diff --git a/CHANGE_LOG.TXT b/CHANGE_LOG.TXT index d0e0398204..51ad5e305c 100644 --- a/CHANGE_LOG.TXT +++ b/CHANGE_LOG.TXT @@ -1,9 +1,6 @@ //----------------------------------------------------------------------------- -1.3.1 05/22/2014 - - New features: - - Added new "combination" WarpScan methods for efficiently computing - both inclusive and exclusive prefix scans (and sums). +1.3.1 05/23/2014 - Bug fixes: - Workaround for a benign WAW race warning reported by cuda-memcheck in BlockScan specialized for BLOCK_SCAN_WARP_SCANS algorithm. @@ -34,6 +31,8 @@ allocated dynamically by the host at the kernel call site. - Most CUB programs having typical 1D usage should not require any changes to accomodate these updates. + - Added new "combination" WarpScan methods for efficiently computing + both inclusive and exclusive prefix scans (and sums). - Bug fixes: - Fixed bug in cub::WarpScan (which affected cub::BlockScan and cub::DeviceScan) where incorrect results (e.g., NAN) would often be diff --git a/README.md b/README.md index 3eae36af7b..1927d593e6 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@

About CUB

-Current release: v1.3.0 (May 12, 2014) +Current release: v1.3.1 (May 23, 2014) We recommend the [CUB Project Website](http://nvlabs.github.com/cub) and the [cub-users discussion forum](http://groups.google.com/group/cub-users) for further information and examples. @@ -78,17 +78,25 @@ shared memory needed by the thread block. (Alternatively these storage types could be aliased to global memory allocations).

-

Releases

- -See [CUB Project Website](http://nvlabs.github.com/cub) for more information. +

Stable Releases

+ +CUB releases are labeled using version identifiers having three fields: +*epoch.feature.update*. The *epoch* field corresponds to support for +a major change in the CUDA programming model. The *feature* field +corresponds to a stable set of features, functionality, and interface. The +*update* field corresponds to a bug-fix or performance update for that +feature set. At the moment, we do not publicly provide non-stable releases +such as development snapshots, beta releases or rolling releases. (Feel free +to contact us if you would like such things.) See the +[CUB Project Website](http://nvlabs.github.com/cub) for more information. | Date | Version | | ---- | ------- | -| 05/12/2014 | [CUB v1.3.0 Primary Release](https://github.com/NVlabs/cub/archive/1.3.0.zip) | -| 04/01/2014 | [CUB v1.2.3 Primary Release](https://github.com/NVlabs/cub/archive/1.2.3.zip) | -| 12/10/2013 | [CUB v1.1.1 Primary Release](https://github.com/NVlabs/cub/archive/1.1.1.zip) | -| 08/08/2013 | [CUB v1.0.1 Primary Release](https://github.com/NVlabs/cub/archive/1.0.1.zip) | -| 03/07/2013 | [CUB v0.9.0 Preview Release](https://github.com/NVlabs/cub/archive/0.9.zip) | +| 05/23/2014 | [CUB v1.3.1](https://github.com/NVlabs/cub/archive/1.3.1.zip) | +| 04/01/2014 | [CUB v1.2.3](https://github.com/NVlabs/cub/archive/1.2.3.zip) | +| 12/10/2013 | [CUB v1.1.1](https://github.com/NVlabs/cub/archive/1.1.1.zip) | +| 08/08/2013 | [CUB v1.0.1](https://github.com/NVlabs/cub/archive/1.0.1.zip) | +| 03/07/2013 | [CUB v0.9.0](https://github.com/NVlabs/cub/archive/0.9.zip) |

diff --git a/cub/warp/warp_scan.cuh b/cub/warp/warp_scan.cuh index ba604ec311..a065f9846a 100644 --- a/cub/warp/warp_scan.cuh +++ b/cub/warp/warp_scan.cuh @@ -1183,7 +1183,7 @@ public: /** - * \brief Computes an exclusive prefix scan using the specified binary scan functor across the calling warp. The \p warp_prefix_op value from thread-thread-lane0 is applied to all scan outputs. Also computes the warp-wide \p warp_aggregate of all inputs for thread-thread-lane0. + * \brief Computes an exclusive prefix scan using the specified binary scan functor across the calling warp. The \p warp_prefix_op value from warp-lane0 is applied to all scan outputs. Also computes the warp-wide \p warp_aggregate of all inputs for warp-lane0. * * The \p warp_prefix_op functor must implement a member function T operator()(T warp_aggregate)}. * The functor's input parameter \p warp_aggregate is the same value also returned by the scan operation. diff --git a/docs/extra_stylesheet.css b/docs/extra_stylesheet.css index 17815e0602..82a196b249 100644 --- a/docs/extra_stylesheet.css +++ b/docs/extra_stylesheet.css @@ -2,8 +2,12 @@ * General *****************************************************************************/ -body, table, div, p, dl { - font: 12px/22px arial,sans-serif; +body, div, p, dl { + font: 12px/22px arial,sans-serif; +} + +table { + font: 12px/18px arial,sans-serif; } body { diff --git a/docs/html/CHANGE_LOG.TXT b/docs/html/CHANGE_LOG.TXT index d0e0398204..51ad5e305c 100644 --- a/docs/html/CHANGE_LOG.TXT +++ b/docs/html/CHANGE_LOG.TXT @@ -1,9 +1,6 @@ //----------------------------------------------------------------------------- -1.3.1 05/22/2014 - - New features: - - Added new "combination" WarpScan methods for efficiently computing - both inclusive and exclusive prefix scans (and sums). +1.3.1 05/23/2014 - Bug fixes: - Workaround for a benign WAW race warning reported by cuda-memcheck in BlockScan specialized for BLOCK_SCAN_WARP_SCANS algorithm. @@ -34,6 +31,8 @@ allocated dynamically by the host at the kernel call site. - Most CUB programs having typical 1D usage should not require any changes to accomodate these updates. + - Added new "combination" WarpScan methods for efficiently computing + both inclusive and exclusive prefix scans (and sums). - Bug fixes: - Fixed bug in cub::WarpScan (which affected cub::BlockScan and cub::DeviceScan) where incorrect results (e.g., NAN) would often be diff --git a/docs/html/annotated.html b/docs/html/annotated.html index 93df51ac7c..ea752de513 100644 --- a/docs/html/annotated.html +++ b/docs/html/annotated.html @@ -228,7 +228,7 @@