[llvm-mca] LSUnit: use a SmallSet to model load/store queues. NFCI

Also, try to minimize the number of queries to the memory queues to speedup the
analysis.

On average, this change gives a small 2% speedup. For memcpy-like kernels, the
speedup is up to 5.5%.

llvm-svn: 347469

2 files changed, 32 insertions, 25 deletions

diff --git a/llvm/tools/llvm-mca/include/HardwareUnits/LSUnit.h b/llvm/tools/llvm-mca/include/HardwareUnits/LSUnit.h
index 6b36282ca72..bfe3b01c4de 100644
--- a/llvm/tools/llvm-mca/include/HardwareUnits/LSUnit.h
+++ b/llvm/tools/llvm-mca/include/HardwareUnits/LSUnit.h
@@ -17,7 +17,7 @@
 #define LLVM_TOOLS_LLVM_MCA_LSUNIT_H
 
 #include "HardwareUnits/HardwareUnit.h"
-#include <set>
+#include "llvm/ADT/SmallSet.h"
 
 namespace llvm {
 namespace mca {
@@ -99,8 +99,8 @@ class LSUnit : public HardwareUnit {
   // If true, loads will never alias with stores. This is the default.
   bool NoAlias;
 
-  std::set<unsigned> LoadQueue;
-  std::set<unsigned> StoreQueue;
+  SmallSet<unsigned, 16> LoadQueue;
+  SmallSet<unsigned, 16> StoreQueue;
 
   void assignLQSlot(unsigned Index);
   void assignSQSlot(unsigned Index);
@@ -109,12 +109,12 @@ class LSUnit : public HardwareUnit {
   // An instruction that both 'mayStore' and 'HasUnmodeledSideEffects' is
   // conservatively treated as a store barrier. It forces older store to be
   // executed before newer stores are issued.
-  std::set<unsigned> StoreBarriers;
+  SmallSet<unsigned, 8> StoreBarriers;
 
   // An instruction that both 'MayLoad' and 'HasUnmodeledSideEffects' is
   // conservatively treated as a load barrier. It forces older loads to execute
   // before newer loads are issued.
-  std::set<unsigned> LoadBarriers;
+  SmallSet<unsigned, 8> LoadBarriers;
 
   bool isSQEmpty() const { return StoreQueue.empty(); }
   bool isLQEmpty() const { return LoadQueue.empty(); }
diff --git a/llvm/tools/llvm-mca/lib/HardwareUnits/LSUnit.cpp b/llvm/tools/llvm-mca/lib/HardwareUnits/LSUnit.cpp
index 6923c6e0dc8..ae020c68432 100644
--- a/llvm/tools/llvm-mca/lib/HardwareUnits/LSUnit.cpp
+++ b/llvm/tools/llvm-mca/lib/HardwareUnits/LSUnit.cpp
@@ -136,31 +136,38 @@ bool LSUnit::isReady(const InstRef &IR) const {
 }
 
 void LSUnit::onInstructionExecuted(const InstRef &IR) {
+  const InstrDesc &Desc = IR.getInstruction()->getDesc();
   const unsigned Index = IR.getSourceIndex();
-  std::set<unsigned>::iterator it = LoadQueue.find(Index);
-  if (it != LoadQueue.end()) {
-    LLVM_DEBUG(dbgs() << "[LSUnit]: Instruction idx=" << Index
-                      << " has been removed from the load queue.\n");
-    LoadQueue.erase(it);
-  }
+  bool IsALoad = Desc.MayLoad;
+  bool IsAStore = Desc.MayStore;
 
-  it = StoreQueue.find(Index);
-  if (it != StoreQueue.end()) {
-    LLVM_DEBUG(dbgs() << "[LSUnit]: Instruction idx=" << Index
-                      << " has been removed from the store queue.\n");
-    StoreQueue.erase(it);
+  if (IsALoad) {
+    if (LoadQueue.erase(Index)) {
+      LLVM_DEBUG(dbgs() << "[LSUnit]: Instruction idx=" << Index
+                        << " has been removed from the load queue.\n");
+    }
+    if (!LoadBarriers.empty() && Index == *LoadBarriers.begin()) {
+      LLVM_DEBUG(
+          dbgs() << "[LSUnit]: Instruction idx=" << Index
+                 << " has been removed from the set of load barriers.\n");
+      LoadBarriers.erase(Index);
+    }
   }
 
-  if (!StoreBarriers.empty() && Index == *StoreBarriers.begin()) {
-    LLVM_DEBUG(dbgs() << "[LSUnit]: Instruction idx=" << Index
-                      << " has been removed from the set of store barriers.\n");
-    StoreBarriers.erase(StoreBarriers.begin());
-  }
-  if (!LoadBarriers.empty() && Index == *LoadBarriers.begin()) {
-    LLVM_DEBUG(dbgs() << "[LSUnit]: Instruction idx=" << Index
-                      << " has been removed from the set of load barriers.\n");
-    LoadBarriers.erase(LoadBarriers.begin());
+  if (IsAStore) {
+    if (StoreQueue.erase(Index)) {
+      LLVM_DEBUG(dbgs() << "[LSUnit]: Instruction idx=" << Index
+                        << " has been removed from the store queue.\n");
+    }
+
+    if (!StoreBarriers.empty() && Index == *StoreBarriers.begin()) {
+      LLVM_DEBUG(
+          dbgs() << "[LSUnit]: Instruction idx=" << Index
+                 << " has been removed from the set of store barriers.\n");
+      StoreBarriers.erase(Index);
+    }
   }
 }
+
 } // namespace mca
 } // namespace llvm