Adds checkasm for DMVR SAD AVX2 implementation.
Benchmarks ( AMD 7940HS )
vvc_sad_8_16bpc_c: 112.5
vvc_sad_8_16bpc_avx2: 2.5
vvc_sad_16_16bpc_c: 232.5
vvc_sad_16_16bpc_avx2: 22.5
vvc_sad_32_16bpc_c: 912.5
vvc_sad_32_16bpc_avx2: 82.5
vvc_sad_64_16bpc_c: 3582.5
vvc_sad_64_16bpc_avx2: 392.5
vvc_sad_128_16bpc_c: 16702.5
vvc_sad_128_16bpc_avx2: 1912.5
Before:
BQTerrace_1920x1080_60_10_420_22_RA.vvc | 80.7 |
Chimera_8bit_1080P_1000_frames.vvc | 158.0 |
NovosobornayaSquare_1920x1080.bin | 159.7 |
RitualDance_1920x1080_60_10_420_37_RA.266 | 146.3 |
After:
BQTerrace_1920x1080_60_10_420_22_RA.vvc | 82.7 |
Chimera_8bit_1080P_1000_frames.vvc | 167.0 |
NovosobornayaSquare_1920x1080.bin | 166.3 |
RitualDance_1920x1080_60_10_420_37_RA.266 | 154.0 |
---
tests/checkasm/vvc_mc.c | 38 ++++++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/tests/checkasm/vvc_mc.c b/tests/checkasm/vvc_mc.c
index 97f57cb401..77dd32fbbb 100644
--- a/tests/checkasm/vvc_mc.c
+++ b/tests/checkasm/vvc_mc.c
@@ -322,8 +322,46 @@ static void check_avg(void)
report("avg");
}
+static void check_vvc_sad(void)
+{
+ const int bit_depth = 10;
+ VVCDSPContext c;
+ LOCAL_ALIGNED_32(uint16_t, src0, [MAX_CTU_SIZE * MAX_CTU_SIZE * 4]);
+ LOCAL_ALIGNED_32(uint16_t, src1, [MAX_CTU_SIZE * MAX_CTU_SIZE * 4]);
+ declare_func(int, const int16_t *src0, const int16_t *src1, int dx, int
dy, int block_w, int block_h);
+
+ ff_vvc_dsp_init(&c, bit_depth);
+ memset(src0, 0, MAX_CTU_SIZE * MAX_CTU_SIZE * 2);
+ memset(src1, 0, MAX_CTU_SIZE * MAX_CTU_SIZE * 2);
+
+ randomize_pixels(src0, src1, MAX_CTU_SIZE * MAX_CTU_SIZE * 2);
+ for (int h = 8; h <= MAX_CTU_SIZE; h *= 2) {
+ for (int w = 8; w <= MAX_CTU_SIZE; w *= 2) {
+ for(int offy = 0; offy <= 4; offy++) {
+ for(int offx = 0; offx <= 4; offx++) {
+ if(check_func(c.inter.sad[av_log2(w)-2], "vvc_sad_%dx%d",
w, h)) {
+ int result0;
+ int result1;
+
+ result0 = call_ref(src0 + PIXEL_STRIDE * 2 + 2, src1
+ PIXEL_STRIDE * 2 + 2, offx, offy, w, h);
+ result1 = call_new(src0 + PIXEL_STRIDE * 2 + 2, src1
+ PIXEL_STRIDE * 2 + 2, offx, offy, w, h);
+
+ if (result1 != result0)
+ fail();
+ if(w == h && offx == 0 && offy == 0)
+ bench_new(src0 + PIXEL_STRIDE * 2 + 2, src1 +
PIXEL_STRIDE * 2 + 2, offx, offy, w, h);
+ }
+ }
+ }
+ }
+ }
+
+ report("check_vvc_sad");
+}
+
void checkasm_check_vvc_mc(void)
{
+ check_vvc_sad();
check_put_vvc_luma();
check_put_vvc_luma_uni();
check_put_vvc_chroma();
--
2.44.0
_______________________________________________
ffmpeg-devel mailing list
[email protected]
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
[email protected] with subject "unsubscribe".
