Skip to content

CLBlast 1.5.2

Compare
Choose a tag to compare
@CNugteren CNugteren released this 20 Jan 13:22
· 117 commits to master since this release

CLBlast version 1.5.2. Changes since previous release (version 1.5.1):

  • Changed XAMAX/XAMIN to more likely return first rather than last min/max index, updated API docs
  • Added batched routines to pyclblast
  • Added CLBLAST_VERSION_MAJOR/MINOR/PATCH defines in headers to store version numbering
  • Several small improvements to the benchmark script (thanks to 'baryluk')
  • Fixed a bug in the caching when using a context with multiple devices
  • Fixed a bug in the tuners related to global workgroup size not being a multiple of the local
  • Various minor fixes and enhancements
  • Added tuned parameters for various devices (see doc/tuning.md)