On 8/8/22 00:48, ling xu wrote:
Signed-off-by: ling xu <ling1...@intel.com>
Co-authored-by: Zhou Zhao <zhou.z...@intel.com>
Co-authored-by: Jun Jin <jun.i....@intel.com>
---
tests/unit/test-xbzrle.c | 307 ++++++++++++++++++++++++++++++++++++---
1 file changed, 290 insertions(+), 17 deletions(-)
diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c
index ef951b6e54..653016826f 100644
--- a/tests/unit/test-xbzrle.c
+++ b/tests/unit/test-xbzrle.c
@@ -38,111 +38,280 @@ static void test_uleb(void)
g_assert(val == 0);
}
-static void test_encode_decode_zero(void)
+static float *test_encode_decode_zero(void)
{
uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE);
uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE);
+ uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE);
+ uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE);
int i = 0;
- int dlen = 0;
+ int dlen = 0, dlen512 = 0;
int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006);
for (i = diff_len; i > 0; i--) {
buffer[1000 + i] = i;
+ buffer512[1000 + i] = i;
}
buffer[1000 + diff_len + 3] = 103;
buffer[1000 + diff_len + 5] = 105;
+ buffer512[1000 + diff_len + 3] = 103;
+ buffer512[1000 + diff_len + 5] = 105;
+
/* encode zero page */
+ time_t t_start, t_end, t_start512, t_end512;
+ t_start = clock();
dlen = xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, compressed,
XBZRLE_PAGE_SIZE);
+ t_end = clock();
+ float time_val = difftime(t_end, t_start);
g_assert(dlen == 0);
+ t_start512 = clock();
+ dlen512 = xbzrle_encode_buffer_512(buffer512, buffer512, XBZRLE_PAGE_SIZE,
+ compressed512, XBZRLE_PAGE_SIZE);
+ t_end512 = clock();
+ float time_val512 = difftime(t_end512, t_start512);
+ g_assert(dlen512 == 0);
+
+ static float result_zero[2];
+ result_zero[0] = time_val;
+ result_zero[1] = time_val512;
+
g_free(buffer);
g_free(compressed);
+ g_free(buffer512);
+ g_free(compressed512);
+
+ return result_zero;
+}
Why are you returning a pointer to static storage?
I'll note that this isn't so much "testing" as "benchmarking".
Does the speedup from using 512-bit vectors make up for the clock slowdown that is
enforced on the cpu cluster? As far as I know, it is still quite rare for avx512 to
actually pay off.
I suggest you model testing on test_buffer_is_zero_next_accel().
r~
