From d556eb7e27c25ae20befb0811bc8a3423241431d Mon Sep 17 00:00:00 2001
From: Jeremy Morse <jeremy.morse@sony.com>
Date: Wed, 2 Feb 2022 12:12:32 +0000
Subject: [PATCH] [DebugInfo][InstrRef][NFC] Cache some PHI resolutions

Install a cache of DBG_INSTR_REF -> ValueIDNum resolutions, for scenarios
where the value has to be reconstructed from several DBG_PHIs. Whenever
this happens, it's because branch folding + tail duplication has messed
with the SSA form of the program, and we have to solve a mini SSA problem
to find the variable value. This is always called twice, so it makes sense
to cache the value.

This gives a ~0.5% geomean compile-time-performance improvement on CTMark.

Differential Revision: https://reviews.llvm.org/D118455
---
 llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.cpp | 16 ++++++++++++++++
 llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h   | 12 ++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.cpp b/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.cpp
index 2e69a5e..25d764d 100644
--- a/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.cpp
+++ b/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.cpp
@@ -3122,6 +3122,7 @@ bool InstrRefBasedLDV::ExtendRanges(MachineFunction &MF,
   DebugPHINumToValue.clear();
   OverlapFragments.clear();
   SeenFragments.clear();
+  SeenDbgPHIs.clear();
 
   return Changed;
 }
@@ -3387,6 +3388,21 @@ Optional<ValueIDNum> InstrRefBasedLDV::resolveDbgPHIs(MachineFunction &MF,
                                                       ValueIDNum **MLiveIns,
                                                       MachineInstr &Here,
                                                       uint64_t InstrNum) {
+  // This function will be called twice per DBG_INSTR_REF, and might end up
+  // computing lots of SSA information: memoize it.
+  auto SeenDbgPHIIt = SeenDbgPHIs.find(&Here);
+  if (SeenDbgPHIIt != SeenDbgPHIs.end())
+    return SeenDbgPHIIt->second;
+
+  Optional<ValueIDNum> Result =
+      resolveDbgPHIsImpl(MF, MLiveOuts, MLiveIns, Here, InstrNum);
+  SeenDbgPHIs.insert({&Here, Result});
+  return Result;
+}
+
+Optional<ValueIDNum> InstrRefBasedLDV::resolveDbgPHIsImpl(
+    MachineFunction &MF, ValueIDNum **MLiveOuts, ValueIDNum **MLiveIns,
+    MachineInstr &Here, uint64_t InstrNum) {
   // Pick out records of DBG_PHI instructions that have been observed. If there
   // are none, then we cannot compute a value number.
   auto RangePair = std::equal_range(DebugPHINumToValue.begin(),
diff --git a/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h b/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h
index fe1d292..1e1bb75 100644
--- a/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h
+++ b/llvm/lib/CodeGen/LiveDebugValues/InstrRefBasedImpl.h
@@ -864,6 +864,12 @@ private:
   OverlapMap OverlapFragments;
   VarToFragments SeenFragments;
 
+  /// Mapping of DBG_INSTR_REF instructions to their values, for those
+  /// DBG_INSTR_REFs that call resolveDbgPHIs. These variable references solve
+  /// a mini SSA problem caused by DBG_PHIs being cloned, this collection caches
+  /// the result.
+  DenseMap<MachineInstr *, Optional<ValueIDNum>> SeenDbgPHIs;
+
   /// True if we need to examine call instructions for stack clobbers. We
   /// normally assume that they don't clobber SP, but stack probes on Windows
   /// do.
@@ -944,6 +950,12 @@ private:
                                       ValueIDNum **MLiveIns, MachineInstr &Here,
                                       uint64_t InstrNum);
 
+  Optional<ValueIDNum> resolveDbgPHIsImpl(MachineFunction &MF,
+                                          ValueIDNum **MLiveOuts,
+                                          ValueIDNum **MLiveIns,
+                                          MachineInstr &Here,
+                                          uint64_t InstrNum);
+
   /// Step through the function, recording register definitions and movements
   /// in an MLocTracker. Convert the observations into a per-block transfer
   /// function in \p MLocTransfer, suitable for using with the machine value
-- 
2.7.4