Lines Matching refs:SIMD
10 2. Fixed a regression in the SIMD feature detection code, introduced by
11 the AVX2 SIMD extensions (2.0 beta1[1]), that was known to cause an illegal
75 8. Fixed a severe performance issue in the Loongson MMI SIMD extensions that
91 functions in the MIPS DSPr2 SIMD extensions are now disabled at compile time
95 3. Fixed a regression in the SIMD feature detection code, introduced by
96 the AVX2 SIMD extensions (2.0 beta1[1]), that caused libjpeg-turbo to crash on
155 7. The new CMake-based build system will now disable the MIPS DSPr2 SIMD
175 1. Added AVX2 SIMD implementations of the colorspace conversion, chroma
280 12. The SIMD function symbols for x86[-64]/ELF, MIPS/ELF, macOS/x86[-64] (if
285 13. Added Loongson MMI SIMD implementations of the RGB-to-YCbCr and
295 15. Added SIMD acceleration for progressive Huffman encoding on SSE2-capable
353 2. Fixed a regression introduced by 1.5.1[1] that prevented the MIPS DSPR2 SIMD
360 4. libjpeg-turbo should now build and run with full AltiVec SIMD acceleration
412 the 32-bit x86 SIMD extensions with NASM versions prior to 2.04. This was a
422 used to force-enable a particular SIMD instruction set if multiple instruction
424 feature detection is bulletproof and multiple SIMD instruction sets are
427 since the ARM implementations of libjpeg-turbo can only use one SIMD
453 caused by an ABI conformance issue in some of libjpeg-turbo's 64-bit NEON SIMD
464 The h1v2 fancy upsampling algorithm is not currently SIMD-accelerated.
466 5. If merged upsampling isn't SIMD-accelerated but YCbCr-to-RGB conversion is,
501 10. Fixed another ABI conformance issue in the 64-bit ARM (AArch64) NEON SIMD
536 5. Fixed an issue in the ARM 32-bit SIMD-accelerated Huffman encoder that
553 1. Added full SIMD acceleration for PowerPC platforms using AltiVec VMX
554 (128-bit SIMD) instructions. Although the performance of libjpeg-turbo on
580 6. The MIPS DSPr2 SIMD code can now be compiled to support either FR=0 or FR=1
589 8. Removed the unnecessary `.arch` directive from the ARM64 NEON SIMD code.
602 10. The x86-64 SIMD code can now be disabled at run time by setting the
603 `JSIMD_FORCENONE` environment variable to `1` (the other SIMD implementations
611 12. Added SIMD acceleration for Huffman encoding on SSE2-capable x86 and x86-64
618 benchmarking or regression testing, SIMD-accelerated Huffman encoding can be
621 13. Added ARM 64-bit (ARMv8) NEON SIMD implementations of the commonly-used
628 14. Added SIMD acceleration for Huffman encoding on NEON-capable ARM 32-bit
644 For the purposes of benchmarking or regression testing, SIMD-accelerated
653 16. Optimized the ARM 64-bit (ARMv8) NEON SIMD decompression routines to
688 an x86-64 ABI conformance issue in some of libjpeg-turbo's 64-bit SSE2 SIMD
730 question are not implemented using SIMD instructions on a particular platform.
741 SIMD-enabled libjpeg-turbo MIPS build was executed with the `-nosmooth` option
742 on a MIPS machine that lacked DSPr2 support. The MIPS SIMD routines for h2v1
780 2. The non-SIMD RGB565 color conversion code did not work correctly on big
839 12. Fixed issues that were preventing the ARM 64-bit SIMD code from compiling
876 2. Added SIMD acceleration for DSPr2-capable MIPS platforms. This speeds up
909 7. Improved the accuracy and performance of the non-SIMD implementation of the
919 used, then this code path is SIMD-accelerated on ARM platforms.
944 14. Added ARM 64-bit SIMD acceleration for the YCC-to-RGB color conversion
1052 not be SIMD-accelerated when using any of these new scaling factors.
1094 SIMD code with NASM 0.98.
1120 2. When libjpeg-turbo was built without SIMD support and merged (non-fancy)
1126 3. Fixed a bug whereby the libjpeg-turbo SSE2 SIMD code would not preserve the
1136 SSE2 SIMD code, is apparently implemented in microcode on AMD processors, and
1141 6. Added SIMD acceleration for performing 4:2:2 upsampling on NEON-capable ARM
1146 running the 32-bit SSE2 SIMD code in libjpeg-turbo, decompressing a 4:2:0 or
1152 8. Fixed an issue whereby attempting to build the SIMD extensions with Xcode
1169 2. Fixed out-of-bounds read in SSE2 SIMD code that occurred when decompressing
1209 3. Added SIMD routines for RGB-to-grayscale color conversion, which
1214 on platforms for which SIMD acceleration is not available.
1236 10. Added SIMD acceleration for ARM Linux and iOS platforms that support
1290 this, the libjpeg-turbo SIMD function names are no longer prefixed with an
1316 1. The algorithm used by the SIMD quantization function cannot produce correct
1318 used. Thus, the non-SIMD quantization function is now used for those cases,
1393 2. Fixed typo in SIMD dispatch routines that was causing 4:2:2 upsampling to