diff options
| author | James Darnley <jdarnley@obe.tv> | 2022-12-14 17:16:28 +0100 |
|---|---|---|
| committer | James Darnley <jdarnley@obe.tv> | 2022-12-20 15:02:45 +0100 |
| commit | 6af453ca389c56cb113876628cb173577faa9464 (patch) | |
| tree | 168dc608e5811b6d38ab8bfb61f0335524065828 /tests | |
| parent | f30b4c2f47ab689a570a9b36b2e96e78bb462691 (diff) | |
avcodec/x86: add avx512icl function for v210dec
Ice Lake (Xeon Silver 4316): 2.01x faster (1147±36.8 vs. 571±38.2 decicycles) compared with avx2
Diffstat (limited to 'tests')
| -rw-r--r-- | tests/checkasm/v210dec.c | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/tests/checkasm/v210dec.c b/tests/checkasm/v210dec.c index 6aef519cc5..93993bae71 100644 --- a/tests/checkasm/v210dec.c +++ b/tests/checkasm/v210dec.c @@ -54,12 +54,12 @@ void checkasm_check_v210dec(void) if (check_func(h.unpack_frame, "v210_unpack")) { uint32_t src0[NUM_SAMPLES/3]; uint32_t src1[NUM_SAMPLES/3]; - uint16_t y0[NUM_SAMPLES/2]; - uint16_t y1[NUM_SAMPLES/2]; - uint16_t u0[NUM_SAMPLES/4]; - uint16_t u1[NUM_SAMPLES/4]; - uint16_t v0[NUM_SAMPLES/4]; - uint16_t v1[NUM_SAMPLES/4]; + uint16_t y0[NUM_SAMPLES/2 + 15]; + uint16_t y1[NUM_SAMPLES/2 + 15]; + uint16_t u0[NUM_SAMPLES/4 + 7]; + uint16_t u1[NUM_SAMPLES/4 + 7]; + uint16_t v0[NUM_SAMPLES/4 + 7]; + uint16_t v1[NUM_SAMPLES/4 + 7]; declare_func(void, const uint32_t *src, uint16_t *y, uint16_t *u, uint16_t *v, int width); const int pixels = NUM_SAMPLES / 2 / 6 * 6; |