[llvm-mca] Add the ability to mark regions of code for analysis (PR36875)

This patch teaches llvm-mca how to parse code comments in search for special
"markers" used to select regions of code.

Example:

# LLVM-MCA-BEGIN My Code Region
  ....
# LLVM-MCA-END

The MCAsmLexer now delegates to an object of class MCACommentParser (i.e. an
AsmCommentConsumer) the parsing of code comments to search for begin/end code
region markers.

A comment starting with substring "LLVM-MCA-BEGIN" marks the beginning of a new
region of code.  A comment starting with substring "LLVM-MCA-END" marks the end
of the last region.

This implementation doesn't allow regions to overlap. Each region can have a
optional description; internally, each region is identified by a range of source
code locations (SMLoc).

MCInst objects are added to a region R only if the source location for the
MCInst is in the range of locations specified by R.

By default, the tool allocates an implicit "Default" code region which contains
every source location.  See new tests llvm-mca-marker-*.s for a few examples.

A new Backend object is created for every region. So, the analysis is conducted
on every parsed code region.  The final report is the union of the reports
generated for every code region.  Note that empty regions are skipped.

Special "[#] Code Region - ..." strings are used in the report to mark the
portion which is specific to a code region only. For example, see
llvm-mca-markers-5.s.

Differential Revision: https://reviews.llvm.org/D45433

llvm-svn: 329590

1 files changed, 105 insertions, 42 deletions

diff --git a/llvm/tools/llvm-mca/llvm-mca.cpp b/llvm/tools/llvm-mca/llvm-mca.cpp
index 91bcb90b3a4..3f9682da17f 100644
--- a/llvm/tools/llvm-mca/llvm-mca.cpp
+++ b/llvm/tools/llvm-mca/llvm-mca.cpp
@@ -23,6 +23,7 @@
 
 #include "BackendPrinter.h"
 #include "BackendStatistics.h"
+#include "CodeRegion.h"
 #include "InstructionInfoView.h"
 #include "InstructionTables.h"
 #include "RegisterFileStatistics.h"
@@ -158,6 +159,44 @@ const Target *getTarget(const char *ProgName) {
   return TheTarget;
 }
 
+// A comment consumer that parses strings.
+// The only valid tokens are strings.
+class MCACommentConsumer : public AsmCommentConsumer {
+public:
+  mca::CodeRegions &Regions;
+
+  MCACommentConsumer(mca::CodeRegions &R) : Regions(R) {}
+  void HandleComment(SMLoc Loc, StringRef CommentText) override {
+    // Skip empty comments.
+    StringRef Comment(CommentText);
+    if (Comment.empty())
+      return;
+
+    // Skip spaces and tabs
+    unsigned Position = Comment.find_first_not_of(" \t");
+    if (Position >= Comment.size())
+      // we reached the end of the comment. Bail out.
+      return;
+
+    Comment = Comment.drop_front(Position);
+    if (Comment.consume_front("LLVM-MCA-END")) {
+      Regions.endRegion(Loc);
+      return;
+    }
+
+    // Now try to parse string LLVM-MCA-BEGIN
+    if (!Comment.consume_front("LLVM-MCA-BEGIN"))
+      return;
+
+    // Skip spaces and tabs
+    Position = Comment.find_first_not_of(" \t");
+    if (Position < Comment.size())
+      Comment.drop_front(Position);
+    // Use the rest of the string as a descriptor for this code snippet.
+    Regions.beginRegion(Comment, Loc);
+  }
+};
+
 int AssembleInput(const char *ProgName, MCAsmParser &Parser,
                   const Target *TheTarget, MCSubtargetInfo &STI,
                   MCInstrInfo &MCII, MCTargetOptions &MCOptions) {
@@ -186,17 +225,16 @@ ErrorOr<std::unique_ptr<ToolOutputFile>> getOutputStream() {
 }
 
 class MCStreamerWrapper final : public MCStreamer {
-  using InstVec = std::vector<std::unique_ptr<const MCInst>>;
-  InstVec &Insts;
+  mca::CodeRegions &Regions;
 
 public:
-  MCStreamerWrapper(MCContext &Context, InstVec &Vec)
-      : MCStreamer(Context), Insts(Vec) {}
+  MCStreamerWrapper(MCContext &Context, mca::CodeRegions &R)
+      : MCStreamer(Context), Regions(R) {}
 
   // We only want to intercept the emission of new instructions.
   virtual void EmitInstruction(const MCInst &Inst, const MCSubtargetInfo &STI,
                                bool /* unused */) override {
-    Insts.emplace_back(new MCInst(Inst));
+    Regions.addInstruction(llvm::make_unique<const MCInst>(Inst));
   }
 
   bool EmitSymbolAttribute(MCSymbol *Symbol, MCSymbolAttr Attribute) override {
@@ -213,7 +251,10 @@ public:
   void EmitCOFFSymbolType(int Type) override {}
   void EndCOFFSymbolDef() override {}
 
-  const InstVec &GetInstructionSequence() const { return Insts; }
+  const std::vector<std::unique_ptr<const MCInst>> &
+  GetInstructionSequence(unsigned Index) const {
+    return Regions.getInstructionSequence(Index);
+  }
 };
 } // end of anonymous namespace
 
@@ -272,9 +313,8 @@ int main(int argc, char **argv) {
 
   std::unique_ptr<buffer_ostream> BOS;
 
-  std::unique_ptr<mca::SourceMgr> S = llvm::make_unique<mca::SourceMgr>(
-      PrintInstructionTables ? 1 : Iterations);
-  MCStreamerWrapper Str(Ctx, S->getSequence());
+  mca::CodeRegions Regions(SrcMgr);
+  MCStreamerWrapper Str(Ctx, Regions);
 
   std::unique_ptr<MCInstrInfo> MCII(TheTarget->createMCInstrInfo());
   std::unique_ptr<MCSubtargetInfo> STI(
@@ -310,10 +350,14 @@ int main(int argc, char **argv) {
   }
 
   std::unique_ptr<MCAsmParser> P(createMCAsmParser(SrcMgr, Ctx, Str, *MAI));
+  MCAsmLexer &Lexer = P->getLexer();
+  MCACommentConsumer CC(Regions);
+  Lexer.setCommentConsumer(&CC);
+
   if (AssembleInput(ProgName, *P, TheTarget, *STI, *MCII, MCOptions))
     return 1;
 
-  if (S->isEmpty()) {
+  if (Regions.empty()) {
     errs() << "error: no assembly instructions found.\n";
     return 1;
   }
@@ -336,49 +380,68 @@ int main(int argc, char **argv) {
   // Create an instruction builder.
   mca::InstrBuilder IB(*STI, *MCII);
 
-  if (PrintInstructionTables) {
-    mca::InstructionTables IT(STI->getSchedModel(), IB, *S);
-
-    if (PrintInstructionInfoView) {
-      IT.addView(
-          llvm::make_unique<mca::InstructionInfoView>(*STI, *MCII, *S, *IP));
+  // Number each region in the sequence.
+  unsigned RegionIdx = 0;
+  for (const std::unique_ptr<mca::CodeRegion> &Region : Regions) {
+    // Skip empty code regions.
+    if (Region->empty())
+      continue;
+
+    // Don't print the header of this region if it is the default region, and
+    // it doesn't have an end location.
+    if (Region->startLoc().isValid() || Region->endLoc().isValid()) {
+      TOF->os() << "\n[" << RegionIdx++ << "] Code Region";
+      StringRef Desc = Region->getDescription();
+      if (!Desc.empty())
+        TOF->os() << " - " << Desc;
+      TOF->os() << "\n\n";
     }
 
-    IT.addView(llvm::make_unique<mca::ResourcePressureView>(*STI, *IP, *S));
-    IT.run();
-    IT.printReport(TOF->os());
-    TOF->keep();
-    return 0;
-  }
+    mca::SourceMgr S(Region->getInstructions(),
+                     PrintInstructionTables ? 1 : Iterations);
+
+    if (PrintInstructionTables) {
+      mca::InstructionTables IT(STI->getSchedModel(), IB, S);
+
+      if (PrintInstructionInfoView) {
+        IT.addView(
+            llvm::make_unique<mca::InstructionInfoView>(*STI, *MCII, S, *IP));
+      }
 
-  mca::Backend B(*STI, *MRI, IB, *S, Width, RegisterFileSize, LoadQueueSize,
-                 StoreQueueSize, AssumeNoAlias);
-  mca::BackendPrinter Printer(B);
+      IT.addView(llvm::make_unique<mca::ResourcePressureView>(*STI, *IP, S));
+      IT.run();
+      IT.printReport(TOF->os());
+      continue;
+    }
+
+    mca::Backend B(*STI, *MRI, IB, S, Width, RegisterFileSize, LoadQueueSize,
+                   StoreQueueSize, AssumeNoAlias);
+    mca::BackendPrinter Printer(B);
 
-  Printer.addView(llvm::make_unique<mca::SummaryView>(*S, Width));
+    Printer.addView(llvm::make_unique<mca::SummaryView>(S, Width));
+    if (PrintInstructionInfoView)
+      Printer.addView(
+          llvm::make_unique<mca::InstructionInfoView>(*STI, *MCII, S, *IP));
 
-  if (PrintInstructionInfoView)
-    Printer.addView(
-        llvm::make_unique<mca::InstructionInfoView>(*STI, *MCII, *S, *IP));
+    if (PrintModeVerbose)
+      Printer.addView(llvm::make_unique<mca::BackendStatistics>(*STI));
 
-  if (PrintModeVerbose)
-    Printer.addView(llvm::make_unique<mca::BackendStatistics>(*STI));
+    if (PrintRegisterFileStats)
+      Printer.addView(llvm::make_unique<mca::RegisterFileStatistics>(*STI));
 
-  if (PrintRegisterFileStats)
-    Printer.addView(llvm::make_unique<mca::RegisterFileStatistics>(*STI));
+    if (PrintResourcePressureView)
+      Printer.addView(
+          llvm::make_unique<mca::ResourcePressureView>(*STI, *IP, S));
 
-  if (PrintResourcePressureView)
-    Printer.addView(
-        llvm::make_unique<mca::ResourcePressureView>(*STI, *IP, *S));
+    if (PrintTimelineView) {
+      Printer.addView(llvm::make_unique<mca::TimelineView>(
+          *STI, *IP, S, TimelineMaxIterations, TimelineMaxCycles));
+    }
 
-  if (PrintTimelineView) {
-    Printer.addView(llvm::make_unique<mca::TimelineView>(
-        *STI, *IP, *S, TimelineMaxIterations, TimelineMaxCycles));
+    B.run();
+    Printer.printReport(TOF->os());
   }
 
-  B.run();
-  Printer.printReport(TOF->os());
   TOF->keep();
-
   return 0;
 }