Further improve string bench timing

Further improve the timings of the string benchmarks.  Ensure most take
between 1 and 4 seconds to improve accuracy.  Overall time taken increases
by 35%.  Tested on AArch64.

Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>

	* benchtests/bench-math-inlines.c: Increase iterations.
	* benchtests/bench-memcmp.c: Likewise.
	* benchtests/bench-rawmemchr.c: Likewise.
	* benchtests/bench-strcmp.c: Likewise.
	* benchtests/bench-strcpy_chk.c: Likewise.
	* benchtests/bench-string.h (INNER_LOOP_ITERS8): Add define.
	(INNER_LOOP_ITERS_MEDIUM): Increase iterations.
	(INNER_LOOP_ITERS_SMALL): Likewise.
	* benchtests/bench-strncat.c: Increase iterations.
	* benchtests/bench-strncmp.c: Increase iterations.
	* benchtests/bench-strncpy.c: Reduce iterations for wide strings.
	* benchtests/bench-strrchr.c: Increase iterations.
	* benchtests/bench-strstr.c: Keep iterations unchanged.
	* benchtests/bench-strtod.c: Increase iterations.

1 files changed, 1 insertions, 1 deletions

diff --git a/benchtests/bench-strncpy.c b/benchtests/bench-strncpy.c
index c6a6799a2f..a26232f423 100644
--- a/benchtests/bench-strncpy.c
+++ b/benchtests/bench-strncpy.c
@@ -54,7 +54,7 @@ typedef CHAR *(*proto_t) (CHAR *, const CHAR *, size_t);
 static void
 do_one_test (impl_t *impl, CHAR *dst, const CHAR *src, size_t len, size_t n)
 {
-  size_t i, iters = INNER_LOOP_ITERS_LARGE;
+  size_t i, iters = INNER_LOOP_ITERS_LARGE * (4 / CHARBYTES);
   timing_t start, stop, cur;
 
   if (CALL (impl, dst, src, n) != STRNCPY_RESULT (dst, len, n))