llvm · aeubanks · Jan 29, 2025 · Jan 1, 2025
diff --git a/llvm/include/llvm/Passes/PassBuilder.h b/llvm/include/llvm/Passes/PassBuilder.h
@@ -465,6 +465,17 @@ class PassBuilder {
     VectorizerStartEPCallbacks.push_back(C);
   }
 
+  /// Register a callback for a default optimizer pipeline extension
+  /// point
+  ///
+  /// This extension point allows adding optimization passes after the
+  /// vectorizer and other highly target specific optimization passes are
+  /// executed.
+  void registerVectorizerEndEPCallback(
+      const std::function<void(FunctionPassManager &, OptimizationLevel)> &C) {
+    VectorizerEndEPCallbacks.push_back(C);
+  }
+
   /// Register a callback for a default optimizer pipeline extension point.
   ///
   /// This extension point allows adding optimization once at the start of the
@@ -631,6 +642,8 @@ class PassBuilder {
                                            OptimizationLevel Level);
   void invokeVectorizerStartEPCallbacks(FunctionPassManager &FPM,
                                         OptimizationLevel Level);
+  void invokeVectorizerEndEPCallbacks(FunctionPassManager &FPM,
+                                      OptimizationLevel Level);
   void invokeOptimizerEarlyEPCallbacks(ModulePassManager &MPM,
                                        OptimizationLevel Level,
                                        ThinOrFullLTOPhase Phase);
@@ -759,6 +772,8 @@ class PassBuilder {
       CGSCCOptimizerLateEPCallbacks;
   SmallVector<std::function<void(FunctionPassManager &, OptimizationLevel)>, 2>
       VectorizerStartEPCallbacks;
+  SmallVector<std::function<void(FunctionPassManager &, OptimizationLevel)>, 2>
+      VectorizerEndEPCallbacks;
   // Module callbacks
   SmallVector<std::function<void(ModulePassManager &, OptimizationLevel,
                                  ThinOrFullLTOPhase)>,

diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -360,6 +360,11 @@ void PassBuilder::invokeVectorizerStartEPCallbacks(FunctionPassManager &FPM,
   for (auto &C : VectorizerStartEPCallbacks)
     C(FPM, Level);
 }
+void PassBuilder::invokeVectorizerEndEPCallbacks(FunctionPassManager &FPM,
+                                                 OptimizationLevel Level) {
+  for (auto &C : VectorizerEndEPCallbacks)
+    C(FPM, Level);
+}
 void PassBuilder::invokeOptimizerEarlyEPCallbacks(ModulePassManager &MPM,
                                                   OptimizationLevel Level,
                                                   ThinOrFullLTOPhase Phase) {
@@ -1534,6 +1539,8 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
 
   addVectorPasses(Level, OptimizePM, /* IsFullLTO */ false);
 
+  invokeVectorizerEndEPCallbacks(OptimizePM, Level);
+
   // LoopSink pass sinks instructions hoisted by LICM, which serves as a
   // canonicalization pass that enables other optimizations. As a result,
   // LoopSink pass needs to be a very late IR pass to avoid undoing LICM
@@ -2048,6 +2055,8 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
   MainFPM.addPass(MoveAutoInitPass());
   MainFPM.addPass(MergedLoadStoreMotionPass());
 
+  invokeVectorizerStartEPCallbacks(MainFPM, Level);
+
   LoopPassManager LPM;
   if (EnableLoopFlatten && Level.getSpeedupLevel() > 1)
     LPM.addPass(LoopFlattenPass());
@@ -2068,6 +2077,8 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
 
   addVectorPasses(Level, MainFPM, /* IsFullLTO */ true);
 
+  invokeVectorizerEndEPCallbacks(MainFPM, Level);
+
   // Run the OpenMPOpt CGSCC pass again late.
   MPM.addPass(createModuleToPostOrderCGSCCPassAdaptor(
       OpenMPOptCGSCCPass(ThinOrFullLTOPhase::FullLTOPostLink)));
@@ -2231,6 +2242,13 @@ PassBuilder::buildO0DefaultPipeline(OptimizationLevel Level,
       MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
   }
 
+  if (!VectorizerEndEPCallbacks.empty()) {
+    FunctionPassManager FPM;
+    invokeVectorizerEndEPCallbacks(FPM, Level);
+    if (!FPM.isEmpty())
+      MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
+  }
+
   ModulePassManager CoroPM;
   CoroPM.addPass(CoroEarlyPass());
   CGSCCPassManager CGPM;

diff --git a/llvm/test/Other/new-pm-O0-ep-callbacks.ll b/llvm/test/Other/new-pm-O0-ep-callbacks.ll
@@ -3,6 +3,7 @@
 ; RUN: opt -disable-output -debug-pass-manager -passes-ep-scalar-optimizer-late=no-op-function -passes='default<O0>' 2>&1 < %s | FileCheck %s
 ; RUN: opt -disable-output -debug-pass-manager -passes-ep-cgscc-optimizer-late=no-op-cgscc -passes='default<O0>' 2>&1 < %s | FileCheck %s
 ; RUN: opt -disable-output -debug-pass-manager -passes-ep-vectorizer-start=no-op-function -passes='default<O0>' 2>&1 < %s | FileCheck %s
+; RUN: opt -disable-output -debug-pass-manager -passes-ep-vectorizer-end=no-op-function -passes='default<O0>' 2>&1 < %s | FileCheck %s
 ; RUN: opt -disable-output -debug-pass-manager -passes-ep-pipeline-start=no-op-module -passes='default<O0>' 2>&1 < %s | FileCheck %s
 ; RUN: opt -disable-output -debug-pass-manager -passes-ep-pipeline-early-simplification=no-op-module -passes='default<O0>' 2>&1 < %s | FileCheck %s
 ; RUN: opt -disable-output -debug-pass-manager -passes-ep-optimizer-early=no-op-module -passes='default<O0>' 2>&1 < %s | FileCheck %s

diff --git a/llvm/test/Other/new-pm-defaults.ll b/llvm/test/Other/new-pm-defaults.ll
@@ -51,6 +51,10 @@
 ; RUN:     -passes='default<O3>' -S  %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-DEFAULT,CHECK-O3,%llvmcheckext,CHECK-EP-VECTORIZER-START,CHECK-O23SZ
 ; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
+; RUN:     -passes-ep-vectorizer-end='no-op-function' \
+; RUN:     -passes='default<O3>' -S  %s 2>&1 \
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-DEFAULT,CHECK-O3,%llvmcheckext,CHECK-EP-VECTORIZER-END,CHECK-O23SZ
+; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
 ; RUN:     -passes-ep-pipeline-start='no-op-module' \
 ; RUN:     -passes='default<O3>' -S  %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-DEFAULT,CHECK-O3,%llvmcheckext,CHECK-EP-PIPELINE-START,CHECK-O23SZ
@@ -274,6 +278,7 @@
 ; CHECK-O-NEXT: Running pass: LCSSAPass
 ; CHECK-O-NEXT: Running pass: LICMPass
 ; CHECK-O-NEXT: Running pass: AlignmentFromAssumptionsPass
+; CHECK-EP-VECTORIZER-END-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O-NEXT: Running pass: LoopSinkPass
 ; CHECK-O-NEXT: Running pass: InstSimplifyPass
 ; CHECK-O-NEXT: Running pass: DivRemPairsPass

diff --git a/llvm/test/Other/new-pm-lto-defaults.ll b/llvm/test/Other/new-pm-lto-defaults.ll
@@ -18,14 +18,20 @@
 ; RUN:     -passes='lto<O3>' -S  %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ
 ; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
+; RUN:     -passes='lto<O3>' -S  %s -passes-ep-vectorizer-start='no-op-function' 2>&1 \
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-EP-VECTORIZER-START
+; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
+; RUN:     -passes='lto<O3>' -S  %s -passes-ep-vectorizer-end='no-op-function' 2>&1 \
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-EP-VECTORIZER-END
+; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
 ; RUN:     -passes='lto<Os>' -S %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-OS,CHECK-O23SZ
 ; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
 ; RUN:     -passes='lto<Oz>' -S %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O23SZ
 ; RUN: opt -disable-verify -verify-analysis-invalidation=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
 ; RUN:     -passes='lto<O3>' -S  %s -passes-ep-peephole='no-op-function' 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-EP-Peephole
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-EP-PEEPHOLE
 
 ; CHECK-EP: Running pass: NoOpModulePass
 ; CHECK-O: Running pass: CrossDSOCFIPass
@@ -69,7 +75,7 @@
 ; CHECK-O23SZ-NEXT: Running pass: InstCombinePass
 ; CHECK-O23SZ-NEXT: Running analysis: LastRunTrackingAnalysis
 ; CHECK-O23SZ-NEXT: Running pass: AggressiveInstCombinePass
-; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass
+; CHECK-EP-PEEPHOLE-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O23SZ-NEXT: Running pass: ExpandVariadicsPass
 ; CHECK-O23SZ-NEXT: Running pass: ModuleInlinerWrapperPass
 ; CHECK-O23SZ-NEXT: Running analysis: InlineAdvisorAnalysis
@@ -81,7 +87,7 @@
 ; CHECK-O23SZ-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O23SZ-NEXT: Running pass: ArgumentPromotionPass
 ; CHECK-O23SZ-NEXT: Running pass: InstCombinePass
-; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass
+; CHECK-EP-PEEPHOLE-NEXT: Running pass: NoOpFunctionPass
 ; CHECK-O23SZ-NEXT: Running pass: ConstraintEliminationPass
 ; CHECK-O23SZ-NEXT: Running analysis: LoopAnalysis on foo
 ; CHECK-O23SZ-NEXT: Running analysis: ScalarEvolutionAnalysis on foo
@@ -109,6 +115,7 @@
 ; CHECK-O23SZ-NEXT: Running pass: DSEPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: MoveAutoInitPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: MergedLoadStoreMotionPass on foo
+; CHECK-EP-VECTORIZER-START-NEXT: Running pass: NoOpFunctionPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: LoopSimplifyPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: LCSSAPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: IndVarSimplifyPass on loop
@@ -137,7 +144,8 @@
 ; CHECK-O23SZ-NEXT: Running pass: LCSSAPass
 ; CHECK-O23SZ-NEXT: Running pass: LICMPass
 ; CHECK-O23SZ-NEXT: Running pass: AlignmentFromAssumptionsPass on foo
-; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass on foo
+; CHECK-EP-VECTORIZER-END-NEXT: Running pass: NoOpFunctionPass on foo
+; CHECK-EP-PEEPHOLE-NEXT: Running pass: NoOpFunctionPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O-NEXT: Running pass: LowerTypeTestsPass

diff --git a/llvm/test/Other/pass-pipeline-parsing.ll b/llvm/test/Other/pass-pipeline-parsing.ll
@@ -264,6 +264,9 @@
 ; RUN: opt -passes-ep-vectorizer-start=bad -passes=no-op-function \
 ; RUN:       /dev/null -disable-output 2>&1 | FileCheck %s -check-prefix=PASSES-EP-VECTORIZERSTART-ERR
 ; PASSES-EP-VECTORIZERSTART-ERR: Could not parse -passes-ep-vectorizer-start pipeline: unknown function pass 'bad'
+; RUN: opt -passes-ep-vectorizer-end=bad -passes=no-op-function \
+; RUN:       /dev/null -disable-output 2>&1 | FileCheck %s -check-prefix=PASSES-EP-VECTORIZEREND-ERR
+; PASSES-EP-VECTORIZEREND-ERR: Could not parse -passes-ep-vectorizer-end pipeline: unknown function pass 'bad'
 ; RUN: opt -passes-ep-pipeline-start=bad -passes=no-op-function \
 ; RUN:       /dev/null -disable-output 2>&1 | FileCheck %s -check-prefix=PASSES-EP-PIPELINESTART-ERR
 ; PASSES-EP-PIPELINESTART-ERR: Could not parse -passes-ep-pipeline-start pipeline: unknown pass name 'bad'

diff --git a/llvm/tools/opt/NewPMDriver.cpp b/llvm/tools/opt/NewPMDriver.cpp
@@ -122,6 +122,11 @@ static cl::opt<std::string> VectorizerStartEPPipeline(
     cl::desc("A textual description of the function pass pipeline inserted at "
              "the VectorizerStart extension point into default pipelines"),
     cl::Hidden);
+static cl::opt<std::string> VectorizerEndEPPipeline(
+    "passes-ep-vectorizer-end",
+    cl::desc("A textual description of the function pass pipeline inserted at "
+             "the VectorizerEnd extension point into default pipelines"),
+    cl::Hidden);
 static cl::opt<std::string> PipelineStartEPPipeline(
     "passes-ep-pipeline-start",
     cl::desc("A textual description of the module pass pipeline inserted at "
@@ -285,6 +290,12 @@ static void registerEPCallbacks(PassBuilder &PB) {
           ExitOnError Err("Unable to parse VectorizerStartEP pipeline: ");
           Err(PB.parsePassPipeline(PM, VectorizerStartEPPipeline));
         });
+  if (tryParsePipelineText<FunctionPassManager>(PB, VectorizerEndEPPipeline))
+    PB.registerVectorizerEndEPCallback(
+        [&PB](FunctionPassManager &PM, OptimizationLevel Level) {
+          ExitOnError Err("Unable to parse VectorizerEndEP pipeline: ");
+          Err(PB.parsePassPipeline(PM, VectorizerEndEPPipeline));
+        });
   if (tryParsePipelineText<ModulePassManager>(PB, PipelineStartEPPipeline))
     PB.registerPipelineStartEPCallback(
         [&PB](ModulePassManager &PM, OptimizationLevel) {