diff options
| author | Jonathan Kim <jkm@hdfgroup.org> | 2012-03-06 15:41:55 (GMT) |
|---|---|---|
| committer | Jonathan Kim <jkm@hdfgroup.org> | 2012-03-06 15:41:55 (GMT) |
| commit | 185cc9746b5fa539f68f4a16800e34e773fe02d7 (patch) | |
| tree | 780f7bac279def2e15e19fde523867c6069a1d9d /release_docs | |
| parent | 6a2c50b10af4bc88e4b1a1a95cb3f9be813d61f2 (diff) | |
| download | hdf5-185cc9746b5fa539f68f4a16800e34e773fe02d7.zip hdf5-185cc9746b5fa539f68f4a16800e34e773fe02d7.tar.gz hdf5-185cc9746b5fa539f68f4a16800e34e773fe02d7.tar.bz2 | |
[svn-r22031] Purpose:
Task for HDFFV-7862 - Select data by chunk direction to improve performance in h5repack
Description:
h5repack sometimes became very slow when handling big chunked datasets in
certain cases. (when chunk boundary doesn't match with a hyperslab boundary.)
The main issue was from figuring out a hypeslab without considering chunk
boundary to read from and write to such datasets.
The update was made to figure out a better hyperslab unit with considering
chunk boundary to improve performance for such cases prior to the update.
Tested:
jam (linux32-LE), koala (linux64-LE), ostrich (linuxppc64-BE), tejeda (mac32-LE), linew (solaris-BE), Windows
Diffstat (limited to 'release_docs')
| -rw-r--r-- | release_docs/RELEASE.txt | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/release_docs/RELEASE.txt b/release_docs/RELEASE.txt index 3beb250..d8124db 100644 --- a/release_docs/RELEASE.txt +++ b/release_docs/RELEASE.txt @@ -68,7 +68,10 @@ New Features Tools ----- - - None + - h5repack: Improved performance for hanlding big chunked datasets (size > 128MB). + Especially performance would be much better prior to the update, for the cases + that chunk dimentions look like "1024x5x1" (opposite to "1x5x1024"). When big + numbers are toward front and small numbers are toward back in chunk dimentions. High-Level APIs --------------- |