Remove countMaskInv caching in bench framework

We were saving a div by caching the inverse as a float, but this
ended up requiring a int -> float -> int conversion, which takes
almost as much time as the difference between float mul and div.

There are lots of other more pressing issues with the bench
framework which probably require simply removing the adaptive
iteration count stuff anyway.

Author: TheBlueMatt

src/bench/bench.cpp

@@ -55,21 +55,20 @@ bool benchmark::State::KeepRunning()
     else {
         now = gettimedouble();
         double elapsed = now - lastTime;
-        double elapsedOne = elapsed * countMaskInv;
+        double elapsedOne = elapsed / (countMask + 1);
         if (elapsedOne < minTime) minTime = elapsedOne;
         if (elapsedOne > maxTime) maxTime = elapsedOne;
 
         // We only use relative values, so don't have to handle 64-bit wrap-around specially
         nowCycles = perf_cpucycles();
-        uint64_t elapsedOneCycles = (nowCycles - lastCycles) * countMaskInv;
+        uint64_t elapsedOneCycles = (nowCycles - lastCycles) / (countMask + 1);
         if (elapsedOneCycles < minCycles) minCycles = elapsedOneCycles;
         if (elapsedOneCycles > maxCycles) maxCycles = elapsedOneCycles;
 
         if (elapsed*128 < maxElapsed) {
           // If the execution was much too fast (1/128th of maxElapsed), increase the count mask by 8x and restart timing.
           // The restart avoids including the overhead of this code in the measurement.
           countMask = ((countMask<<3)|7) & ((1LL<<60)-1);
-          countMaskInv = 1./(countMask+1);
           count = 0;
           minTime = std::numeric_limits<double>::max();
           maxTime = std::numeric_limits<double>::min();
@@ -81,7 +80,6 @@ bool benchmark::State::KeepRunning()
           uint64_t newCountMask = ((countMask<<1)|1) & ((1LL<<60)-1);
           if ((count & newCountMask)==0) {
               countMask = newCountMask;
-              countMaskInv = 1./(countMask+1);
           }
         }
     }

src/bench/bench.h

@@ -41,7 +41,7 @@ namespace benchmark {
         std::string name;
         double maxElapsed;
         double beginTime;
-        double lastTime, minTime, maxTime, countMaskInv;
+        double lastTime, minTime, maxTime;
         uint64_t count;
         uint64_t countMask;
         uint64_t beginCycles;
@@ -55,7 +55,6 @@ namespace benchmark {
             minCycles = std::numeric_limits<uint64_t>::max();
             maxCycles = std::numeric_limits<uint64_t>::min();
             countMask = 1;
-            countMaskInv = 1./(countMask + 1);
         }
         bool KeepRunning();
     };