From 2e877090f958131accb8c7e5ac10e5b9865d1735 Mon Sep 17 00:00:00 2001
From: Stone Chen <chen.stonechen@gmail.com>
Date: Tue, 21 May 2024 20:00:34 -0400
Subject: [PATCH] tests/checkasm: Add check_vvc_sad to vvc_mc.c

Adds checkasm for DMVR SAD AVX2 implementation.

Benchmarks ( AMD 7940HS )
vvc_sad_8x8_c: 50.3
vvc_sad_8x8_avx2: 0.3
vvc_sad_16x16_c: 250.3
vvc_sad_16x16_avx2: 10.3
vvc_sad_32x32_c: 1020.3
vvc_sad_32x32_avx2: 60.3
vvc_sad_64x64_c: 3850.3
vvc_sad_64x64_avx2: 220.3
vvc_sad_128x128_c: 14100.3
vvc_sad_128x128_avx2: 840.3

Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
---
 tests/checkasm/vvc_mc.c | 40 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/tests/checkasm/vvc_mc.c b/tests/checkasm/vvc_mc.c
index a5ec7b7869..1e889e2cff 100644
--- a/tests/checkasm/vvc_mc.c
+++ b/tests/checkasm/vvc_mc.c
@@ -45,7 +45,7 @@ static const int sizes[] = { 2, 4, 8, 16, 32, 64, 128 };
 #define randomize_buffers(buf0, buf1, size, mask)           \
     do {                                                    \
         int k;                                              \
-        for (k = 0; k < size; k += 4) {                     \
+        for (k = 0; k < size; k += 4 / sizeof(*buf0)) {     \
             uint32_t r = rnd() & mask;                      \
             AV_WN32A(buf0 + k, r);                          \
             AV_WN32A(buf1 + k, r);                          \
@@ -324,8 +324,46 @@ 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 * sizeof(uint16_t));
+    memset(src1, 0, MAX_CTU_SIZE * MAX_CTU_SIZE * 4 * sizeof(uint16_t));
+
+    randomize_pixels(src0, src1, MAX_CTU_SIZE * MAX_CTU_SIZE * 4);
+     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, "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("sad");
+}
+
 void checkasm_check_vvc_mc(void)
 {
+    check_vvc_sad();
     check_put_vvc_luma();
     check_put_vvc_luma_uni();
     check_put_vvc_chroma();