Allow multiple input domains to be run in the same benchmark program

Some math functions have distinct performance characteristics in
specific domains of inputs, where some inputs return via a fast path
while other inputs require multiple precision calculations, that too
at different precision levels.  The way to implement different domains
was to have a separate source file and benchmark definition, resulting
in separate programs.

This clutters up the benchmark, so this change allows these domains to
be consolidated into the same input file.  To do this, the input file
format is now enhanced to allow comments with a preceding # and
directives with two # at the begining of a line.  A directive that
looks like:

tells the benchmark generation script that what follows is a different
domain of inputs.  The value of the 'name' directive (in this case,
foo) is used in the output.  The two input domains are then executed
sequentially and their results collated separately.  with the above
directive, there would be two lines in the result that look like:

func(): ....
func(foo): ...

1 files changed, 41 insertions, 38 deletions

diff --git a/benchtests/bench-skeleton.c b/benchtests/bench-skeleton.c
index bbd151b..7359184 100644
--- a/benchtests/bench-skeleton.c
+++ b/benchtests/bench-skeleton.c
@@ -25,12 +25,11 @@
 #define TIMESPEC_AFTER(a, b) \
   (((a).tv_sec == (b).tv_sec) ?						      \
      ((a).tv_nsec > (b).tv_nsec) :					      \
-        ((a).tv_sec > (b).tv_sec))
+	((a).tv_sec > (b).tv_sec))
 int
 main (int argc, char **argv)
 {
   unsigned long i, k;
-  uint64_t total = 0, max = 0, min = 0x7fffffffffffffff;
   struct timespec start, end, runtime;
 
   memset (&runtime, 0, sizeof (runtime));
@@ -45,53 +44,57 @@ main (int argc, char **argv)
      but it's better than having nothing at all.  */
   unsigned long iters = 1000 * start.tv_nsec;
 
-  /* Run for approxmately DURATION seconds.  */
-  clock_gettime (CLOCK_MONOTONIC_RAW, &runtime);
-  runtime.tv_sec += DURATION;
-
-  double d_total_i = 0;
-  while (1)
+  for (int v = 0; v < NUM_VARIANTS; v++)
     {
-      for (i = 0; i < NUM_SAMPLES; i++)
-	{
-	  clock_gettime (CLOCK_PROCESS_CPUTIME_ID, &start);
-	  for (k = 0; k < iters; k++)
-	    BENCH_FUNC(i);
-	  clock_gettime (CLOCK_PROCESS_CPUTIME_ID, &end);
+      /* Run for approximately DURATION seconds.  */
+      clock_gettime (CLOCK_MONOTONIC_RAW, &runtime);
+      runtime.tv_sec += DURATION;
 
-	  uint64_t cur = (end.tv_nsec - start.tv_nsec
-			 + ((end.tv_sec - start.tv_sec)
-			    * (uint64_t) 1000000000));
+      double d_total_i = 0;
+      uint64_t total = 0, max = 0, min = 0x7fffffffffffffff;
+      while (1)
+	{
+	  for (i = 0; i < NUM_SAMPLES (v); i++)
+	    {
+	      clock_gettime (CLOCK_PROCESS_CPUTIME_ID, &start);
+	      for (k = 0; k < iters; k++)
+		BENCH_FUNC (v, i);
+	      clock_gettime (CLOCK_PROCESS_CPUTIME_ID, &end);
 
-	  if (cur > max)
-	    max = cur;
+	      uint64_t cur = (end.tv_nsec - start.tv_nsec
+			      + ((end.tv_sec - start.tv_sec)
+				 * (uint64_t) 1000000000));
 
-	  if (cur < min)
-	    min = cur;
+	      if (cur > max)
+		max = cur;
 
-	  total += cur;
+	      if (cur < min)
+		min = cur;
 
-	  d_total_i += iters;
-	}
+	      total += cur;
 
-      struct timespec curtime;
+	      d_total_i += iters;
+	    }
+	  struct timespec curtime;
 
-      memset (&curtime, 0, sizeof (curtime));
-      clock_gettime (CLOCK_MONOTONIC_RAW, &curtime);
-      if (TIMESPEC_AFTER (curtime, runtime))
-	goto done;
-    }
+	  memset (&curtime, 0, sizeof (curtime));
+	  clock_gettime (CLOCK_MONOTONIC_RAW, &curtime);
+	  if (TIMESPEC_AFTER (curtime, runtime))
+	    goto done;
+	}
 
-  double d_total_s;
-  double d_iters;
+      double d_total_s;
+      double d_iters;
 
- done:
-  d_total_s = total * 1e-9;
-  d_iters = iters;
+    done:
+      d_total_s = total * 1e-9;
+      d_iters = iters;
 
-  printf (FUNCNAME ": ITERS:%g: TOTAL:%gs, MAX:%gns, MIN:%gns, %g iter/s\n",
-	  d_total_i, d_total_s, max / d_iters, min / d_iters,
-	  d_total_i / d_total_s);
+      printf ("%s: ITERS:%g: TOTAL:%gs, MAX:%gns, MIN:%gns, %g iter/s\n",
+	      VARIANT (v),
+	      d_total_i, d_total_s, max / d_iters, min / d_iters,
+	      d_total_i / d_total_s);
+    }
 
   return 0;
 }