From d461dcfa0684db5251a7d3cae8d6cff3b45036d3 Mon Sep 17 00:00:00 2001 From: Teresa Johnson Date: Mon, 24 Apr 2017 20:30:42 +0000 Subject: [PATCH] Update profile during memory instrinsic optimization Summary: Ensure that the new merge BB (which contains the rest of the original BB after the mem op being optimized) gets a profile frequency, in case there are additional mem ops later in the BB. Otherwise they get skipped as the merge BB looks cold. Reviewers: davidxl, xur Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D32447 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301244 91177308-0d34-0410-b5e6-96231b3b80d8 --- .../Instrumentation/IndirectCallPromotion.cpp | 4 +++- test/Transforms/PGOProfile/memop_size_opt.ll | 21 ++++++++++++++----- 2 files changed, 19 insertions(+), 6 deletions(-) diff --git a/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp b/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp index 61d627673c9..d7eb857cff7 100644 --- a/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp +++ b/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp @@ -943,14 +943,16 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) { BasicBlock *BB = MI->getParent(); DEBUG(dbgs() << "\n\n== Basic Block Before ==\n"); DEBUG(dbgs() << *BB << "\n"); + auto OrigBBFreq = BFI.getBlockFreq(BB); BasicBlock *DefaultBB = SplitBlock(BB, MI); BasicBlock::iterator It(*MI); ++It; assert(It != DefaultBB->end()); BasicBlock *MergeBB = SplitBlock(DefaultBB, &(*It)); - DefaultBB->setName("MemOP.Default"); MergeBB->setName("MemOP.Merge"); + BFI.setBlockFreq(MergeBB, OrigBBFreq.getFrequency()); + DefaultBB->setName("MemOP.Default"); auto &Ctx = Func.getContext(); IRBuilder<> IRB(BB); diff --git a/test/Transforms/PGOProfile/memop_size_opt.ll b/test/Transforms/PGOProfile/memop_size_opt.ll index c7c42f3c1d3..19a2b7ed293 100644 --- a/test/Transforms/PGOProfile/memop_size_opt.ll +++ b/test/Transforms/PGOProfile/memop_size_opt.ll @@ -4,7 +4,7 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" -define void @foo(i8* %dst, i8* %src, i32* %a, i32 %n) !prof !27 { +define void @foo(i8* %dst, i8* %src, i8* %dst2, i8* %src2, i32* %a, i32 %n) !prof !27 { entry: br label %for.cond @@ -28,19 +28,29 @@ for.body3: %add = add nsw i32 %i.0, 1 %conv = sext i32 %add to i64 call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !30 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i32 1, i1 false), !prof !31 br label %for.inc -; MEMOP_OPT: switch i64 %conv, label %[[Default_LABEL:.*]] [ +; MEMOP_OPT: switch i64 %conv, label %[[DEFAULT_LABEL:.*]] [ ; MEMOP_OPT: i64 1, label %[[CASE_1_LABEL:.*]] ; MEMOP_OPT: ], !prof [[SWITCH_BW:![0-9]+]] ; MEMOP_OPT: [[CASE_1_LABEL]]: ; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i32 1, i1 false) ; MEMOP_OPT: br label %[[MERGE_LABEL:.*]] -; MEMOP_OPT: [[Default_LABEL]]: -; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false) -; MEMOP_OPT-NOT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof +; MEMOP_OPT: [[DEFAULT_LABEL]]: +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false){{[[:space:]]}} ; MEMOP_OPT: br label %[[MERGE_LABEL]] ; MEMOP_OPT: [[MERGE_LABEL]]: +; MEMOP_OPT: switch i64 %conv, label %[[DEFAULT_LABEL2:.*]] [ +; MEMOP_OPT: i64 1, label %[[CASE_1_LABEL2:.*]] +; MEMOP_OPT: ], !prof [[SWITCH_BW:![0-9]+]] +; MEMOP_OPT: [[CASE_1_LABEL2]]: +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 1, i32 1, i1 false) +; MEMOP_OPT: br label %[[MERGE_LABEL2:.*]] +; MEMOP_OPT: [[DEFAULT_LABEL2]]: +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i32 1, i1 false){{[[:space:]]}} +; MEMOP_OPT: br label %[[MERGE_LABEL2]] +; MEMOP_OPT: [[MERGE_LABEL2]]: ; MEMOP_OPT: br label %for.inc ; MEMOP_OPT: [[SWITCH_BW]] = !{!"branch_weights", i32 457, i32 99} @@ -92,6 +102,7 @@ for.end6: !28 = !{!"branch_weights", i32 20, i32 1} !29 = !{!"branch_weights", i32 556, i32 20} !30 = !{!"VP", i32 1, i64 556, i64 1, i64 99, i64 2, i64 88, i64 3, i64 77, i64 9, i64 72, i64 4, i64 66, i64 5, i64 55, i64 6, i64 44, i64 7, i64 33, i64 8, i64 22} +!31 = !{!"VP", i32 1, i64 556, i64 1, i64 99, i64 2, i64 88, i64 3, i64 77, i64 9, i64 72, i64 4, i64 66, i64 5, i64 55, i64 6, i64 44, i64 7, i64 33, i64 8, i64 22} declare void @llvm.lifetime.start(i64, i8* nocapture) -- 2.40.0