|
hipCUB
|
See README.md on how to build the hipCUB documentation using Doxygen.
DeviceSegmentedReduce::ArgMin and DeviceSegmentedReduce::ArgMax by returning the segment-relative index instead of the absolute one.DeviceSegmentedReduce::ArgMin for inputs where the segment minimum is smaller than the value returned for empty segments. An equivalent fix is applied to DeviceSegmentedReduce::ArgMax.DOWNLOAD_ROCPRIM, forcing rocPRIM to download can be done with DEPENDENCIES_FORCE_DOWNLOAD. debug_synchronous no longer works on CUDA platform. CUB_DEBUG_SYNC should be used to enable those checks.DeviceReduce::Sum does not compile on CUDA platform for mixed extended-floating-point/floating-point InputT and OutputT types.DeviceHistogram::HistogramEven fails on CUDA platform for [LevelT, SampleIteratorT] = [int, int].DeviceHistogram::MultiHistogramEven fails on CUDA platform for [LevelT, SampleIteratorT] = [int, int/unsigned short/float/double] and [LevelT, SampleIteratorT] = [float, double].BlockShuffle, BlockLoad, and BlockStore. BlockScan by adding ExclusiveScan, benchmark coverage of BlockRadixSort by adding SortBlockedToStriped, and benchmark coverage of WarpScan by adding Broadcast.BlockRadixRankMatch is currently broken under the rocPRIM backend.BlockRadixRankMatch with a warp size that does not exactly divide the block size is broken under the CUB backend.BlockAdjacentDifference::SubtractLeftPartialTile that takes a predecessor item. DeviceRadixSort, DeviceSegmentedRadixSort and DeviceSegmentedSort.BlockRadixRankMatch is currently broken under the rocPRIM backend.BlockRadixRankMatch with a warp size that does not exactly divide the block size is broken under the CUB backend.DeviceHistogram, DeviceScan, DevicePartition, DeviceReduce, DeviceSegmentedReduce, DeviceSegmentedRadixSort, DeviceRadixSort, DeviceSpmv, DeviceMergeSort, DeviceSegmentedSort Device_scan and device_segmented_scan: inclusive_scan now uses the input-type as accumulator-type, exclusive_scan uses initial-value-type.
.deb packages, and hipcub-devel for .rpm packages). As hipCUB is a header-only library, there is no runtime package. To aid in the transition, the development package sets the "provides" field to provide the package hipcub, so that existing packages depending on hipcub can continue to work. This provides feature is introduced as a deprecated feature and will be removed in a future ROCm release.
1.8.13