}
}
+static av_always_inline void idct10(uint8_t *dst, ptrdiff_t stride,
+ int16_t *input, int type)
+{
+ int16_t *ip = input;
+
+ int A, B, C, D, Ad, Bd, Cd, Dd, E, F, G, H;
+ int Ed, Gd, Add, Bdd, Fd, Hd;
+
+ int i;
+
+ /* Inverse DCT on the rows now */
+ for (i = 0; i < 4; i++) {
+ /* Check for non-zero values */
+ if (ip[0 * 8] | ip[1 * 8] | ip[2 * 8] | ip[3 * 8]) {
+ A = M(xC1S7, ip[1 * 8]);
+ B = M(xC7S1, ip[1 * 8]);
+ C = M(xC3S5, ip[3 * 8]);
+ D = -M(xC5S3, ip[3 * 8]);
+
+ Ad = M(xC4S4, (A - C));
+ Bd = M(xC4S4, (B - D));
+
+ Cd = A + C;
+ Dd = B + D;
+
+ E = M(xC4S4, ip[0 * 8]);
+ F = E;
+
+ G = M(xC2S6, ip[2 * 8]);
+ H = M(xC6S2, ip[2 * 8]);
+
+ Ed = E - G;
+ Gd = E + G;
+
+ Add = F + Ad;
+ Bdd = Bd - H;
+
+ Fd = F - Ad;
+ Hd = Bd + H;
+
+ /* Final sequence of operations over-write original inputs */
+ ip[0 * 8] = Gd + Cd;
+ ip[7 * 8] = Gd - Cd;
+
+ ip[1 * 8] = Add + Hd;
+ ip[2 * 8] = Add - Hd;
+
+ ip[3 * 8] = Ed + Dd;
+ ip[4 * 8] = Ed - Dd;
+
+ ip[5 * 8] = Fd + Bdd;
+ ip[6 * 8] = Fd - Bdd;
+
+ }
+
+ ip += 1;
+ }
+
+ ip = input;
+
+ for (i = 0; i < 8; i++) {
+ /* Check for non-zero values (bitwise or faster than ||) */
+ if (ip[0] | ip[1] | ip[2] | ip[3]) {
+ A = M(xC1S7, ip[1]);
+ B = M(xC7S1, ip[1]);
+ C = M(xC3S5, ip[3]);
+ D = -M(xC5S3, ip[3]);
+
+ Ad = M(xC4S4, (A - C));
+ Bd = M(xC4S4, (B - D));
+
+ Cd = A + C;
+ Dd = B + D;
+
+ E = M(xC4S4, ip[0]);
+ if (type == 1)
+ E += 16 * 128;
+ F = E;
+
+ G = M(xC2S6, ip[2]);
+ H = M(xC6S2, ip[2]);
+
+ Ed = E - G;
+ Gd = E + G;
+
+ Add = F + Ad;
+ Bdd = Bd - H;
+
+ Fd = F - Ad;
+ Hd = Bd + H;
+
+ Gd += 8;
+ Add += 8;
+ Ed += 8;
+ Fd += 8;
+
+ /* Final sequence of operations over-write original inputs. */
+ if (type == 1) {
+ dst[0 * stride] = av_clip_uint8((Gd + Cd) >> 4);
+ dst[7 * stride] = av_clip_uint8((Gd - Cd) >> 4);
+
+ dst[1 * stride] = av_clip_uint8((Add + Hd) >> 4);
+ dst[2 * stride] = av_clip_uint8((Add - Hd) >> 4);
+
+ dst[3 * stride] = av_clip_uint8((Ed + Dd) >> 4);
+ dst[4 * stride] = av_clip_uint8((Ed - Dd) >> 4);
+
+ dst[5 * stride] = av_clip_uint8((Fd + Bdd) >> 4);
+ dst[6 * stride] = av_clip_uint8((Fd - Bdd) >> 4);
+ } else {
+ dst[0 * stride] = av_clip_uint8(dst[0 * stride] + ((Gd + Cd) >> 4));
+ dst[7 * stride] = av_clip_uint8(dst[7 * stride] + ((Gd - Cd) >> 4));
+
+ dst[1 * stride] = av_clip_uint8(dst[1 * stride] + ((Add + Hd) >> 4));
+ dst[2 * stride] = av_clip_uint8(dst[2 * stride] + ((Add - Hd) >> 4));
+
+ dst[3 * stride] = av_clip_uint8(dst[3 * stride] + ((Ed + Dd) >> 4));
+ dst[4 * stride] = av_clip_uint8(dst[4 * stride] + ((Ed - Dd) >> 4));
+
+ dst[5 * stride] = av_clip_uint8(dst[5 * stride] + ((Fd + Bdd) >> 4));
+ dst[6 * stride] = av_clip_uint8(dst[6 * stride] + ((Fd - Bdd) >> 4));
+ }
+ } else {
+ if (type == 1) {
+ dst[0*stride] =
+ dst[1*stride] =
+ dst[2*stride] =
+ dst[3*stride] =
+ dst[4*stride] =
+ dst[5*stride] =
+ dst[6*stride] =
+ dst[7*stride] = 128;
+ }
+ }
+
+ ip += 8;
+ dst++;
+ }
+}
+
+void ff_vp3dsp_idct10_put(uint8_t *dest, ptrdiff_t stride, int16_t *block)
+{
+ idct10(dest, stride, block, 1);
+ memset(block, 0, sizeof(*block) * 64);
+}
+
+void ff_vp3dsp_idct10_add(uint8_t *dest, ptrdiff_t stride, int16_t *block)
+{
+ idct10(dest, stride, block, 2);
+ memset(block, 0, sizeof(*block) * 64);
+}
+
static void vp3_idct_put_c(uint8_t *dest /* align 8 */, ptrdiff_t stride,
int16_t *block /* align 16 */)
{
block[0] = 0;
}
-static void vp3_v_loop_filter_c(uint8_t *first_pixel, ptrdiff_t stride,
- int *bounding_values)
+static av_always_inline void vp3_v_loop_filter_c(uint8_t *first_pixel, ptrdiff_t stride,
+ int *bounding_values, int count)
{
unsigned char *end;
int filter_value;
const ptrdiff_t nstride = -stride;
- for (end = first_pixel + 8; first_pixel < end; first_pixel++) {
+ for (end = first_pixel + count; first_pixel < end; first_pixel++) {
filter_value = (first_pixel[2 * nstride] - first_pixel[stride]) +
(first_pixel[0] - first_pixel[nstride]) * 3;
filter_value = bounding_values[(filter_value + 4) >> 3];
}
}
-static void vp3_h_loop_filter_c(uint8_t *first_pixel, ptrdiff_t stride,
- int *bounding_values)
+static av_always_inline void vp3_h_loop_filter_c(uint8_t *first_pixel, ptrdiff_t stride,
+ int *bounding_values, int count)
{
unsigned char *end;
int filter_value;
- for (end = first_pixel + 8 * stride; first_pixel != end; first_pixel += stride) {
+ for (end = first_pixel + count * stride; first_pixel != end; first_pixel += stride) {
filter_value = (first_pixel[-2] - first_pixel[1]) +
(first_pixel[ 0] - first_pixel[-1]) * 3;
filter_value = bounding_values[(filter_value + 4) >> 3];
}
}
+#define LOOP_FILTER(prefix, suffix, dim, count) \
+void prefix##_##dim##_loop_filter_##count##suffix(uint8_t *first_pixel, ptrdiff_t stride, \
+ int *bounding_values) \
+{ \
+ vp3_##dim##_loop_filter_c(first_pixel, stride, bounding_values, count); \
+}
+
+static LOOP_FILTER(vp3,_c, v, 8)
+static LOOP_FILTER(vp3,_c, h, 8)
+LOOP_FILTER(ff_vp3dsp, , v, 12)
+LOOP_FILTER(ff_vp3dsp, , h, 12)
+
static void put_no_rnd_pixels_l2(uint8_t *dst, const uint8_t *src1,
const uint8_t *src2, ptrdiff_t stride, int h)
{
c->idct_put = vp3_idct_put_c;
c->idct_add = vp3_idct_add_c;
c->idct_dc_add = vp3_idct_dc_add_c;
- c->v_loop_filter = vp3_v_loop_filter_c;
- c->h_loop_filter = vp3_h_loop_filter_c;
+ c->v_loop_filter = c->v_loop_filter_unaligned = vp3_v_loop_filter_8_c;
+ c->h_loop_filter = c->h_loop_filter_unaligned = vp3_h_loop_filter_8_c;
if (ARCH_ARM)
ff_vp3dsp_init_arm(c, flags);
}
if (value)
bounding_values[128] = value;
- bounding_values[129] = bounding_values[130] = filter_limit * 0x02020202;
+ bounding_values[129] = bounding_values[130] = filter_limit * 0x02020202U;
}
projects / ffmpeg / blobdiff