[llvm] Add function feature extraction analysis

Summary:
This patch introduces an analysis pass to extract function features,
which will be needed by the ML InlineAdvisor.

RFC: http://lists.llvm.org/pipermail/llvm-dev/2020-April/140763.html

Reviewers: davidxl, dblaikie, jdoerfert

Subscribers: mgorny, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D80579

diff --git a/llvm/include/llvm/Analysis/ML/InlineFeaturesAnalysis.h b/llvm/include/llvm/Analysis/ML/InlineFeaturesAnalysis.h
new file mode 100644 (file)
index 0000000..694cae3
--- /dev/null
+++ b/llvm/include/llvm/Analysis/ML/InlineFeaturesAnalysis.h
@@ -0,0 +1,37 @@
+#ifndef LLVM_INLINEFEATURESANALYSIS_H_
+#define LLVM_INLINEFEATURESANALYSIS_H_
+
+#include "llvm/IR/PassManager.h"
+
+namespace llvm {
+class Function;
+
+class InlineFeaturesAnalysis
+    : public AnalysisInfoMixin<InlineFeaturesAnalysis> {
+public:
+  static AnalysisKey Key;
+  struct Result {
+    /// Number of basic blocks
+    int64_t BasicBlockCount = 0;
+
+    /// Number of blocks reached from a conditional instruction, or that are
+    /// 'cases' of a SwitchInstr.
+    // FIXME: We may want to replace this with a more meaningful metric, like
+    // number of conditionally executed blocks:
+    // 'if (a) s();' would be counted here as 2 blocks, just like
+    // 'if (a) s(); else s2(); s3();' would.
+    int64_t BlocksReachedFromConditionalInstruction = 0;
+
+    /// Number of uses of this function, plus 1 if the function is callable
+    /// outside the module.
+    int64_t Uses = 0;
+
+    /// Number of direct calls made from this function to other functions
+    /// defined in this module.
+    int64_t DirectCallsToDefinedFunctions = 0;
+  };
+  Result run(const Function &F, FunctionAnalysisManager &FAM);
+};
+
+} // namespace llvm
+#endif // LLVM_INLINEFEATURESANALYSIS_H_
\ No newline at end of file

diff --git a/llvm/lib/Analysis/CMakeLists.txt b/llvm/lib/Analysis/CMakeLists.txt
index 7ae053f..8fa832f 100644 (file)
--- a/llvm/lib/Analysis/CMakeLists.txt
+++ b/llvm/lib/Analysis/CMakeLists.txt
@@ -1,3 +1,5 @@
+add_subdirectory(ML)
+
 add_llvm_component_library(LLVMAnalysis
   AliasAnalysis.cpp
   AliasAnalysisEvaluator.cpp
@@ -106,4 +108,9 @@ add_llvm_component_library(LLVMAnalysis
 
   DEPENDS
   intrinsics_gen
+  LLVMMLPolicies
+
+
+  LINK_LIBS
+  LLVMMLPolicies
   )

diff --git a/llvm/lib/Analysis/ML/CMakeLists.txt b/llvm/lib/Analysis/ML/CMakeLists.txt
new file mode 100644 (file)
index 0000000..05039a9
--- /dev/null
+++ b/llvm/lib/Analysis/ML/CMakeLists.txt
@@ -0,0 +1,9 @@
+set (SOURCES InlineFeaturesAnalysis.cpp)
+
+add_llvm_library(LLVMMLPolicies STATIC
+  ${SOURCES}
+
+  DEPENDS
+  intrinsics_gen
+
+  )

diff --git a/llvm/lib/Analysis/ML/InlineFeaturesAnalysis.cpp b/llvm/lib/Analysis/ML/InlineFeaturesAnalysis.cpp
new file mode 100644 (file)
index 0000000..d81e9b3
--- /dev/null
+++ b/llvm/lib/Analysis/ML/InlineFeaturesAnalysis.cpp
@@ -0,0 +1,28 @@
+#include "llvm/Analysis/ML/InlineFeaturesAnalysis.h"
+#include "llvm/IR/Instructions.h"
+
+using namespace llvm;
+
+AnalysisKey InlineFeaturesAnalysis::Key;
+
+InlineFeaturesAnalysis::Result
+InlineFeaturesAnalysis::run(const Function &F, FunctionAnalysisManager &FAM) {
+  Result Ret;
+  Ret.Uses = ((!F.hasLocalLinkage()) ? 1 : 0) + F.getNumUses();
+  for (const auto &BB : F) {
+    ++Ret.BasicBlockCount;
+    if (const auto *BI = dyn_cast<BranchInst>(BB.getTerminator())) {
+      if (BI->isConditional())
+        Ret.BlocksReachedFromConditionalInstruction += BI->getNumSuccessors();
+    } else if (const auto *SI = dyn_cast<SwitchInst>(BB.getTerminator()))
+      Ret.BlocksReachedFromConditionalInstruction +=
+          (SI->getNumCases() + (nullptr != SI->getDefaultDest()));
+    for (const auto &I : BB)
+      if (auto *CS = dyn_cast<CallBase>(&I)) {
+        const auto *Callee = CS->getCalledFunction();
+        if (Callee && !Callee->isIntrinsic() && !Callee->isDeclaration())
+          ++Ret.DirectCallsToDefinedFunctions;
+      }
+  }
+  return Ret;
+}
\ No newline at end of file

diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
index 014ef83..0999f78 100644 (file)
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -40,6 +40,7 @@
 #include "llvm/Analysis/LoopCacheAnalysis.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/LoopNestAnalysis.h"
+#include "llvm/Analysis/ML/InlineFeaturesAnalysis.h"
 #include "llvm/Analysis/MemoryDependenceAnalysis.h"
 #include "llvm/Analysis/MemorySSA.h"
 #include "llvm/Analysis/ModuleSummaryAnalysis.h"

diff --git a/llvm/lib/Passes/PassRegistry.def b/llvm/lib/Passes/PassRegistry.def
index 03c4379..dd75a41 100644 (file)
--- a/llvm/lib/Passes/PassRegistry.def
+++ b/llvm/lib/Passes/PassRegistry.def
@@ -134,6 +134,7 @@ FUNCTION_ANALYSIS("domfrontier", DominanceFrontierAnalysis())
 FUNCTION_ANALYSIS("loops", LoopAnalysis())
 FUNCTION_ANALYSIS("lazy-value-info", LazyValueAnalysis())
 FUNCTION_ANALYSIS("da", DependenceAnalysis())
+FUNCTION_ANALYSIS("inliner-features", InlineFeaturesAnalysis())
 FUNCTION_ANALYSIS("memdep", MemoryDependenceAnalysis())
 FUNCTION_ANALYSIS("memoryssa", MemorySSAAnalysis())
 FUNCTION_ANALYSIS("phi-values", PhiValuesAnalysis())

diff --git a/llvm/unittests/Analysis/CMakeLists.txt b/llvm/unittests/Analysis/CMakeLists.txt
index f344d6c..6cc14d1 100644 (file)
--- a/llvm/unittests/Analysis/CMakeLists.txt
+++ b/llvm/unittests/Analysis/CMakeLists.txt
@@ -41,3 +41,5 @@ add_llvm_unittest(AnalysisTests
   ValueTrackingTest.cpp
   VectorUtilsTest.cpp
   )
+
+add_subdirectory(ML)
\ No newline at end of file

diff --git a/llvm/unittests/Analysis/ML/CMakeLists.txt b/llvm/unittests/Analysis/ML/CMakeLists.txt
new file mode 100644 (file)
index 0000000..8d1c903
--- /dev/null
+++ b/llvm/unittests/Analysis/ML/CMakeLists.txt
@@ -0,0 +1,12 @@
+set(LLVM_LINK_COMPONENTS
+  Analysis  
+  AsmParser
+  Core
+  MLPolicies
+  Support
+  TransformUtils
+  )
+
+add_llvm_unittest(MLAnalysisTests
+  InlineFeaturesAnalysisTest.cpp
+  )

diff --git a/llvm/unittests/Analysis/ML/InlineFeaturesAnalysisTest.cpp b/llvm/unittests/Analysis/ML/InlineFeaturesAnalysisTest.cpp
new file mode 100644 (file)
index 0000000..4dfc0bd
--- /dev/null
+++ b/llvm/unittests/Analysis/ML/InlineFeaturesAnalysisTest.cpp
@@ -0,0 +1,77 @@
+//===- InlineFeaturesAnalysisTest.cpp - inline features unit tests --------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Analysis/ML/InlineFeaturesAnalysis.h"
+#include "llvm/AsmParser/Parser.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Support/SourceMgr.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+
+static std::unique_ptr<Module> parseIR(LLVMContext &C, const char *IR) {
+  SMDiagnostic Err;
+  std::unique_ptr<Module> Mod = parseAssemblyString(IR, Err, C);
+  if (!Mod)
+    Err.print("MLAnalysisTests", errs());
+  return Mod;
+}
+
+TEST(InlineFeaturesTest, BasicTest) {
+  LLVMContext C;
+  std::unique_ptr<Module> M = parseIR(C,
+                                      R"IR(
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+declare i32 @f1(i32)
+declare i32 @f2(i32)
+
+define i32 @branches(i32) {
+  %cond = icmp slt i32 %0, 3
+  br i1 %cond, label %then, label %else
+
+then:
+  %ret.1 = call i32 @f1(i32 %0)
+  br label %last.block
+
+else:
+  %ret.2 = call i32 @f2(i32 %0)
+  br label %last.block
+
+last.block:
+  %ret = phi i32 [%ret.1, %then], [%ret.2, %else]
+  ret i32 %ret
+}
+
+define internal i32 @top() {
+  %1 = call i32 @branches(i32 2)
+  %2 = call i32 @f1(i32 %1)
+  ret i32 %2
+}
+)IR");
+
+  FunctionAnalysisManager FAM;
+  InlineFeaturesAnalysis FA;
+
+  auto BranchesFeatures = FA.run(*M->getFunction("branches"), FAM);
+  EXPECT_EQ(BranchesFeatures.BasicBlockCount, 4);
+  EXPECT_EQ(BranchesFeatures.BlocksReachedFromConditionalInstruction, 2);
+  EXPECT_EQ(BranchesFeatures.DirectCallsToDefinedFunctions, 0);
+  // 2 Users: top is one. The other is added because @branches is not internal,
+  // so it may have external callers.
+  EXPECT_EQ(BranchesFeatures.Uses, 2);
+
+  auto TopFeatures = FA.run(*M->getFunction("top"), FAM);
+  EXPECT_EQ(TopFeatures.BasicBlockCount, 1);
+  EXPECT_EQ(TopFeatures.BlocksReachedFromConditionalInstruction, 0);
+  EXPECT_EQ(TopFeatures.DirectCallsToDefinedFunctions, 1);
+  EXPECT_EQ(TopFeatures.Uses, 0);
+}