break; \
}
+static av_always_inline void
+yuv2rgb_full_X_vsx_template(SwsContext *c, const int16_t *lumFilter,
+ const int16_t **lumSrc, int lumFilterSize,
+ const int16_t *chrFilter, const int16_t **chrUSrc,
+ const int16_t **chrVSrc, int chrFilterSize,
+ const int16_t **alpSrc, uint8_t *dest,
+ int dstW, int y, enum AVPixelFormat target, int hasAlpha)
+{
+ vector int16_t vv;
+ vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32;
+ vector int32_t R_l, R_r, G_l, G_r, B_l, B_r;
+ vector int32_t tmp, tmp2, tmp3, tmp4;
+ vector uint16_t rd16, gd16, bd16;
+ vector uint8_t rd, bd, gd, ad, out0, out1, tmp8;
+ vector int16_t vlumFilter[MAX_FILTER_SIZE], vchrFilter[MAX_FILTER_SIZE];
+ const vector int32_t ystart = vec_splats(1 << 9);
+ const vector int32_t uvstart = vec_splats((1 << 9) - (128 << 19));
+ const vector uint16_t zero16 = vec_splat_u16(0);
+ const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset);
+ const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff);
+ const vector int32_t y_add = vec_splats(1 << 21);
+ const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff);
+ const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff);
+ const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff);
+ const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff);
+ const vector int32_t rgbclip = vec_splats(1 << 30);
+ const vector int32_t zero32 = vec_splat_s32(0);
+ const vector uint32_t shift22 = vec_splats(22U);
+ const vector uint32_t shift10 = vec_splat_u32(10);
+ int i, j;
+
+ // Various permutations
+ const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0,
+ 0x1, 0x11, 0,
+ 0x2, 0x12, 0,
+ 0x3, 0x13, 0,
+ 0x4, 0x14, 0,
+ 0x5 };
+ const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0,
+ 0x6, 0x16, 0,
+ 0x7, 0x17, 0 };
+ const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10,
+ 0x3, 0x4, 0x11,
+ 0x6, 0x7, 0x12,
+ 0x9, 0xa, 0x13,
+ 0xc, 0xd, 0x14,
+ 0xf };
+ const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15,
+ 0x2, 0x3, 0x16,
+ 0x5, 0x6, 0x17 };
+
+ ad = vec_splats((uint8_t) 255);
+
+ for (i = 0; i < lumFilterSize; i++)
+ vlumFilter[i] = vec_splats(lumFilter[i]);
+ for (i = 0; i < chrFilterSize; i++)
+ vchrFilter[i] = vec_splats(chrFilter[i]);
+
+ for (i = 0; i < dstW; i += 8) {
+ vy32_l =
+ vy32_r = ystart;
+ vu32_l =
+ vu32_r =
+ vv32_l =
+ vv32_r = uvstart;
+
+ for (j = 0; j < lumFilterSize; j++) {
+ vv = vec_ld(0, &lumSrc[j][i]);
+ tmp = vec_mule(vv, vlumFilter[j]);
+ tmp2 = vec_mulo(vv, vlumFilter[j]);
+ tmp3 = vec_mergeh(tmp, tmp2);
+ tmp4 = vec_mergel(tmp, tmp2);
+
+ vy32_l = vec_adds(vy32_l, tmp3);
+ vy32_r = vec_adds(vy32_r, tmp4);
+ }
+
+ for (j = 0; j < chrFilterSize; j++) {
+ vv = vec_ld(0, &chrUSrc[j][i]);
+ tmp = vec_mule(vv, vchrFilter[j]);
+ tmp2 = vec_mulo(vv, vchrFilter[j]);
+ tmp3 = vec_mergeh(tmp, tmp2);
+ tmp4 = vec_mergel(tmp, tmp2);
+
+ vu32_l = vec_adds(vu32_l, tmp3);
+ vu32_r = vec_adds(vu32_r, tmp4);
+
+ vv = vec_ld(0, &chrVSrc[j][i]);
+ tmp = vec_mule(vv, vchrFilter[j]);
+ tmp2 = vec_mulo(vv, vchrFilter[j]);
+ tmp3 = vec_mergeh(tmp, tmp2);
+ tmp4 = vec_mergel(tmp, tmp2);
+
+ vv32_l = vec_adds(vv32_l, tmp3);
+ vv32_r = vec_adds(vv32_r, tmp4);
+ }
+
+ vy32_l = vec_sra(vy32_l, shift10);
+ vy32_r = vec_sra(vy32_r, shift10);
+ vu32_l = vec_sra(vu32_l, shift10);
+ vu32_r = vec_sra(vu32_r, shift10);
+ vv32_l = vec_sra(vv32_l, shift10);
+ vv32_r = vec_sra(vv32_r, shift10);
+
+ vy32_l = vec_sub(vy32_l, y_offset);
+ vy32_r = vec_sub(vy32_r, y_offset);
+ vy32_l = vec_mul(vy32_l, y_coeff);
+ vy32_r = vec_mul(vy32_r, y_coeff);
+ vy32_l = vec_add(vy32_l, y_add);
+ vy32_r = vec_add(vy32_r, y_add);
+
+ R_l = vec_mul(vv32_l, v2r_coeff);
+ R_l = vec_add(R_l, vy32_l);
+ R_r = vec_mul(vv32_r, v2r_coeff);
+ R_r = vec_add(R_r, vy32_r);
+ G_l = vec_mul(vv32_l, v2g_coeff);
+ tmp32 = vec_mul(vu32_l, u2g_coeff);
+ G_l = vec_add(G_l, vy32_l);
+ G_l = vec_add(G_l, tmp32);
+ G_r = vec_mul(vv32_r, v2g_coeff);
+ tmp32 = vec_mul(vu32_r, u2g_coeff);
+ G_r = vec_add(G_r, vy32_r);
+ G_r = vec_add(G_r, tmp32);
+
+ B_l = vec_mul(vu32_l, u2b_coeff);
+ B_l = vec_add(B_l, vy32_l);
+ B_r = vec_mul(vu32_r, u2b_coeff);
+ B_r = vec_add(B_r, vy32_r);
+
+ WRITERGB
+ }
+}
+
#define SETUP(x, buf0, alpha1, buf1, alpha) { \
x = vec_ld(0, buf0); \
tmp = vec_mule(x, alpha1); \
}
}
+static av_always_inline void
+yuv2rgb_2_vsx_template(SwsContext *c, const int16_t *buf[2],
+ const int16_t *ubuf[2], const int16_t *vbuf[2],
+ const int16_t *abuf[2], uint8_t *dest, int dstW,
+ int yalpha, int uvalpha, int y,
+ enum AVPixelFormat target, int hasAlpha)
+{
+ const int16_t *buf0 = buf[0], *buf1 = buf[1],
+ *ubuf0 = ubuf[0], *ubuf1 = ubuf[1],
+ *vbuf0 = vbuf[0], *vbuf1 = vbuf[1],
+ *abuf0 = hasAlpha ? abuf[0] : NULL,
+ *abuf1 = hasAlpha ? abuf[1] : NULL;
+ const int16_t yalpha1 = 4096 - yalpha;
+ const int16_t uvalpha1 = 4096 - uvalpha;
+ vector int16_t vy, vu, vv, A = vec_splat_s16(0);
+ vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32;
+ vector int32_t R_l, R_r, G_l, G_r, B_l, B_r, vud32_l, vud32_r, vvd32_l, vvd32_r;
+ vector int32_t tmp, tmp2, tmp3, tmp4, tmp5, tmp6;
+ vector uint16_t rd16, gd16, bd16;
+ vector uint8_t rd, bd, gd, ad, out0, out1, tmp8;
+ const vector int16_t vyalpha1 = vec_splats(yalpha1);
+ const vector int16_t vuvalpha1 = vec_splats(uvalpha1);
+ const vector int16_t vyalpha = vec_splats((int16_t) yalpha);
+ const vector int16_t vuvalpha = vec_splats((int16_t) uvalpha);
+ const vector uint16_t zero16 = vec_splat_u16(0);
+ const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset);
+ const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff);
+ const vector int32_t y_add = vec_splats(1 << 21);
+ const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff);
+ const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff);
+ const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff);
+ const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff);
+ const vector int32_t rgbclip = vec_splats(1 << 30);
+ const vector int32_t zero32 = vec_splat_s32(0);
+ const vector uint32_t shift19 = vec_splats(19U);
+ const vector uint32_t shift22 = vec_splats(22U);
+ const vector uint32_t shift10 = vec_splat_u32(10);
+ const vector int32_t dec128 = vec_splats(128 << 19);
+ const vector int32_t add18 = vec_splats(1 << 18);
+ int i;
+
+ // Various permutations
+ const vector uint8_t doubleleft = (vector uint8_t) {0, 1, 2, 3,
+ 0, 1, 2, 3,
+ 4, 5, 6, 7,
+ 4, 5, 6, 7 };
+ const vector uint8_t doubleright = (vector uint8_t) {8, 9, 10, 11,
+ 8, 9, 10, 11,
+ 12, 13, 14, 15,
+ 12, 13, 14, 15 };
+ const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0,
+ 0x1, 0x11, 0,
+ 0x2, 0x12, 0,
+ 0x3, 0x13, 0,
+ 0x4, 0x14, 0,
+ 0x5 };
+ const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0,
+ 0x6, 0x16, 0,
+ 0x7, 0x17, 0 };
+ const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10,
+ 0x3, 0x4, 0x11,
+ 0x6, 0x7, 0x12,
+ 0x9, 0xa, 0x13,
+ 0xc, 0xd, 0x14,
+ 0xf };
+ const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15,
+ 0x2, 0x3, 0x16,
+ 0x5, 0x6, 0x17 };
+
+ av_assert2(yalpha <= 4096U);
+ av_assert2(uvalpha <= 4096U);
+
+ for (i = 0; i < (dstW + 1) >> 1; i += 8) {
+ SETUP(vy, &buf0[i * 2], vyalpha1, &buf1[i * 2], vyalpha);
+ vy32_l = vec_sra(tmp3, shift10);
+ vy32_r = vec_sra(tmp4, shift10);
+
+ SETUP(vu, &ubuf0[i], vuvalpha1, &ubuf1[i], vuvalpha);
+ tmp3 = vec_sub(tmp3, dec128);
+ tmp4 = vec_sub(tmp4, dec128);
+ vu32_l = vec_sra(tmp3, shift10);
+ vu32_r = vec_sra(tmp4, shift10);
+
+ SETUP(vv, &vbuf0[i], vuvalpha1, &vbuf1[i], vuvalpha);
+ tmp3 = vec_sub(tmp3, dec128);
+ tmp4 = vec_sub(tmp4, dec128);
+ vv32_l = vec_sra(tmp3, shift10);
+ vv32_r = vec_sra(tmp4, shift10);
+
+ if (hasAlpha) {
+ SETUP(A, &abuf0[i], vyalpha1, &abuf1[i], vyalpha);
+ tmp3 = vec_add(tmp3, add18);
+ tmp4 = vec_add(tmp4, add18);
+ tmp3 = vec_sra(tmp3, shift19);
+ tmp4 = vec_sra(tmp4, shift19);
+ A = vec_packs(tmp3, tmp4);
+ ad = vec_packsu(A, (vector int16_t) zero16);
+ } else {
+ ad = vec_splats((uint8_t) 255);
+ }
+
+ vy32_l = vec_sub(vy32_l, y_offset);
+ vy32_r = vec_sub(vy32_r, y_offset);
+ vy32_l = vec_mul(vy32_l, y_coeff);
+ vy32_r = vec_mul(vy32_r, y_coeff);
+ vy32_l = vec_add(vy32_l, y_add);
+ vy32_r = vec_add(vy32_r, y_add);
+
+ // Use the first UV half
+ vud32_l = vec_perm(vu32_l, vu32_l, doubleleft);
+ vud32_r = vec_perm(vu32_l, vu32_l, doubleright);
+ vvd32_l = vec_perm(vv32_l, vv32_l, doubleleft);
+ vvd32_r = vec_perm(vv32_l, vv32_l, doubleright);
+
+ R_l = vec_mul(vvd32_l, v2r_coeff);
+ R_l = vec_add(R_l, vy32_l);
+ R_r = vec_mul(vvd32_r, v2r_coeff);
+ R_r = vec_add(R_r, vy32_r);
+ G_l = vec_mul(vvd32_l, v2g_coeff);
+ tmp32 = vec_mul(vud32_l, u2g_coeff);
+ G_l = vec_add(G_l, vy32_l);
+ G_l = vec_add(G_l, tmp32);
+ G_r = vec_mul(vvd32_r, v2g_coeff);
+ tmp32 = vec_mul(vud32_r, u2g_coeff);
+ G_r = vec_add(G_r, vy32_r);
+ G_r = vec_add(G_r, tmp32);
+
+ B_l = vec_mul(vud32_l, u2b_coeff);
+ B_l = vec_add(B_l, vy32_l);
+ B_r = vec_mul(vud32_r, u2b_coeff);
+ B_r = vec_add(B_r, vy32_r);
+
+ WRITERGB
+
+ // New Y for the second half
+ SETUP(vy, &buf0[i * 2 + 8], vyalpha1, &buf1[i * 2 + 8], vyalpha);
+ vy32_l = vec_sra(tmp3, shift10);
+ vy32_r = vec_sra(tmp4, shift10);
+
+ vy32_l = vec_sub(vy32_l, y_offset);
+ vy32_r = vec_sub(vy32_r, y_offset);
+ vy32_l = vec_mul(vy32_l, y_coeff);
+ vy32_r = vec_mul(vy32_r, y_coeff);
+ vy32_l = vec_add(vy32_l, y_add);
+ vy32_r = vec_add(vy32_r, y_add);
+
+ // Second UV half
+ vud32_l = vec_perm(vu32_r, vu32_r, doubleleft);
+ vud32_r = vec_perm(vu32_r, vu32_r, doubleright);
+ vvd32_l = vec_perm(vv32_r, vv32_r, doubleleft);
+ vvd32_r = vec_perm(vv32_r, vv32_r, doubleright);
+
+ R_l = vec_mul(vvd32_l, v2r_coeff);
+ R_l = vec_add(R_l, vy32_l);
+ R_r = vec_mul(vvd32_r, v2r_coeff);
+ R_r = vec_add(R_r, vy32_r);
+ G_l = vec_mul(vvd32_l, v2g_coeff);
+ tmp32 = vec_mul(vud32_l, u2g_coeff);
+ G_l = vec_add(G_l, vy32_l);
+ G_l = vec_add(G_l, tmp32);
+ G_r = vec_mul(vvd32_r, v2g_coeff);
+ tmp32 = vec_mul(vud32_r, u2g_coeff);
+ G_r = vec_add(G_r, vy32_r);
+ G_r = vec_add(G_r, tmp32);
+
+ B_l = vec_mul(vud32_l, u2b_coeff);
+ B_l = vec_add(B_l, vy32_l);
+ B_r = vec_mul(vud32_r, u2b_coeff);
+ B_r = vec_add(B_r, vy32_r);
+
+ WRITERGB
+ }
+}
+
#undef SETUP
static av_always_inline void
#undef WRITERGB
+#define YUV2RGBWRAPPERX(name, base, ext, fmt, hasAlpha) \
+static void name ## ext ## _X_vsx(SwsContext *c, const int16_t *lumFilter, \
+ const int16_t **lumSrc, int lumFilterSize, \
+ const int16_t *chrFilter, const int16_t **chrUSrc, \
+ const int16_t **chrVSrc, int chrFilterSize, \
+ const int16_t **alpSrc, uint8_t *dest, int dstW, \
+ int y) \
+{ \
+ name ## base ## _X_vsx_template(c, lumFilter, lumSrc, lumFilterSize, \
+ chrFilter, chrUSrc, chrVSrc, chrFilterSize, \
+ alpSrc, dest, dstW, y, fmt, hasAlpha); \
+}
+
#define YUV2RGBWRAPPERX2(name, base, ext, fmt, hasAlpha) \
static void name ## ext ## _2_vsx(SwsContext *c, const int16_t *buf[2], \
const int16_t *ubuf[2], const int16_t *vbuf[2], \
YUV2RGBWRAPPER(yuv2, rgb, rgb24, AV_PIX_FMT_RGB24, 0)
YUV2RGBWRAPPER(yuv2, rgb, bgr24, AV_PIX_FMT_BGR24, 0)
+YUV2RGBWRAPPERX2(yuv2, rgb, bgrx32, AV_PIX_FMT_BGRA, 0)
+YUV2RGBWRAPPERX2(yuv2, rgb, rgbx32, AV_PIX_FMT_RGBA, 0)
+YUV2RGBWRAPPERX2(yuv2, rgb, xrgb32, AV_PIX_FMT_ARGB, 0)
+YUV2RGBWRAPPERX2(yuv2, rgb, xbgr32, AV_PIX_FMT_ABGR, 0)
+
+YUV2RGBWRAPPERX2(yuv2, rgb, rgb24, AV_PIX_FMT_RGB24, 0)
+YUV2RGBWRAPPERX2(yuv2, rgb, bgr24, AV_PIX_FMT_BGR24, 0)
+
YUV2RGBWRAPPER(yuv2, rgb_full, bgrx32_full, AV_PIX_FMT_BGRA, 0)
YUV2RGBWRAPPER(yuv2, rgb_full, rgbx32_full, AV_PIX_FMT_RGBA, 0)
YUV2RGBWRAPPER(yuv2, rgb_full, xrgb32_full, AV_PIX_FMT_ARGB, 0)
YUV2RGBWRAPPERX2(yuv2, rgb_full, rgb24_full, AV_PIX_FMT_RGB24, 0)
YUV2RGBWRAPPERX2(yuv2, rgb_full, bgr24_full, AV_PIX_FMT_BGR24, 0)
+YUV2RGBWRAPPERX(yuv2, rgb_full, bgrx32_full, AV_PIX_FMT_BGRA, 0)
+YUV2RGBWRAPPERX(yuv2, rgb_full, rgbx32_full, AV_PIX_FMT_RGBA, 0)
+YUV2RGBWRAPPERX(yuv2, rgb_full, xrgb32_full, AV_PIX_FMT_ARGB, 0)
+YUV2RGBWRAPPERX(yuv2, rgb_full, xbgr32_full, AV_PIX_FMT_ABGR, 0)
+
+YUV2RGBWRAPPERX(yuv2, rgb_full, rgb24_full, AV_PIX_FMT_RGB24, 0)
+YUV2RGBWRAPPERX(yuv2, rgb_full, bgr24_full, AV_PIX_FMT_BGR24, 0)
+
static av_always_inline void
write422(const vector int16_t vy1, const vector int16_t vy2,
const vector int16_t vu, const vector int16_t vv,
YUV2PACKEDWRAPPER(yuv2, 422, yvyu422, AV_PIX_FMT_YVYU422)
YUV2PACKEDWRAPPER(yuv2, 422, uyvy422, AV_PIX_FMT_UYVY422)
+static void hyscale_fast_vsx(SwsContext *c, int16_t *dst, int dstWidth,
+ const uint8_t *src, int srcW, int xInc)
+{
+ int i;
+ unsigned int xpos = 0, xx;
+ vector uint8_t vin, vin2, vperm;
+ vector int8_t vmul, valpha;
+ vector int16_t vtmp, vtmp2, vtmp3, vtmp4;
+ vector uint16_t vd_l, vd_r, vcoord16[2];
+ vector uint32_t vcoord[4];
+ const vector uint32_t vadd = (vector uint32_t) {
+ 0,
+ xInc * 1,
+ xInc * 2,
+ xInc * 3,
+ };
+ const vector uint16_t vadd16 = (vector uint16_t) { // Modulo math
+ 0,
+ xInc * 1,
+ xInc * 2,
+ xInc * 3,
+ xInc * 4,
+ xInc * 5,
+ xInc * 6,
+ xInc * 7,
+ };
+ const vector uint32_t vshift16 = vec_splats((uint32_t) 16);
+ const vector uint16_t vshift9 = vec_splat_u16(9);
+ const vector uint8_t vzero = vec_splat_u8(0);
+ const vector uint16_t vshift = vec_splat_u16(7);
+
+ for (i = 0; i < dstWidth; i += 16) {
+ vcoord16[0] = vec_splats((uint16_t) xpos);
+ vcoord16[1] = vec_splats((uint16_t) (xpos + xInc * 8));
+
+ vcoord16[0] = vec_add(vcoord16[0], vadd16);
+ vcoord16[1] = vec_add(vcoord16[1], vadd16);
+
+ vcoord16[0] = vec_sr(vcoord16[0], vshift9);
+ vcoord16[1] = vec_sr(vcoord16[1], vshift9);
+ valpha = (vector int8_t) vec_pack(vcoord16[0], vcoord16[1]);
+
+ xx = xpos >> 16;
+ vin = vec_vsx_ld(0, &src[xx]);
+
+ vcoord[0] = vec_splats(xpos & 0xffff);
+ vcoord[1] = vec_splats((xpos & 0xffff) + xInc * 4);
+ vcoord[2] = vec_splats((xpos & 0xffff) + xInc * 8);
+ vcoord[3] = vec_splats((xpos & 0xffff) + xInc * 12);
+
+ vcoord[0] = vec_add(vcoord[0], vadd);
+ vcoord[1] = vec_add(vcoord[1], vadd);
+ vcoord[2] = vec_add(vcoord[2], vadd);
+ vcoord[3] = vec_add(vcoord[3], vadd);
+
+ vcoord[0] = vec_sr(vcoord[0], vshift16);
+ vcoord[1] = vec_sr(vcoord[1], vshift16);
+ vcoord[2] = vec_sr(vcoord[2], vshift16);
+ vcoord[3] = vec_sr(vcoord[3], vshift16);
+
+ vcoord16[0] = vec_pack(vcoord[0], vcoord[1]);
+ vcoord16[1] = vec_pack(vcoord[2], vcoord[3]);
+ vperm = vec_pack(vcoord16[0], vcoord16[1]);
+
+ vin = vec_perm(vin, vin, vperm);
+
+ vin2 = vec_vsx_ld(1, &src[xx]);
+ vin2 = vec_perm(vin2, vin2, vperm);
+
+ vmul = (vector int8_t) vec_sub(vin2, vin);
+ vtmp = vec_mule(vmul, valpha);
+ vtmp2 = vec_mulo(vmul, valpha);
+ vtmp3 = vec_mergeh(vtmp, vtmp2);
+ vtmp4 = vec_mergel(vtmp, vtmp2);
+
+ vd_l = (vector uint16_t) vec_mergeh(vin, vzero);
+ vd_r = (vector uint16_t) vec_mergel(vin, vzero);
+ vd_l = vec_sl(vd_l, vshift);
+ vd_r = vec_sl(vd_r, vshift);
+
+ vd_l = vec_add(vd_l, (vector uint16_t) vtmp3);
+ vd_r = vec_add(vd_r, (vector uint16_t) vtmp4);
+
+ vec_st((vector int16_t) vd_l, 0, &dst[i]);
+ vec_st((vector int16_t) vd_r, 0, &dst[i + 8]);
+
+ xpos += xInc * 16;
+ }
+ for (i=dstWidth-1; (i*xInc)>>16 >=srcW-1; i--)
+ dst[i] = src[srcW-1]*128;
+}
+
+#define HCSCALE(in, out) \
+ vin = vec_vsx_ld(0, &in[xx]); \
+ vin = vec_perm(vin, vin, vperm); \
+\
+ vin2 = vec_vsx_ld(1, &in[xx]); \
+ vin2 = vec_perm(vin2, vin2, vperm); \
+\
+ vtmp = vec_mule(vin, valphaxor); \
+ vtmp2 = vec_mulo(vin, valphaxor); \
+ vtmp3 = vec_mergeh(vtmp, vtmp2); \
+ vtmp4 = vec_mergel(vtmp, vtmp2); \
+\
+ vtmp = vec_mule(vin2, valpha); \
+ vtmp2 = vec_mulo(vin2, valpha); \
+ vd_l = vec_mergeh(vtmp, vtmp2); \
+ vd_r = vec_mergel(vtmp, vtmp2); \
+\
+ vd_l = vec_add(vd_l, vtmp3); \
+ vd_r = vec_add(vd_r, vtmp4); \
+\
+ vec_st((vector int16_t) vd_l, 0, &out[i]); \
+ vec_st((vector int16_t) vd_r, 0, &out[i + 8])
+
+static void hcscale_fast_vsx(SwsContext *c, int16_t *dst1, int16_t *dst2,
+ int dstWidth, const uint8_t *src1,
+ const uint8_t *src2, int srcW, int xInc)
+{
+ int i;
+ unsigned int xpos = 0, xx;
+ vector uint8_t vin, vin2, vperm;
+ vector uint8_t valpha, valphaxor;
+ vector uint16_t vtmp, vtmp2, vtmp3, vtmp4;
+ vector uint16_t vd_l, vd_r, vcoord16[2];
+ vector uint32_t vcoord[4];
+ const vector uint8_t vxor = vec_splats((uint8_t) 127);
+ const vector uint32_t vadd = (vector uint32_t) {
+ 0,
+ xInc * 1,
+ xInc * 2,
+ xInc * 3,
+ };
+ const vector uint16_t vadd16 = (vector uint16_t) { // Modulo math
+ 0,
+ xInc * 1,
+ xInc * 2,
+ xInc * 3,
+ xInc * 4,
+ xInc * 5,
+ xInc * 6,
+ xInc * 7,
+ };
+ const vector uint32_t vshift16 = vec_splats((uint32_t) 16);
+ const vector uint16_t vshift9 = vec_splat_u16(9);
+
+ for (i = 0; i < dstWidth; i += 16) {
+ vcoord16[0] = vec_splats((uint16_t) xpos);
+ vcoord16[1] = vec_splats((uint16_t) (xpos + xInc * 8));
+
+ vcoord16[0] = vec_add(vcoord16[0], vadd16);
+ vcoord16[1] = vec_add(vcoord16[1], vadd16);
+
+ vcoord16[0] = vec_sr(vcoord16[0], vshift9);
+ vcoord16[1] = vec_sr(vcoord16[1], vshift9);
+ valpha = vec_pack(vcoord16[0], vcoord16[1]);
+ valphaxor = vec_xor(valpha, vxor);
+
+ xx = xpos >> 16;
+
+ vcoord[0] = vec_splats(xpos & 0xffff);
+ vcoord[1] = vec_splats((xpos & 0xffff) + xInc * 4);
+ vcoord[2] = vec_splats((xpos & 0xffff) + xInc * 8);
+ vcoord[3] = vec_splats((xpos & 0xffff) + xInc * 12);
+
+ vcoord[0] = vec_add(vcoord[0], vadd);
+ vcoord[1] = vec_add(vcoord[1], vadd);
+ vcoord[2] = vec_add(vcoord[2], vadd);
+ vcoord[3] = vec_add(vcoord[3], vadd);
+
+ vcoord[0] = vec_sr(vcoord[0], vshift16);
+ vcoord[1] = vec_sr(vcoord[1], vshift16);
+ vcoord[2] = vec_sr(vcoord[2], vshift16);
+ vcoord[3] = vec_sr(vcoord[3], vshift16);
+
+ vcoord16[0] = vec_pack(vcoord[0], vcoord[1]);
+ vcoord16[1] = vec_pack(vcoord[2], vcoord[3]);
+ vperm = vec_pack(vcoord16[0], vcoord16[1]);
+
+ HCSCALE(src1, dst1);
+ HCSCALE(src2, dst2);
+
+ xpos += xInc * 16;
+ }
+ for (i=dstWidth-1; (i*xInc)>>16 >=srcW-1; i--) {
+ dst1[i] = src1[srcW-1]*128;
+ dst2[i] = src2[srcW-1]*128;
+ }
+}
+
+#undef HCSCALE
+
+static void hScale8To19_vsx(SwsContext *c, int16_t *_dst, int dstW,
+ const uint8_t *src, const int16_t *filter,
+ const int32_t *filterPos, int filterSize)
+{
+ int i, j;
+ int32_t *dst = (int32_t *) _dst;
+ vector int16_t vfilter, vin;
+ vector uint8_t vin8;
+ vector int32_t vout;
+ const vector uint8_t vzero = vec_splat_u8(0);
+ const vector uint8_t vunusedtab[8] = {
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf},
+ (vector uint8_t) {0x0, 0x1, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0x10, 0x10},
+ };
+ const vector uint8_t vunused = vunusedtab[filterSize % 8];
+
+ if (filterSize == 1) {
+ for (i = 0; i < dstW; i++) {
+ int srcPos = filterPos[i];
+ int val = 0;
+ for (j = 0; j < filterSize; j++) {
+ val += ((int)src[srcPos + j]) * filter[filterSize * i + j];
+ }
+ dst[i] = FFMIN(val >> 3, (1 << 19) - 1); // the cubic equation does overflow ...
+ }
+ } else {
+ for (i = 0; i < dstW; i++) {
+ const int srcPos = filterPos[i];
+ vout = vec_splat_s32(0);
+ for (j = 0; j < filterSize; j += 8) {
+ vin8 = vec_vsx_ld(0, &src[srcPos + j]);
+ vin = (vector int16_t) vec_mergeh(vin8, vzero);
+ if (j + 8 > filterSize) // Remove the unused elements on the last round
+ vin = vec_perm(vin, (vector int16_t) vzero, vunused);
+
+ vfilter = vec_vsx_ld(0, &filter[filterSize * i + j]);
+ vout = vec_msums(vin, vfilter, vout);
+ }
+ vout = vec_sums(vout, (vector int32_t) vzero);
+ dst[i] = FFMIN(vout[3] >> 3, (1 << 19) - 1);
+ }
+ }
+}
+
+static void hScale16To19_vsx(SwsContext *c, int16_t *_dst, int dstW,
+ const uint8_t *_src, const int16_t *filter,
+ const int32_t *filterPos, int filterSize)
+{
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->srcFormat);
+ int i, j;
+ int32_t *dst = (int32_t *) _dst;
+ const uint16_t *src = (const uint16_t *) _src;
+ int bits = desc->comp[0].depth - 1;
+ int sh = bits - 4;
+ vector int16_t vfilter, vin;
+ vector int32_t vout, vtmp, vtmp2, vfilter32_l, vfilter32_r;
+ const vector uint8_t vzero = vec_splat_u8(0);
+ const vector uint8_t vunusedtab[8] = {
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf},
+ (vector uint8_t) {0x0, 0x1, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0x10, 0x10},
+ };
+ const vector uint8_t vunused = vunusedtab[filterSize % 8];
+
+ if ((isAnyRGB(c->srcFormat) || c->srcFormat==AV_PIX_FMT_PAL8) && desc->comp[0].depth<16) {
+ sh = 9;
+ } else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
+ sh = 16 - 1 - 4;
+ }
+
+ if (filterSize == 1) {
+ for (i = 0; i < dstW; i++) {
+ int srcPos = filterPos[i];
+ int val = 0;
+
+ for (j = 0; j < filterSize; j++) {
+ val += src[srcPos + j] * filter[filterSize * i + j];
+ }
+ // filter=14 bit, input=16 bit, output=30 bit, >> 11 makes 19 bit
+ dst[i] = FFMIN(val >> sh, (1 << 19) - 1);
+ }
+ } else {
+ for (i = 0; i < dstW; i++) {
+ const int srcPos = filterPos[i];
+ vout = vec_splat_s32(0);
+ for (j = 0; j < filterSize; j += 8) {
+ vin = (vector int16_t) vec_vsx_ld(0, &src[srcPos + j]);
+ if (j + 8 > filterSize) // Remove the unused elements on the last round
+ vin = vec_perm(vin, (vector int16_t) vzero, vunused);
+
+ vfilter = vec_vsx_ld(0, &filter[filterSize * i + j]);
+ vfilter32_l = vec_unpackh(vfilter);
+ vfilter32_r = vec_unpackl(vfilter);
+
+ vtmp = (vector int32_t) vec_mergeh(vin, (vector int16_t) vzero);
+ vtmp2 = (vector int32_t) vec_mergel(vin, (vector int16_t) vzero);
+
+ vtmp = vec_mul(vtmp, vfilter32_l);
+ vtmp2 = vec_mul(vtmp2, vfilter32_r);
+
+ vout = vec_adds(vout, vtmp);
+ vout = vec_adds(vout, vtmp2);
+ }
+ vout = vec_sums(vout, (vector int32_t) vzero);
+ dst[i] = FFMIN(vout[3] >> sh, (1 << 19) - 1);
+ }
+ }
+}
+
+static void hScale16To15_vsx(SwsContext *c, int16_t *dst, int dstW,
+ const uint8_t *_src, const int16_t *filter,
+ const int32_t *filterPos, int filterSize)
+{
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->srcFormat);
+ int i, j;
+ const uint16_t *src = (const uint16_t *) _src;
+ int sh = desc->comp[0].depth - 1;
+ vector int16_t vfilter, vin;
+ vector int32_t vout, vtmp, vtmp2, vfilter32_l, vfilter32_r;
+ const vector uint8_t vzero = vec_splat_u8(0);
+ const vector uint8_t vunusedtab[8] = {
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf},
+ (vector uint8_t) {0x0, 0x1, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0x10, 0x10, 0x10, 0x10},
+ (vector uint8_t) {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0x10, 0x10},
+ };
+ const vector uint8_t vunused = vunusedtab[filterSize % 8];
+
+ if (sh<15) {
+ sh = isAnyRGB(c->srcFormat) || c->srcFormat==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1);
+ } else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
+ sh = 16 - 1;
+ }
+
+ if (filterSize == 1) {
+ for (i = 0; i < dstW; i++) {
+ int srcPos = filterPos[i];
+ int val = 0;
+
+ for (j = 0; j < filterSize; j++) {
+ val += src[srcPos + j] * filter[filterSize * i + j];
+ }
+ // filter=14 bit, input=16 bit, output=30 bit, >> 15 makes 15 bit
+ dst[i] = FFMIN(val >> sh, (1 << 15) - 1);
+ }
+ } else {
+ for (i = 0; i < dstW; i++) {
+ const int srcPos = filterPos[i];
+ vout = vec_splat_s32(0);
+ for (j = 0; j < filterSize; j += 8) {
+ vin = (vector int16_t) vec_vsx_ld(0, &src[srcPos + j]);
+ if (j + 8 > filterSize) // Remove the unused elements on the last round
+ vin = vec_perm(vin, (vector int16_t) vzero, vunused);
+
+ vfilter = vec_vsx_ld(0, &filter[filterSize * i + j]);
+ vfilter32_l = vec_unpackh(vfilter);
+ vfilter32_r = vec_unpackl(vfilter);
+
+ vtmp = (vector int32_t) vec_mergeh(vin, (vector int16_t) vzero);
+ vtmp2 = (vector int32_t) vec_mergel(vin, (vector int16_t) vzero);
+
+ vtmp = vec_mul(vtmp, vfilter32_l);
+ vtmp2 = vec_mul(vtmp2, vfilter32_r);
+
+ vout = vec_adds(vout, vtmp);
+ vout = vec_adds(vout, vtmp2);
+ }
+ vout = vec_sums(vout, (vector int32_t) vzero);
+ dst[i] = FFMIN(vout[3] >> sh, (1 << 15) - 1);
+ }
+ }
+}
+
#endif /* !HAVE_BIGENDIAN */
#endif /* HAVE_VSX */
#if HAVE_VSX
enum AVPixelFormat dstFormat = c->dstFormat;
const int cpu_flags = av_get_cpu_flags();
+ const unsigned char power8 = HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8;
if (!(cpu_flags & AV_CPU_FLAG_VSX))
return;
#if !HAVE_BIGENDIAN
- if (c->srcBpc == 8 && c->dstBpc <= 14) {
- c->hyScale = c->hcScale = hScale_real_vsx;
+ if (c->srcBpc == 8) {
+ if (c->dstBpc <= 14) {
+ c->hyScale = c->hcScale = hScale_real_vsx;
+ if (c->flags & SWS_FAST_BILINEAR && c->dstW >= c->srcW && c->chrDstW >= c->chrSrcW) {
+ c->hyscale_fast = hyscale_fast_vsx;
+ c->hcscale_fast = hcscale_fast_vsx;
+ }
+ } else {
+ c->hyScale = c->hcScale = hScale8To19_vsx;
+ }
+ } else {
+ if (power8) {
+ c->hyScale = c->hcScale = c->dstBpc > 14 ? hScale16To19_vsx
+ : hScale16To15_vsx;
+ }
}
- if (!is16BPS(dstFormat) && !isNBPS(dstFormat) &&
- dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
+ if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat) &&
dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE &&
!c->needAlpha) {
c->yuv2planeX = yuv2planeX_vsx;
if (c->flags & SWS_FULL_CHR_H_INT) {
switch (dstFormat) {
case AV_PIX_FMT_RGB24:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
c->yuv2packed1 = yuv2rgb24_full_1_vsx;
c->yuv2packed2 = yuv2rgb24_full_2_vsx;
+ c->yuv2packedX = yuv2rgb24_full_X_vsx;
}
break;
case AV_PIX_FMT_BGR24:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
c->yuv2packed1 = yuv2bgr24_full_1_vsx;
c->yuv2packed2 = yuv2bgr24_full_2_vsx;
+ c->yuv2packedX = yuv2bgr24_full_X_vsx;
}
break;
case AV_PIX_FMT_BGRA:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2bgrx32_full_1_vsx;
c->yuv2packed2 = yuv2bgrx32_full_2_vsx;
+ c->yuv2packedX = yuv2bgrx32_full_X_vsx;
}
}
break;
case AV_PIX_FMT_RGBA:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2rgbx32_full_1_vsx;
c->yuv2packed2 = yuv2rgbx32_full_2_vsx;
+ c->yuv2packedX = yuv2rgbx32_full_X_vsx;
}
}
break;
case AV_PIX_FMT_ARGB:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2xrgb32_full_1_vsx;
c->yuv2packed2 = yuv2xrgb32_full_2_vsx;
+ c->yuv2packedX = yuv2xrgb32_full_X_vsx;
}
}
break;
case AV_PIX_FMT_ABGR:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2xbgr32_full_1_vsx;
c->yuv2packed2 = yuv2xbgr32_full_2_vsx;
+ c->yuv2packedX = yuv2xbgr32_full_X_vsx;
}
}
break;
c->yuv2packedX = yuv2uyvy422_X_vsx;
break;
case AV_PIX_FMT_BGRA:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2bgrx32_1_vsx;
+ c->yuv2packed2 = yuv2bgrx32_2_vsx;
}
}
break;
case AV_PIX_FMT_RGBA:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2rgbx32_1_vsx;
+ c->yuv2packed2 = yuv2rgbx32_2_vsx;
}
}
break;
case AV_PIX_FMT_ARGB:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2xrgb32_1_vsx;
+ c->yuv2packed2 = yuv2xrgb32_2_vsx;
}
}
break;
case AV_PIX_FMT_ABGR:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
if (!c->needAlpha) {
c->yuv2packed1 = yuv2xbgr32_1_vsx;
+ c->yuv2packed2 = yuv2xbgr32_2_vsx;
}
}
break;
case AV_PIX_FMT_RGB24:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
c->yuv2packed1 = yuv2rgb24_1_vsx;
+ c->yuv2packed2 = yuv2rgb24_2_vsx;
}
break;
case AV_PIX_FMT_BGR24:
- if (HAVE_POWER8 && cpu_flags & AV_CPU_FLAG_POWER8) {
+ if (power8) {
c->yuv2packed1 = yuv2bgr24_1_vsx;
+ c->yuv2packed2 = yuv2bgr24_2_vsx;
}
break;
}
projects / ffmpeg / blobdiff