Index: lib/ProfileData/InstrProf.cpp =================================================================== --- lib/ProfileData/InstrProf.cpp +++ lib/ProfileData/InstrProf.cpp @@ -136,6 +136,9 @@ // (when \c InLTO is true): LTO's internalization privatizes many global linkage // symbols. This happens after value profile annotation, but those internal // linkage functions should not have a source prefix. +// Additionally, for ThinLTO mode, exported internal functions are promoted +// and renamed. We need to ensure that the original internal PGO name is +// used when computing the GUID that is compared against the profiled GUIDs. // To differentiate compiler generated internal symbols from original ones, // PGOFuncName meta data are created and attached to the original internal // symbols in the value profile annotation step Index: lib/Transforms/IPO/PassManagerBuilder.cpp =================================================================== --- lib/Transforms/IPO/PassManagerBuilder.cpp +++ lib/Transforms/IPO/PassManagerBuilder.cpp @@ -373,6 +373,7 @@ void PassManagerBuilder::populateModulePassManager( legacy::PassManagerBase &MPM) { + // Allow forcing function attributes as a debugging and tuning aid. MPM.add(createForceFunctionAttrsLegacyPass()); @@ -405,6 +406,12 @@ addInitialAliasAnalysisPasses(MPM); + // For ThinLTO we perform indirect call promotion early, before globalopt. + // Otherwise imported available_externally functions look unreferenced and + // are removed. + if (PerformThinLTO) + MPM.add(createPGOIndirectCallPromotionLegacyPass(/*InLTO = */ true)); + if (!DisableUnitAtATime) { // Infer attributes about declarations if possible. MPM.add(createInferFunctionAttrsLegacyPass()); @@ -427,11 +434,12 @@ /// PGO instrumentation is added during the compile phase for ThinLTO, do /// not run it a second time addPGOInstrPasses(MPM); + // Indirect call promotion that promotes intra-module targets only. + // For ThinLTO this is done earlier due to interactions with globalopt + // for imported functions. + MPM.add(createPGOIndirectCallPromotionLegacyPass()); } - // Indirect call promotion that promotes intra-module targets only. - MPM.add(createPGOIndirectCallPromotionLegacyPass()); - if (EnableNonLTOGlobalsModRef) // We add a module alias analysis pass here. In part due to bugs in the // analysis infrastructure this "works" in that the analysis stays alive Index: test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll =================================================================== --- test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll +++ test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll @@ -1,7 +1,16 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" +source_filename = "thinlto_indirect_call_promotion.c" + define void @a() { entry: ret void } + +define internal void @c() !PGOFuncName !1 { +entry: + ret void +} + +!1 = !{!"thinlto_indirect_call_promotion.c:c"} Index: test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll =================================================================== --- test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll +++ test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll @@ -4,26 +4,33 @@ ; RUN: llvm-lto -thinlto -o %t3 %t.bc %t2.bc ; RUN: opt -function-import -summary-file %t3.thinlto.bc %t.bc -o %t4.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS -; IMPORTS: Import a +; IMPORTS-DAG: Import a +; IMPORTS-DAG: Import c -; RUN: opt %t4.bc -pgo-icall-prom -S -icp-count-threshold=1 | FileCheck %s --check-prefix=ICALL-PROM -; RUN: opt %t4.bc -pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-count-threshold=1 2>&1 | FileCheck %s --check-prefix=PASS-REMARK +; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S -icp-count-threshold=1 | FileCheck %s --check-prefix=ICALL-PROM +; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-count-threshold=1 2>&1 | FileCheck %s --check-prefix=PASS-REMARK ; PASS-REMARK: Promote indirect call to a with count 1 out of 1 +; PASS-REMARK: Promote indirect call to c.llvm.0 with count 1 out of 1 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" @foo = external local_unnamed_addr global void ()*, align 8 +@bar = external local_unnamed_addr global void ()*, align 8 define i32 @main() local_unnamed_addr { entry: %0 = load void ()*, void ()** @foo, align 8 ; ICALL-PROM: br i1 %{{[0-9]+}}, label %if.true.direct_targ, label %if.false.orig_indirect, !prof [[BRANCH_WEIGHT:![0-9]+]] tail call void %0(), !prof !1 + %1 = load void ()*, void ()** @bar, align 8 +; ICALL-PROM: br i1 %{{[0-9]+}}, label %if.true.direct_targ1, label %if.false.orig_indirect2, !prof [[BRANCH_WEIGHT:![0-9]+]] + tail call void %1(), !prof !2 ret i32 0 } !1 = !{!"VP", i32 0, i64 1, i64 -6289574019528802036, i64 1} +!2 = !{!"VP", i32 0, i64 1, i64 591260329866125152, i64 1} ; Should not have a VP annotation on new indirect call (check before and after ; branch_weights annotation).