This is an archive of the discontinued LLVM Phabricator instance.

Differential D136241

[NFC][CostModel] Added floating point frem test for SVE
ClosedPublic

Authored by jolanta.jensen on Oct 19 2022, 3:37 AM.

Details

Reviewers
paulwalker-arm
mgabka
Commits
rG66e3589cd75d: [NFC][CostModel] Added floating point frem test for SVE

Diff Detail

Event Timeline

jolanta.jensen created this revision.Oct 19 2022, 3:37 AM
Herald added a project: Restricted Project. · View Herald TranscriptOct 19 2022, 3:37 AM
Herald added a subscriber: tschuett. · View Herald Transcript
jolanta.jensen requested review of this revision.Oct 19 2022, 3:37 AM
Herald added a project: Restricted Project. · View Herald TranscriptOct 19 2022, 3:37 AM
Herald added a subscriber: llvm-commits. · View Herald Transcript
jolanta.jensen added a reviewer: paulwalker-arm.Oct 19 2022, 3:39 AM
jolanta.jensen added a reviewer: mgabka.
Harbormaster completed remote builds in B192960: Diff 468853.Oct 19 2022, 4:25 AM
paulwalker-arm accepted this revision.Oct 19 2022, 5:08 AM
This revision is now accepted and ready to land.Oct 19 2022, 5:08 AM
Matt added a subscriber: Matt.Oct 19 2022, 5:16 AM
Closed by commit rG66e3589cd75d: [NFC][CostModel] Added floating point frem test for SVE (authored by jolanta.jensen). · Explain WhyOct 19 2022, 12:35 PM
This revision was automatically updated to reflect the committed changes.
jolanta.jensen added a commit: rG66e3589cd75d: [NFC][CostModel] Added floating point frem test for SVE.

Revision Contents

PathSize
llvm/
test/
Analysis/
CostModel/
AArch64/
26 lines

Diff 469011

llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll

Show First 20 Lines • Show All 128 Lines • ▼ Show 20 Lines;
%V4F32 = fdiv <vscale x 4 x float> undef, undef %V4F32 = fdiv <vscale x 4 x float> undef, undef
%V8F32 = fdiv <vscale x 8 x float> undef, undef %V8F32 = fdiv <vscale x 8 x float> undef, undef
%V2F64 = fdiv <vscale x 2 x double> undef, undef %V2F64 = fdiv <vscale x 2 x double> undef, undef
%V4F64 = fdiv <vscale x 4 x double> undef, undef %V4F64 = fdiv <vscale x 4 x double> undef, undef
ret void ret void
} }
define void @frem() {
; CHECK-LABEL: 'frem'
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V4F16 = frem <vscale x 4 x half> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V8F16 = frem <vscale x 8 x half> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V16F16 = frem <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V2F32 = frem <vscale x 2 x float> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V4F32 = frem <vscale x 4 x float> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V8F32 = frem <vscale x 8 x float> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V2F64 = frem <vscale x 2 x double> undef, undef
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V4F64 = frem <vscale x 4 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V4F16 = frem <vscale x 4 x half> undef, undef
%V8F16 = frem <vscale x 8 x half> undef, undef
%V16F16 = frem <vscale x 16 x half> undef, undef
%V2F32 = frem <vscale x 2 x float> undef, undef
%V4F32 = frem <vscale x 4 x float> undef, undef
%V8F32 = frem <vscale x 8 x float> undef, undef
%V2F64 = frem <vscale x 2 x double> undef, undef
%V4F64 = frem <vscale x 4 x double> undef, undef
ret void
}