mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH 4/4] perf/x86-64: allow passing an iteration count to "bench mem mem{cpy,set}"
@ 2012-01-18 13:29 Jan Beulich
  2012-01-26 13:34 ` [tip:perf/core] perf bench: Allow passing an iteration count to " bench " tip-bot for Jan Beulich
  0 siblings, 1 reply; 2+ messages in thread
From: Jan Beulich @ 2012-01-18 13:29 UTC (permalink / raw)
  To: a.p.zijlstra, mingo, acme, paulus; +Cc: linux-kernel

"perf stat ... perf bench mem mem..." is pretty meaningless when using
small block sizes (as the overhead of the invocation of each test run
basically hides the actual test result in the noise). Repeating the
actually interesting function's invocation a number of times allows the
results to become meaningful.

Signed-off-by: Jan Beulich <jbeulich@suse.com>

--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -24,6 +24,7 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
+static int		iterations	= 1;
 static bool		use_clock;
 static int		clock_fd;
 static bool		only_prefault;
@@ -35,6 +36,8 @@ static const struct option options[] = {
 		    "available unit: B, MB, GB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memcpy() invocation this number of times"),
 	OPT_BOOLEAN('c', "clock", &use_clock,
 		    "Use CPU clock for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
@@ -121,6 +124,7 @@ static u64 do_memcpy_clock(memcpy_t fn, 
 {
 	u64 clock_start = 0ULL, clock_end = 0ULL;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
@@ -128,7 +132,8 @@ static u64 do_memcpy_clock(memcpy_t fn, 
 		fn(dst, src, len);
 
 	clock_start = get_clock();
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	clock_end = get_clock();
 
 	free(src);
@@ -140,6 +145,7 @@ static double do_memcpy_gettimeofday(mem
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
@@ -147,7 +153,8 @@ static double do_memcpy_gettimeofday(mem
 		fn(dst, src, len);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -24,6 +24,7 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
+static int		iterations	= 1;
 static bool		use_clock;
 static int		clock_fd;
 static bool		only_prefault;
@@ -35,6 +36,8 @@ static const struct option options[] = {
 		    "available unit: B, MB, GB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memset() invocation this number of times"),
 	OPT_BOOLEAN('c', "clock", &use_clock,
 		    "Use CPU clock for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
@@ -117,6 +120,7 @@ static u64 do_memset_clock(memset_t fn, 
 {
 	u64 clock_start = 0ULL, clock_end = 0ULL;
 	void *dst = NULL;
+	int i;
 
 	alloc_mem(&dst, len);
 
@@ -124,7 +128,8 @@ static u64 do_memset_clock(memset_t fn, 
 		fn(dst, -1, len);
 
 	clock_start = get_clock();
-	fn(dst, 0, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
 	clock_end = get_clock();
 
 	free(dst);
@@ -135,6 +140,7 @@ static double do_memset_gettimeofday(mem
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	void *dst = NULL;
+	int i;
 
 	alloc_mem(&dst, len);
 
@@ -142,7 +148,8 @@ static double do_memset_gettimeofday(mem
 		fn(dst, -1, len);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	fn(dst, 0, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);




^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2012-01-26 13:34 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2012-01-18 13:29 [PATCH 4/4] perf/x86-64: allow passing an iteration count to "bench mem mem{cpy,set}" Jan Beulich
2012-01-26 13:34 ` [tip:perf/core] perf bench: Allow passing an iteration count to " bench " tip-bot for Jan Beulich

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome