[FFmpeg-devel] [PATCH v4 2/2][GSoC 2024] tests/checkasm: Add check_vvc_sad to vvc_mc.c

[Stone Chen]

Adds checkasm for DMVR SAD AVX2 implementation.

Benchmarks ( AMD 7940HS )
vvc_sad_8x8_c: 70.0
vvc_sad_8x8_avx2: 10.0
vvc_sad_16x16_c: 280.0
vvc_sad_16x16_avx2: 20.0
vvc_sad_32x32_c: 1020.0
vvc_sad_32x32_avx2: 70.0
vvc_sad_64x64_c: 3560.0
vvc_sad_64x64_avx2: 270.0
vvc_sad_128x128_c: 13760.0
vvc_sad_128x128_avx2: 1070.0
---
 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..e251400bfc 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 * 4);
+    memset(src1, 0, MAX_CTU_SIZE * MAX_CTU_SIZE * 4);
+
+    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, "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();
-- 
2.45.0