|
f3a8684c
|
2016-01-07T00:19:43
|
|
SSE2 SIMD implementation of Huffman encoding
Full-color compression speedups relative to libjpeg-turbo 1.4.2:
2.8 GHz Intel Xeon W3530, Linux, 64-bit: 2.2-18% (avg. 9.5%)
2.8 GHz Intel Xeon W3530, Linux, 32-bit: 10-25% (avg. 17%)
2.3 GHz AMD A10-4600M APU, Linux, 64-bit: 4.9-17% (avg. 11%)
2.3 GHz AMD A10-4600M APU, Linux, 32-bit: 8.8-19% (avg. 15%)
3.0 GHz Intel Core i7, OS X, 64-bit: 3.5-16% (avg. 10%)
3.0 GHz Intel Core i7, OS X, 32-bit: 4.8-14% (avg. 11%)
2.6 GHz AMD Athlon 64 X2 5050e:
Performance-neutral (give or take a few percent)
Full-color compression speedups relative to IPP:
2.8 GHz Intel Xeon W3530, Linux, 64-bit: 4.8-34% (avg. 19%)
2.8 GHz Intel Xeon W3530, Linux, 32-bit: -19%-7.0% (avg. -7.0%)
Refer to #42 for discussion. Numerous other approaches were attempted,
but this one proved to be the most performant across all platforms.
This commit also fixes #3 (works around, really-- the clang-compiled version
of jchuff.c still performs 20% worse than its GCC-compiled counterpart, but
that code is now bypassed by the new SSE2 Huffman algorithm.)
Based on:
https://github.com/mayeut/libjpeg-turbo/commit/2cb4d41330e1edc4469f6b97ba73b73abfbeb02f
https://github.com/mayeut/libjpeg-turbo/commit/36c94e050d117912adbff9fbcc6fe307df240168
|
|
8b5a0093
|
2015-01-21T17:42:28
|
|
Oops. The MIPS SIMD implementations of h2v1 and h2v2 upsampling were not checking for DSPr2 support, so running 'djpeg -nosmooth' on a non-DSPr2-enabled platform caused an "illegal instruction" error.
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/branches/1.4.x@1523 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
d729f4da
|
2014-08-23T15:47:51
|
|
ARM NEON SIMD support for YCC-to-RGB565 conversion, and optimizations to the existing YCC-to-RGB conversion code:
-----
https://github.com/ssvb/libjpeg-turbo/commit/aee36252be20054afce371a92406fc66ba6627b5.patch
From aee36252be20054afce371a92406fc66ba6627b5 Mon Sep 17 00:00:00 2001
From: Siarhei Siamashka <siarhei.siamashka@gmail.com>
Date: Wed, 13 Aug 2014 03:50:22 +0300
Subject: [PATCH] ARM: Faster NEON yuv->rgb conversion for Krait and Cortex-A15
The older code was developed and tested only on ARM Cortex-A8 and ARM Cortex-A9.
Tuning it for newer ARM processors can introduce some speed-up (up to 20%).
The performance of the inner loop (conversion of 8 pixels) improves from
~27 cycles down to ~22 cycles on Qualcomm Krait 300, and from ~20 cycles
down to ~18 cycles on ARM Cortex-A15.
The performance remains exactly the same on ARM Cortex-A7 (~58 cycles),
ARM Cortex-A8 (~25 cycles) and ARM Cortex-A9 (~30 cycles) processors.
Also use larger indentation in the source code for separating two independent
instruction streams.
-----
https://github.com/ssvb/libjpeg-turbo/commit/a5efdbf22ce9c1acd4b14a353cec863c2c57557e.patch
From a5efdbf22ce9c1acd4b14a353cec863c2c57557e Mon Sep 17 00:00:00 2001
From: Siarhei Siamashka <siarhei.siamashka@gmail.com>
Date: Wed, 13 Aug 2014 07:23:09 +0300
Subject: [PATCH] ARM: NEON optimized yuv->rgb565 conversion
The performance of the inner loop (conversion of 8 pixels):
* ARM Cortex-A7: ~55 cycles
* ARM Cortex-A8: ~28 cycles
* ARM Cortex-A9: ~32 cycles
* ARM Cortex-A15: ~20 cycles
* Qualcomm Krait: ~24 cycles
Based on the Linaro rgb565 patch from
https://sourceforge.net/p/libjpeg-turbo/patches/24/
but implements better instructions scheduling.
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1385 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
495e4342
|
2014-05-19T19:13:22
|
|
Allow for building the MIPS DSPr2 extensions if the host is mips-* as well as mipsel-*. The DSPr2 extensions are little endian, so we still have to check that the compiler defines __MIPSEL__ before enabling them. This paves the way for supporting big-endian MIPS, and in the near term, it allows the SIMD extensions to be built with Sourcery CodeBench.
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1316 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
5ef46305
|
2014-05-18T20:04:47
|
|
SIMD-accelerated int upsample routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1315 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
c728cfd8
|
2014-05-18T19:36:05
|
|
Fix MIPS build
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1314 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
1419852c
|
2014-05-15T19:45:11
|
|
Clean up code formatting in the SIMD interface functions
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1305 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
1b3fd7ee
|
2014-05-15T18:26:01
|
|
SIMD-accelerated NULL convert routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1304 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
6a61c1e6
|
2014-05-14T15:00:10
|
|
SIMD-accelerated h2v2 smooth downsampling routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1301 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
b844eaa3
|
2014-05-13T18:40:14
|
|
SIMD-accelerated merged upsampling routines for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1297 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
34347862
|
2014-05-06T09:53:21
|
|
SIMD-accelerated slow integer IDCT routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1269 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
fff6c23a
|
2013-10-12T21:39:20
|
|
SIMD-accelerated integer convsamp routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1059 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
3d727281
|
2013-10-09T18:39:44
|
|
SIMD-accelerated floating point quantize and convsamp routines for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1058 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
d3131c1b
|
2013-10-08T02:18:59
|
|
SIMD-accelerated fast integer inverse DCT routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1056 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
71e06a7d
|
2013-10-08T02:11:21
|
|
SIMD-accelerated fast integer forward DCT routine for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1055 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
a6b7fbd3
|
2013-09-30T18:13:27
|
|
SIMD-accelerated slow integer forward DCT and quantize routines for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1054 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
e5005917
|
2013-09-27T17:51:08
|
|
SIMD-accelerated 3/4 and 3/2 decompression scaling for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1047 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
2ccf4d1a
|
2013-09-27T17:43:23
|
|
SIMD-accelerated 1/2 and 1/4 decompression scaling for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1046 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
49eaa757
|
2013-09-27T17:39:57
|
|
SIMD-optimized RGB-to-grayscale conversion for MIPS DSPr2
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@1045 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
16962c11
|
2013-07-27T21:50:02
|
|
SIMD support for performing upsampling using MIPS DSPr2 instructions
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@996 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
6f2d3c2c
|
2013-07-27T21:48:18
|
|
SIMD support for performing downsampling using MIPS DSPr2 instructions
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@995 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
86fbf35f
|
2013-07-27T21:44:14
|
|
SIMD support for performing fancy upsampling using MIPS DSPr2 instructions
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@994 632fc199-4ca6-4c93-a231-07263d6284db
|
|
|
0be9fa57
|
2013-07-24T21:50:20
|
|
SIMD support for performing color conversion using MIPS DSPr2 instructions
git-svn-id: svn+ssh://svn.code.sf.net/p/libjpeg-turbo/code/trunk@993 632fc199-4ca6-4c93-a231-07263d6284db
|