Release Notes: This release adds support for out-of-place prefix sums (although with the same type for source and destination). It also saves program binaries in the cache for faster startup on some platforms.
Release Notes: This release fixes a bug that could cause incorrect sorting results, depending on the results of autotuning.
Release Notes: This bugfix release fixes a race condition in the radix sort, introduced in 1.2.1. It also works around a driver bug in the AMD APP SDK for CPU devices.
Release Notes: This release has no API changes, but significantly improves performance. Recent AMD GPUs get more than 3 times faster in some cases, but NVIDIA GPUs also see a nice performance boost.
Release Notes: This release autotunes kernel parameters on the target system for improved performance, in some cases a 2x improvement. Refer to the user manual for instructions on performing the autotuning. There are also some minor bugfixes.
Release Notes: This release adds a facility to retrieve all the OpenCL events associated with enqueued commands, making it easier to profile them.
Release Notes: This release adds support for building on Windows, using MSVC.
Release Notes: This release fixes a build system error that caused builds to fail when documentation was built from a pristine installation.