aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/bench/mem-memcpy.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/bench/mem-memcpy.c')
-rw-r--r--tools/perf/bench/mem-memcpy.c106
1 files changed, 57 insertions, 49 deletions
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index db82021f4b9..5ce71d3b72c 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -5,7 +5,6 @@
*
* Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*/
-#include <ctype.h>
#include "../perf.h"
#include "../util/util.h"
@@ -24,19 +23,22 @@
static const char *length_str = "1MB";
static const char *routine = "default";
-static bool use_clock;
-static int clock_fd;
+static int iterations = 1;
+static bool use_cycle;
+static int cycle_fd;
static bool only_prefault;
static bool no_prefault;
static const struct option options[] = {
OPT_STRING('l', "length", &length_str, "1MB",
"Specify length of memory to copy. "
- "available unit: B, MB, GB (upper and lower)"),
+ "Available units: B, KB, MB, GB and TB (upper and lower)"),
OPT_STRING('r', "routine", &routine, "default",
"Specify routine to copy"),
- OPT_BOOLEAN('c', "clock", &use_clock,
- "Use CPU clock for measuring"),
+ OPT_INTEGER('i', "iterations", &iterations,
+ "repeat memcpy() invocation this number of times"),
+ OPT_BOOLEAN('c', "cycle", &use_cycle,
+ "Use cycles event instead of gettimeofday() for measuring"),
OPT_BOOLEAN('o', "only-prefault", &only_prefault,
"Show only the result with page faults before memcpy()"),
OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -56,7 +58,7 @@ struct routine routines[] = {
{ "default",
"Default memcpy() provided by glibc",
memcpy },
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
#include "mem-memcpy-x86-64-asm-def.h"
@@ -74,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = {
NULL
};
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES
};
-static void init_clock(void)
+static void init_cycle(void)
{
- clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+ cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
- if (clock_fd < 0 && errno == ENOSYS)
+ if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
else
- BUG_ON(clock_fd < 0);
+ BUG_ON(cycle_fd < 0);
}
-static u64 get_clock(void)
+static u64 get_cycle(void)
{
int ret;
u64 clk;
- ret = read(clock_fd, &clk, sizeof(u64));
+ ret = read(cycle_fd, &clk, sizeof(u64));
BUG_ON(ret != sizeof(u64));
return clk;
@@ -109,37 +111,42 @@ static double timeval2double(struct timeval *ts)
static void alloc_mem(void **dst, void **src, size_t length)
{
*dst = zalloc(length);
- if (!dst)
+ if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
*src = zalloc(length);
- if (!src)
+ if (!*src)
die("memory allocation failed - maybe length is too large?\n");
+ /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
+ memset(*src, 0, length);
}
-static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
{
- u64 clock_start = 0ULL, clock_end = 0ULL;
+ u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *src = NULL, *dst = NULL;
+ int i;
alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
- clock_start = get_clock();
- fn(dst, src, len);
- clock_end = get_clock();
+ cycle_start = get_cycle();
+ for (i = 0; i < iterations; ++i)
+ fn(dst, src, len);
+ cycle_end = get_cycle();
free(src);
free(dst);
- return clock_end - clock_start;
+ return cycle_end - cycle_start;
}
static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
void *src = NULL, *dst = NULL;
+ int i;
alloc_mem(&src, &dst, len);
@@ -147,7 +154,8 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
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);
@@ -171,22 +179,22 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
} while (0)
int bench_mem_memcpy(int argc, const char **argv,
- const char *prefix __used)
+ const char *prefix __maybe_unused)
{
int i;
size_t len;
double result_bps[2];
- u64 result_clock[2];
+ u64 result_cycle[2];
argc = parse_options(argc, argv, options,
bench_mem_memcpy_usage, 0);
- if (use_clock)
- init_clock();
+ if (use_cycle)
+ init_cycle();
len = (size_t)perf_atoll((char *)length_str);
- result_clock[0] = result_clock[1] = 0ULL;
+ result_cycle[0] = result_cycle[1] = 0ULL;
result_bps[0] = result_bps[1] = 0.0;
if ((s64)len <= 0) {
@@ -217,11 +225,11 @@ int bench_mem_memcpy(int argc, const char **argv,
if (!only_prefault && !no_prefault) {
/* show both of results */
- if (use_clock) {
- result_clock[0] =
- do_memcpy_clock(routines[i].fn, len, false);
- result_clock[1] =
- do_memcpy_clock(routines[i].fn, len, true);
+ if (use_cycle) {
+ result_cycle[0] =
+ do_memcpy_cycle(routines[i].fn, len, false);
+ result_cycle[1] =
+ do_memcpy_cycle(routines[i].fn, len, true);
} else {
result_bps[0] =
do_memcpy_gettimeofday(routines[i].fn,
@@ -231,9 +239,9 @@ int bench_mem_memcpy(int argc, const char **argv,
len, true);
}
} else {
- if (use_clock) {
- result_clock[pf] =
- do_memcpy_clock(routines[i].fn,
+ if (use_cycle) {
+ result_cycle[pf] =
+ do_memcpy_cycle(routines[i].fn,
len, only_prefault);
} else {
result_bps[pf] =
@@ -245,12 +253,12 @@ int bench_mem_memcpy(int argc, const char **argv,
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
if (!only_prefault && !no_prefault) {
- if (use_clock) {
- printf(" %14lf Clock/Byte\n",
- (double)result_clock[0]
+ if (use_cycle) {
+ printf(" %14lf Cycle/Byte\n",
+ (double)result_cycle[0]
/ (double)len);
- printf(" %14lf Clock/Byte (with prefault)\n",
- (double)result_clock[1]
+ printf(" %14lf Cycle/Byte (with prefault)\n",
+ (double)result_cycle[1]
/ (double)len);
} else {
print_bps(result_bps[0]);
@@ -259,9 +267,9 @@ int bench_mem_memcpy(int argc, const char **argv,
printf(" (with prefault)\n");
}
} else {
- if (use_clock) {
- printf(" %14lf Clock/Byte",
- (double)result_clock[pf]
+ if (use_cycle) {
+ printf(" %14lf Cycle/Byte",
+ (double)result_cycle[pf]
/ (double)len);
} else
print_bps(result_bps[pf]);
@@ -271,17 +279,17 @@ int bench_mem_memcpy(int argc, const char **argv,
break;
case BENCH_FORMAT_SIMPLE:
if (!only_prefault && !no_prefault) {
- if (use_clock) {
+ if (use_cycle) {
printf("%lf %lf\n",
- (double)result_clock[0] / (double)len,
- (double)result_clock[1] / (double)len);
+ (double)result_cycle[0] / (double)len,
+ (double)result_cycle[1] / (double)len);
} else {
printf("%lf %lf\n",
result_bps[0], result_bps[1]);
}
} else {
- if (use_clock) {
- printf("%lf\n", (double)result_clock[pf]
+ if (use_cycle) {
+ printf("%lf\n", (double)result_cycle[pf]
/ (double)len);
} else
printf("%lf\n", result_bps[pf]);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 16:28:17 +0000