CUDPP
2.1
CUDA Data-Parallel Primitives Library
|
Main library header file. Defines public interface. More...
#include <stdlib.h>
#include "cudpp_config.h"
Classes | |
struct | CUDPPConfiguration |
Configuration struct used to specify algorithm, datatype, operator, and options when creating a plan for CUDPP algorithms. More... | |
Functions | |
CUDPP_DLL CUDPPResult | cudppCreate (CUDPPHandle *theCudpp) |
Creates an instance of the CUDPP library, and returns a handle. More... | |
CUDPP_DLL CUDPPResult | cudppDestroy (CUDPPHandle theCudpp) |
Destroys an instance of the CUDPP library given its handle. More... | |
CUDPP_DLL CUDPPResult | cudppPlan (const CUDPPHandle cudppHandle, CUDPPHandle *planHandle, CUDPPConfiguration config, size_t n, size_t rows, size_t rowPitch) |
Create a CUDPP plan. More... | |
CUDPP_DLL CUDPPResult | cudppDestroyPlan (CUDPPHandle plan) |
Destroy a CUDPP Plan. More... | |
CUDPP_DLL CUDPPResult | cudppScan (const CUDPPHandle planHandle, void *d_out, const void *d_in, size_t numElements) |
Performs a scan operation of numElements on its input in GPU memory (d_in) and places the output in GPU memory (d_out), with the scan parameters specified in the plan pointed to by planHandle. More... | |
CUDPP_DLL CUDPPResult | cudppMultiScan (const CUDPPHandle planHandle, void *d_out, const void *d_in, size_t numElements, size_t numRows) |
Performs numRows parallel scan operations of numElements each on its input (d_in) and places the output in d_out, with the scan parameters set by config. Exactly like cudppScan except that it runs on multiple rows in parallel. More... | |
CUDPP_DLL CUDPPResult | cudppSegmentedScan (const CUDPPHandle planHandle, void *d_out, const void *d_idata, const unsigned int *d_iflags, size_t numElements) |
Performs a segmented scan operation of numElements on its input in GPU memory (d_idata) and places the output in GPU memory (d_out), with the scan parameters specified in the plan pointed to by planHandle. More... | |
CUDPP_DLL CUDPPResult | cudppCompact (const CUDPPHandle planHandle, void *d_out, size_t *d_numValidElements, const void *d_in, const unsigned int *d_isValid, size_t numElements) |
Given an array d_in and an array of 1/0 flags in deviceValid, returns a compacted array in d_out of corresponding only the "valid" values from d_in. More... | |
CUDPP_DLL CUDPPResult | cudppReduce (const CUDPPHandle planHandle, void *d_out, const void *d_in, size_t numElements) |
Reduces an array to a single element using a binary associative operator. More... | |
CUDPP_DLL CUDPPResult | cudppRadixSort (const CUDPPHandle planHandle, void *d_keys, void *d_values, size_t numElements) |
Sorts key-value pairs or keys only. More... | |
CUDPP_DLL CUDPPResult | cudppMergeSort (const CUDPPHandle planHandle, void *d_keys, void *d_values, size_t numElements) |
Sorts key-value pairs or keys only. More... | |
CUDPP_DLL CUDPPResult | cudppStringSort (const CUDPPHandle planHandle, unsigned char *d_stringVals, unsigned int *d_address, unsigned char termC, size_t numElements, size_t stringArrayLength) |
Sorts strings. Keys are the first four characters of the string, and values are the addresses where the strings reside in memory (stringVals) More... | |
CUDPP_DLL CUDPPResult | cudppSparseMatrix (const CUDPPHandle cudppHandle, CUDPPHandle *sparseMatrixHandle, CUDPPConfiguration config, size_t n, size_t rows, const void *A, const unsigned int *h_rowIndices, const unsigned int *h_indices) |
Create a CUDPP Sparse Matrix Object. More... | |
CUDPP_DLL CUDPPResult | cudppDestroySparseMatrix (CUDPPHandle sparseMatrixHandle) |
Destroy a CUDPP Sparse Matrix Object. More... | |
CUDPP_DLL CUDPPResult | cudppSparseMatrixVectorMultiply (const CUDPPHandle sparseMatrixHandle, void *d_y, const void *d_x) |
Perform matrix-vector multiply y = A*x for arbitrary sparse matrix A and vector x. More... | |
CUDPP_DLL CUDPPResult | cudppRand (const CUDPPHandle planHandle, void *d_out, size_t numElements) |
Rand puts numElements random 32-bit elements into d_out. More... | |
CUDPP_DLL CUDPPResult | cudppRandSeed (const CUDPPHandle planHandle, unsigned int seed) |
Sets the seed used for rand. More... | |
CUDPP_DLL CUDPPResult | cudppTridiagonal (CUDPPHandle planHandle, void *a, void *b, void *c, void *d, void *x, int systemSize, int numSystems) |
Solves tridiagonal linear systems. More... | |
CUDPP_DLL CUDPPResult | cudppCompress (CUDPPHandle planHandle, unsigned char *d_uncompressed, int *d_bwtIndex, unsigned int *d_histSize, unsigned int *d_hist, unsigned int *d_encodeOffset, unsigned int *d_compressedSize, unsigned int *d_compressed, size_t numElements) |
Compresses data stream. More... | |
CUDPP_DLL CUDPPResult | cudppBurrowsWheelerTransform (CUDPPHandle planHandle, unsigned char *d_in, unsigned char *d_out, int *d_index, size_t numElements) |
Performs the Burrows-Wheeler Transform. More... | |
CUDPP_DLL CUDPPResult | cudppMoveToFrontTransform (CUDPPHandle planHandle, unsigned char *d_in, unsigned char *d_out, size_t numElements) |
Performs the Move-to-Front Transform. More... | |
CUDPP_DLL CUDPPResult | cudppListRank (CUDPPHandle planHandle, void *d_ranked_values, void *d_unranked_values, void *d_next_indices, size_t head, size_t numElements) |
Performs list ranking of linked list node values. More... | |
Main library header file. Defines public interface.
The CUDPP public interface is a C-only interface to enable linking with code written in other languages (e.g. C, C++, and Fortran). While the internals of CUDPP are not limited to C (C++ features are used), the public interface is entirely C (thus it is declared "extern C").
enum CUDPPResult |
CUDPP Result codes returned by CUDPP API functions.
enum CUDPPOption |
Options for configuring CUDPP algorithms.
Enumerator | |
---|---|
CUDPP_OPTION_FORWARD |
Algorithms operate forward: from start to end of input array |
CUDPP_OPTION_BACKWARD |
Algorithms operate backward: from end to start of array |
CUDPP_OPTION_EXCLUSIVE |
Exclusive (for scans) - scan includes all elements up to (but not including) the current element |
CUDPP_OPTION_INCLUSIVE |
Inclusive (for scans) - scan includes all elements up to and including the current element |
CUDPP_OPTION_CTA_LOCAL |
Algorithm performed only on the CTAs (blocks) with no communication between blocks.
|
CUDPP_OPTION_KEYS_ONLY |
No associated value to a key (for global radix sort) |
CUDPP_OPTION_KEY_VALUE_PAIRS |
Each key has an associated value |
enum CUDPPDatatype |
Datatypes supported by CUDPP algorithms.
enum CUDPPOperator |
Operators supported by CUDPP algorithms (currently scan and segmented scan).
These are all binary associative operators.
enum CUDPPAlgorithm |
Algorithms supported by CUDPP. Used to create appropriate plans using cudppPlan.