Hi,

Blosc is a high-performance compressor optimized for binary data that 
can also be used as a filter for HDF5.  In 1.1, I've fixed a couple of 
issues that affects this filter functionality.

Enjoy!

===============================================================
 Announcing Blosc 1.1
 A blocking, shuffling and lossless compression library
===============================================================

What is new?
============

- Added code for emulating pthreads API on Windows.  No need to link
  explicitly with pthreads lib on Windows anymore.

- New BLOSC_MAX_BUFFERSIZE, BLOSC_MAX_TYPESIZE and BLOSC_MAX_THREADS
  symbols are available in blosc.h.  These can be useful for
  validating parameters in clients.  Thanks to Robert Smallshire for
  suggesting that.

- A new BLOSC_MIN_HEADER_LENGTH symbol in blosc.h tells how many bytes
  long is the minimum length of a Blosc header.

- Fixed a problem with the computation of the blocksize in the Blosc
  filter for HDF5.

- Many fixes, specially related with thread synchronization in
  scenarios where a fork of a thread Blosc is done.  This situation is
  handled correctly now.

- Added a new `blosc_getitem()` call to allow the retrieval of items
  in sizes smaller than the complete buffer.  That is useful for the
  carray project, but it can certainly be so for others too.

For more info, please see the RELEASE_NOTES.txt file.

What is it?
===========

Blosc [1]_ is a high performance compressor optimized for binary data.
It has been designed to transmit data to the processor cache faster
than the traditional, non-compressed, direct memory fetch approach via
a memcpy() OS call.  Blosc is the first compressor (that I'm aware of)
that is meant not only to reduce the size of large datasets on-disk or
in-memory, but also to accelerate memory-bound computations.

It uses the blocking technique (as described in [2]_) to reduce
activity on the memory bus as much as possible.  In short, this
technique works by dividing datasets in blocks that are small enough
to fit in caches of modern processors and perform compression /
decompression there.  It also leverages, if available, SIMD
instructions (SSE2) and multi-threading capabilities of CPUs, in order
to accelerate the compression / decompression process to a maximum.

You can see some recent benchmarks about Blosc performance in [3]_,
and in combination with PyTables in [4]_, [5]_ and [6]_.

.. [1] http://blosc.pytables.org
.. [2] http://www.pytables.org/docs/CISE-12-2-ScientificPro.pdf
.. [3] http://blosc.pytables.org/trac/wiki/SyntheticBenchmarks
.. [4] http://www.pytables.org/docs/manual/ch05.html#chunksizeFineTune
.. [5] http://pytables.org/moin/ComputingKernel
.. [6] http://pytables.org/moin/PyTablesPro


Download sources
================

Please go to:

http://blosc.pytables.org/sources/

and download the stable release from here.

Blosc is distributed using the MIT license, see LICENSES/BLOSC.txt for
details.

-- 
Francesc Alted

_______________________________________________
Hdf-forum is for HDF software users discussion.
[email protected]
http://mail.hdfgroup.org/mailman/listinfo/hdf-forum_hdfgroup.org

Reply via email to