Add CallSiteSplitting pass

Summary: This change add a pass which tries to split a call-site to pass more constrained arguments if its argument is predicated in the control flow so that we can expose better context to the later passes (e.g, inliner, jump threading, or IPA-CP based function cloning, etc.). As of now we support two cases : 1) If a call site is dominated by an OR condition and if any of its arguments are predicated on this OR condition, try to split the condition with more constrained arguments. For example, in the code below, we try to split the call site since we can predicate the argument (ptr) based on the OR condition. Split from : if (!ptr || c) callee(ptr); to : if (!ptr) callee(null ptr) // set the known constant value else if (c) callee(nonnull ptr) // set non-null attribute in the argument 2) We can also split a call-site based on constant incoming values of a PHI For example, from : BB0: %c = icmp eq i32 %i1, %i2 br i1 %c, label %BB2, label %BB1 BB1: br label %BB2 BB2: %p = phi i32 [ 0, %BB0 ], [ 1, %BB1 ] call void @bar(i32 %p) to BB0: %c = icmp eq i32 %i1, %i2 br i1 %c, label %BB2-split0, label %BB1 BB1: br label %BB2-split1 BB2-split0: call void @bar(i32 0) br label %BB2 BB2-split1: call void @bar(i32 1) br label %BB2 BB2: %p = phi i32 [ 0, %BB2-split0 ], [ 1, %BB2-split1 ] Reviewers: davidxl, huntergr, chandlerc, mcrosier, eraman, davide Reviewed By: davidxl Subscribers: sdesmalen, ashutosh.nema, fhahn, mssimpso, aemerson, mgorny, mehdi_amini, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D39137 llvm-svn: 317351
llvm · Nov 3, 2017 · 2a58933 · 2a58933
1 parent 5de70d9
commit 2a58933
Show file tree

Hide file tree

Showing 14 changed files with 1,014 additions and 3 deletions.
diff --git a/llvm/include/llvm/InitializePasses.h b/llvm/include/llvm/InitializePasses.h
@@ -80,6 +80,7 @@ void initializeBranchFolderPassPass(PassRegistry&);
 void initializeBranchProbabilityInfoWrapperPassPass(PassRegistry&);
 void initializeBranchRelaxationPass(PassRegistry&);
 void initializeBreakCriticalEdgesPass(PassRegistry&);
+void initializeCallSiteSplittingLegacyPassPass(PassRegistry&);
 void initializeCFGOnlyPrinterLegacyPassPass(PassRegistry&);
 void initializeCFGOnlyViewerLegacyPassPass(PassRegistry&);
 void initializeCFGPrinterLegacyPassPass(PassRegistry&);

diff --git a/llvm/include/llvm/Transforms/Scalar.h b/llvm/include/llvm/Transforms/Scalar.h
@@ -73,6 +73,14 @@ FunctionPass *createDeadCodeEliminationPass();
 //
 FunctionPass *createDeadStoreEliminationPass();
 
+
+//===----------------------------------------------------------------------===//
+//
+// CallSiteSplitting - This pass split call-site based on its known argument
+// values.
+FunctionPass *createCallSiteSplittingPass();
+
+
 //===----------------------------------------------------------------------===//
 //
 // AggressiveDCE - This pass uses the SSA based Aggressive DCE algorithm.  This

diff --git a/llvm/include/llvm/Transforms/Scalar/CallSiteSplitting.h b/llvm/include/llvm/Transforms/Scalar/CallSiteSplitting.h
@@ -0,0 +1,29 @@
+//===- CallSiteSplitting..h - Callsite Splitting ------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_SCALAR_CALLSITESPLITTING__H
+#define LLVM_TRANSFORMS_SCALAR_CALLSITESPLITTING__H
+
+#include "llvm/ADT/SetVector.h"
+#include "llvm/Analysis/AssumptionCache.h"
+#include "llvm/IR/Dominators.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/Support/Compiler.h"
+#include <vector>
+
+namespace llvm {
+
+struct CallSiteSplittingPass : PassInfoMixin<CallSiteSplittingPass> {
+  /// \brief Run the pass over the function.
+  PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
+};
+} // end namespace llvm
+
+#endif // LLVM_TRANSFORMS_SCALAR_CALLSITESPLITTING__H
diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
@@ -89,6 +89,7 @@
 #include "llvm/Transforms/Scalar/ADCE.h"
 #include "llvm/Transforms/Scalar/AlignmentFromAssumptions.h"
 #include "llvm/Transforms/Scalar/BDCE.h"
+#include "llvm/Transforms/Scalar/CallSiteSplitting.h"
 #include "llvm/Transforms/Scalar/ConstantHoisting.h"
 #include "llvm/Transforms/Scalar/CorrelatedValuePropagation.h"
 #include "llvm/Transforms/Scalar/DCE.h"
@@ -548,6 +549,9 @@ PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
   EarlyFPM.addPass(SROA());
   EarlyFPM.addPass(EarlyCSEPass());
   EarlyFPM.addPass(LowerExpectIntrinsicPass());
+  if (Level == O3)
+    EarlyFPM.addPass(CallSiteSplittingPass());
+
   // In SamplePGO ThinLTO backend, we need instcombine before profile annotation
   // to convert bitcast to direct calls so that they can be inlined during the
   // profile annotation prepration step.
@@ -920,13 +924,16 @@ ModulePassManager PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
   MPM.addPass(InferFunctionAttrsPass());
 
   if (Level > 1) {
+    FunctionPassManager EarlyFPM(DebugLogging);
+    EarlyFPM.addPass(CallSiteSplittingPass());
+    MPM.addPass(createModuleToFunctionPassAdaptor(std::move(EarlyFPM)));
+
     // Indirect call promotion. This should promote all the targets that are
     // left by the earlier promotion pass that promotes intra-module targets.
     // This two-step promotion is to save the compile time. For LTO, it should
     // produce the same result as if we only do promotion here.
     MPM.addPass(PGOIndirectCallPromotion(
         true /* InLTO */, PGOOpt && !PGOOpt->SampleProfileFile.empty()));
-
     // Propagate constants at call sites into the functions they call.  This
     // opens opportunities for globalopt (and inlining) by substituting function
     // pointers passed as arguments to direct uses of functions.

diff --git a/llvm/lib/Passes/PassRegistry.def b/llvm/lib/Passes/PassRegistry.def
@@ -140,6 +140,7 @@ FUNCTION_PASS("add-discriminators", AddDiscriminatorsPass())
 FUNCTION_PASS("alignment-from-assumptions", AlignmentFromAssumptionsPass())
 FUNCTION_PASS("bdce", BDCEPass())
 FUNCTION_PASS("break-crit-edges", BreakCriticalEdgesPass())
+FUNCTION_PASS("callsite-splitting", CallSiteSplittingPass())
 FUNCTION_PASS("consthoist", ConstantHoistingPass())
 FUNCTION_PASS("correlated-propagation", CorrelatedValuePropagationPass())
 FUNCTION_PASS("dce", DCEPass())

diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -467,6 +467,9 @@ void PassManagerBuilder::populateModulePassManager(
 
   addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
 
+  if (OptLevel > 2)
+    MPM.add(createCallSiteSplittingPass());
+
   MPM.add(createIPSCCPPass());          // IP SCCP
   MPM.add(createCalledValuePropagationPass());
   MPM.add(createGlobalOptimizerPass()); // Optimize out global vars
@@ -703,6 +706,9 @@ void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
   PM.add(createInferFunctionAttrsLegacyPass());
 
   if (OptLevel > 1) {
+    // Split call-site with more constrained arguments.
+    PM.add(createCallSiteSplittingPass());
+
     // Indirect call promotion. This should promote all the targets that are
     // left by the earlier promotion pass that promotes intra-module targets.
     // This two-step promotion is to save the compile time. For LTO, it should

diff --git a/llvm/lib/Transforms/Scalar/CMakeLists.txt b/llvm/lib/Transforms/Scalar/CMakeLists.txt
@@ -2,6 +2,7 @@ add_llvm_library(LLVMScalarOpts
   ADCE.cpp
   AlignmentFromAssumptions.cpp
   BDCE.cpp
+  CallSiteSplitting.cpp
   ConstantHoisting.cpp
   ConstantProp.cpp
   CorrelatedValuePropagation.cpp