perf bench: Prepare memcpy for merge
The memset benchmark is largely copy-pasted from the memcpy benchmark. Prepare the memcpy file for merge with memset by extracting out a generic function. Signed-off-by: Rabin Vincent <rabin.vincent@axis.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Rabin Vincent <rabinv@axis.com> Link: http://lkml.kernel.org/r/1417535441-3965-1-git-send-email-rabin.vincent@axis.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
cfa0bd52d0
commit
308197b947
@ -52,16 +52,18 @@ typedef void *(*memcpy_t)(void *, const void *, size_t);
|
|||||||
struct routine {
|
struct routine {
|
||||||
const char *name;
|
const char *name;
|
||||||
const char *desc;
|
const char *desc;
|
||||||
memcpy_t fn;
|
union {
|
||||||
|
memcpy_t memcpy;
|
||||||
|
} fn;
|
||||||
};
|
};
|
||||||
|
|
||||||
struct routine routines[] = {
|
struct routine memcpy_routines[] = {
|
||||||
{ "default",
|
{ .name = "default",
|
||||||
"Default memcpy() provided by glibc",
|
.desc = "Default memcpy() provided by glibc",
|
||||||
memcpy },
|
.fn.memcpy = memcpy },
|
||||||
#ifdef HAVE_ARCH_X86_64_SUPPORT
|
#ifdef HAVE_ARCH_X86_64_SUPPORT
|
||||||
|
|
||||||
#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
|
#define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn},
|
||||||
#include "mem-memcpy-x86-64-asm-def.h"
|
#include "mem-memcpy-x86-64-asm-def.h"
|
||||||
#undef MEMCPY_FN
|
#undef MEMCPY_FN
|
||||||
|
|
||||||
@ -69,7 +71,7 @@ struct routine routines[] = {
|
|||||||
|
|
||||||
{ NULL,
|
{ NULL,
|
||||||
NULL,
|
NULL,
|
||||||
NULL }
|
{NULL} }
|
||||||
};
|
};
|
||||||
|
|
||||||
static const char * const bench_mem_memcpy_usage[] = {
|
static const char * const bench_mem_memcpy_usage[] = {
|
||||||
@ -110,63 +112,6 @@ static double timeval2double(struct timeval *ts)
|
|||||||
(double)ts->tv_usec / (double)1000000;
|
(double)ts->tv_usec / (double)1000000;
|
||||||
}
|
}
|
||||||
|
|
||||||
static void alloc_mem(void **dst, void **src, size_t length)
|
|
||||||
{
|
|
||||||
*dst = zalloc(length);
|
|
||||||
if (!*dst)
|
|
||||||
die("memory allocation failed - maybe length is too large?\n");
|
|
||||||
|
|
||||||
*src = zalloc(length);
|
|
||||||
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_cycle(memcpy_t fn, size_t len, bool prefault)
|
|
||||||
{
|
|
||||||
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);
|
|
||||||
|
|
||||||
cycle_start = get_cycle();
|
|
||||||
for (i = 0; i < iterations; ++i)
|
|
||||||
fn(dst, src, len);
|
|
||||||
cycle_end = get_cycle();
|
|
||||||
|
|
||||||
free(src);
|
|
||||||
free(dst);
|
|
||||||
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);
|
|
||||||
|
|
||||||
if (prefault)
|
|
||||||
fn(dst, src, len);
|
|
||||||
|
|
||||||
BUG_ON(gettimeofday(&tv_start, NULL));
|
|
||||||
for (i = 0; i < iterations; ++i)
|
|
||||||
fn(dst, src, len);
|
|
||||||
BUG_ON(gettimeofday(&tv_end, NULL));
|
|
||||||
|
|
||||||
timersub(&tv_end, &tv_start, &tv_diff);
|
|
||||||
|
|
||||||
free(src);
|
|
||||||
free(dst);
|
|
||||||
return (double)((double)len / timeval2double(&tv_diff));
|
|
||||||
}
|
|
||||||
|
|
||||||
#define pf (no_prefault ? 0 : 1)
|
#define pf (no_prefault ? 0 : 1)
|
||||||
|
|
||||||
#define print_bps(x) do { \
|
#define print_bps(x) do { \
|
||||||
@ -180,8 +125,16 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
|
|||||||
printf(" %14lf GB/Sec", x / K / K / K); \
|
printf(" %14lf GB/Sec", x / K / K / K); \
|
||||||
} while (0)
|
} while (0)
|
||||||
|
|
||||||
int bench_mem_memcpy(int argc, const char **argv,
|
struct bench_mem_info {
|
||||||
const char *prefix __maybe_unused)
|
const struct routine *routines;
|
||||||
|
u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault);
|
||||||
|
double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault);
|
||||||
|
const char *const *usage;
|
||||||
|
};
|
||||||
|
|
||||||
|
static int bench_mem_common(int argc, const char **argv,
|
||||||
|
const char *prefix __maybe_unused,
|
||||||
|
struct bench_mem_info *info)
|
||||||
{
|
{
|
||||||
int i;
|
int i;
|
||||||
size_t len;
|
size_t len;
|
||||||
@ -189,7 +142,7 @@ int bench_mem_memcpy(int argc, const char **argv,
|
|||||||
u64 result_cycle[2];
|
u64 result_cycle[2];
|
||||||
|
|
||||||
argc = parse_options(argc, argv, options,
|
argc = parse_options(argc, argv, options,
|
||||||
bench_mem_memcpy_usage, 0);
|
info->usage, 0);
|
||||||
|
|
||||||
if (no_prefault && only_prefault) {
|
if (no_prefault && only_prefault) {
|
||||||
fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
|
fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
|
||||||
@ -213,16 +166,16 @@ int bench_mem_memcpy(int argc, const char **argv,
|
|||||||
if (only_prefault && no_prefault)
|
if (only_prefault && no_prefault)
|
||||||
only_prefault = no_prefault = false;
|
only_prefault = no_prefault = false;
|
||||||
|
|
||||||
for (i = 0; routines[i].name; i++) {
|
for (i = 0; info->routines[i].name; i++) {
|
||||||
if (!strcmp(routines[i].name, routine))
|
if (!strcmp(info->routines[i].name, routine))
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
if (!routines[i].name) {
|
if (!info->routines[i].name) {
|
||||||
printf("Unknown routine:%s\n", routine);
|
printf("Unknown routine:%s\n", routine);
|
||||||
printf("Available routines...\n");
|
printf("Available routines...\n");
|
||||||
for (i = 0; routines[i].name; i++) {
|
for (i = 0; info->routines[i].name; i++) {
|
||||||
printf("\t%s ... %s\n",
|
printf("\t%s ... %s\n",
|
||||||
routines[i].name, routines[i].desc);
|
info->routines[i].name, info->routines[i].desc);
|
||||||
}
|
}
|
||||||
return 1;
|
return 1;
|
||||||
}
|
}
|
||||||
@ -234,25 +187,25 @@ int bench_mem_memcpy(int argc, const char **argv,
|
|||||||
/* show both of results */
|
/* show both of results */
|
||||||
if (use_cycle) {
|
if (use_cycle) {
|
||||||
result_cycle[0] =
|
result_cycle[0] =
|
||||||
do_memcpy_cycle(routines[i].fn, len, false);
|
info->do_cycle(&info->routines[i], len, false);
|
||||||
result_cycle[1] =
|
result_cycle[1] =
|
||||||
do_memcpy_cycle(routines[i].fn, len, true);
|
info->do_cycle(&info->routines[i], len, true);
|
||||||
} else {
|
} else {
|
||||||
result_bps[0] =
|
result_bps[0] =
|
||||||
do_memcpy_gettimeofday(routines[i].fn,
|
info->do_gettimeofday(&info->routines[i],
|
||||||
len, false);
|
len, false);
|
||||||
result_bps[1] =
|
result_bps[1] =
|
||||||
do_memcpy_gettimeofday(routines[i].fn,
|
info->do_gettimeofday(&info->routines[i],
|
||||||
len, true);
|
len, true);
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
if (use_cycle) {
|
if (use_cycle) {
|
||||||
result_cycle[pf] =
|
result_cycle[pf] =
|
||||||
do_memcpy_cycle(routines[i].fn,
|
info->do_cycle(&info->routines[i],
|
||||||
len, only_prefault);
|
len, only_prefault);
|
||||||
} else {
|
} else {
|
||||||
result_bps[pf] =
|
result_bps[pf] =
|
||||||
do_memcpy_gettimeofday(routines[i].fn,
|
info->do_gettimeofday(&info->routines[i],
|
||||||
len, only_prefault);
|
len, only_prefault);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@ -310,3 +263,76 @@ int bench_mem_memcpy(int argc, const char **argv,
|
|||||||
|
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static void memcpy_alloc_mem(void **dst, void **src, size_t length)
|
||||||
|
{
|
||||||
|
*dst = zalloc(length);
|
||||||
|
if (!*dst)
|
||||||
|
die("memory allocation failed - maybe length is too large?\n");
|
||||||
|
|
||||||
|
*src = zalloc(length);
|
||||||
|
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_cycle(const struct routine *r, size_t len, bool prefault)
|
||||||
|
{
|
||||||
|
u64 cycle_start = 0ULL, cycle_end = 0ULL;
|
||||||
|
void *src = NULL, *dst = NULL;
|
||||||
|
memcpy_t fn = r->fn.memcpy;
|
||||||
|
int i;
|
||||||
|
|
||||||
|
memcpy_alloc_mem(&src, &dst, len);
|
||||||
|
|
||||||
|
if (prefault)
|
||||||
|
fn(dst, src, len);
|
||||||
|
|
||||||
|
cycle_start = get_cycle();
|
||||||
|
for (i = 0; i < iterations; ++i)
|
||||||
|
fn(dst, src, len);
|
||||||
|
cycle_end = get_cycle();
|
||||||
|
|
||||||
|
free(src);
|
||||||
|
free(dst);
|
||||||
|
return cycle_end - cycle_start;
|
||||||
|
}
|
||||||
|
|
||||||
|
static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
|
||||||
|
bool prefault)
|
||||||
|
{
|
||||||
|
struct timeval tv_start, tv_end, tv_diff;
|
||||||
|
memcpy_t fn = r->fn.memcpy;
|
||||||
|
void *src = NULL, *dst = NULL;
|
||||||
|
int i;
|
||||||
|
|
||||||
|
memcpy_alloc_mem(&src, &dst, len);
|
||||||
|
|
||||||
|
if (prefault)
|
||||||
|
fn(dst, src, len);
|
||||||
|
|
||||||
|
BUG_ON(gettimeofday(&tv_start, NULL));
|
||||||
|
for (i = 0; i < iterations; ++i)
|
||||||
|
fn(dst, src, len);
|
||||||
|
BUG_ON(gettimeofday(&tv_end, NULL));
|
||||||
|
|
||||||
|
timersub(&tv_end, &tv_start, &tv_diff);
|
||||||
|
|
||||||
|
free(src);
|
||||||
|
free(dst);
|
||||||
|
return (double)((double)len / timeval2double(&tv_diff));
|
||||||
|
}
|
||||||
|
|
||||||
|
int bench_mem_memcpy(int argc, const char **argv,
|
||||||
|
const char *prefix __maybe_unused)
|
||||||
|
{
|
||||||
|
struct bench_mem_info info = {
|
||||||
|
.routines = memcpy_routines,
|
||||||
|
.do_cycle = do_memcpy_cycle,
|
||||||
|
.do_gettimeofday = do_memcpy_gettimeofday,
|
||||||
|
.usage = bench_mem_memcpy_usage,
|
||||||
|
};
|
||||||
|
|
||||||
|
return bench_mem_common(argc, argv, prefix, &info);
|
||||||
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user