[tip:perf/core] perf bench: Also allow measuring memset()
From: tip-bot for Jan Beulich
Date: Thu Jan 26 2012 - 08:33:49 EST
Commit-ID: be3de80dc2e671d9ee15e69fe9cd84d2b71e2225
Gitweb: http://git.kernel.org/tip/be3de80dc2e671d9ee15e69fe9cd84d2b71e2225
Author: Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Tue, 24 Jan 2012 10:03:22 -0200
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Tue, 24 Jan 2012 20:25:32 -0200
perf bench: Also allow measuring memset()
This simply clones the respective memcpy() implementation.
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/4F16D743020000780006D735@xxxxxxxxxxxxxxxxxxxx
Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/Makefile | 4 +-
tools/perf/bench/bench.h | 1 +
tools/perf/bench/mem-memset-arch.h | 12 ++++
tools/perf/bench/mem-memset-x86-64-asm-def.h | 12 ++++
tools/perf/bench/mem-memset-x86-64-asm.S | 6 ++
tools/perf/bench/{mem-memcpy.c => mem-memset.c} | 78 +++++++++++------------
tools/perf/builtin-bench.c | 3 +
tools/perf/util/include/asm/dwarf2.h | 4 +-
8 files changed, 76 insertions(+), 44 deletions(-)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index ac86d67..599031a 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -61,7 +61,7 @@ ifeq ($(ARCH),x86_64)
ifeq (${IS_X86_64}, 1)
RAW_ARCH := x86_64
ARCH_CFLAGS := -DARCH_X86_64
- ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+ ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
endif
@@ -362,8 +362,10 @@ BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
ifeq ($(RAW_ARCH),x86_64)
BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
endif
BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index f7781c6..a09bece 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -4,6 +4,7 @@
extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
#define BENCH_FORMAT_DEFAULT_STR "default"
#define BENCH_FORMAT_DEFAULT 0
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
new file mode 100644
index 0000000..a040fa7
--- /dev/null
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc) \
+ extern void *fn(void *, int, size_t);
+
+#include "mem-memset-x86-64-asm-def.h"
+
+#undef MEMSET_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
new file mode 100644
index 0000000..a71dff9
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -0,0 +1,12 @@
+
+MEMSET_FN(__memset,
+ "x86-64-unrolled",
+ "unrolled memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c,
+ "x86-64-stosq",
+ "movsq-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c_e,
+ "x86-64-stosb",
+ "movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
new file mode 100644
index 0000000..cb92170
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -0,0 +1,6 @@
+#define memset MEMSET /* don't hide glibc's memset() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemset_c globl memset_c; memset_c
+#define Lmemset_c_e globl memset_c_e; memset_c_e
+#include "../../../arch/x86/lib/memset_64.S"
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memset.c
similarity index 76%
copy from tools/perf/bench/mem-memcpy.c
copy to tools/perf/bench/mem-memset.c
index db82021..9c0c6f0 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memset.c
@@ -1,9 +1,9 @@
/*
- * mem-memcpy.c
+ * mem-memset.c
*
- * memcpy: Simple memory copy in various ways
+ * memset: Simple memory set in various ways
*
- * Written by Hitoshi Mitake <mitake@xxxxxxxxxxxxxxxxxxxxx>
+ * Trivial clone of mem-memcpy.c.
*/
#include <ctype.h>
@@ -12,7 +12,7 @@
#include "../util/parse-options.h"
#include "../util/header.h"
#include "bench.h"
-#include "mem-memcpy-arch.h"
+#include "mem-memset-arch.h"
#include <stdio.h>
#include <stdlib.h>
@@ -38,29 +38,29 @@ static const struct option options[] = {
OPT_BOOLEAN('c', "clock", &use_clock,
"Use CPU clock for measuring"),
OPT_BOOLEAN('o', "only-prefault", &only_prefault,
- "Show only the result with page faults before memcpy()"),
+ "Show only the result with page faults before memset()"),
OPT_BOOLEAN('n', "no-prefault", &no_prefault,
- "Show only the result without page faults before memcpy()"),
+ "Show only the result without page faults before memset()"),
OPT_END()
};
-typedef void *(*memcpy_t)(void *, const void *, size_t);
+typedef void *(*memset_t)(void *, int, size_t);
struct routine {
const char *name;
const char *desc;
- memcpy_t fn;
+ memset_t fn;
};
-struct routine routines[] = {
+static const struct routine routines[] = {
{ "default",
- "Default memcpy() provided by glibc",
- memcpy },
+ "Default memset() provided by glibc",
+ memset },
#ifdef ARCH_X86_64
-#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
-#include "mem-memcpy-x86-64-asm-def.h"
-#undef MEMCPY_FN
+#define MEMSET_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
#endif
@@ -69,8 +69,8 @@ struct routine routines[] = {
NULL }
};
-static const char * const bench_mem_memcpy_usage[] = {
- "perf bench mem memcpy <options>",
+static const char * const bench_mem_memset_usage[] = {
+ "perf bench mem memset <options>",
NULL
};
@@ -106,53 +106,47 @@ static double timeval2double(struct timeval *ts)
(double)ts->tv_usec / (double)1000000;
}
-static void alloc_mem(void **dst, void **src, size_t length)
+static void alloc_mem(void **dst, 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");
}
-static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
{
u64 clock_start = 0ULL, clock_end = 0ULL;
- void *src = NULL, *dst = NULL;
+ void *dst = NULL;
- alloc_mem(&src, &dst, len);
+ alloc_mem(&dst, len);
if (prefault)
- fn(dst, src, len);
+ fn(dst, -1, len);
clock_start = get_clock();
- fn(dst, src, len);
+ fn(dst, 0, len);
clock_end = get_clock();
- free(src);
free(dst);
return clock_end - clock_start;
}
-static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
+static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
- void *src = NULL, *dst = NULL;
+ void *dst = NULL;
- alloc_mem(&src, &dst, len);
+ alloc_mem(&dst, len);
if (prefault)
- fn(dst, src, len);
+ fn(dst, -1, len);
BUG_ON(gettimeofday(&tv_start, NULL));
- fn(dst, src, len);
+ fn(dst, 0, 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));
}
@@ -170,7 +164,7 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
printf(" %14lf GB/Sec", x / K / K / K); \
} while (0)
-int bench_mem_memcpy(int argc, const char **argv,
+int bench_mem_memset(int argc, const char **argv,
const char *prefix __used)
{
int i;
@@ -179,7 +173,7 @@ int bench_mem_memcpy(int argc, const char **argv,
u64 result_clock[2];
argc = parse_options(argc, argv, options,
- bench_mem_memcpy_usage, 0);
+ bench_mem_memset_usage, 0);
if (use_clock)
init_clock();
@@ -219,25 +213,25 @@ int bench_mem_memcpy(int argc, const char **argv,
/* show both of results */
if (use_clock) {
result_clock[0] =
- do_memcpy_clock(routines[i].fn, len, false);
+ do_memset_clock(routines[i].fn, len, false);
result_clock[1] =
- do_memcpy_clock(routines[i].fn, len, true);
+ do_memset_clock(routines[i].fn, len, true);
} else {
result_bps[0] =
- do_memcpy_gettimeofday(routines[i].fn,
+ do_memset_gettimeofday(routines[i].fn,
len, false);
result_bps[1] =
- do_memcpy_gettimeofday(routines[i].fn,
+ do_memset_gettimeofday(routines[i].fn,
len, true);
}
} else {
if (use_clock) {
result_clock[pf] =
- do_memcpy_clock(routines[i].fn,
+ do_memset_clock(routines[i].fn,
len, only_prefault);
} else {
result_bps[pf] =
- do_memcpy_gettimeofday(routines[i].fn,
+ do_memset_gettimeofday(routines[i].fn,
len, only_prefault);
}
}
@@ -249,7 +243,7 @@ int bench_mem_memcpy(int argc, const char **argv,
printf(" %14lf Clock/Byte\n",
(double)result_clock[0]
/ (double)len);
- printf(" %14lf Clock/Byte (with prefault)\n",
+ printf(" %14lf Clock/Byte (with prefault)\n ",
(double)result_clock[1]
/ (double)len);
} else {
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index fcb9626..b0e74ab 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -52,6 +52,9 @@ static struct bench_suite mem_suites[] = {
{ "memcpy",
"Simple memory copy in various ways",
bench_mem_memcpy },
+ { "memset",
+ "Simple memory set in various ways",
+ bench_mem_memset },
suite_all,
{ NULL,
NULL,
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
index bb4198e..afe3819 100644
--- a/tools/perf/util/include/asm/dwarf2.h
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -2,10 +2,12 @@
#ifndef PERF_DWARF2_H
#define PERF_DWARF2_H
-/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+/* dwarf2.h ... dummy header file for including arch/x86/lib/mem{cpy,set}_64.S */
#define CFI_STARTPROC
#define CFI_ENDPROC
+#define CFI_REMEMBER_STATE
+#define CFI_RESTORE_STATE
#endif /* PERF_DWARF2_H */
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/