1 Background 2 ========== 3 4 libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2, 5 NEON, AltiVec) to accelerate baseline JPEG compression and decompression on 6 x86, x86-64, ARM, and PowerPC systems. On such systems, libjpeg-turbo is 7 generally 2-6x as fast as libjpeg, all else being equal. On other types of 8 systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by 9 virtue of its highly-optimized Huffman coding routines. In many cases, the 10 performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs. 11 12 libjpeg-turbo implements both the traditional libjpeg API as well as the less 13 powerful but more straightforward TurboJPEG API. libjpeg-turbo also features 14 colorspace extensions that allow it to compress from/decompress to 32-bit and 15 big-endian pixel buffers (RGBX, XBGR, etc.), as well as a full-featured Java 16 interface. 17 18 libjpeg-turbo was originally based on libjpeg/SIMD, an MMX-accelerated 19 derivative of libjpeg v6b developed by Miyasaka Masaru. The TigerVNC and 20 VirtualGL projects made numerous enhancements to the codec in 2009, and in 21 early 2010, libjpeg-turbo spun off into an independent project, with the goal 22 of making high-speed JPEG compression/decompression technology available to a 23 broader range of users and developers. 24 25 26 License 27 ======= 28 29 libjpeg-turbo is covered by three compatible BSD-style open source licenses. 30 Refer to [LICENSE.md](LICENSE.md) for a roll-up of license terms. 31 32 33 Building libjpeg-turbo 34 ====================== 35 36 Refer to [BUILDING.md](BUILDING.md) for complete instructions. 37 38 39 Using libjpeg-turbo 40 =================== 41 42 libjpeg-turbo includes two APIs that can be used to compress and decompress 43 JPEG images: 44 45 - **TurboJPEG API**<br> 46 This API provides an easy-to-use interface for compressing and decompressing 47 JPEG images in memory. It also provides some functionality that would not be 48 straightforward to achieve using the underlying libjpeg API, such as 49 generating planar YUV images and performing multiple simultaneous lossless 50 transforms on an image. The Java interface for libjpeg-turbo is written on 51 top of the TurboJPEG API. 52 53 - **libjpeg API**<br> 54 This is the de facto industry-standard API for compressing and decompressing 55 JPEG images. It is more difficult to use than the TurboJPEG API but also 56 more powerful. The libjpeg API implementation in libjpeg-turbo is both 57 API/ABI-compatible and mathematically compatible with libjpeg v6b. It can 58 also optionally be configured to be API/ABI-compatible with libjpeg v7 and v8 59 (see below.) 60 61 There is no significant performance advantage to either API when both are used 62 to perform similar operations. 63 64 Colorspace Extensions 65 --------------------- 66 67 libjpeg-turbo includes extensions that allow JPEG images to be compressed 68 directly from (and decompressed directly to) buffers that use BGR, BGRX, 69 RGBX, XBGR, and XRGB pixel ordering. This is implemented with ten new 70 colorspace constants: 71 72 JCS_EXT_RGB /* red/green/blue */ 73 JCS_EXT_RGBX /* red/green/blue/x */ 74 JCS_EXT_BGR /* blue/green/red */ 75 JCS_EXT_BGRX /* blue/green/red/x */ 76 JCS_EXT_XBGR /* x/blue/green/red */ 77 JCS_EXT_XRGB /* x/red/green/blue */ 78 JCS_EXT_RGBA /* red/green/blue/alpha */ 79 JCS_EXT_BGRA /* blue/green/red/alpha */ 80 JCS_EXT_ABGR /* alpha/blue/green/red */ 81 JCS_EXT_ARGB /* alpha/red/green/blue */ 82 83 Setting `cinfo.in_color_space` (compression) or `cinfo.out_color_space` 84 (decompression) to one of these values will cause libjpeg-turbo to read the 85 red, green, and blue values from (or write them to) the appropriate position in 86 the pixel when compressing from/decompressing to an RGB buffer. 87 88 Your application can check for the existence of these extensions at compile 89 time with: 90 91 #ifdef JCS_EXTENSIONS 92 93 At run time, attempting to use these extensions with a libjpeg implementation 94 that does not support them will result in a "Bogus input colorspace" error. 95 Applications can trap this error in order to test whether run-time support is 96 available for the colorspace extensions. 97 98 When using the RGBX, BGRX, XBGR, and XRGB colorspaces during decompression, the 99 X byte is undefined, and in order to ensure the best performance, libjpeg-turbo 100 can set that byte to whatever value it wishes. If an application expects the X 101 byte to be used as an alpha channel, then it should specify `JCS_EXT_RGBA`, 102 `JCS_EXT_BGRA`, `JCS_EXT_ABGR`, or `JCS_EXT_ARGB`. When these colorspace 103 constants are used, the X byte is guaranteed to be 0xFF, which is interpreted 104 as opaque. 105 106 Your application can check for the existence of the alpha channel colorspace 107 extensions at compile time with: 108 109 #ifdef JCS_ALPHA_EXTENSIONS 110 111 [jcstest.c](jcstest.c), located in the libjpeg-turbo source tree, demonstrates 112 how to check for the existence of the colorspace extensions at compile time and 113 run time. 114 115 libjpeg v7 and v8 API/ABI Emulation 116 ----------------------------------- 117 118 With libjpeg v7 and v8, new features were added that necessitated extending the 119 compression and decompression structures. Unfortunately, due to the exposed 120 nature of those structures, extending them also necessitated breaking backward 121 ABI compatibility with previous libjpeg releases. Thus, programs that were 122 built to use libjpeg v7 or v8 did not work with libjpeg-turbo, since it is 123 based on the libjpeg v6b code base. Although libjpeg v7 and v8 are not 124 as widely used as v6b, enough programs (including a few Linux distros) made 125 the switch that there was a demand to emulate the libjpeg v7 and v8 ABIs 126 in libjpeg-turbo. It should be noted, however, that this feature was added 127 primarily so that applications that had already been compiled to use libjpeg 128 v7+ could take advantage of accelerated baseline JPEG encoding/decoding 129 without recompiling. libjpeg-turbo does not claim to support all of the 130 libjpeg v7+ features, nor to produce identical output to libjpeg v7+ in all 131 cases (see below.) 132 133 By passing an argument of `--with-jpeg7` or `--with-jpeg8` to `configure`, or 134 an argument of `-DWITH_JPEG7=1` or `-DWITH_JPEG8=1` to `cmake`, you can build a 135 version of libjpeg-turbo that emulates the libjpeg v7 or v8 ABI, so that 136 programs that are built against libjpeg v7 or v8 can be run with libjpeg-turbo. 137 The following section describes which libjpeg v7+ features are supported and 138 which aren't. 139 140 ### Support for libjpeg v7 and v8 Features 141 142 #### Fully supported 143 144 - **libjpeg: IDCT scaling extensions in decompressor**<br> 145 libjpeg-turbo supports IDCT scaling with scaling factors of 1/8, 1/4, 3/8, 146 1/2, 5/8, 3/4, 7/8, 9/8, 5/4, 11/8, 3/2, 13/8, 7/4, 15/8, and 2/1 (only 1/4 147 and 1/2 are SIMD-accelerated.) 148 149 - **libjpeg: Arithmetic coding** 150 151 - **libjpeg: In-memory source and destination managers**<br> 152 See notes below. 153 154 - **cjpeg: Separate quality settings for luminance and chrominance**<br> 155 Note that the libpjeg v7+ API was extended to accommodate this feature only 156 for convenience purposes. It has always been possible to implement this 157 feature with libjpeg v6b (see rdswitch.c for an example.) 158 159 - **cjpeg: 32-bit BMP support** 160 161 - **cjpeg: `-rgb` option** 162 163 - **jpegtran: Lossless cropping** 164 165 - **jpegtran: `-perfect` option** 166 167 - **jpegtran: Forcing width/height when performing lossless crop** 168 169 - **rdjpgcom: `-raw` option** 170 171 - **rdjpgcom: Locale awareness** 172 173 174 #### Not supported 175 176 NOTE: As of this writing, extensive research has been conducted into the 177 usefulness of DCT scaling as a means of data reduction and SmartScale as a 178 means of quality improvement. The reader is invited to peruse the research at 179 <http://www.libjpeg-turbo.org/About/SmartScale> and draw his/her own conclusions, 180 but it is the general belief of our project that these features have not 181 demonstrated sufficient usefulness to justify inclusion in libjpeg-turbo. 182 183 - **libjpeg: DCT scaling in compressor**<br> 184 `cinfo.scale_num` and `cinfo.scale_denom` are silently ignored. 185 There is no technical reason why DCT scaling could not be supported when 186 emulating the libjpeg v7+ API/ABI, but without the SmartScale extension (see 187 below), only scaling factors of 1/2, 8/15, 4/7, 8/13, 2/3, 8/11, 4/5, and 188 8/9 would be available, which is of limited usefulness. 189 190 - **libjpeg: SmartScale**<br> 191 `cinfo.block_size` is silently ignored. 192 SmartScale is an extension to the JPEG format that allows for DCT block 193 sizes other than 8x8. Providing support for this new format would be 194 feasible (particularly without full acceleration.) However, until/unless 195 the format becomes either an official industry standard or, at minimum, an 196 accepted solution in the community, we are hesitant to implement it, as 197 there is no sense of whether or how it might change in the future. It is 198 our belief that SmartScale has not demonstrated sufficient usefulness as a 199 lossless format nor as a means of quality enhancement, and thus our primary 200 interest in providing this feature would be as a means of supporting 201 additional DCT scaling factors. 202 203 - **libjpeg: Fancy downsampling in compressor**<br> 204 `cinfo.do_fancy_downsampling` is silently ignored. 205 This requires the DCT scaling feature, which is not supported. 206 207 - **jpegtran: Scaling**<br> 208 This requires both the DCT scaling and SmartScale features, which are not 209 supported. 210 211 - **Lossless RGB JPEG files**<br> 212 This requires the SmartScale feature, which is not supported. 213 214 ### What About libjpeg v9? 215 216 libjpeg v9 introduced yet another field to the JPEG compression structure 217 (`color_transform`), thus making the ABI backward incompatible with that of 218 libjpeg v8. This new field was introduced solely for the purpose of supporting 219 lossless SmartScale encoding. Furthermore, there was actually no reason to 220 extend the API in this manner, as the color transform could have just as easily 221 been activated by way of a new JPEG colorspace constant, thus preserving 222 backward ABI compatibility. 223 224 Our research (see link above) has shown that lossless SmartScale does not 225 generally accomplish anything that can't already be accomplished better with 226 existing, standard lossless formats. Therefore, at this time it is our belief 227 that there is not sufficient technical justification for software projects to 228 upgrade from libjpeg v8 to libjpeg v9, and thus there is not sufficient 229 technical justification for us to emulate the libjpeg v9 ABI. 230 231 In-Memory Source/Destination Managers 232 ------------------------------------- 233 234 By default, libjpeg-turbo 1.3 and later includes the `jpeg_mem_src()` and 235 `jpeg_mem_dest()` functions, even when not emulating the libjpeg v8 API/ABI. 236 Previously, it was necessary to build libjpeg-turbo from source with libjpeg v8 237 API/ABI emulation in order to use the in-memory source/destination managers, 238 but several projects requested that those functions be included when emulating 239 the libjpeg v6b API/ABI as well. This allows the use of those functions by 240 programs that need them, without breaking ABI compatibility for programs that 241 don't, and it allows those functions to be provided in the "official" 242 libjpeg-turbo binaries. 243 244 Those who are concerned about maintaining strict conformance with the libjpeg 245 v6b or v7 API can pass an argument of `--without-mem-srcdst` to `configure` or 246 an argument of `-DWITH_MEM_SRCDST=0` to `cmake` prior to building 247 libjpeg-turbo. This will restore the pre-1.3 behavior, in which 248 `jpeg_mem_src()` and `jpeg_mem_dest()` are only included when emulating the 249 libjpeg v8 API/ABI. 250 251 On Un*x systems, including the in-memory source/destination managers changes 252 the dynamic library version from 62.1.0 to 62.2.0 if using libjpeg v6b API/ABI 253 emulation and from 7.1.0 to 7.2.0 if using libjpeg v7 API/ABI emulation. 254 255 Note that, on most Un*x systems, the dynamic linker will not look for a 256 function in a library until that function is actually used. Thus, if a program 257 is built against libjpeg-turbo 1.3+ and uses `jpeg_mem_src()` or 258 `jpeg_mem_dest()`, that program will not fail if run against an older version 259 of libjpeg-turbo or against libjpeg v7- until the program actually tries to 260 call `jpeg_mem_src()` or `jpeg_mem_dest()`. Such is not the case on Windows. 261 If a program is built against the libjpeg-turbo 1.3+ DLL and uses 262 `jpeg_mem_src()` or `jpeg_mem_dest()`, then it must use the libjpeg-turbo 1.3+ 263 DLL at run time. 264 265 Both cjpeg and djpeg have been extended to allow testing the in-memory 266 source/destination manager functions. See their respective man pages for more 267 details. 268 269 270 Mathematical Compatibility 271 ========================== 272 273 For the most part, libjpeg-turbo should produce identical output to libjpeg 274 v6b. The one exception to this is when using the floating point DCT/IDCT, in 275 which case the outputs of libjpeg v6b and libjpeg-turbo can differ for the 276 following reasons: 277 278 - The SSE/SSE2 floating point DCT implementation in libjpeg-turbo is ever so 279 slightly more accurate than the implementation in libjpeg v6b, but not by 280 any amount perceptible to human vision (generally in the range of 0.01 to 281 0.08 dB gain in PNSR.) 282 283 - When not using the SIMD extensions, libjpeg-turbo uses the more accurate 284 (and slightly faster) floating point IDCT algorithm introduced in libjpeg 285 v8a as opposed to the algorithm used in libjpeg v6b. It should be noted, 286 however, that this algorithm basically brings the accuracy of the floating 287 point IDCT in line with the accuracy of the slow integer IDCT. The floating 288 point DCT/IDCT algorithms are mainly a legacy feature, and they do not 289 produce significantly more accuracy than the slow integer algorithms (to put 290 numbers on this, the typical difference in PNSR between the two algorithms 291 is less than 0.10 dB, whereas changing the quality level by 1 in the upper 292 range of the quality scale is typically more like a 1.0 dB difference.) 293 294 - If the floating point algorithms in libjpeg-turbo are not implemented using 295 SIMD instructions on a particular platform, then the accuracy of the 296 floating point DCT/IDCT can depend on the compiler settings. 297 298 While libjpeg-turbo does emulate the libjpeg v8 API/ABI, under the hood it is 299 still using the same algorithms as libjpeg v6b, so there are several specific 300 cases in which libjpeg-turbo cannot be expected to produce the same output as 301 libjpeg v8: 302 303 - When decompressing using scaling factors of 1/2 and 1/4, because libjpeg v8 304 implements those scaling algorithms differently than libjpeg v6b does, and 305 libjpeg-turbo's SIMD extensions are based on the libjpeg v6b behavior. 306 307 - When using chrominance subsampling, because libjpeg v8 implements this 308 with its DCT/IDCT scaling algorithms rather than with a separate 309 downsampling/upsampling algorithm. In our testing, the subsampled/upsampled 310 output of libjpeg v8 is less accurate than that of libjpeg v6b for this 311 reason. 312 313 - When decompressing using a scaling factor > 1 and merged (AKA "non-fancy" or 314 "non-smooth") chrominance upsampling, because libjpeg v8 does not support 315 merged upsampling with scaling factors > 1. 316 317 318 Performance Pitfalls 319 ==================== 320 321 Restart Markers 322 --------------- 323 324 The optimized Huffman decoder in libjpeg-turbo does not handle restart markers 325 in a way that makes the rest of the libjpeg infrastructure happy, so it is 326 necessary to use the slow Huffman decoder when decompressing a JPEG image that 327 has restart markers. This can cause the decompression performance to drop by 328 as much as 20%, but the performance will still be much greater than that of 329 libjpeg. Many consumer packages, such as PhotoShop, use restart markers when 330 generating JPEG images, so images generated by those programs will experience 331 this issue. 332 333 Fast Integer Forward DCT at High Quality Levels 334 ----------------------------------------------- 335 336 The algorithm used by the SIMD-accelerated quantization function cannot produce 337 correct results whenever the fast integer forward DCT is used along with a JPEG 338 quality of 98-100. Thus, libjpeg-turbo must use the non-SIMD quantization 339 function in those cases. This causes performance to drop by as much as 40%. 340 It is therefore strongly advised that you use the slow integer forward DCT 341 whenever encoding images with a JPEG quality of 98 or higher. 342
