<feed xmlns='http://www.w3.org/2005/Atom'>
<title>openjpeg/src/lib/openjp2/dwt.c, branch opj_idwt53_h_cas0_SSE2</title>
<subtitle>Fork of openjpeg library for JPEG2000 encoding and decoding</subtitle>
<id>https://git.carlh.net/cgit/openjpeg/atom?h=opj_idwt53_h_cas0_SSE2</id>
<link rel='self' href='https://git.carlh.net/cgit/openjpeg/atom?h=opj_idwt53_h_cas0_SSE2'/>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/'/>
<updated>2017-06-20T23:09:02Z</updated>
<entry>
<title>dwt.c: implement SSE2 idwt5x3 horizontal when len is multiple of 8. Speed gain is very marginal however</title>
<updated>2017-06-20T23:09:02Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2017-06-20T23:09:02Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=288f4720638e5c411bd5ddb8944dd5575584ea1d'/>
<id>urn:sha1:288f4720638e5c411bd5ddb8944dd5575584ea1d</id>
<content type='text'>
</content>
</entry>
<entry>
<title>dwt.c: small cleanup</title>
<updated>2017-06-20T23:07:56Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2017-06-20T23:07:56Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=f6e3475cc9328e5378e96e72b5adf29fb07c5feb'/>
<id>urn:sha1:f6e3475cc9328e5378e96e72b5adf29fb07c5feb</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Improve performance of inverse DWT 5x3 (#953)</title>
<updated>2017-06-20T16:01:34Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2017-06-20T15:56:25Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=fa55b52d19f39765d7f108d654a8f87035a5772f'/>
<id>urn:sha1:fa55b52d19f39765d7f108d654a8f87035a5772f</id>
<content type='text'>
* Use single-pass lifting inverse wavelet transform.
* For vertical pass, use SSE2 when available so as to process 8 columns
  in parallel. This is the most beneficial improvement, since the
  vertical pass involves a lot of cache trashing.

With the bench_dwt utility with default arguments (16383x16383 image),
time goes from 4.064 s to 1.212 s.
</content>
</entry>
<entry>
<title>Fix astyle issue</title>
<updated>2017-06-17T14:37:56Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2017-06-17T14:37:56Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=32b20b93e04d38303f736e975eb5f483fda01ca5'/>
<id>urn:sha1:32b20b93e04d38303f736e975eb5f483fda01ca5</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Fix warnings with recent GCC versions</title>
<updated>2017-06-17T12:09:31Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2017-06-17T12:09:31Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=cc07aec6c7b50090c3f471ca2c68d0ffa8aa4ff1'/>
<id>urn:sha1:cc07aec6c7b50090c3f471ca2c68d0ffa8aa4ff1</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Reformat whole codebase with astyle.options (#128)</title>
<updated>2017-05-09T18:46:20Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2017-05-09T13:44:46Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=563bd8499e63db976ca8358216138647593354bc'/>
<id>urn:sha1:563bd8499e63db976ca8358216138647593354bc</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Remove TODO for overflow check (#842)</title>
<updated>2016-09-15T21:51:34Z</updated>
<author>
<name>Matthieu Darbois</name>
<email>mayeut@users.noreply.github.com</email>
</author>
<published>2016-09-15T21:51:34Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=6e7616c83cb01d9b7a5a35e093ff9ff6741acc74'/>
<id>urn:sha1:6e7616c83cb01d9b7a5a35e093ff9ff6741acc74</id>
<content type='text'>
The check was already done. It’s been simplified.
Reformat to get consistent style throughout the functions.
</content>
</entry>
<entry>
<title>Add overflow checks for opj_aligned_malloc (#841)</title>
<updated>2016-09-14T23:57:53Z</updated>
<author>
<name>Matthieu Darbois</name>
<email>mayeut@users.noreply.github.com</email>
</author>
<published>2016-09-14T23:57:53Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=9a07ccb3d0f076388e4da684a3bfd4327125c721'/>
<id>urn:sha1:9a07ccb3d0f076388e4da684a3bfd4327125c721</id>
<content type='text'>
See
https://pdfium.googlesource.com/pdfium/+/b20ab6c7acb3be1393461eb650ca8fa4660c937e/third_party/libopenjpeg20/0020-opj_aligned_malloc.patch</content>
</entry>
<entry>
<title>Fix some warnings (#838)</title>
<updated>2016-09-13T22:12:43Z</updated>
<author>
<name>Matthieu Darbois</name>
<email>mayeut@users.noreply.github.com</email>
</author>
<published>2016-09-13T22:12:43Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=0954bc11e3ab6a39d86e5ed51286da4b8989743d'/>
<id>urn:sha1:0954bc11e3ab6a39d86e5ed51286da4b8989743d</id>
<content type='text'>
Fix warnings introduced by uclouvain/openjpeg#786</content>
</entry>
<entry>
<title>Merge branch 'master' of https://github.com/uclouvain/openjpeg into tier1_optimizations_multithreading_2</title>
<updated>2016-09-08T08:30:09Z</updated>
<author>
<name>Even Rouault</name>
<email>even.rouault@spatialys.com</email>
</author>
<published>2016-09-08T08:30:09Z</published>
<link rel='alternate' type='text/html' href='https://git.carlh.net/cgit/openjpeg/commit/?id=48c16b2c199210a3c20b306a737eac5fc2c8f6c9'/>
<id>urn:sha1:48c16b2c199210a3c20b306a737eac5fc2c8f6c9</id>
<content type='text'>
Conflicts:
	src/lib/openjp2/t1.c
</content>
</entry>
</feed>
