DPDK patches and discussions
 help / color / mirror / Atom feed
From: zhihong.wang@intel.com
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 3/4] app/test: Extended test coverage in test_memcpy_perf.c
Date: Mon, 19 Jan 2015 09:53:33 +0800	[thread overview]
Message-ID: <1421632414-10027-4-git-send-email-zhihong.wang@intel.com> (raw)
In-Reply-To: <1421632414-10027-1-git-send-email-zhihong.wang@intel.com>

Main code changes:

1. Added more typical data points for a thorough performance test

2. Added unaligned test cases since it's common in DPDK usage

Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
---
 app/test/test_memcpy_perf.c | 238 +++++++++++++++++++++++++++++---------------
 1 file changed, 156 insertions(+), 82 deletions(-)

diff --git a/app/test/test_memcpy_perf.c b/app/test/test_memcpy_perf.c
index 7809610..4875af1 100644
--- a/app/test/test_memcpy_perf.c
+++ b/app/test/test_memcpy_perf.c
@@ -54,9 +54,10 @@
 /* List of buffer sizes to test */
 #if TEST_VALUE_RANGE == 0
 static size_t buf_sizes[] = {
-	0, 1, 7, 8, 9, 15, 16, 17, 31, 32, 33, 63, 64, 65, 127, 128, 129, 255,
-	256, 257, 320, 384, 511, 512, 513, 1023, 1024, 1025, 1518, 1522, 1600,
-	2048, 3072, 4096, 5120, 6144, 7168, 8192
+	1, 2, 3, 4, 5, 6, 7, 8, 9, 12, 15, 16, 17, 31, 32, 33, 63, 64, 65, 127, 128,
+	129, 191, 192, 193, 255, 256, 257, 319, 320, 321, 383, 384, 385, 447, 448,
+	449, 511, 512, 513, 767, 768, 769, 1023, 1024, 1025, 1518, 1522, 1536, 1600,
+	2048, 2560, 3072, 3584, 4096, 4608, 5120, 5632, 6144, 6656, 7168, 7680, 8192
 };
 /* MUST be as large as largest packet size above */
 #define SMALL_BUFFER_SIZE       8192
@@ -78,7 +79,7 @@ static size_t buf_sizes[TEST_VALUE_RANGE];
 #define TEST_BATCH_SIZE         100
 
 /* Data is aligned on this many bytes (power of 2) */
-#define ALIGNMENT_UNIT          16
+#define ALIGNMENT_UNIT          32
 
 /*
  * Pointers used in performance tests. The two large buffers are for uncached
@@ -94,19 +95,19 @@ init_buffers(void)
 {
 	unsigned i;
 
-	large_buf_read = rte_malloc("memcpy", LARGE_BUFFER_SIZE, ALIGNMENT_UNIT);
+	large_buf_read = rte_malloc("memcpy", LARGE_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
 	if (large_buf_read == NULL)
 		goto error_large_buf_read;
 
-	large_buf_write = rte_malloc("memcpy", LARGE_BUFFER_SIZE, ALIGNMENT_UNIT);
+	large_buf_write = rte_malloc("memcpy", LARGE_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
 	if (large_buf_write == NULL)
 		goto error_large_buf_write;
 
-	small_buf_read = rte_malloc("memcpy", SMALL_BUFFER_SIZE, ALIGNMENT_UNIT);
+	small_buf_read = rte_malloc("memcpy", SMALL_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
 	if (small_buf_read == NULL)
 		goto error_small_buf_read;
 
-	small_buf_write = rte_malloc("memcpy", SMALL_BUFFER_SIZE, ALIGNMENT_UNIT);
+	small_buf_write = rte_malloc("memcpy", SMALL_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
 	if (small_buf_write == NULL)
 		goto error_small_buf_write;
 
@@ -140,25 +141,25 @@ free_buffers(void)
 
 /*
  * Get a random offset into large array, with enough space needed to perform
- * max copy size. Offset is aligned.
+ * max copy size. Offset is aligned, uoffset is used for unalignment setting.
  */
 static inline size_t
-get_rand_offset(void)
+get_rand_offset(size_t uoffset)
 {
-	return ((rte_rand() % (LARGE_BUFFER_SIZE - SMALL_BUFFER_SIZE)) &
-	                ~(ALIGNMENT_UNIT - 1));
+	return (((rte_rand() % (LARGE_BUFFER_SIZE - SMALL_BUFFER_SIZE)) &
+			~(ALIGNMENT_UNIT - 1)) + uoffset);
 }
 
 /* Fill in source and destination addresses. */
 static inline void
-fill_addr_arrays(size_t *dst_addr, int is_dst_cached,
-		size_t *src_addr, int is_src_cached)
+fill_addr_arrays(size_t *dst_addr, int is_dst_cached, size_t dst_uoffset,
+				 size_t *src_addr, int is_src_cached, size_t src_uoffset)
 {
 	unsigned int i;
 
 	for (i = 0; i < TEST_BATCH_SIZE; i++) {
-		dst_addr[i] = (is_dst_cached) ? 0 : get_rand_offset();
-		src_addr[i] = (is_src_cached) ? 0 : get_rand_offset();
+		dst_addr[i] = (is_dst_cached) ? dst_uoffset : get_rand_offset(dst_uoffset);
+		src_addr[i] = (is_src_cached) ? src_uoffset : get_rand_offset(src_uoffset);
 	}
 }
 
@@ -169,16 +170,17 @@ fill_addr_arrays(size_t *dst_addr, int is_dst_cached,
  */
 static void
 do_uncached_write(uint8_t *dst, int is_dst_cached,
-		const uint8_t *src, int is_src_cached, size_t size)
+				  const uint8_t *src, int is_src_cached, size_t size)
 {
 	unsigned i, j;
 	size_t dst_addrs[TEST_BATCH_SIZE], src_addrs[TEST_BATCH_SIZE];
 
 	for (i = 0; i < (TEST_ITERATIONS / TEST_BATCH_SIZE); i++) {
-		fill_addr_arrays(dst_addrs, is_dst_cached,
-			 src_addrs, is_src_cached);
-		for (j = 0; j < TEST_BATCH_SIZE; j++)
+		fill_addr_arrays(dst_addrs, is_dst_cached, 0,
+						 src_addrs, is_src_cached, 0);
+		for (j = 0; j < TEST_BATCH_SIZE; j++) {
 			rte_memcpy(dst+dst_addrs[j], src+src_addrs[j], size);
+		}
 	}
 }
 
@@ -186,52 +188,129 @@ do_uncached_write(uint8_t *dst, int is_dst_cached,
  * Run a single memcpy performance test. This is a macro to ensure that if
  * the "size" parameter is a constant it won't be converted to a variable.
  */
-#define SINGLE_PERF_TEST(dst, is_dst_cached, src, is_src_cached, size) do {   \
-	unsigned int iter, t;                                                 \
-	size_t dst_addrs[TEST_BATCH_SIZE], src_addrs[TEST_BATCH_SIZE];        \
-	uint64_t start_time, total_time = 0;                                  \
-	uint64_t total_time2 = 0;                                             \
-	for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) {  \
-		fill_addr_arrays(dst_addrs, is_dst_cached,                    \
-		                 src_addrs, is_src_cached);                   \
-		start_time = rte_rdtsc();                                     \
-		for (t = 0; t < TEST_BATCH_SIZE; t++)                         \
-			rte_memcpy(dst+dst_addrs[t], src+src_addrs[t], size); \
-		total_time += rte_rdtsc() - start_time;                       \
-	}                                                                     \
-	for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) {  \
-		fill_addr_arrays(dst_addrs, is_dst_cached,                    \
-		                 src_addrs, is_src_cached);                   \
-		start_time = rte_rdtsc();                                     \
-		for (t = 0; t < TEST_BATCH_SIZE; t++)                         \
-			memcpy(dst+dst_addrs[t], src+src_addrs[t], size);     \
-		total_time2 += rte_rdtsc() - start_time;                      \
-	}                                                                     \
-	printf("%8.0f -",  (double)total_time /TEST_ITERATIONS);              \
-	printf("%5.0f",  (double)total_time2 / TEST_ITERATIONS);              \
+#define SINGLE_PERF_TEST(dst, is_dst_cached, dst_uoffset,                   \
+						 src, is_src_cached, src_uoffset, size)             \
+do {                                                                        \
+	unsigned int iter, t;                                                   \
+	size_t dst_addrs[TEST_BATCH_SIZE], src_addrs[TEST_BATCH_SIZE];          \
+	uint64_t start_time, total_time = 0;                                    \
+	uint64_t total_time2 = 0;                                               \
+	for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) {    \
+		fill_addr_arrays(dst_addrs, is_dst_cached, dst_uoffset,             \
+						 src_addrs, is_src_cached, src_uoffset);            \
+		start_time = rte_rdtsc();                                           \
+		for (t = 0; t < TEST_BATCH_SIZE; t++)                               \
+			rte_memcpy(dst+dst_addrs[t], src+src_addrs[t], size);           \
+		total_time += rte_rdtsc() - start_time;                             \
+	}                                                                       \
+	for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) {    \
+		fill_addr_arrays(dst_addrs, is_dst_cached, dst_uoffset,             \
+						 src_addrs, is_src_cached, src_uoffset);            \
+		start_time = rte_rdtsc();                                           \
+		for (t = 0; t < TEST_BATCH_SIZE; t++)                               \
+			memcpy(dst+dst_addrs[t], src+src_addrs[t], size);               \
+		total_time2 += rte_rdtsc() - start_time;                            \
+	}                                                                       \
+	printf("%8.0f -",  (double)total_time /TEST_ITERATIONS);                \
+	printf("%5.0f",  (double)total_time2 / TEST_ITERATIONS);                \
 } while (0)
 
-/* Run memcpy() tests for each cached/uncached permutation. */
-#define ALL_PERF_TESTS_FOR_SIZE(n) do {                             \
-	if (__builtin_constant_p(n))                                \
-		printf("\nC%6u", (unsigned)n);                      \
-	else                                                        \
-		printf("\n%7u", (unsigned)n);                       \
-	SINGLE_PERF_TEST(small_buf_write, 1, small_buf_read, 1, n); \
-	SINGLE_PERF_TEST(large_buf_write, 0, small_buf_read, 1, n); \
-	SINGLE_PERF_TEST(small_buf_write, 1, large_buf_read, 0, n); \
-	SINGLE_PERF_TEST(large_buf_write, 0, large_buf_read, 0, n); \
+/* Run aligned memcpy tests for each cached/uncached permutation */
+#define ALL_PERF_TESTS_FOR_SIZE(n)                                       \
+do {                                                                     \
+	if (__builtin_constant_p(n))                                         \
+		printf("\nC%6u", (unsigned)n);                                   \
+	else                                                                 \
+		printf("\n%7u", (unsigned)n);                                    \
+	SINGLE_PERF_TEST(small_buf_write, 1, 0, small_buf_read, 1, 0, n);    \
+	SINGLE_PERF_TEST(large_buf_write, 0, 0, small_buf_read, 1, 0, n);    \
+	SINGLE_PERF_TEST(small_buf_write, 1, 0, large_buf_read, 0, 0, n);    \
+	SINGLE_PERF_TEST(large_buf_write, 0, 0, large_buf_read, 0, 0, n);    \
 } while (0)
 
-/*
- * Run performance tests for a number of different sizes and cached/uncached
- * permutations.
- */
+/* Run unaligned memcpy tests for each cached/uncached permutation */
+#define ALL_PERF_TESTS_FOR_SIZE_UNALIGNED(n)                             \
+do {                                                                     \
+	if (__builtin_constant_p(n))                                         \
+		printf("\nC%6u", (unsigned)n);                                   \
+	else                                                                 \
+		printf("\n%7u", (unsigned)n);                                    \
+	SINGLE_PERF_TEST(small_buf_write, 1, 1, small_buf_read, 1, 5, n);    \
+	SINGLE_PERF_TEST(large_buf_write, 0, 1, small_buf_read, 1, 5, n);    \
+	SINGLE_PERF_TEST(small_buf_write, 1, 1, large_buf_read, 0, 5, n);    \
+	SINGLE_PERF_TEST(large_buf_write, 0, 1, large_buf_read, 0, 5, n);    \
+} while (0)
+
+/* Run memcpy tests for constant length */
+#define ALL_PERF_TEST_FOR_CONSTANT                                       \
+{                                                                        \
+	TEST_CONSTANT(1U); TEST_CONSTANT(2U); TEST_CONSTANT(3U);             \
+	TEST_CONSTANT(4U); TEST_CONSTANT(5U); TEST_CONSTANT(6U);             \
+	TEST_CONSTANT(7U); TEST_CONSTANT(8U); TEST_CONSTANT(9U);             \
+	TEST_CONSTANT(12U); TEST_CONSTANT(15U); TEST_CONSTANT(16U);          \
+	TEST_CONSTANT(17U); TEST_CONSTANT(31U); TEST_CONSTANT(32U);          \
+	TEST_CONSTANT(33U); TEST_CONSTANT(63U); TEST_CONSTANT(64U);          \
+	TEST_CONSTANT(65U); TEST_CONSTANT(127U); TEST_CONSTANT(128U);        \
+	TEST_CONSTANT(129U); TEST_CONSTANT(191U); TEST_CONSTANT(192U);       \
+	TEST_CONSTANT(193U); TEST_CONSTANT(255U); TEST_CONSTANT(256U);       \
+	TEST_CONSTANT(257U); TEST_CONSTANT(319U); TEST_CONSTANT(320U);       \
+	TEST_CONSTANT(321U); TEST_CONSTANT(383U); TEST_CONSTANT(384U);       \
+	TEST_CONSTANT(385U); TEST_CONSTANT(447U); TEST_CONSTANT(448U);       \
+	TEST_CONSTANT(449U); TEST_CONSTANT(511U); TEST_CONSTANT(512U);       \
+	TEST_CONSTANT(513U); TEST_CONSTANT(767U); TEST_CONSTANT(768U);       \
+	TEST_CONSTANT(769U); TEST_CONSTANT(1023U); TEST_CONSTANT(1024U);     \
+	TEST_CONSTANT(1025U); TEST_CONSTANT(1518U); TEST_CONSTANT(1522U);    \
+	TEST_CONSTANT(1536U); TEST_CONSTANT(1600U); TEST_CONSTANT(2048U);    \
+	TEST_CONSTANT(2560U); TEST_CONSTANT(3072U); TEST_CONSTANT(3584U);    \
+	TEST_CONSTANT(4096U); TEST_CONSTANT(4608U); TEST_CONSTANT(5120U);    \
+	TEST_CONSTANT(5632U); TEST_CONSTANT(6144U); TEST_CONSTANT(6656U);    \
+	TEST_CONSTANT(7168U); TEST_CONSTANT(7680U); TEST_CONSTANT(8192U);    \
+}
+
+/* Run all memcpy tests for aligned constant cases */
+static inline void
+perf_test_constant_aligned(void)
+{
+#define TEST_CONSTANT ALL_PERF_TESTS_FOR_SIZE
+	ALL_PERF_TEST_FOR_CONSTANT;
+#undef TEST_CONSTANT
+}
+
+/* Run all memcpy tests for unaligned constant cases */
+static inline void
+perf_test_constant_unaligned(void)
+{
+#define TEST_CONSTANT ALL_PERF_TESTS_FOR_SIZE_UNALIGNED
+	ALL_PERF_TEST_FOR_CONSTANT;
+#undef TEST_CONSTANT
+}
+
+/* Run all memcpy tests for aligned variable cases */
+static inline void
+perf_test_variable_aligned(void)
+{
+	unsigned n = sizeof(buf_sizes) / sizeof(buf_sizes[0]);
+	unsigned i;
+	for (i = 0; i < n; i++) {
+		ALL_PERF_TESTS_FOR_SIZE((size_t)buf_sizes[i]);
+	}
+}
+
+/* Run all memcpy tests for unaligned variable cases */
+static inline void
+perf_test_variable_unaligned(void)
+{
+	unsigned n = sizeof(buf_sizes) / sizeof(buf_sizes[0]);
+	unsigned i;
+	for (i = 0; i < n; i++) {
+		ALL_PERF_TESTS_FOR_SIZE_UNALIGNED((size_t)buf_sizes[i]);
+	}
+}
+
+/* Run all memcpy tests */
 static int
 perf_test(void)
 {
-	const unsigned num_buf_sizes = sizeof(buf_sizes) / sizeof(buf_sizes[0]);
-	unsigned i;
 	int ret;
 
 	ret = init_buffers();
@@ -239,7 +318,8 @@ perf_test(void)
 		return ret;
 
 #if TEST_VALUE_RANGE != 0
-	/* Setup buf_sizes array, if required */
+	/* Set up buf_sizes array, if required */
+	unsigned i;
 	for (i = 0; i < TEST_VALUE_RANGE; i++)
 		buf_sizes[i] = i;
 #endif
@@ -248,28 +328,23 @@ perf_test(void)
 	do_uncached_write(large_buf_write, 0, small_buf_read, 1, SMALL_BUFFER_SIZE);
 
 	printf("\n** rte_memcpy() - memcpy perf. tests (C = compile-time constant) **\n"
-	       "======= ============== ============== ============== ==============\n"
-	       "   Size Cache to cache   Cache to mem   Mem to cache     Mem to mem\n"
-	       "(bytes)        (ticks)        (ticks)        (ticks)        (ticks)\n"
-	       "------- -------------- -------------- -------------- --------------");
-
-	/* Do tests where size is a variable */
-	for (i = 0; i < num_buf_sizes; i++) {
-		ALL_PERF_TESTS_FOR_SIZE((size_t)buf_sizes[i]);
-	}
+		   "======= ============== ============== ============== ==============\n"
+		   "   Size Cache to cache   Cache to mem   Mem to cache     Mem to mem\n"
+		   "(bytes)        (ticks)        (ticks)        (ticks)        (ticks)\n"
+		   "------- -------------- -------------- -------------- --------------");
+
+	printf("\n========================== %2dB aligned ============================", ALIGNMENT_UNIT);
+	/* Do aligned tests where size is a variable */
+	perf_test_variable_aligned();
 	printf("\n------- -------------- -------------- -------------- --------------");
-	/* Do tests where size is a compile-time constant */
-	ALL_PERF_TESTS_FOR_SIZE(63U);
-	ALL_PERF_TESTS_FOR_SIZE(64U);
-	ALL_PERF_TESTS_FOR_SIZE(65U);
-	ALL_PERF_TESTS_FOR_SIZE(255U);
-	ALL_PERF_TESTS_FOR_SIZE(256U);
-	ALL_PERF_TESTS_FOR_SIZE(257U);
-	ALL_PERF_TESTS_FOR_SIZE(1023U);
-	ALL_PERF_TESTS_FOR_SIZE(1024U);
-	ALL_PERF_TESTS_FOR_SIZE(1025U);
-	ALL_PERF_TESTS_FOR_SIZE(1518U);
-
+	/* Do aligned tests where size is a compile-time constant */
+	perf_test_constant_aligned();
+	printf("\n=========================== Unaligned =============================");
+	/* Do unaligned tests where size is a variable */
+	perf_test_variable_unaligned();
+	printf("\n------- -------------- -------------- -------------- --------------");
+	/* Do unaligned tests where size is a compile-time constant */
+	perf_test_constant_unaligned();
 	printf("\n======= ============== ============== ============== ==============\n\n");
 
 	free_buffers();
@@ -277,7 +352,6 @@ perf_test(void)
 	return 0;
 }
 
-
 static int
 test_memcpy_perf(void)
 {
-- 
1.9.3

  parent reply	other threads:[~2015-01-19  1:53 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-01-19  1:53 [dpdk-dev] [PATCH 0/4] DPDK memcpy optimization zhihong.wang
2015-01-19  1:53 ` [dpdk-dev] [PATCH 1/4] app/test: Disabled VTA for memcpy test in app/test/Makefile zhihong.wang
2015-01-19  1:53 ` [dpdk-dev] [PATCH 2/4] app/test: Removed unnecessary test cases in test_memcpy.c zhihong.wang
2015-01-19  1:53 ` zhihong.wang [this message]
2015-01-19  1:53 ` [dpdk-dev] [PATCH 4/4] lib/librte_eal: Optimized memcpy in arch/x86/rte_memcpy.h for both SSE and AVX platforms zhihong.wang
2015-01-20 17:15   ` Stephen Hemminger
2015-01-20 19:16     ` Neil Horman
2015-01-21  3:18       ` Wang, Zhihong
2015-01-25 20:02     ` Jim Thompson
2015-01-26 14:43   ` Wodkowski, PawelX
2015-01-27  5:12     ` Wang, Zhihong
2015-01-19 13:02 ` [dpdk-dev] [PATCH 0/4] DPDK memcpy optimization Neil Horman
2015-01-20  3:01   ` Wang, Zhihong
2015-01-20 15:11     ` Neil Horman
2015-01-20 16:14       ` Bruce Richardson
2015-01-21  3:44         ` Wang, Zhihong
2015-01-21 11:40           ` Bruce Richardson
2015-01-21 12:02           ` Ananyev, Konstantin
2015-01-21 12:38             ` Neil Horman
2015-01-23  3:26               ` Wang, Zhihong
2015-01-21 12:36           ` Marc Sune
2015-01-21 13:02             ` Bruce Richardson
2015-01-21 13:21               ` Marc Sune
2015-01-21 13:26                 ` Bruce Richardson
2015-01-21 19:49                   ` Stephen Hemminger
2015-01-21 20:54                     ` Neil Horman
2015-01-21 21:25                       ` Jim Thompson
2015-01-22  0:53                         ` Stephen Hemminger
2015-01-22  9:06                         ` Luke Gorrie
2015-01-22 13:29                           ` Jay Rolette
2015-01-22 18:27                             ` Luke Gorrie
2015-01-22 19:36                               ` Jay Rolette
2015-01-22 18:21                       ` EDMISON, Kelvin (Kelvin)
2015-01-27  8:22                         ` Wang, Zhihong
2015-01-28 21:48                           ` EDMISON, Kelvin (Kelvin)
2015-01-29  1:53                             ` Wang, Zhihong
2015-01-23  6:52                   ` Wang, Zhihong
2015-01-26 18:29                     ` Ananyev, Konstantin
2015-01-27  1:42                       ` Wang, Zhihong
2015-01-27 11:30                         ` Ananyev, Konstantin
2015-01-27 12:19                           ` Ananyev, Konstantin
2015-01-28  2:06                             ` Wang, Zhihong
2015-01-25 14:50 ` Luke Gorrie
2015-01-26  1:30   ` Wang, Zhihong
2015-01-26  8:03     ` Luke Gorrie
2015-01-27  7:19       ` Wang, Zhihong
2015-01-27 13:57         ` [dpdk-dev] [snabb-devel] " Luke Gorrie
2015-01-29  3:42 ` [dpdk-dev] " Fu, JingguoX

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1421632414-10027-4-git-send-email-zhihong.wang@intel.com \
    --to=zhihong.wang@intel.com \
    --cc=dev@dpdk.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).