[MCA] Show aggregate over Average Wait times for the whole snippet (PR43219)

Summary:
As disscused in https://bugs.llvm.org/show_bug.cgi?id=43219,
i believe it may be somewhat useful to show //some// aggregates
over all the sea of statistics provided.

Example:
```
Average Wait times (based on the timeline view):
[0]: Executions
[1]: Average time spent waiting in a scheduler's queue
[2]: Average time spent waiting in a scheduler's queue while ready
[3]: Average time elapsed from WB until retire stage

      [0]    [1]    [2]    [3]
0.     3     1.0    1.0    4.7       vmulps     %xmm0, %xmm1, %xmm2
1.     3     2.7    0.0    2.3       vhaddps    %xmm2, %xmm2, %xmm3
2.     3     6.0    0.0    0.0       vhaddps    %xmm3, %xmm3, %xmm4
       3     3.2    0.3    2.3       <total>
```
I.e. we average the averages.

Reviewers: andreadb, mattd, RKSimon

Reviewed By: andreadb

Subscribers: gbedwell, arphaman, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D68714

llvm-svn: 374361

1 files changed, 41 insertions, 9 deletions

diff --git a/llvm/tools/llvm-mca/Views/TimelineView.cpp b/llvm/tools/llvm-mca/Views/TimelineView.cpp
index fe3f16ba344..1e7caa297ac 100644
--- a/llvm/tools/llvm-mca/Views/TimelineView.cpp
+++ b/llvm/tools/llvm-mca/Views/TimelineView.cpp
@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "Views/TimelineView.h"
+#include <numeric>
 
 namespace llvm {
 namespace mca {
@@ -132,25 +133,38 @@ void TimelineView::printWaitTimeEntry(formatted_raw_ostream &OS,
                                       const WaitTimeEntry &Entry,
                                       unsigned SourceIndex,
                                       unsigned Executions) const {
-  OS << SourceIndex << '.';
+  bool PrintingTotals = SourceIndex == Source.size();
+  unsigned CumulativeExecutions = PrintingTotals ? Timeline.size() : Executions;
+
+  if (!PrintingTotals)
+    OS << SourceIndex << '.';
+
   OS.PadToColumn(7);
 
   double AverageTime1, AverageTime2, AverageTime3;
-  AverageTime1 = (double)Entry.CyclesSpentInSchedulerQueue / Executions;
-  AverageTime2 = (double)Entry.CyclesSpentInSQWhileReady / Executions;
-  AverageTime3 = (double)Entry.CyclesSpentAfterWBAndBeforeRetire / Executions;
+  AverageTime1 =
+      (double)Entry.CyclesSpentInSchedulerQueue / CumulativeExecutions;
+  AverageTime2 = (double)Entry.CyclesSpentInSQWhileReady / CumulativeExecutions;
+  AverageTime3 =
+      (double)Entry.CyclesSpentAfterWBAndBeforeRetire / CumulativeExecutions;
 
   OS << Executions;
   OS.PadToColumn(13);
-  int BufferSize = UsedBuffer[SourceIndex].second;
-  tryChangeColor(OS, Entry.CyclesSpentInSchedulerQueue, Executions, BufferSize);
+
+  int BufferSize = PrintingTotals ? 0 : UsedBuffer[SourceIndex].second;
+  if (!PrintingTotals)
+    tryChangeColor(OS, Entry.CyclesSpentInSchedulerQueue, CumulativeExecutions,
+                   BufferSize);
   OS << format("%.1f", floor((AverageTime1 * 10) + 0.5) / 10);
   OS.PadToColumn(20);
-  tryChangeColor(OS, Entry.CyclesSpentInSQWhileReady, Executions, BufferSize);
+  if (!PrintingTotals)
+    tryChangeColor(OS, Entry.CyclesSpentInSQWhileReady, CumulativeExecutions,
+                   BufferSize);
   OS << format("%.1f", floor((AverageTime2 * 10) + 0.5) / 10);
   OS.PadToColumn(27);
-  tryChangeColor(OS, Entry.CyclesSpentAfterWBAndBeforeRetire, Executions,
-                 STI.getSchedModel().MicroOpBufferSize);
+  if (!PrintingTotals)
+    tryChangeColor(OS, Entry.CyclesSpentAfterWBAndBeforeRetire,
+                   CumulativeExecutions, STI.getSchedModel().MicroOpBufferSize);
   OS << format("%.1f", floor((AverageTime3 * 10) + 0.5) / 10);
 
   if (OS.has_colors())
@@ -190,6 +204,24 @@ void TimelineView::printAverageWaitTimes(raw_ostream &OS) const {
 
     ++IID;
   }
+
+  // If the timeline contains more than one instruction,
+  // let's also print global averages.
+  if (Source.size() != 1) {
+    WaitTimeEntry TotalWaitTime = std::accumulate(
+        WaitTime.begin(), WaitTime.end(), WaitTimeEntry{0, 0, 0},
+        [](const WaitTimeEntry &A, const WaitTimeEntry &B) {
+          return WaitTimeEntry{
+              A.CyclesSpentInSchedulerQueue + B.CyclesSpentInSchedulerQueue,
+              A.CyclesSpentInSQWhileReady + B.CyclesSpentInSQWhileReady,
+              A.CyclesSpentAfterWBAndBeforeRetire +
+                  B.CyclesSpentAfterWBAndBeforeRetire};
+        });
+    printWaitTimeEntry(FOS, TotalWaitTime, IID, Executions);
+    FOS << "   "
+        << "<total>" << '\n';
+    InstrStream.flush();
+  }
 }
 
 void TimelineView::printTimelineViewEntry(formatted_raw_ostream &OS,