jsimd_altivec.h 4.2 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798
  1. /*
  2. * AltiVec optimizations for libjpeg-turbo
  3. *
  4. * Copyright (C) 2014-2015, D. R. Commander. All Rights Reserved.
  5. *
  6. * This software is provided 'as-is', without any express or implied
  7. * warranty. In no event will the authors be held liable for any damages
  8. * arising from the use of this software.
  9. *
  10. * Permission is granted to anyone to use this software for any purpose,
  11. * including commercial applications, and to alter it and redistribute it
  12. * freely, subject to the following restrictions:
  13. *
  14. * 1. The origin of this software must not be misrepresented; you must not
  15. * claim that you wrote the original software. If you use this software
  16. * in a product, an acknowledgment in the product documentation would be
  17. * appreciated but is not required.
  18. * 2. Altered source versions must be plainly marked as such, and must not be
  19. * misrepresented as being the original software.
  20. * 3. This notice may not be removed or altered from any source distribution.
  21. */
  22. #define JPEG_INTERNALS
  23. #include "../../jinclude.h"
  24. #include "../../jpeglib.h"
  25. #include "../../jsimd.h"
  26. #include "../../jdct.h"
  27. #include "../../jsimddct.h"
  28. #include "../jsimd.h"
  29. #include <altivec.h>
  30. /* Common code */
  31. #define __4X(a) a, a, a, a
  32. #define __4X2(a, b) a, b, a, b, a, b, a, b
  33. #define __8X(a) __4X(a), __4X(a)
  34. #define __16X(a) __8X(a), __8X(a)
  35. #define TRANSPOSE(row, col) { \
  36. __vector short row04l, row04h, row15l, row15h, \
  37. row26l, row26h, row37l, row37h; \
  38. __vector short col01e, col01o, col23e, col23o, \
  39. col45e, col45o, col67e, col67o; \
  40. \
  41. /* transpose coefficients (phase 1) */ \
  42. row04l = vec_mergeh(row##0, row##4); /* row04l=(00 40 01 41 02 42 03 43) */ \
  43. row04h = vec_mergel(row##0, row##4); /* row04h=(04 44 05 45 06 46 07 47) */ \
  44. row15l = vec_mergeh(row##1, row##5); /* row15l=(10 50 11 51 12 52 13 53) */ \
  45. row15h = vec_mergel(row##1, row##5); /* row15h=(14 54 15 55 16 56 17 57) */ \
  46. row26l = vec_mergeh(row##2, row##6); /* row26l=(20 60 21 61 22 62 23 63) */ \
  47. row26h = vec_mergel(row##2, row##6); /* row26h=(24 64 25 65 26 66 27 67) */ \
  48. row37l = vec_mergeh(row##3, row##7); /* row37l=(30 70 31 71 32 72 33 73) */ \
  49. row37h = vec_mergel(row##3, row##7); /* row37h=(34 74 35 75 36 76 37 77) */ \
  50. \
  51. /* transpose coefficients (phase 2) */ \
  52. col01e = vec_mergeh(row04l, row26l); /* col01e=(00 20 40 60 01 21 41 61) */ \
  53. col23e = vec_mergel(row04l, row26l); /* col23e=(02 22 42 62 03 23 43 63) */ \
  54. col45e = vec_mergeh(row04h, row26h); /* col45e=(04 24 44 64 05 25 45 65) */ \
  55. col67e = vec_mergel(row04h, row26h); /* col67e=(06 26 46 66 07 27 47 67) */ \
  56. col01o = vec_mergeh(row15l, row37l); /* col01o=(10 30 50 70 11 31 51 71) */ \
  57. col23o = vec_mergel(row15l, row37l); /* col23o=(12 32 52 72 13 33 53 73) */ \
  58. col45o = vec_mergeh(row15h, row37h); /* col45o=(14 34 54 74 15 35 55 75) */ \
  59. col67o = vec_mergel(row15h, row37h); /* col67o=(16 36 56 76 17 37 57 77) */ \
  60. \
  61. /* transpose coefficients (phase 3) */ \
  62. col##0 = vec_mergeh(col01e, col01o); /* col0=(00 10 20 30 40 50 60 70) */ \
  63. col##1 = vec_mergel(col01e, col01o); /* col1=(01 11 21 31 41 51 61 71) */ \
  64. col##2 = vec_mergeh(col23e, col23o); /* col2=(02 12 22 32 42 52 62 72) */ \
  65. col##3 = vec_mergel(col23e, col23o); /* col3=(03 13 23 33 43 53 63 73) */ \
  66. col##4 = vec_mergeh(col45e, col45o); /* col4=(04 14 24 34 44 54 64 74) */ \
  67. col##5 = vec_mergel(col45e, col45o); /* col5=(05 15 25 35 45 55 65 75) */ \
  68. col##6 = vec_mergeh(col67e, col67o); /* col6=(06 16 26 36 46 56 66 76) */ \
  69. col##7 = vec_mergel(col67e, col67o); /* col7=(07 17 27 37 47 57 67 77) */ \
  70. }
  71. #ifndef min
  72. #define min(a, b) ((a) < (b) ? (a) : (b))
  73. #endif
  74. /* Macros to abstract big/little endian bit twiddling */
  75. #if __BIG_ENDIAN__
  76. #define VEC_LD(a, b) vec_ld(a, b)
  77. #define VEC_ST(a, b, c) vec_st(a, b, c)
  78. #define VEC_UNPACKHU(a) vec_mergeh(pb_zero, a)
  79. #define VEC_UNPACKLU(a) vec_mergel(pb_zero, a)
  80. #else
  81. #define VEC_LD(a, b) vec_vsx_ld(a, b)
  82. #define VEC_ST(a, b, c) vec_vsx_st(a, b, c)
  83. #define VEC_UNPACKHU(a) vec_mergeh(a, pb_zero)
  84. #define VEC_UNPACKLU(a) vec_mergel(a, pb_zero)
  85. #endif