
%pi = alloca double
|
|
store double 0x400921FB54442D18, ptr %pi
|
|
%fac = load double, ptr %pi
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i = phi i64 [ %inc, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds float, ptr %X, i64 %i
|
|
%0 = load float, ptr %arrayidx, align 4
|
|
%conv = fpext float %0 to double, !dbg !10
|
|
%mul = fmul double %conv, %fac
|
|
%conv1 = fptrunc double %mul to float
|
|
store float %conv1, ptr %arrayidx, align 4
|
|
%arrayidx5 = getelementptr inbounds float, ptr %Y, i64 %i
|
|
%1 = load float, ptr %arrayidx5, align 4
|
|
%conv2 = fpext float %1 to double, !dbg !11
|
|
%mul2 = fmul double %conv2, %fac
|
|
%conv3 = fptrunc double %mul2 to float
|
|
store float %conv3, ptr %arrayidx5, align 4
|
|
%inc = add nuw nsw i64 %i, 1
|
|
%exitcond.not = icmp eq i64 %inc, %N
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|
|
|
|
!llvm.dbg.cu = !{!0}
|
|
!llvm.module.flags = !{!3}
|
|
|
|
!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 12.0.0", isOptimized: true, runtimeVersion: 0, emissionKind: NoDebug, enums: !2, splitDebugInlining: false, nameTableKind: None)
|
|
!1 = !DIFile(filename: "mixed-precision.c", directory: "/tmp/mixed-precision.c")
|
|
!2 = !{}
|
|
!3 = !{i32 2, !"Debug Info Version", i32 3}
|
|
!6 = distinct !DISubprogram(name: "f", scope: !1, file: !1, line: 1, type: !8, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
|
|
!7 = distinct !DISubprogram(name: "g", scope: !1, file: !1, line: 5, type: !8, scopeLine: 5, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
|
|
!8 = !DISubroutineType(types: !2)
|
|
!9 = !DILocation(line: 3, column: 26, scope: !6)
|
|
!10 = !DILocation(line: 7, column: 16, scope: !7)
|
|
!11 = !DILocation(line: 8, column: 8, scope: !7)
|