Gitiles
Code Review Sign In
review.blissroms.org / platform_external_libjpeg-turbo / 2e2ea8e02c4ebf28decb4944227f8d40ebfe1835
  1. 2e2ea8e Document AltiVec extensions by DRC · 11 years ago
  2. 246b01b Revert r1506 (we actually are generating columns with the IDCT, so the naming makes sense in retrospect); further de-confusification in the forward DCT by DRC · 11 years ago
  3. c4e3c36 De-confusify the variable names a bit -- "out" represents the output of the IDCT kernel, so use "final" to represent the packed data that will be stored to memory. by DRC · 11 years ago
  4. 2ab5ea6 Add the ability to benchmark YCCK JPEG compression/decompression. This is particularly useful since that is the only way to test the performance of the "plain" upsampling routines, which are accelerated on some platforms. by DRC · 11 years ago
  5. c641cdd AltiVec SIMD implementation of H2V1 and H2V2 plain upsampling (used only when decompressing YCCK images with fast upsampling enabled.) by DRC · 11 years ago
  6. 86af36a AltiVec SIMD implementation of H2V1 and H2V2 merged upsampling by DRC · 11 years ago
  7. 11c4010 Fix an overread detected by valgrind by DRC · 11 years ago
  8. 2517ef7 Fix bugs in the AltiVec fancy upsampling routines uncovered during additional testing with small image sizes. Since the input width is half the output width, the upsampler should only write a second 16-byte chuck if there are more than 8 input columns left. Additionally, if the width is < 16, then we need to insert a dummy sample (the SSE2 code does this as well, but I neglected to port that portion of the code for some reason.) by DRC · 11 years ago
  9. 9ab2c10 In the process of developing the AltiVec extensions, it was discovered that the normal regression tests aren't sufficient to test the behavior of the library with very small image sizes and when compressing from/decompressing to a subregion of a larger image buffer. Thus, an additional regression test was added that takes advantage of the tiled compression/decompression feature in tjbench. by DRC · 11 years ago
  10. cbcb536 Fix a bug in the AltiVec downsampling routines uncovered during additional testing with small image sizes. Since the output width is half the input width, the downsampler should only read a second 16-byte chunk if there are more than 8 output columns left. by DRC · 11 years ago
  11. ada430b Make the formatting and naming of variables and constants more consistent by DRC · 11 years ago
  12. 406bb01 Make the formatting and naming of variables and constants more consistent by DRC · 11 years ago
  13. a6a24c2 Make the formatting and naming of variables and constants more consistent by DRC · 11 years ago
  14. 52a4ec6 AltiVec SIMD implementation of H2V1 and H2V2 fancy upsampling by DRC · 11 years ago
  15. cf78941 by DRC · 11 years ago
  16. 8f7f49a by DRC · 11 years ago
  17. 51eba06 Minor code readability tweak by DRC · 11 years ago
  18. d71a6e0 Use intrinsics for loading aligned data in the IDCT functions. This has no effect on performance, but it makes it more obvious what that code is doing. by DRC · 11 years ago
  19. f0abd46 Bump copyright year by DRC · 11 years ago
  20. ac4daa7 AltiVec SIMD implementation of YCC-to-RGB color conversion by DRC · 11 years ago
  21. af69295 Fix minor issue in code comments by DRC · 11 years ago
  22. 6aed112 Fix minor issue in code comments by DRC · 11 years ago
  23. a500575 Simplify the code somewhat. It actually wasn't necessary to have a "fast path" and a "medium path"-- they perform the same. by DRC · 11 years ago
  24. 2534788 Overhaul the AltiVec vector loading code in the compression-side colorspace conversion routines. The existing code was sometimes overreading the source buffer (at least according to valgrind), and it was necessary to increase the complexity of the code in order to prevent this without significantly compromising performance. by DRC · 11 years ago
  25. 8de75d0 Fix minor issue in code comments by DRC · 11 years ago
  26. 2204820 AltiVec SIMD implementation of 2x1 and 2x2 downsampling by DRC · 11 years ago
  27. 2b223a0 Oops. Delete the duplicate copy of [lib]turbojpeg.dll in the binary directory when uninstalling the package. by DRC · 11 years ago
  28. c4930d8 Oops. Delete the duplicate copy of [lib]turbojpeg.dll in the binary directory when uninstalling the package. by DRC · 11 years ago
  29. 577ecd9 AltiVec SIMD implementation of sample conversion and integer quantization by DRC · 11 years ago
  30. ff30c63 Document the fact that the AltiVec implementation uses the same modified algorithms as the SSE2 implementation by DRC · 11 years ago
  31. 4545308 Use intrinsics for loading/storing data in the DCT/IDCT functions. This has no effect on the performance of the aligned loads/stores, but it makes it more obvious what that code is doing. Using intrinsics for the unaligned stores in the inverse DCT functions increases overall decompression performance by 1-2%. by DRC · 11 years ago
  32. b1fec4f AltiVec SIMD implementation of RGB-to-Grayscale color conversion by DRC · 11 years ago
  33. 5976e42 Remove unneeded code; Make sure jccolor-altivec.o will be rebuilt if jccolext-altivec.c changes. by DRC · 11 years ago
  34. 62bae20 AltiVec SIMD implementation of RGB-to-YCC color conversion by DRC · 11 years ago
  35. 8163aad Make test a phony target so things don't go haywire if there is a file named test.c in the current directory. by DRC · 11 years ago
  36. 99f125e Maintain the traditional order of the regression tests while allowing the TurboJPEG and libjpeg portions to be executed separately by DRC · 11 years ago
  37. 13af139 Make comments more consistent by DRC · 11 years ago
  38. 87fd253 Add a "quicktest" pseudo-target, for those times when you just don't want to sit through 11 iterations of TJUnitTest. by DRC · 11 years ago
  39. bf8a5fe Cosmetic tweaks to the PowerPC SIMD stubs by DRC · 11 years ago
  40. 535674b Split AltiVec algorithms into separate files for ease of maintenance; Rename constants using lowercase so they are not confused with macros by DRC · 11 years ago
  41. c9da785 Optimizations to the AltiVec DCT algorithms (pre-compute constants and combine multiply/add operations) by DRC · 11 years ago
  42. 0691162 AltiVec SIMD implementation of slow integer inverse DCT by DRC · 11 years ago
  43. 9cb418d Use macros to allocate constants statically, rather than reading them from a table using vec_splat*(). This improves code readability and probably improves performance a bit as well. by DRC · 11 years ago
  44. 935d1d6 Swap the order of the IFAST and ISLOW FDCT functions so that it matches the order of the prototypes in jsimd.h and the stubs in jsimd_powerpc.c. by DRC · 11 years ago
  45. 86ae591 Include ARMv8 binaries when generating a combined OS X/iOS package using 'make iosdmg' by DRC · 11 years ago
  46. d51e6c2 Document that the ARMv8/iOS issues are now fixed by DRC · 11 years ago
  47. 6842c7c Remove reference to install.txt, which we do not include from the IJG distribution by DRC · 11 years ago
  48. 6e6b28c Include ARMv8 binaries when generating a combined OS X/iOS package using 'make iosdmg' by DRC · 11 years ago
  49. b9c4b58 In the output of the configure script, indicate whether gas-preprocessor.pl is being used along with the assembler. by DRC · 11 years ago
  50. 62999d7 Modify the ARM64 assembly file so that it uses only syntax that the clang assembler in XCode 5.x can understand. These changes should all be cosmetic in nature-- they do not change the meaning or readability of the code nor the ability to build it for Linux. Actually, the code is now more in compliance with the ARM64 programming manual. In addition to these changes, there were a couple of instructions that clang simply doesn't support, so gas-preprocessor.pl was modified so that it now converts those into equivalent instructions that clang can handle. by DRC · 11 years ago
  51. ceb552a Add iOS architectures to the shared libraries generated by the Mac/iOS packaging system. I have no idea how useful this is for "standard" iOS application development, but it is useful in a jailbreak environment, and iOS 8 supposedly allows shared libs in "official" apps as well. by DRC · 11 years ago
  52. e59196d 1.4.0 by DRC · 11 years ago
  53. 6cb7f40 AltiVec SIMD implementation of fast integer inverse DCT by DRC · 11 years ago
  54. 040435a Further cleanup of the AltiVec forward DCT code: by DRC · 11 years ago
  55. fb0c394 AltiVec SIMD implementation of slow integer forward DCT; Clean up fast integer forward DCT code so that it is easier to see how it derives from the SSE2 code and to make it play more nicely with the slow FDCT code. by DRC · 11 years ago
  56. e1ac401 Fix cosmetic issues in AltiVec comments by DRC · 11 years ago
  57. 3f764b7 Fix 'make dist' by DRC · 11 years ago
  58. 1e2f496 Fix 'make dist' by DRC · 11 years ago
  59. 4c773cf Fix typos in test names by DRC · 11 years ago
  60. a29d6b4 Remove unused code by DRC · 11 years ago
  61. b329697 Fix build when INPUT_SMOOTHING_SUPPORTED is undefined by DRC · 11 years ago
  62. 2a6b831 Some software also needs the FAR macro. Ugh. Also wordsmithing. by DRC · 11 years ago
  63. e2dd3e3 Restore the JPP() and JMETHOD() macros. Even though libjpeg-turbo doesn't use them anymore, other software apparently does: by DRC · 11 years ago
  64. 0f4469c Oops. Include the tjPlane*() functions in the mapfile so that they are exposed in the shared library on ELF systems. by DRC · 11 years ago
  65. 402a715 Fix Huffman local buffer overrun discovered by Debian developers when attempting to transform a junk image using ImageMagick: by DRC · 11 years ago
  66. 306add8 Fix whitespace issues introduced with previous commit. by DRC · 11 years ago
  67. 9665f5e Print the library version and exit whenever -version is passed to cjpeg, djpeg, or jpegtran. by DRC · 11 years ago
  68. ea1eea4 Sometimes the sampling factors in grayscale images can be > 1 (for instance, if compressing using 'cjpeg -sample 2x2 -grayscale'.) Technically, sampling factors have no meaning with grayscale JPEGs, and the libjpeg decompressor ignores them in that case. Thus, the TurboJPEG decompressor should ignore them as well. by DRC · 11 years ago
  69. 3ebcf7c Make TJCompressor.close() and TJDecompressor.close() idempotent by DRC · 11 years ago
  70. 803b5d2 Uses clz and bsr instructions for bit counting on ARM64 platforms as well. by DRC · 11 years ago
  71. eca0637 Remove trailing spaces by DRC · 11 years ago
  72. 55620c6 Another oops. tjBufSizeYUV2() should return -1 if width < 1. by DRC · 11 years ago
  73. 2240974 Oops. tjPlaneSizeYUV() should return -1 if componentID > 0 and subsamp==TJSAMP_GRAY. by DRC · 11 years ago
  74. 7affbfc The AltiVec code actually works on 32-bit PowerPC platforms as well, so change the "powerpc64" token to "powerpc". Also clean up the shift code, which wasn't building properly on OS X. by DRC · 11 years ago
  75. cd2d8e1 AltiVec SIMD implementation of fast forward DCT by DRC · 11 years ago
  76. f72f1f2 Bump version to 1.5 alpha1 to prepare for new features by DRC · 11 years ago
  77. bbd9b71 When building libjpeg-turbo on Un*x systems, INT32 is usually typedef'ed to long, not int, so we need to specify an int pointer when doing a 4-byte write to the RGB565 output buffer. On little endian systems, this doesn't matter, but when you write a 32-bit int to a 64-bit long pointer address on a big endian system, you are writing to the upper 4 bytes, not the lower 4 bytes. NOTE: this will probably break on big endian systems that use 16-bit ints (are there any of those still around?) by DRC · 11 years ago
  78. c0a8256 When building libjpeg-turbo on Un*x systems, INT32 is usually typedef'ed to long, not int, so we need to specify an int pointer when doing a 4-byte write to the RGB565 output buffer. On little endian systems, this doesn't matter, but when you write a 32-bit int to a 64-bit long pointer address on a big endian system, you are writing to the upper 4 bytes, not the lower 4 bytes. NOTE: this will probably break on big endian systems that use 16-bit ints (are there any of those still around?) by DRC · 11 years ago
  79. 1d4c51a Fix Windows build by DRC · 11 years ago
  80. 72a3cc0 Fix issues with RGB565 color conversion on big endian machines. The RGB565 routines are now abstracted in a separate file, with separate little-endian and big-endian versions defined at compile time through the use of macros (this is similar to how the colorspace extension routines work.) This allows big-endian machines to take advantage of the same performance optimizations as little-endian machines, and it retains the performance on little-endian machines, since the conditional branch for endianness is at a very coarse-grained level. by DRC · 11 years ago
  81. eb8d096 Fix build on OS X PowerPC platforms by DRC · 11 years ago
  82. 339589f Fix build on OS X PowerPC platforms by DRC · 11 years ago
  83. fe77fa2 Oops. Forgot to alter the version header in the change log to indicate the release of 1.4 beta. by DRC · 11 years ago
  84. 88b6c97 Create 1.4.x branch by DRC · 11 years ago
  85. 0a9a252 Rename the ARM64 assembly file to match the C file by DRC · 11 years ago
  86. de26249 Fix several mathematical issues discovered in the ARM64 NEON code while running the extended regression tests introduced in r1267. Specific comments can be found in the original patches: by DRC · 11 years ago
  87. a6efae1 Reformat code per Siarhei's original patch (to clearly indicate that the offset instructions are completely independent) and add Siarhei as an individual author (he no longer works for Nokia.) by DRC · 11 years ago
  88. e947139 Clarify forward compatibility of iOS/ARM builds by DRC · 11 years ago
  89. bdc7650 ARM64 NEON SIMD support for YCC-to-RGB565 conversion by DRC · 11 years ago
  90. d729f4d ARM NEON SIMD support for YCC-to-RGB565 conversion, and optimizations to the existing YCC-to-RGB conversion code: by DRC · 11 years ago
  91. eb66974 Ensure that tjFree() is used for any JPEG buffers that might have been dynamically allocated by the compress/transform functions. To keep things simple, we use tjAlloc() for the statically-allocated buffer as well, so that tjFree() can always be used to free the buffer, regardless of whether it was allocated by tjbench or by the TurboJPEG library. This fixes crashes that occurred on Windows when running tjunittest or tjbench with the -alloc flag. by DRC · 11 years ago
  92. f5644c3 Ensure that tjFree() is used for any JPEG buffers that might have been dynamically allocated by the compress/transform functions. To keep things simple, we use tjAlloc() for the statically-allocated buffer as well, so that tjFree() can always be used to free the buffer, regardless of whether it was allocated by tjbench or by the TurboJPEG library. This fixes crashes that occurred on Windows when running tjunittest or tjbench with the -alloc flag. by DRC · 11 years ago
  93. 55e328e Revert r1335 and r1336. It was a valiant effort, but on Windows, xmm8-xmm15 are non-volatile, and the overhead of pushing them onto the stack at the beginning of each function and popping them at the end was causing worse performance (in the neighborhood of 3-5%) than just using the work areas and limiting the register usage to xmm0-xmm7. Best to leave the SSE2 code alone. We can optimize the register usage for AVX2, once that port takes place. by DRC · 11 years ago
  94. 3d51898 Don't use sudo when building a Debian package unless the user is non-root by DRC · 11 years ago
  95. bdb36e1 Windows doesn't have setenv(). Go, go Gadget Macros. by DRC · 11 years ago
  96. 022a901 1.4 beta1 by DRC · 11 years ago
  97. e408761 Fix 'make dist' by DRC · 11 years ago
  98. 9b012bd Don't use sudo when building a Debian package unless the user is non-root by DRC · 11 years ago
  99. 0713c1b Add a set of undocumented environment variables and Java system properties that allow compression features of libjpeg that are not normally exposed in the TurboJPEG API to be enabled. These features are not normally exposed because, for the most part, they aren't "turbo" features, but it is still useful to be able to benchmark them without modifying the code. by DRC · 11 years ago
  100. 2e2ce5a .func/.endfunc are only necessary when generating STABS debug info, which basically went out of style with parachute pants and Rick Astley. At any rate, none of the platforms for which we're building the ARM code use it (DWARF is the common format these days), and the .func/.endfunc directives cause the clang integrated assembler to fail (http://llvm.org/bugs/show_bug.cgi?id=20424). by DRC · 11 years ago