[llvm-mca] Delay calculation of Cycles per Resources, separate the cycles and resource quantities.

Summary:
This patch removes the storing of accumulated floating point data 
within the llvm-mca library.

This patch splits-up the two quantities: cycles and number of resource units.
By splitting-up these two quantities, we delay the calculation of "cycles per resource unit"
until that value is read, reducing the chance of accumulating floating point error. 

I considered using the APFloat, but after measuring performance, for a large (many iteration)
sample, I decided to go with this faster solution.

Reviewers: andreadb, courbet, RKSimon

Reviewed By: andreadb

Subscribers: llvm-commits, javed.absar, tschuett, gbedwell

Differential Revision: https://reviews.llvm.org/D51903

llvm-svn: 341980

llvm/tools/llvm-mca/Views/ResourcePressureView.cpp

@@ -46,7 +46,8 @@ void ResourcePressureView::onEvent(const HWInstructionEvent &Event) {
     return;
   const auto &IssueEvent = static_cast<const HWInstructionIssuedEvent &>(Event);
   const unsigned SourceIdx = Event.IR.getSourceIndex() % Source.size();
-  for (const std::pair<ResourceRef, double> &Use : IssueEvent.UsedResources) {
+  for (const std::pair<ResourceRef, ResourceCycles> &Use :
+       IssueEvent.UsedResources) {
     const ResourceRef &RR = Use.first;
     assert(Resource2VecIndex.find(RR.first) != Resource2VecIndex.end());
     unsigned R2VIndex = Resource2VecIndex[RR.first];

llvm/tools/llvm-mca/Views/ResourcePressureView.h

@@ -79,7 +79,7 @@ class ResourcePressureView : public View {
   llvm::DenseMap<unsigned, unsigned> Resource2VecIndex;
 
   // Table of resources used by instructions.
-  std::vector<double> ResourceUsage;
+  std::vector<ResourceCycles> ResourceUsage;
   unsigned NumResourceUnits;
 
   const llvm::MCInst &GetMCInstFromIndex(unsigned Index) const;

llvm/tools/llvm-mca/include/HWEventListener.h

@@ -16,8 +16,8 @@
 #define LLVM_TOOLS_LLVM_MCA_HWEVENTLISTENER_H
 
 #include "Instruction.h"
+#include "Support.h"
 #include "llvm/ADT/ArrayRef.h"
-#include <utility>
 
 namespace mca {
 
@@ -61,11 +61,12 @@ public:
 class HWInstructionIssuedEvent : public HWInstructionEvent {
 public:
   using ResourceRef = std::pair<uint64_t, uint64_t>;
-  HWInstructionIssuedEvent(const InstRef &IR,
-                           llvm::ArrayRef<std::pair<ResourceRef, double>> UR)
+  HWInstructionIssuedEvent(
+      const InstRef &IR,
+      llvm::ArrayRef<std::pair<ResourceRef, ResourceCycles>> UR)
       : HWInstructionEvent(HWInstructionEvent::Issued, IR), UsedResources(UR) {}
 
-  llvm::ArrayRef<std::pair<ResourceRef, double>> UsedResources;
+  llvm::ArrayRef<std::pair<ResourceRef, ResourceCycles>> UsedResources;
 };
 
 class HWInstructionDispatchedEvent : public HWInstructionEvent {

llvm/tools/llvm-mca/include/HardwareUnits/ResourceManager.h

@@ -17,6 +17,7 @@
 #define LLVM_TOOLS_LLVM_MCA_RESOURCE_MANAGER_H
 
 #include "Instruction.h"
+#include "Support.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallVector.h"
@@ -344,7 +345,7 @@ public:
 
   void issueInstruction(
       const InstrDesc &Desc,
-      llvm::SmallVectorImpl<std::pair<ResourceRef, double>> &Pipes);
+      llvm::SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &Pipes);
 
   void cycleEvent(llvm::SmallVectorImpl<ResourceRef> &ResourcesFreed);
 

llvm/tools/llvm-mca/include/HardwareUnits/Scheduler.h

@@ -18,6 +18,7 @@
 #include "HardwareUnits/HardwareUnit.h"
 #include "HardwareUnits/LSUnit.h"
 #include "ResourceManager.h"
+#include "Support.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/MC/MCSchedule.h"
 
@@ -103,7 +104,7 @@ class Scheduler : public HardwareUnit {
   /// Issue an instruction without updating the ready queue.
   void issueInstructionImpl(
       InstRef &IR,
-      llvm::SmallVectorImpl<std::pair<ResourceRef, double>> &Pipes);
+      llvm::SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &Pipes);
 
   // Identify instructions that have finished executing, and remove them from
   // the IssuedSet. References to executed instructions are added to input
@@ -164,10 +165,10 @@ public:
   /// Issue an instruction and populates a vector of used pipeline resources,
   /// and a vector of instructions that transitioned to the ready state as a
   /// result of this event.
-  void
-  issueInstruction(InstRef &IR,
-                   llvm::SmallVectorImpl<std::pair<ResourceRef, double>> &Used,
-                   llvm::SmallVectorImpl<InstRef> &Ready);
+  void issueInstruction(
+      InstRef &IR,
+      llvm::SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &Used,
+      llvm::SmallVectorImpl<InstRef> &Ready);
 
   /// Returns true if IR has to be issued immediately, or if IR is a zero
   /// latency instruction.

llvm/tools/llvm-mca/include/Stages/ExecuteStage.h

@@ -59,9 +59,9 @@ public:
   llvm::Error cycleStart() override;
   llvm::Error execute(InstRef &IR) override;
 
-  void
-  notifyInstructionIssued(const InstRef &IR,
-                          llvm::ArrayRef<std::pair<ResourceRef, double>> Used);
+  void notifyInstructionIssued(
+      const InstRef &IR,
+      llvm::ArrayRef<std::pair<ResourceRef, ResourceCycles>> Used);
   void notifyInstructionExecuted(const InstRef &IR);
   void notifyInstructionReady(const InstRef &IR);
   void notifyResourceAvailable(const ResourceRef &RR);

llvm/tools/llvm-mca/include/Stages/InstructionTables.h

@@ -28,7 +28,7 @@ namespace mca {
 class InstructionTables final : public Stage {
   const llvm::MCSchedModel &SM;
   InstrBuilder &IB;
-  llvm::SmallVector<std::pair<ResourceRef, double>, 4> UsedResources;
+  llvm::SmallVector<std::pair<ResourceRef, ResourceCycles>, 4> UsedResources;
 
 public:
   InstructionTables(const llvm::MCSchedModel &Model, InstrBuilder &Builder)

llvm/tools/llvm-mca/include/Support.h

@@ -21,6 +21,46 @@
 
 namespace mca {
 
+/// This class represents the number of cycles per resource (fractions of
+/// cycles).  That quantity is managed here as a ratio, and accessed via the
+/// double cast-operator below.  The two quantities, number of cycles and
+/// number of resources, are kept separate.  This is used by the
+/// ResourcePressureView to calculate the average resource cycles
+/// per instruction/iteration.
+class ResourceCycles {
+  unsigned Numerator, Denominator;
+
+public:
+  ResourceCycles() : Numerator(0), Denominator(1) {}
+  ResourceCycles(unsigned Cycles, unsigned ResourceUnits = 1)
+      : Numerator(Cycles), Denominator(ResourceUnits) {}
+
+  operator double() const {
+    assert(Denominator && "Invalid denominator (must be non-zero).");
+    return (Denominator == 1) ? Numerator : (double)Numerator / Denominator;
+  }
+
+  // Add the components of RHS to this instance.  Instead of calculating
+  // the final value here, we keep track of the numerator and denominator
+  // separately, to reduce floating point error.
+  ResourceCycles &operator+=(const ResourceCycles &RHS) {
+    if (Denominator == RHS.Denominator)
+      Numerator += RHS.Numerator;
+    else {
+      // Create a common denominator for LHS and RHS by calculating the least
+      // common multiple from the GCD.
+      unsigned GCD =
+          llvm::GreatestCommonDivisor64(Denominator, RHS.Denominator);
+      unsigned LCM = (Denominator * RHS.Denominator) / GCD;
+      unsigned LHSNumerator = Numerator * (LCM / Denominator);
+      unsigned RHSNumerator = RHS.Numerator * (LCM / RHS.Denominator);
+      Numerator = LHSNumerator + RHSNumerator;
+      Denominator = LCM;
+    }
+    return *this;
+  }
+};
+
 /// Populates vector Masks with processor resource masks.
 ///
 /// The number of bits set in a mask depends on the processor resource type.

llvm/tools/llvm-mca/lib/HardwareUnits/ResourceManager.cpp

@@ -247,7 +247,7 @@ bool ResourceManager::mustIssueImmediately(const InstrDesc &Desc) const {
 
 void ResourceManager::issueInstruction(
     const InstrDesc &Desc,
-    SmallVectorImpl<std::pair<ResourceRef, double>> &Pipes) {
+    SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &Pipes) {
   for (const std::pair<uint64_t, ResourceUsage> &R : Desc.Resources) {
     const CycleSegment &CS = R.second.CS;
     if (!CS.size()) {
@@ -263,8 +263,8 @@ void ResourceManager::issueInstruction(
       // Replace the resource mask with a valid processor resource index.
       const ResourceState &RS = *Resources[getResourceStateIndex(Pipe.first)];
       Pipe.first = RS.getProcResourceID();
-      Pipes.emplace_back(
-          std::pair<ResourceRef, double>(Pipe, static_cast<double>(CS.size())));
+      Pipes.emplace_back(std::pair<ResourceRef, ResourceCycles>(
+          Pipe, ResourceCycles(CS.size())));
     } else {
       assert((countPopulation(R.first) > 1) && "Expected a group!");
       // Mark this group as reserved.

llvm/tools/llvm-mca/lib/HardwareUnits/Scheduler.cpp

@@ -66,7 +66,7 @@ Scheduler::Status Scheduler::isAvailable(const InstRef &IR) const {
 
 void Scheduler::issueInstructionImpl(
     InstRef &IR,
-    SmallVectorImpl<std::pair<ResourceRef, double>> &UsedResources) {
+    SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &UsedResources) {
   Instruction *IS = IR.getInstruction();
   const InstrDesc &D = IS->getDesc();
 
@@ -86,7 +86,8 @@ void Scheduler::issueInstructionImpl(
 
 // Release the buffered resources and issue the instruction.
 void Scheduler::issueInstruction(
-    InstRef &IR, SmallVectorImpl<std::pair<ResourceRef, double>> &UsedResources,
+    InstRef &IR,
+    SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &UsedResources,
     SmallVectorImpl<InstRef> &ReadyInstructions) {
   const Instruction &Inst = *IR.getInstruction();
   bool HasDependentUsers = Inst.hasDependentUsers();

llvm/tools/llvm-mca/lib/Stages/ExecuteStage.cpp

@@ -53,11 +53,11 @@ bool ExecuteStage::isAvailable(const InstRef &IR) const {
 }
 
 Error ExecuteStage::issueInstruction(InstRef &IR) {
-  SmallVector<std::pair<ResourceRef, double>, 4> Used;
+  SmallVector<std::pair<ResourceRef, ResourceCycles>, 4> Used;
   SmallVector<InstRef, 4> Ready;
   HWS.issueInstruction(IR, Used, Ready);
 
-  notifyReservedOrReleasedBuffers(IR, /* Reserved */false);
+  notifyReservedOrReleasedBuffers(IR, /* Reserved */ false);
   notifyInstructionIssued(IR, Used);
   if (IR.getInstruction()->isExecuted()) {
     notifyInstructionExecuted(IR);
@@ -120,7 +120,7 @@ Error ExecuteStage::execute(InstRef &IR) {
   // be released after MCIS is issued, and all the ResourceCycles for those
   // units have been consumed.
   HWS.dispatch(IR);
-  notifyReservedOrReleasedBuffers(IR, /* Reserved */true);
+  notifyReservedOrReleasedBuffers(IR, /* Reserved */ true);
   if (!HWS.isReady(IR))
     return ErrorSuccess();
 
@@ -156,10 +156,10 @@ void ExecuteStage::notifyResourceAvailable(const ResourceRef &RR) {
 }
 
 void ExecuteStage::notifyInstructionIssued(
-    const InstRef &IR, ArrayRef<std::pair<ResourceRef, double>> Used) {
+    const InstRef &IR, ArrayRef<std::pair<ResourceRef, ResourceCycles>> Used) {
   LLVM_DEBUG({
     dbgs() << "[E] Instruction Issued: #" << IR << '\n';
-    for (const std::pair<ResourceRef, unsigned> &Resource : Used) {
+    for (const std::pair<ResourceRef, ResourceCycles> &Resource : Used) {
       dbgs() << "[E] Resource Used: [" << Resource.first.first << '.'
              << Resource.first.second << "], ";
       dbgs() << "cycles: " << Resource.second << '\n';

llvm/tools/llvm-mca/lib/Stages/InstructionTables.cpp

@@ -31,17 +31,17 @@ Error InstructionTables::execute(InstRef &IR) {
     // Skip zero-cycle resources (i.e., unused resources).
     if (!Resource.second.size())
       continue;
-    double Cycles = static_cast<double>(Resource.second.size());
+    unsigned Cycles = Resource.second.size();
     unsigned Index = std::distance(
         Masks.begin(), std::find(Masks.begin(), Masks.end(), Resource.first));
     const MCProcResourceDesc &ProcResource = *SM.getProcResource(Index);
     unsigned NumUnits = ProcResource.NumUnits;
     if (!ProcResource.SubUnitsIdxBegin) {
       // The number of cycles consumed by each unit.
-      Cycles /= NumUnits;
       for (unsigned I = 0, E = NumUnits; I < E; ++I) {
         ResourceRef ResourceUnit = std::make_pair(Index, 1U << I);
-        UsedResources.emplace_back(std::make_pair(ResourceUnit, Cycles));
+        UsedResources.emplace_back(
+            std::make_pair(ResourceUnit, ResourceCycles(Cycles, NumUnits)));
       }
       continue;
     }
@@ -53,10 +53,10 @@ Error InstructionTables::execute(InstRef &IR) {
       unsigned SubUnitIdx = ProcResource.SubUnitsIdxBegin[I1];
       const MCProcResourceDesc &SubUnit = *SM.getProcResource(SubUnitIdx);
       // Compute the number of cycles consumed by each resource unit.
-      double RUCycles = Cycles / (NumUnits * SubUnit.NumUnits);
       for (unsigned I2 = 0, E2 = SubUnit.NumUnits; I2 < E2; ++I2) {
         ResourceRef ResourceUnit = std::make_pair(SubUnitIdx, 1U << I2);
-        UsedResources.emplace_back(std::make_pair(ResourceUnit, RUCycles));
+        UsedResources.emplace_back(std::make_pair(
+            ResourceUnit, ResourceCycles(Cycles, NumUnits * SubUnit.NumUnits)));
       }
     }
   }