From 0905d7effcb3395d4157895e1d77bbcb252e55c8 Mon Sep 17 00:00:00 2001 From: Allison Vacanti Date: Wed, 27 Oct 2021 15:02:34 -0400 Subject: [PATCH] Update changelog for 1.15.0-RC1. --- CHANGELOG.md | 16 +++++++++------- README.md | 2 +- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2fe83daf6a..7be6c5186b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,13 +1,13 @@ -# CUB 1.15.0 (NVIDIA HPC SDK 21.11) +# CUB 1.15.0 ## Summary -CUB 1.15.0 accompanies the NVIDIA HPC SDK 21.11 release. It includes a -new `cub::DeviceSegmentedSort` algorithm, which demonstrates up to 5000x speedup -compared to `cub::DeviceSegmentedRadixSort` when sorting a large number of small -segments. A new `cub::FutureValue` helper allows the `cub::DeviceScan` -algorithms to lazily load the `initial_value` from a pointer. `cub::DeviceScan` -also added `ScanByKey` functionality. +CUB 1.15.0 includes a new `cub::DeviceSegmentedSort` algorithm, which +demonstrates up to 5000x speedup compared to `cub::DeviceSegmentedRadixSort` +when sorting a large number of small segments. A new `cub::FutureValue` +helper allows the `cub::DeviceScan` algorithms to lazily load the +`initial_value` from a pointer. `cub::DeviceScan` also added `ScanByKey` +functionality. The new `DeviceSegmentedSort` algorithm partitions segments into size groups. Each group is processed with specialized kernels using a variety of sorting @@ -84,6 +84,8 @@ kernel launches. (@matt-stack) for this contribution. - NVIDIA/cub#388: Fix debug assertion on MSVC when using `cub::CachingDeviceAllocator`. +- NVIDIA/cub#395: Support building with `__CUDA_NO_HALF_CONVERSIONS__`. Thanks + to Xiang Gao (@zasdfgbnm) for this contribution. # CUB 1.14.0 (NVIDIA HPC SDK 21.9) diff --git a/README.md b/README.md index b3c112040c..0811c69996 100644 --- a/README.md +++ b/README.md @@ -100,7 +100,7 @@ See the [changelog](CHANGELOG.md) for details about specific releases. | CUB Release | Included In | | ------------------------- | --------------------------------------- | -| 1.15.0 | NVIDIA HPC SDK 21.11 | +| 1.15.0 | TBD | | 1.14.0 | NVIDIA HPC SDK 21.9 | | 1.13.1 | CUDA Toolkit 11.5 | | 1.13.0 | NVIDIA HPC SDK 21.7 |