From ad4e5dbd3dab94de54aca7ff094a38a0e60ca594 Mon Sep 17 00:00:00 2001 From: Alexander Alekhin Date: Mon, 23 Mar 2020 18:09:21 +0000 Subject: [PATCH] 3rdparty: libjpeg-turbo 2.0.2 => 2.0.4 - https://github.com/libjpeg-turbo/libjpeg-turbo/releases/tag/2.0.4 --- 3rdparty/libjpeg-turbo/CMakeLists.txt | 4 +- 3rdparty/libjpeg-turbo/README.md | 62 ++++++++++++++++----------- 3rdparty/libjpeg-turbo/src/jchuff.c | 12 ++++-- 3rdparty/libjpeg-turbo/src/jcmaster.c | 2 +- 3rdparty/libjpeg-turbo/src/jcphuff.c | 4 +- 3rdparty/libjpeg-turbo/src/jdhuff.c | 10 +++-- 3rdparty/libjpeg-turbo/src/jdmerge.c | 2 - 3rdparty/libjpeg-turbo/src/jdsample.c | 14 +++--- 3rdparty/libjpeg-turbo/src/jfdctint.c | 2 +- 3rdparty/libjpeg-turbo/src/jidctint.c | 2 +- 3rdparty/libjpeg-turbo/src/jidctred.c | 2 +- 11 files changed, 68 insertions(+), 48 deletions(-) diff --git a/3rdparty/libjpeg-turbo/CMakeLists.txt b/3rdparty/libjpeg-turbo/CMakeLists.txt index 531a00e017..b2c01acbc0 100644 --- a/3rdparty/libjpeg-turbo/CMakeLists.txt +++ b/3rdparty/libjpeg-turbo/CMakeLists.txt @@ -4,9 +4,9 @@ ocv_warnings_disable(CMAKE_C_FLAGS -Wunused-parameter -Wsign-compare -Wshorten-6 set(VERSION_MAJOR 2) set(VERSION_MINOR 0) -set(VERSION_REVISION 2) +set(VERSION_REVISION 4) set(VERSION ${VERSION_MAJOR}.${VERSION_MINOR}.${VERSION_REVISION}) -set(LIBJPEG_TURBO_VERSION_NUMBER 2000002) +set(LIBJPEG_TURBO_VERSION_NUMBER 2000004) string(TIMESTAMP BUILD "opencv-${OPENCV_VERSION}-libjpeg-turbo") if(CMAKE_BUILD_TYPE STREQUAL "Debug") diff --git a/3rdparty/libjpeg-turbo/README.md b/3rdparty/libjpeg-turbo/README.md index a769259891..e7ff743a47 100644 --- a/3rdparty/libjpeg-turbo/README.md +++ b/3rdparty/libjpeg-turbo/README.md @@ -1,14 +1,14 @@ Background ========== -libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2, -AVX2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression -on x86, x86-64, ARM, and PowerPC systems, as well as progressive JPEG -compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is -generally 2-6x as fast as libjpeg, all else being equal. On other types of -systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by -virtue of its highly-optimized Huffman coding routines. In many cases, the -performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs. +libjpeg-turbo is a JPEG image codec that uses SIMD instructions to accelerate +baseline JPEG compression and decompression on x86, x86-64, ARM, PowerPC, and +MIPS systems, as well as progressive JPEG compression on x86 and x86-64 +systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg, +all else being equal. On other types of systems, libjpeg-turbo can still +outperform libjpeg by a significant amount, by virtue of its highly-optimized +Huffman coding routines. In many cases, the performance of libjpeg-turbo +rivals that of proprietary high-speed JPEG codecs. libjpeg-turbo implements both the traditional libjpeg API as well as the less powerful but more straightforward TurboJPEG API. libjpeg-turbo also features @@ -135,25 +135,24 @@ without recompiling. libjpeg-turbo does not claim to support all of the libjpeg v7+ features, nor to produce identical output to libjpeg v7+ in all cases (see below.) -By passing an argument of `--with-jpeg7` or `--with-jpeg8` to `configure`, or -an argument of `-DWITH_JPEG7=1` or `-DWITH_JPEG8=1` to `cmake`, you can build a -version of libjpeg-turbo that emulates the libjpeg v7 or v8 ABI, so that -programs that are built against libjpeg v7 or v8 can be run with libjpeg-turbo. -The following section describes which libjpeg v7+ features are supported and -which aren't. +By passing an argument of `-DWITH_JPEG7=1` or `-DWITH_JPEG8=1` to `cmake`, you +can build a version of libjpeg-turbo that emulates the libjpeg v7 or v8 ABI, so +that programs that are built against libjpeg v7 or v8 can be run with +libjpeg-turbo. The following section describes which libjpeg v7+ features are +supported and which aren't. ### Support for libjpeg v7 and v8 Features #### Fully supported -- **libjpeg: IDCT scaling extensions in decompressor**
+- **libjpeg API: IDCT scaling extensions in decompressor**
libjpeg-turbo supports IDCT scaling with scaling factors of 1/8, 1/4, 3/8, 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 and 1/2 are SIMD-accelerated.) -- **libjpeg: Arithmetic coding** +- **libjpeg API: Arithmetic coding** -- **libjpeg: In-memory source and destination managers**
+- **libjpeg API: In-memory source and destination managers**
See notes below. - **cjpeg: Separate quality settings for luminance and chrominance**
@@ -185,14 +184,14 @@ means of quality improvement. The reader is invited to peruse the research at but it is the general belief of our project that these features have not demonstrated sufficient usefulness to justify inclusion in libjpeg-turbo. -- **libjpeg: DCT scaling in compressor**
+- **libjpeg API: DCT scaling in compressor**
`cinfo.scale_num` and `cinfo.scale_denom` are silently ignored. There is no technical reason why DCT scaling could not be supported when emulating the libjpeg v7+ API/ABI, but without the SmartScale extension (see below), only scaling factors of 1/2, 8/15, 4/7, 8/13, 2/3, 8/11, 4/5, and 8/9 would be available, which is of limited usefulness. -- **libjpeg: SmartScale**
+- **libjpeg API: SmartScale**
`cinfo.block_size` is silently ignored. SmartScale is an extension to the JPEG format that allows for DCT block sizes other than 8x8. Providing support for this new format would be @@ -205,7 +204,7 @@ demonstrated sufficient usefulness to justify inclusion in libjpeg-turbo. interest in providing this feature would be as a means of supporting additional DCT scaling factors. -- **libjpeg: Fancy downsampling in compressor**
+- **libjpeg API: Fancy downsampling in compressor**
`cinfo.do_fancy_downsampling` is silently ignored. This requires the DCT scaling feature, which is not supported. @@ -247,15 +246,14 @@ don't, and it allows those functions to be provided in the "official" libjpeg-turbo binaries. Those who are concerned about maintaining strict conformance with the libjpeg -v6b or v7 API can pass an argument of `--without-mem-srcdst` to `configure` or -an argument of `-DWITH_MEM_SRCDST=0` to `cmake` prior to building -libjpeg-turbo. This will restore the pre-1.3 behavior, in which +v6b or v7 API can pass an argument of `-DWITH_MEM_SRCDST=0` to `cmake` prior to +building libjpeg-turbo. This will restore the pre-1.3 behavior, in which `jpeg_mem_src()` and `jpeg_mem_dest()` are only included when emulating the libjpeg v8 API/ABI. On Un*x systems, including the in-memory source/destination managers changes -the dynamic library version from 62.1.0 to 62.2.0 if using libjpeg v6b API/ABI -emulation and from 7.1.0 to 7.2.0 if using libjpeg v7 API/ABI emulation. +the dynamic library version from 62.2.0 to 62.3.0 if using libjpeg v6b API/ABI +emulation and from 7.2.0 to 7.3.0 if using libjpeg v7 API/ABI emulation. Note that, on most Un*x systems, the dynamic linker will not look for a function in a library until that function is actually used. Thus, if a program @@ -331,7 +329,7 @@ in a way that makes the rest of the libjpeg infrastructure happy, so it is necessary to use the slow Huffman decoder when decompressing a JPEG image that has restart markers. This can cause the decompression performance to drop by as much as 20%, but the performance will still be much greater than that of -libjpeg. Many consumer packages, such as PhotoShop, use restart markers when +libjpeg. Many consumer packages, such as Photoshop, use restart markers when generating JPEG images, so images generated by those programs will experience this issue. @@ -344,3 +342,15 @@ quality of 98-100. Thus, libjpeg-turbo must use the non-SIMD quantization function in those cases. This causes performance to drop by as much as 40%. It is therefore strongly advised that you use the slow integer forward DCT whenever encoding images with a JPEG quality of 98 or higher. + + +Memory Debugger Pitfalls +======================== + +Valgrind and Memory Sanitizer (MSan) can generate false positives +(specifically, incorrect reports of uninitialized memory accesses) when used +with libjpeg-turbo's SIMD extensions. It is generally recommended that the +SIMD extensions be disabled, either by passing an argument of `-DWITH_SIMD=0` +to `cmake` when configuring the build or by setting the environment variable +`JSIMD_FORCENONE` to `1` at run time, when testing libjpeg-turbo with Valgrind, +MSan, or other memory debuggers. diff --git a/3rdparty/libjpeg-turbo/src/jchuff.c b/3rdparty/libjpeg-turbo/src/jchuff.c index 939b3e76a1..cb05055d99 100644 --- a/3rdparty/libjpeg-turbo/src/jchuff.c +++ b/3rdparty/libjpeg-turbo/src/jchuff.c @@ -4,7 +4,7 @@ * This file was part of the Independent JPEG Group's software: * Copyright (C) 1991-1997, Thomas G. Lane. * libjpeg-turbo Modifications: - * Copyright (C) 2009-2011, 2014-2016, 2018, D. R. Commander. + * Copyright (C) 2009-2011, 2014-2016, 2018-2019, D. R. Commander. * Copyright (C) 2015, Matthieu Darbois. * For conditions of distribution and use, see the accompanying README.ijg * file. @@ -43,8 +43,8 @@ */ /* NOTE: Both GCC and Clang define __GNUC__ */ -#if defined __GNUC__ && (defined __arm__ || defined __aarch64__) -#if !defined __thumb__ || defined __thumb2__ +#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__)) +#if !defined(__thumb__) || defined(__thumb2__) #define USE_CLZ_INTRINSIC #endif #endif @@ -356,6 +356,8 @@ dump_buffer(working_state *state) put_buffer = (put_buffer << size) | code; \ } +#if SIZEOF_SIZE_T != 8 && !defined(_WIN64) + #define CHECKBUF15() { \ if (put_bits > 15) { \ EMIT_BYTE() \ @@ -363,6 +365,8 @@ dump_buffer(working_state *state) } \ } +#endif + #define CHECKBUF31() { \ if (put_bits > 31) { \ EMIT_BYTE() \ @@ -428,7 +432,7 @@ dump_buffer(working_state *state) * scanning order-- 1, 8, 16, etc.), then this will produce an encoded block * larger than 200 bytes. */ -#define BUFSIZE (DCTSIZE2 * 4) +#define BUFSIZE (DCTSIZE2 * 8) #define LOAD_BUFFER() { \ if (state->free_in_buffer < BUFSIZE) { \ diff --git a/3rdparty/libjpeg-turbo/src/jcmaster.c b/3rdparty/libjpeg-turbo/src/jcmaster.c index 93b3de6826..998dc40a5c 100644 --- a/3rdparty/libjpeg-turbo/src/jcmaster.c +++ b/3rdparty/libjpeg-turbo/src/jcmaster.c @@ -492,8 +492,8 @@ prepare_for_pass(j_compress_ptr cinfo) */ master->pass_type = output_pass; master->pass_number++; - /*FALLTHROUGH*/ #endif + /*FALLTHROUGH*/ case output_pass: /* Do a data-output pass. */ /* We need not repeat per-scan setup if prior optimization pass did it. */ diff --git a/3rdparty/libjpeg-turbo/src/jcphuff.c b/3rdparty/libjpeg-turbo/src/jcphuff.c index 024d3af0fb..8c4efaf16c 100644 --- a/3rdparty/libjpeg-turbo/src/jcphuff.c +++ b/3rdparty/libjpeg-turbo/src/jcphuff.c @@ -52,8 +52,8 @@ */ /* NOTE: Both GCC and Clang define __GNUC__ */ -#if defined __GNUC__ && (defined __arm__ || defined __aarch64__) -#if !defined __thumb__ || defined __thumb2__ +#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__)) +#if !defined(__thumb__) || defined(__thumb2__) #define USE_CLZ_INTRINSIC #endif #endif diff --git a/3rdparty/libjpeg-turbo/src/jdhuff.c b/3rdparty/libjpeg-turbo/src/jdhuff.c index 95f38e547e..a1128178b0 100644 --- a/3rdparty/libjpeg-turbo/src/jdhuff.c +++ b/3rdparty/libjpeg-turbo/src/jdhuff.c @@ -4,7 +4,7 @@ * This file was part of the Independent JPEG Group's software: * Copyright (C) 1991-1997, Thomas G. Lane. * libjpeg-turbo Modifications: - * Copyright (C) 2009-2011, 2016, 2018, D. R. Commander. + * Copyright (C) 2009-2011, 2016, 2018-2019, D. R. Commander. * For conditions of distribution and use, see the accompanying README.ijg * file. * @@ -589,7 +589,11 @@ decode_mcu_slow(j_decompress_ptr cinfo, JBLOCKROW *MCU_data) if (entropy->dc_needed[blkn]) { /* Convert DC difference to actual value, update last_dc_val */ int ci = cinfo->MCU_membership[blkn]; - s += state.last_dc_val[ci]; + /* This is really just + * s += state.last_dc_val[ci]; + * It is written this way in order to shut up UBSan. + */ + s = (int)((unsigned int)s + (unsigned int)state.last_dc_val[ci]); state.last_dc_val[ci] = s; if (block) { /* Output the DC coefficient (assumes jpeg_natural_order[0] = 0) */ @@ -684,7 +688,7 @@ decode_mcu_fast(j_decompress_ptr cinfo, JBLOCKROW *MCU_data) if (entropy->dc_needed[blkn]) { int ci = cinfo->MCU_membership[blkn]; - s += state.last_dc_val[ci]; + s = (int)((unsigned int)s + (unsigned int)state.last_dc_val[ci]); state.last_dc_val[ci] = s; if (block) (*block)[0] = (JCOEF)s; diff --git a/3rdparty/libjpeg-turbo/src/jdmerge.c b/3rdparty/libjpeg-turbo/src/jdmerge.c index b3fec04f71..dff5a35087 100644 --- a/3rdparty/libjpeg-turbo/src/jdmerge.c +++ b/3rdparty/libjpeg-turbo/src/jdmerge.c @@ -429,8 +429,6 @@ h2v2_merged_upsample(j_decompress_ptr cinfo, JSAMPIMAGE input_buf, #define PACK_TWO_PIXELS_LE(l, r) ((r << 16) | l) #define PACK_TWO_PIXELS_BE(l, r) ((l << 16) | r) -#define PACK_NEED_ALIGNMENT(ptr) (((size_t)(ptr)) & 3) - #define WRITE_TWO_PIXELS_LE(addr, pixels) { \ ((INT16 *)(addr))[0] = (INT16)(pixels); \ ((INT16 *)(addr))[1] = (INT16)((pixels) >> 16); \ diff --git a/3rdparty/libjpeg-turbo/src/jdsample.c b/3rdparty/libjpeg-turbo/src/jdsample.c index 52ee9af49b..50a68b3013 100644 --- a/3rdparty/libjpeg-turbo/src/jdsample.c +++ b/3rdparty/libjpeg-turbo/src/jdsample.c @@ -8,6 +8,7 @@ * Copyright (C) 2010, 2015-2016, D. R. Commander. * Copyright (C) 2014, MIPS Technologies, Inc., California. * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2019, Arm Limited. * For conditions of distribution and use, see the accompanying README.ijg * file. * @@ -315,9 +316,9 @@ h1v2_fancy_upsample(j_decompress_ptr cinfo, jpeg_component_info *compptr, JSAMPARRAY output_data = *output_data_ptr; JSAMPROW inptr0, inptr1, outptr; #if BITS_IN_JSAMPLE == 8 - int thiscolsum; + int thiscolsum, bias; #else - JLONG thiscolsum; + JLONG thiscolsum, bias; #endif JDIMENSION colctr; int inrow, outrow, v; @@ -327,15 +328,18 @@ h1v2_fancy_upsample(j_decompress_ptr cinfo, jpeg_component_info *compptr, for (v = 0; v < 2; v++) { /* inptr0 points to nearest input row, inptr1 points to next nearest */ inptr0 = input_data[inrow]; - if (v == 0) /* next nearest is row above */ + if (v == 0) { /* next nearest is row above */ inptr1 = input_data[inrow - 1]; - else /* next nearest is row below */ + bias = 1; + } else { /* next nearest is row below */ inptr1 = input_data[inrow + 1]; + bias = 2; + } outptr = output_data[outrow++]; for (colctr = 0; colctr < compptr->downsampled_width; colctr++) { thiscolsum = GETJSAMPLE(*inptr0++) * 3 + GETJSAMPLE(*inptr1++); - *outptr++ = (JSAMPLE)((thiscolsum + 1) >> 2); + *outptr++ = (JSAMPLE)((thiscolsum + bias) >> 2); } } inrow++; diff --git a/3rdparty/libjpeg-turbo/src/jfdctint.c b/3rdparty/libjpeg-turbo/src/jfdctint.c index c0391a92be..b47c3061ac 100644 --- a/3rdparty/libjpeg-turbo/src/jfdctint.c +++ b/3rdparty/libjpeg-turbo/src/jfdctint.c @@ -1,7 +1,7 @@ /* * jfdctint.c * - * This file was part of the Independent JPEG Group's software. + * This file was part of the Independent JPEG Group's software: * Copyright (C) 1991-1996, Thomas G. Lane. * libjpeg-turbo Modifications: * Copyright (C) 2015, D. R. Commander. diff --git a/3rdparty/libjpeg-turbo/src/jidctint.c b/3rdparty/libjpeg-turbo/src/jidctint.c index 55573429f1..98425d5fd0 100644 --- a/3rdparty/libjpeg-turbo/src/jidctint.c +++ b/3rdparty/libjpeg-turbo/src/jidctint.c @@ -1,7 +1,7 @@ /* * jidctint.c * - * This file was part of the Independent JPEG Group's software. + * This file was part of the Independent JPEG Group's software: * Copyright (C) 1991-1998, Thomas G. Lane. * Modification developed 2002-2009 by Guido Vollbeding. * libjpeg-turbo Modifications: diff --git a/3rdparty/libjpeg-turbo/src/jidctred.c b/3rdparty/libjpeg-turbo/src/jidctred.c index 1ff352f875..1dd65a94d9 100644 --- a/3rdparty/libjpeg-turbo/src/jidctred.c +++ b/3rdparty/libjpeg-turbo/src/jidctred.c @@ -1,7 +1,7 @@ /* * jidctred.c * - * This file was part of the Independent JPEG Group's software. + * This file was part of the Independent JPEG Group's software: * Copyright (C) 1994-1998, Thomas G. Lane. * libjpeg-turbo Modifications: * Copyright (C) 2015, D. R. Commander.