Refine bench_record and bench_playback:

  - use high-precision wall timer only
  - warm caches once before measuring
  - measure independent samples, calculating statistics
  - add --verbose to control how much data we output

Also removed some unloved features from bench_record.

BUG=skia:
R=jcgregorio@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/338203002

2 files changed, 36 insertions, 3 deletions

diff --git a/bench/BenchTimer.cpp b/bench/BenchTimer.cpp
index 3617f9de58..f3e8e3b0ec 100644
--- a/bench/BenchTimer.cpp
+++ b/bench/BenchTimer.cpp
@@ -76,3 +76,19 @@ void BenchTimer::truncatedEnd() {
     fTruncatedCpu = fTruncatedSysTimer->endCpu() * fDurationScale;
     fTruncatedWall = fTruncatedSysTimer->endWall() * fDurationScale;
 }
+
+WallTimer::WallTimer() : fWall(-1.0), fSysTimer(new BenchSysTimer) {}
+
+WallTimer::~WallTimer() {
+    delete fSysTimer;
+}
+
+void WallTimer::start(double durationScale) {
+    fDurationScale = durationScale;
+    fSysTimer->startWall();
+}
+
+void WallTimer::end() {
+    fWall = fSysTimer->endWall() * fDurationScale;
+}
+
diff --git a/bench/BenchTimer.h b/bench/BenchTimer.h
index 09950a734b..2abf10b80f 100644
--- a/bench/BenchTimer.h
+++ b/bench/BenchTimer.h
@@ -39,12 +39,29 @@ public:
     double fGpu;
 
 private:
-    BenchSysTimer *fSysTimer;
-    BenchSysTimer *fTruncatedSysTimer;
+    BenchSysTimer* fSysTimer;
+    BenchSysTimer* fTruncatedSysTimer;
 #if SK_SUPPORT_GPU
-    BenchGpuTimer *fGpuTimer;
+    BenchGpuTimer* fGpuTimer;
 #endif
     double fDurationScale;  // for this start/end session
 };
 
+// Same as BenchTimer above, supporting only fWall but with much lower overhead.
+// (Typically, ~30ns instead of BenchTimer's ~1us.)
+class WallTimer {
+public:
+    WallTimer();
+    ~WallTimer();
+
+    void start(double durationScale = 1);
+    void end();
+
+    double fWall;
+
+private:
+    BenchSysTimer* fSysTimer;
+    double fDurationScale;
+};
+
 #endif