This is an archive of the discontinued LLVM Phabricator instance.

Differential D114526

[LV][NFC] New test case for compile time known trip count (TC)
ClosedPublic

Authored by ebrevnov on Nov 24 2021, 4:53 AM.

Details

Reviewers
fhahn
Commits
rGeef8f3f85679: [LV][NFC] New test case for compile time known trip count (TC)
Summary

New test to test/track upcoming chnages

Diff Detail

Event Timeline

ebrevnov requested review of this revision.Nov 24 2021, 4:53 AM
ebrevnov created this revision.
Herald added a project: Restricted Project. · View Herald TranscriptNov 24 2021, 4:53 AM
Herald added a subscriber: llvm-commits. · View Herald Transcript
ebrevnov added a child revision: D114528: [LV] Make sure VF doesn't exceed compile time known TC.Nov 24 2021, 5:15 AM
Harbormaster completed remote builds in B135821: Diff 389465.Nov 24 2021, 5:43 AM
fhahn added a subscriber: fhahn.Dec 3 2021, 2:57 AM
fhahn added inline comments.
llvm/test/Transforms/LoopVectorize/X86/known_TC.ll
1

It might be good to have a slightly more descriptive name for the test file, like limit-vf-by-tripcount.ll or something like that.

ebrevnov added inline comments.Dec 3 2021, 3:48 AM
llvm/test/Transforms/LoopVectorize/X86/known_TC.ll
1

Sounds reasonable. Will fix.

ebrevnov updated this revision to Diff 393387.Dec 10 2021, 12:09 AM

Renamed

ebrevnov added a reviewer: fhahn.Dec 10 2021, 12:33 AM
Harbormaster completed remote builds in B138598: Diff 393387.Dec 10 2021, 12:46 AM
fhahn accepted this revision.Dec 10 2021, 1:35 AM

LGTM, thanks!

This revision is now accepted and ready to land.Dec 10 2021, 1:35 AM
Closed by commit rGeef8f3f85679: [LV][NFC] New test case for compile time known trip count (TC) (authored by Evgeniy Brevnov <ybrevnov@azul.com>). · Explain WhyDec 10 2021, 3:26 AM
This revision was automatically updated to reflect the committed changes.
Evgeniy Brevnov <ybrevnov@azul.com> added a commit: rGeef8f3f85679: [LV][NFC] New test case for compile time known trip count (TC).

Revision Contents

PathSize
llvm/
test/
Transforms/
LoopVectorize/
X86/
90 lines

Diff 389465

llvm/test/Transforms/LoopVectorize/X86/known_TC.ll

  • This file was added.
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
fhahnUnsubmitted
Not Done
ReplyInline Actions

It might be good to have a slightly more descriptive name for the test file, like limit-vf-by-tripcount.ll or something like that.

fhahn: It might be good to have a slightly more descriptive name for the test file, like `limit-vf-by…
ebrevnovAuthorUnsubmitted
Done
ReplyInline Actions

Sounds reasonable. Will fix.

ebrevnov: Sounds reasonable. Will fix.
; RUN: opt -loop-vectorize -S %s | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128-ni:1-p2:32:8:8:32-ni:2"
target triple = "x86_64-unknown-linux-gnu"
; TODO: Make sure selected VF for the main loop doesn't exceed TC.
; TODO: Make sure selected VF for the epilog loop doesn't exceed remaining TC.
define void @test1(i8 * noalias %src, i8 * noalias %dst) #0 {
; CHECK-LABEL: @test1(
; CHECK-NEXT: iter.check:
; CHECK-NEXT: br i1 true, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK: vector.main.loop.iter.check:
; CHECK-NEXT: br i1 true, label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, i8* [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <64 x i8>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <64 x i8>, <64 x i8>* [[TMP3]], align 64
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i8* [[TMP5]] to <64 x i8>*
; CHECK-NEXT: store <64 x i8> [[WIDE_LOAD]], <64 x i8>* [[TMP6]], align 64
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 64
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 0
; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 17, 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
; CHECK: vec.epilog.iter.check:
; CHECK-NEXT: br i1 true, label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
; CHECK: vec.epilog.ph:
; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ 0, [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
; CHECK: vec.epilog.vector.body:
; CHECK-NEXT: [[INDEX1:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP8:%.*]] = add i64 [[INDEX1]], 0
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP9]], i32 0
; CHECK-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <32 x i8>*
; CHECK-NEXT: [[WIDE_LOAD4:%.*]] = load <32 x i8>, <32 x i8>* [[TMP11]], align 64
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 [[TMP8]]
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, i8* [[TMP12]], i32 0
; CHECK-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to <32 x i8>*
; CHECK-NEXT: store <32 x i8> [[WIDE_LOAD4]], <32 x i8>* [[TMP14]], align 64
; CHECK-NEXT: [[INDEX_NEXT2]] = add nuw i64 [[INDEX1]], 32
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT2]], 0
; CHECK-NEXT: br i1 [[TMP15]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK: vec.epilog.middle.block:
; CHECK-NEXT: [[CMP_N3:%.*]] = icmp eq i64 17, 0
; CHECK-NEXT: br i1 [[CMP_N3]], label [[EXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK: vec.epilog.scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
; CHECK-NEXT: br label [[LOOP_MEMCPY_EXPANSION:%.*]]
; CHECK: loop-memcpy-expansion:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[I_NEXT:%.*]], [[LOOP_MEMCPY_EXPANSION]] ]
; CHECK-NEXT: [[LDADDR:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 [[I]]
; CHECK-NEXT: [[VAL:%.*]] = load i8, i8* [[LDADDR]], align 64
; CHECK-NEXT: [[STADDR:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 [[I]]
; CHECK-NEXT: store i8 [[VAL]], i8* [[STADDR]], align 64
; CHECK-NEXT: [[I_NEXT]] = add i64 [[I]], 1
; CHECK-NEXT: [[IS_NEXT:%.*]] = icmp ult i64 [[I_NEXT]], 17
; CHECK-NEXT: br i1 [[IS_NEXT]], label [[LOOP_MEMCPY_EXPANSION]], label [[EXIT_LOOPEXIT]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: exit.loopexit:
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop-memcpy-expansion
loop-memcpy-expansion:
%i = phi i64 [ 0, %entry ], [ %i.next, %loop-memcpy-expansion ]
%ldaddr = getelementptr inbounds i8, i8 * %src, i64 %i
%val = load i8, i8 * %ldaddr, align 64
%staddr = getelementptr inbounds i8, i8 * %dst, i64 %i
store i8 %val, i8 * %staddr, align 64
%i.next = add i64 %i, 1
%is.next = icmp ult i64 %i.next, 17
br i1 %is.next, label %loop-memcpy-expansion, label %exit
exit:
ret void
}
attributes #0 = { "target-features"="+avx512f" }