|
|
|
@ -90,35 +90,41 @@ static void check_alf_filter(VVCDSPContext *c, const int bit_depth) |
|
|
|
|
randomize_buffers2(filter, LUMA_PARAMS_SIZE, 1); |
|
|
|
|
randomize_buffers2(clip, LUMA_PARAMS_SIZE, 0); |
|
|
|
|
|
|
|
|
|
for (int h = 4; h <= MAX_CTU_SIZE; h += 8) { |
|
|
|
|
for (int w = 4; w <= MAX_CTU_SIZE; w += 8) { |
|
|
|
|
for (int h = 4; h <= MAX_CTU_SIZE; h += 4) { |
|
|
|
|
for (int w = 4; w <= MAX_CTU_SIZE; w += 4) { |
|
|
|
|
const int ctu_size = MAX_CTU_SIZE; |
|
|
|
|
if (check_func(c->alf.filter[LUMA], "vvc_alf_filter_luma_%dx%d_%d", w, h, bit_depth)) { |
|
|
|
|
const int vb_pos = ctu_size - ALF_VB_POS_ABOVE_LUMA; |
|
|
|
|
memset(dst0, 0, DST_BUF_SIZE); |
|
|
|
|
memset(dst1, 0, DST_BUF_SIZE); |
|
|
|
|
call_ref(dst0, dst_stride, src0 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
call_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
for (int i = 0; i < h; i++) { |
|
|
|
|
if (memcmp(dst0 + i * dst_stride, dst1 + i * dst_stride, w * SIZEOF_PIXEL)) |
|
|
|
|
fail(); |
|
|
|
|
//Both picture size and virtual boundaries are 8-aligned. For luma, we only need to check 8-aligned sizes.
|
|
|
|
|
if (!(w % 8) && !(h % 8)) { |
|
|
|
|
if (check_func(c->alf.filter[LUMA], "vvc_alf_filter_luma_%dx%d_%d", w, h, bit_depth)) { |
|
|
|
|
const int vb_pos = ctu_size - ALF_VB_POS_ABOVE_LUMA; |
|
|
|
|
memset(dst0, 0, DST_BUF_SIZE); |
|
|
|
|
memset(dst1, 0, DST_BUF_SIZE); |
|
|
|
|
call_ref(dst0, dst_stride, src0 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
call_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
for (int i = 0; i < h; i++) { |
|
|
|
|
if (memcmp(dst0 + i * dst_stride, dst1 + i * dst_stride, w * SIZEOF_PIXEL)) |
|
|
|
|
fail(); |
|
|
|
|
} |
|
|
|
|
// Bench only square sizes, and ones with dimensions being a power of two.
|
|
|
|
|
if (w == h && (w & (w - 1)) == 0) |
|
|
|
|
bench_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
} |
|
|
|
|
// Bench only square sizes, and ones with dimensions being a power of two.
|
|
|
|
|
if (w == h && (w & (w - 1)) == 0) |
|
|
|
|
bench_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
} |
|
|
|
|
if (check_func(c->alf.filter[CHROMA], "vvc_alf_filter_chroma_%dx%d_%d", w, h, bit_depth)) { |
|
|
|
|
const int vb_pos = ctu_size - ALF_VB_POS_ABOVE_CHROMA; |
|
|
|
|
memset(dst0, 0, DST_BUF_SIZE); |
|
|
|
|
memset(dst1, 0, DST_BUF_SIZE); |
|
|
|
|
call_ref(dst0, dst_stride, src0 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
call_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
for (int i = 0; i < h; i++) { |
|
|
|
|
if (memcmp(dst0 + i * dst_stride, dst1 + i * dst_stride, w * SIZEOF_PIXEL)) |
|
|
|
|
fail(); |
|
|
|
|
//For chroma, once it exceeds 64, it's not a 4:2:0 format, so we only need to check 8-aligned sizes as well.
|
|
|
|
|
if ((w <= 64 || !(w % 8)) && (h <= 64 || !(h % 8))) { |
|
|
|
|
if (check_func(c->alf.filter[CHROMA], "vvc_alf_filter_chroma_%dx%d_%d", w, h, bit_depth)) { |
|
|
|
|
const int vb_pos = ctu_size - ALF_VB_POS_ABOVE_CHROMA; |
|
|
|
|
memset(dst0, 0, DST_BUF_SIZE); |
|
|
|
|
memset(dst1, 0, DST_BUF_SIZE); |
|
|
|
|
call_ref(dst0, dst_stride, src0 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
call_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
for (int i = 0; i < h; i++) { |
|
|
|
|
if (memcmp(dst0 + i * dst_stride, dst1 + i * dst_stride, w * SIZEOF_PIXEL)) |
|
|
|
|
fail(); |
|
|
|
|
} |
|
|
|
|
if (w == h && (w & (w - 1)) == 0) |
|
|
|
|
bench_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
} |
|
|
|
|
if (w == h && (w & (w - 1)) == 0) |
|
|
|
|
bench_new(dst1, dst_stride, src1 + offset, src_stride, w, h, filter, clip, vb_pos); |
|
|
|
|
} |
|
|
|
|
} |
|
|
|
|
} |
|
|
|
@ -142,8 +148,9 @@ static void check_alf_classify(VVCDSPContext *c, const int bit_depth) |
|
|
|
|
|
|
|
|
|
randomize_buffers(src0, src1, SRC_BUF_SIZE); |
|
|
|
|
|
|
|
|
|
for (int h = 4; h <= MAX_CTU_SIZE; h += 8) { |
|
|
|
|
for (int w = 4; w <= MAX_CTU_SIZE; w += 8) { |
|
|
|
|
//Both picture size and virtual boundaries are 8-aligned. Classify is luma only, we only need to check 8-aligned sizes.
|
|
|
|
|
for (int h = 8; h <= MAX_CTU_SIZE; h += 8) { |
|
|
|
|
for (int w = 8; w <= MAX_CTU_SIZE; w += 8) { |
|
|
|
|
const int id_size = w * h / ALF_BLOCK_SIZE / ALF_BLOCK_SIZE * sizeof(int); |
|
|
|
|
const int vb_pos = MAX_CTU_SIZE - ALF_BLOCK_SIZE; |
|
|
|
|
if (check_func(c->alf.classify, "vvc_alf_classify_%dx%d_%d", w, h, bit_depth)) { |
|
|
|
|