ycbcr422pl_to_rgb565_p.sa

基于DM642平台的视频缩小放大功能 程序源代码

* ========================================================================= *
*   TEXAS INSTRUMENTS, INC.                                                 *
*                                                                           *
*   NAME                                                                    *
*       ycbcr422pl_to_rgb565 -- Planarized YCbCr 4:2:2 to 16-bit RGB 5:6:5  *
*                               color space conversion.                     *
*S                                                                          *
*S  AUTHOR                                                                  *
*S      Joseph Zbiciak                                                      *
*S                                                                          *
*S  REVISION HISTORY                                                        *
*S      25-Aug-2001 Initial complete version . . . . . . .  J. Zbiciak      *
*                                                                           *
*   USAGE                                                                   *
*       This function is C callable, and is called according to this        *
*       C prototype:                                                        *
*                                                                           *
*       void ycbcr422pl_to_rgb565                                           *
*       (                                                                   *
*           const short         coeff[5],  -- Matrix coefficients.          *
*           const unsigned char *y_data,   -- Luminence data  (Y')          *
*           const unsigned char *cb_data,  -- Blue color-diff (B'-Y')       *
*           const unsigned char *cr_data,  -- Red color-diff  (R'-Y')       *
*           unsigned short      *rgb_data, -- RGB 5:6:5 packed pixel out.   *
*           unsigned            num_pixels -- # of luma pixels to process.  *
*       )                                                                   *
*                                                                           *
*       The 'coeff[]' array contains the color-space-conversion matrix      *
*       coefficients.  The 'y_data', 'cb_data' and 'cr_data' pointers       *
*       point to the separate input image planes.  The 'rgb_data' pointer   *
*       points to the output image buffer, and must be word aligned.        *
*                                                                           *
*       The coefficients in the coeff array must be in signed Q13 form.     *
*       These coefficients correspond to the following matrix equation:     *
*                                                                           *
*           [ coeff[0] 0.0000   coeff[1] ]   [ Y' -  16 ]     [ R']         *
*           [ coeff[0] coeff[2] coeff[3] ] * [ Cb - 128 ]  =  [ G']         *
*           [ coeff[0] coeff[4] 0.0000   ]   [ Cr - 128 ]     [ B']         *
*                                                                           *
*   DESCRIPTION                                                             *
*       This kernel performs Y'CbCr to RGB conversion.  From the Color      *
*       FAQ, http://home.inforamp.net/~poynton/ColorFAQ.html :              *
*                                                                           *
*           Various scale factors are applied to (B'-Y') and (R'-Y')        *
*           for different applications.  The Y'PbPr scale factors are       *
*           optimized for component analog video.  The Y'CbCr scaling       *
*           is appropriate for component digital video, JPEG and MPEG.      *
*           Kodak's PhotoYCC(tm) uses scale factors optimized for the       *
*           gamut of film colors.  Y'UV scaling is appropriate as an        *
*           intermediate step in the formation of composite NTSC or PAL     *
*           video signals, but is not appropriate when the components       *
*           are keps separate.  Y'UV nomenclature is now used rather        *
*           loosely, and it sometimes denotes any scaling of (B'-Y')        *
*           and (R'-Y').  Y'IQ coding is obsolete.                          *
*                                                                           *
*       This code can perform various flavors of Y'CbCr to RGB conversion   *
*       as long as the offsets on Y, Cb, and Cr are -16, -128, and -128,    *
*       respectively, and the coefficients match the pattern shown.         *
*                                                                           *
*       The kernel implements the following matrix form, which involves 5   *
*       unique coefficients:                                                *
*                                                                           *
*           [ coeff[0] 0.0000   coeff[1] ]   [ Y' -  16 ]     [ R']         *
*           [ coeff[0] coeff[2] coeff[3] ] * [ Cb - 128 ]  =  [ G']         *
*           [ coeff[0] coeff[4] 0.0000   ]   [ Cr - 128 ]     [ B']         *
*                                                                           *
*       Below are some common coefficient sets, along with the matrix       *
*       equation that they correspond to.   Coefficients are in signed      *
*       Q13 notation, which gives a suitable balance between precision      *
*       and range.                                                          *
*                                                                           *
*       1.  Y'CbCr -> RGB conversion with RGB levels that correspond to     *
*           the 219-level range of Y'.  Expected ranges are [16..235] for   *
*           Y' and [16..240] for Cb and Cr.                                 *
*                                                                           *
*           coeff[] = { 0x2000, 0x2BDD, -0x0AC5, -0x1658, 0x3770 };         *
*                                                                           *
*           [ 1.0000    0.0000    1.3707 ]   [ Y' -  16 ]     [ R']         *
*           [ 1.0000   -0.3365   -0.6982 ] * [ Cb - 128 ]  =  [ G']         *
*           [ 1.0000    1.7324    0.0000 ]   [ Cr - 128 ]     [ B']         *
*                                                                           *
*       2.  Y'CbCr -> RGB conversion with the 219-level range of Y'         *
*           expanded to fill the full RGB dynamic range.  (The matrix has   *
*           been scaled by 255/219.)  Expected ranges are [16..235] for Y'  *
*           and [16..240] for Cb and Cr.                                    *
*                                                                           *
*           coeff[] = { 0x2543, 0x3313, -0x0C8A, -0x1A04, 0x408D };         *
*                                                                           *
*           [ 1.1644    0.0000    1.5960 ]   [ Y' -  16 ]     [ R']         *
*           [ 1.1644   -0.3918   -0.8130 ] * [ Cb - 128 ]  =  [ G']         *
*           [ 1.1644    2.0172    0.0000 ]   [ Cr - 128 ]     [ B']         *
*                                                                           *
*       Other scalings of the color differences (B'-Y') and (R'-Y')         *
*       (sometimes incorrectly referred to as U and V) are supported, as    *
*       long as the color differences are unsigned values centered around   *
*       128 rather than signed values centered around 0, as noted above.    *
*                                                                           *
*       In addition to performing plain color-space conversion, color       *
*       saturation can be adjusted by scaling coeff[1] through coeff[4].    *
*       Similarly, brightness can be adjusted by scaling coeff[0].          *
*       General hue adjustment can not be performed, however, due to the    *
*       two zeros hard-coded in the matrix.                                 *
*                                                                           *
*   TECHNIQUES                                                              *
*       Pixel replication is performed implicitly on chroma data to         *
*       reduce the total number of multiplies required.  The chroma         *
*       portion of the matrix is calculated once for each Cb, Cr pair,      *
*       and the result is added to both Y' samples.                         *
*                                                                           *
*       Matrix Multiplication is performed as a combination of MPY2s and    *
*       DOTP2s. Saturation to 8bit values is performed using SPACKU4        *
*       which takes in 4 signed 16-bit values and saturates them to unsigned*
*       8-bit values. The output of Matrix Multiplication would ideally be  *
*       in a Q13 format. This however, cannot be fed directly to SPACKU4.   *      
*       This implies a shift left by 3 bits, which could be pretty          *
*       expensive in terms of the number of shifts to be performed. Thus,   *
*       to avoid being bottlenecked by so many shifts, the Y, Cr & Cb data  *
*       are shifted left by 3 before multiplication. This is possible       *
*       because they are 8-bit unsigned data. Due to this, the output of    *
*       Matrix Multiplication is in a Q16 format, which can be directly fed *
*       to SPACKU4                                                          *
*                                                                           *
*   ASSUMPTIONS                                                             *
*       The number of luma samples needs to be a multiple of 8 since        *
*       8 pixels are processed in one cycle of the loop                     *  
*                                                                           *
*   NOTES                                                                   *
*       n/a.                                                                *
*                                                                           *
*   SOURCE                                                                  *
*      Poynton, Charles et al.  "The Color FAQ,"  1999.                     *
*          http://home.inforamp.net/~poynton/ColorFAQ.html                  *
*                                                                           *
* ------------------------------------------------------------------------- *
*             Copyright (c) 2001 Texas Instruments, Incorporated.           *
*                            All Rights Reserved.                           *
* ========================================================================= *
                .sect ".text:psa"
                .include "ycbcr422pl_to_rgb565_p.h64"

_ycbcr422pl_to_rgb565_sa: .cproc  A_coef, B_y_data, A_cb_data, B_cr_data, A_rgb_data, B_num_pix

         .reg B_y_7654:B_y_3210,B_cr6420,A_cb6420,B_cr6420_,A_cb6420_,A_y_data
         .reg B_y_76_:B_y_54_,A_y_32_:A_y_10_,B_y_76,B_y_54,A_y_32,A_y_10
         .reg B_cr64:B_cr20,A_cb64:A_cb20,B_y_7_c0:B_y_6_c0,B_y_5_c0:B_y_4_c0
         .reg A_y_3_c0:A_y_2_c0,A_y_1_c0:A_y_0_c0,B_cr6_c1:B_cr4_c1,B_coef
         .reg B_cr2_c1:B_cr0_c1,A_cb6_c4:A_cb4_c4,A_cb2_c4:A_cb0_c4
         .reg B_cr6cb6,B_cr4cb4,A_cb2cr2,A_cb0cr0,B_cg6,B_cg4,A_cg2,A_cg0
         .reg B_r_7,B_r_6,B_r_5,B_r_4,A_r_3,A_r_2,A_r_1,A_r_0,B_g_7
         .reg B_g_6,B_g_5,B_g_4,A_g_3,A_g_2,A_g_1,A_g_0,B_b_7,B_b_6
         .reg B_b_5,B_b_4,A_b_3,A_b_2,A_b_1,A_b_0,B_r_76,B_r_54,A_r_32  
         .reg A_r_10,B_g_76,B_g_54,A_g_32,A_g_10,B_b_76,B_b_54,A_b_32
         .reg A_b_10,B_r_7654,A_r_3210,B_g_7654,A_g_3210,B_b_7654,A_b_3210
         .reg B_r_7654_,B_g_7654_,B_b_7654_,A_r_3210_,A_g_3210_,A_b_3210_
         .reg B_r7_r6:B_r5_r4,A_r3_r2:A_r1_r0,B_g7_g6:B_g5_g4,A_g3_g2:A_g1_g0
         .reg B_b_7654__,A_b_3210__,B_b7_b6:B_b5_b4,A_b3_b2:A_b1_b0
         .reg B_r_b76,B_r_b54,A_r_b32,A_r_b10
         ;.reg B_rgb76,B_rgb54,A_rgb32,A_rgb10
         .reg B_rgb_ptr,B_loopcnt,B_c0,B_c1,B_g_cb,A_g_cr,B_c3c2,A_c2c3,A_c4
         .reg A_k80,A_k08,B_n16,A_msk6,B_msk5,B_k08,B_k01
         .reg B_rgb76:B_rgb54,A_rgb32:A_rgb10
         .reg A_c0, A_k01

         .no_mdep

         MV         B_y_data,      A_y_data

         MV         A_coef,        B_coef

         LDH.D2T2    *B_coef[0],   B_c0              ; luma
         PACK2.2     B_c0,         B_c0,      B_c0   ; Packed luma 
         MV.1x       B_c0,         A_c0

         LDH         *B_coef[1],   B_c1              ; r_cr
         PACK2       B_c1,         B_c1,      B_c1   ; Packed r_cr

         LDH         *B_coef[2],   B_g_cb            ; g_cb 
         LDH         *A_coef[3],   A_g_cr            ; g_cr