XGitUrl: http://git.ffmpeg.org/gitweb/ffmpeg.git/blobdiff_plain/69a6db95ac484c50fc6178c032e05d296cb6c801..d0ce212a7ae2e98e5d9c04a5d38896c1993f50f1:/libswscale/internal_bfin.S?ds=sidebyside
diff git a/libswscale/internal_bfin.S b/libswscale/internal_bfin.S
index f5a89d2..fb7bda7 100644
 a/libswscale/internal_bfin.S
+++ b/libswscale/internal_bfin.S
@@ 2,8 +2,8 @@
* Copyright (C) 2007 Marc Hoffman
* April 20, 2007
*
 * Blackfin Video Color Space Converters Operations
 * convert I420 YV12 to RGB in various formats,
+ * Blackfin video color space converter operations
+ * convert I420 YV12 to RGB in various formats
*
* This file is part of FFmpeg.
*
@@ 24,78 +24,81 @@
/*
 YUV420 to RGB565 conversion. This routine takes a YUV 420 planar macroblock
 and converts it to RGB565. R:5 bits, G:6 bits, B:5 bits.. packed into shorts
+YUV420 to RGB565 conversion. This routine takes a YUV 420 planar macroblock
+and converts it to RGB565. R:5 bits, G:6 bits, B:5 bits.. packed into shorts.
 The following calculation is used for the conversion:
+The following calculation is used for the conversion:
 r = clipz((yoy)*cy + crv*(v128))
 g = clipz((yoy)*cy + cgv*(v128) + cgu*(u128))
 b = clipz((yoy)*cy + cbu*(u128))
+ r = clipz((yoy)*cy + crv*(v128))
+ g = clipz((yoy)*cy + cgv*(v128) + cgu*(u128))
+ b = clipz((yoy)*cy + cbu*(u128))
 y,u,v are pre scaled by a factor of 4 i.e. left shifted to gain precision.
+y,u,v are prescaled by a factor of 4 i.e. leftshifted to gain precision.
 New factorization to elliminate the truncation error which was
 occuring due to the byteop3p.
+New factorization to eliminate the truncation error which was
+occurring due to the byteop3p.
 1) use the bytop16m to subtract quad bytes we use this in U8 this
 then so the offsets need to be renormalized to 8bits.
+1) Use the bytop16m to subtract quad bytes we use this in U8 this
+ then so the offsets need to be renormalized to 8bits.
 2) scale operands up by a factor of 4 not 8 because Blackfin
 multiplies include a shift.
+2) Scale operands up by a factor of 4 not 8 because Blackfin
+ multiplies include a shift.
 3) compute into the accumulators cy*yx0, cy*yx1
+3) Compute into the accumulators cy*yx0, cy*yx1.
 4) compute each of the linear equations
 r = clipz((yoy)*cy + crv*(v128))
+4) Compute each of the linear equations:
+ r = clipz((y  oy) * cy + crv * (v  128))
 g = clipz((yoy)*cy + cgv*(v128) + cgu*(u128))
+ g = clipz((y  oy) * cy + cgv * (v  128) + cgu * (u  128))
 b = clipz((yoy)*cy + cbu*(u128))
+ b = clipz((y  oy) * cy + cbu * (u  128))
 reuse of the accumulators requires that we actually multiply
 twice once with addition and the second time with a subtaction.
+ Reuse of the accumulators requires that we actually multiply
+ twice once with addition and the second time with a subtraction.
 because of this we need to compute the equations in the order R B
 then G saving the writes for B in the case of 24/32 bit color
 formats.
+ Because of this we need to compute the equations in the order R B
+ then G saving the writes for B in the case of 24/32 bit color
+ formats.
 api: yuv2rgb_kind (uint8_t *Y, uint8_t *U, uint8_t *V, int *out,
 int dW, uint32_t *coeffs);
+ API: yuv2rgb_kind (uint8_t *Y, uint8_t *U, uint8_t *V, int *out,
+ int dW, uint32_t *coeffs);
 A B
  
 i2 = cb i3 = cr
 i1 = coeff i0 = y
+ A B
+  
+ i2 = cb i3 = cr
+ i1 = coeff i0 = y
 Where coeffs have the following layout in memory.
+Where coeffs have the following layout in memory.
 uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv;
+uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv;
 coeffs is a pointer to oy.
+coeffs is a pointer to oy.
 the {rgb} masks are only utilized by the 565 packing algorithm. Note the data
 replication is used to simplify the internal algorithms for the dual mac architecture
 of BlackFin.
+The {rgb} masks are only utilized by the 565 packing algorithm. Note the data
+replication is used to simplify the internal algorithms for the dual Mac
+architecture of BlackFin.
 All routines are exported with _ff_bfin_ as a symbol prefix
+All routines are exported with _ff_bfin_ as a symbol prefix.
 rough performance gain compared against O3:
+Rough performance gain compared against O3:
 2779809/1484290 187.28%

 which translates to ~33c/pel to ~57c/pel for the reference vs 17.5
 c/pel for the optimized implementations. Not sure why there is such a
 huge variation on the reference codes on Blackfin I guess it must have
 to do with the memory system.
+2779809/1484290 187.28%
+which translates to ~33c/pel to ~57c/pel for the reference vs 17.5
+c/pel for the optimized implementations. Not sure why there is such a
+huge variation on the reference codes on Blackfin I guess it must have
+to do with the memory system.
*/
#define mL1 .l1.text
#define mL3 .text
+#ifdef __FDPIC__
+#define mL1 .l1.text
+#else
+#define mL1 mL3
+#endif
#define MEM mL1
#define DEFUN(fname,where,interface) \
@@ 531,3 +534,73 @@ DEFUN(uyvytoyv12, mL3, (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8
unlink;
rts;
DEFUN_END(uyvytoyv12)
+
+DEFUN(yuyvtoyv12, mL3, (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
+ long width, long height,
+ long lumStride, long chromStride, long srcStride)):
+ link 0;
+ [sp] = (r7:4,p5:4);
+
+ p0 = r1; // Y top even
+
+ i2 = r2; // *u
+ r2 = [fp + ARG_vdst];
+ i3 = r2; // *v
+
+ r1 = [fp + ARG_srcStride];
+ r2 = r0 + r1;
+ r1 += 8; // i0,i1 is pre read need to correct
+ m0 = r1;
+
+ i0 = r0; // uyvy_T even
+ i1 = r2; // uyvy_B odd
+
+ p2 = [fp + ARG_lumStride];
+ p1 = p0 + p2; // Y bot odd
+
+ p5 = [fp + ARG_width];
+ p4 = [fp + ARG_height];
+ r0 = p5;
+ p4 = p4 >> 1;
+ p5 = p5 >> 2;
+
+ r2 = [fp + ARG_chromStride];
+ r0 = r0 >> 1;
+ r2 = r2  r0;
+ m1 = r2;
+
+ /* I0,I1  src input line pointers
+ * p0,p1  luma output line pointers
+ * I2  dstU
+ * I3  dstV
+ */
+
+ lsetup (0f, 1f) lc1 = p4; // H/2
+0: r0 = [i0++]  r2 = [i1++];
+ r1 = [i0++]  r3 = [i1++];
+ r4 = bytepack(r0, r1);
+ r5 = bytepack(r2, r3);
+ lsetup (2f, 3f) lc0 = p5; // W/4
+2: r0 = r0 >> 8(v)  [p0++] = r4; // yyyyeven
+ r1 = r1 >> 8(v)  [p1++] = r5; // yyyyodd
+ r2 = r2 >> 8(v);
+ r3 = r3 >> 8(v);
+ r4 = byteop1p(r1:0, r3:2);
+ r5 = byteop1p(r1:0, r3:2) (r);
+ r6 = pack(r5.l, r4.l);
+ r7 = pack(r5.h, r4.h)  r0 = [i0++]  r2 = [i1++];
+ r6 = bytepack(r6, r7)  r1 = [i0++]  r3 = [i1++];
+ r4 = bytepack(r0, r1)  w[i2++] = r6.l; // uu
+3: r5 = bytepack(r2, r3)  w[i3++] = r6.h; // vv
+
+ i0 += m0;
+ i1 += m0;
+ i2 += m1;
+ i3 += m1;
+ p0 = p0 + p2;
+1: p1 = p1 + p2;
+
+ (r7:4,p5:4) = [sp++];
+ unlink;
+ rts;
+DEFUN_END(yuyvtoyv12)