Todo List

Member CUDPPCompactPlan::CUDPPCompactPlan (CUDPPConfiguration config, size_t numElements, size_t numRows, size_t rowPitch)

Add support for multirow compaction

Member CUDPP_OPTION_CTA_LOCAL

Currently ignored.

Member launchRandMD5Kernel

: chose a better block size, perhaps a multiple of two is optimal

Member rank4

is the description of "preds" correct?

Member DISALLOW_LOADSTORE_OVERLAP

Parameterize this in case this perf detail changes on future GPUs.

Member cudppScan

Return more specific errors

Member cudppSegmentedScan

Return more specific errors

Member cudppMultiScan

Return more specific errors

Member cudppCompact

[MJH] We need to evaluate whether cudppCompact should be a core member of the public interface. It's not clear to me that what the user always wants is a final compacted array. Often one just wants the array of indices to which each input element should go in the output. The split() routine used in radix sort might make more sense to expose.

Member cudppCompact

Return more specific errors.

Member cudppSort

Determine if we need to provide an "out of place" sort interface.

Member cudppSort

Return more specific errors.

Member cudppSparseMatrixVectorMultiply

Return more specific errors.

Member cudppRand

Currently only MD5 PRNG is supported. We may provide more rand routines in the future.

Member cudppRand

Return more specific errors

Member cudppPlan

: implement cudppReduce()

Member reorderData

Args that are const below should be prototyped as const

Member vectorAddConstant

Test this function -- it is currently not yet used.

Member vectorAddVector

Test this function -- it is currently not yet used.