Contents

• 1. Introduction
  • 1.1. Fortran Interfaces and Wrappers
  • 1.2. Using CUDA Libraries from OpenACC Host Code
  • 1.3. Using CUDA Libraries from OpenACC Device Code
  • 1.4. Using CUDA Libraries from CUDA Fortran Host Code
  • 1.5. Using CUDA Libraries from CUDA Fortran Device Code
  • 1.6. Pointer Modes in cuBLAS and cuSPARSE
  • 1.7. Writing Your Own CUDA Interfaces
  • 1.8. NVIDIA Fortran Compiler Options
• 2. BLAS Runtime APIs
  • 2.1. CUBLAS Definitions and Helper Functions
    • 2.1.1. cublasCreate
    • 2.1.2. cublasDestroy
    • 2.1.3. cublasGetVersion
    • 2.1.4. cublasSetStream
    • 2.1.5. cublasGetStream
    • 2.1.6. cublasGetStatusName
    • 2.1.7. cublasGetStatusString
    • 2.1.8. cublasGetPointerMode
    • 2.1.9. cublasSetPointerMode
    • 2.1.10. cublasGetAtomicsMode
    • 2.1.11. cublasSetAtomicsMode
    • 2.1.12. cublasGetMathMode
    • 2.1.13. cublasSetMathMode
    • 2.1.14. cublasGetSmCountTarget
    • 2.1.15. cublasSetSmCountTarget
    • 2.1.16. cublasGetHandle
    • 2.1.17. cublasSetVector
    • 2.1.18. cublasGetVector
    • 2.1.19. cublasSetMatrix
    • 2.1.20. cublasGetMatrix
    • 2.1.21. cublasSetVectorAsync
    • 2.1.22. cublasGetVectorAsync
    • 2.1.23. cublasSetMatrixAsync
    • 2.1.24. cublasGetMatrixAsync
  • 2.2. Single Precision Functions and Subroutines
    • 2.2.1. isamax
    • 2.2.2. isamin
    • 2.2.3. sasum
    • 2.2.4. saxpy
    • 2.2.5. scopy
    • 2.2.6. sdot
    • 2.2.7. snrm2
    • 2.2.8. srot
    • 2.2.9. srotg
    • 2.2.10. srotm
    • 2.2.11. srotmg
    • 2.2.12. sscal
    • 2.2.13. sswap
    • 2.2.14. sgbmv
    • 2.2.15. sgemv
    • 2.2.16. sger
    • 2.2.17. ssbmv
    • 2.2.18. sspmv
    • 2.2.19. sspr
    • 2.2.20. sspr2
    • 2.2.21. ssymv
    • 2.2.22. ssyr
    • 2.2.23. ssyr2
    • 2.2.24. stbmv
    • 2.2.25. stbsv
    • 2.2.26. stpmv
    • 2.2.27. stpsv
    • 2.2.28. strmv
    • 2.2.29. strsv
    • 2.2.30. sgemm
    • 2.2.31. ssymm
    • 2.2.32. ssyrk
    • 2.2.33. ssyr2k
    • 2.2.34. ssyrkx
    • 2.2.35. strmm
    • 2.2.36. strsm
    • 2.2.37. cublasSgemvBatched
    • 2.2.38. cublasSgemmBatched
    • 2.2.39. cublasSgelsBatched
    • 2.2.40. cublasSgeqrfBatched
    • 2.2.41. cublasSgetrfBatched
    • 2.2.42. cublasSgetriBatched
    • 2.2.43. cublasSgetrsBatched
    • 2.2.44. cublasSmatinvBatched
    • 2.2.45. cublasStrsmBatched
    • 2.2.46. cublasSgemvStridedBatched
    • 2.2.47. cublasSgemmStridedBatched
  • 2.3. Double Precision Functions and Subroutines
    • 2.3.1. idamax
    • 2.3.2. idamin
    • 2.3.3. dasum
    • 2.3.4. daxpy
    • 2.3.5. dcopy
    • 2.3.6. ddot
    • 2.3.7. dnrm2
    • 2.3.8. drot
    • 2.3.9. drotg
    • 2.3.10. drotm
    • 2.3.11. drotmg
    • 2.3.12. dscal
    • 2.3.13. dswap
    • 2.3.14. dgbmv
    • 2.3.15. dgemv
    • 2.3.16. dger
    • 2.3.17. dsbmv
    • 2.3.18. dspmv
    • 2.3.19. dspr
    • 2.3.20. dspr2
    • 2.3.21. dsymv
    • 2.3.22. dsyr
    • 2.3.23. dsyr2
    • 2.3.24. dtbmv
    • 2.3.25. dtbsv
    • 2.3.26. dtpmv
    • 2.3.27. dtpsv
    • 2.3.28. dtrmv
    • 2.3.29. dtrsv
    • 2.3.30. dgemm
    • 2.3.31. dsymm
    • 2.3.32. dsyrk
    • 2.3.33. dsyr2k
    • 2.3.34. dsyrkx
    • 2.3.35. dtrmm
    • 2.3.36. dtrsm
    • 2.3.37. cublasDgemvBatched
    • 2.3.38. cublasDgemmBatched
    • 2.3.39. cublasDgelsBatched
    • 2.3.40. cublasDgeqrfBatched
    • 2.3.41. cublasDgetrfBatched
    • 2.3.42. cublasDgetriBatched
    • 2.3.43. cublasDgetrsBatched
    • 2.3.44. cublasDmatinvBatched
    • 2.3.45. cublasDtrsmBatched
    • 2.3.46. cublasDgemvStridedBatched
    • 2.3.47. cublasDgemmStridedBatched
  • 2.4. Single Precision Complex Functions and Subroutines
    • 2.4.1. icamax
    • 2.4.2. icamin
    • 2.4.3. scasum
    • 2.4.4. caxpy
    • 2.4.5. ccopy
    • 2.4.6. cdotc
    • 2.4.7. cdotu
    • 2.4.8. scnrm2
    • 2.4.9. crot
    • 2.4.10. csrot
    • 2.4.11. crotg
    • 2.4.12. cscal
    • 2.4.13. csscal
    • 2.4.14. cswap
    • 2.4.15. cgbmv
    • 2.4.16. cgemv
    • 2.4.17. cgerc
    • 2.4.18. cgeru
    • 2.4.19. csymv
    • 2.4.20. csyr
    • 2.4.21. csyr2
    • 2.4.22. ctbmv
    • 2.4.23. ctbsv
    • 2.4.24. ctpmv
    • 2.4.25. ctpsv
    • 2.4.26. ctrmv
    • 2.4.27. ctrsv
    • 2.4.28. chbmv
    • 2.4.29. chemv
    • 2.4.30. chpmv
    • 2.4.31. cher
    • 2.4.32. cher2
    • 2.4.33. chpr
    • 2.4.34. chpr2
    • 2.4.35. cgemm
    • 2.4.36. csymm
    • 2.4.37. csyrk
    • 2.4.38. csyr2k
    • 2.4.39. csyrkx
    • 2.4.40. ctrmm
    • 2.4.41. ctrsm
    • 2.4.42. chemm
    • 2.4.43. cherk
    • 2.4.44. cher2k
    • 2.4.45. cherkx
    • 2.4.46. cublasCgemvBatched
    • 2.4.47. cublasCgemmBatched
    • 2.4.48. cublasCgelsBatched
    • 2.4.49. cublasCgeqrfBatched
    • 2.4.50. cublasCgetrfBatched
    • 2.4.51. cublasCgetriBatched
    • 2.4.52. cublasCgetrsBatched
    • 2.4.53. cublasCmatinvBatched
    • 2.4.54. cublasCtrsmBatched
    • 2.4.55. cublasCgemvStridedBatched
    • 2.4.56. cublasCgemmStridedBatched
  • 2.5. Double Precision Complex Functions and Subroutines
    • 2.5.1. izamax
    • 2.5.2. izamin
    • 2.5.3. dzasum
    • 2.5.4. zaxpy
    • 2.5.5. zcopy
    • 2.5.6. zdotc
    • 2.5.7. zdotu
    • 2.5.8. dznrm2
    • 2.5.9. zrot
    • 2.5.10. zsrot
    • 2.5.11. zrotg
    • 2.5.12. zscal
    • 2.5.13. zdscal
    • 2.5.14. zswap
    • 2.5.15. zgbmv
    • 2.5.16. zgemv
    • 2.5.17. zgerc
    • 2.5.18. zgeru
    • 2.5.19. zsymv
    • 2.5.20. zsyr
    • 2.5.21. zsyr2
    • 2.5.22. ztbmv
    • 2.5.23. ztbsv
    • 2.5.24. ztpmv
    • 2.5.25. ztpsv
    • 2.5.26. ztrmv
    • 2.5.27. ztrsv
    • 2.5.28. zhbmv
    • 2.5.29. zhemv
    • 2.5.30. zhpmv
    • 2.5.31. zher
    • 2.5.32. zher2
    • 2.5.33. zhpr
    • 2.5.34. zhpr2
    • 2.5.35. zgemm
    • 2.5.36. zsymm
    • 2.5.37. zsyrk
    • 2.5.38. zsyr2k
    • 2.5.39. zsyrkx
    • 2.5.40. ztrmm
    • 2.5.41. ztrsm
    • 2.5.42. zhemm
    • 2.5.43. zherk
    • 2.5.44. zher2k
    • 2.5.45. zherkx
    • 2.5.46. cublasZgemvBatched
    • 2.5.47. cublasZgemmBatched
    • 2.5.48. cublasZgelsBatched
    • 2.5.49. cublasZgeqrfBatched
    • 2.5.50. cublasZgetrfBatched
    • 2.5.51. cublasZgetriBatched
    • 2.5.52. cublasZgetrsBatched
    • 2.5.53. cublasZmatinvBatched
    • 2.5.54. cublasZtrsmBatched
    • 2.5.55. cublasZgemvStridedBatched
    • 2.5.56. cublasZgemmStridedBatched
  • 2.6. Half Precision Functions and Extension Functions
    • 2.6.1. cublasHgemvBatched
    • 2.6.2. cublasHgemvStridedBatched
    • 2.6.3. cublasHgemm
    • 2.6.4. cublasHgemmBatched
    • 2.6.5. cublasHgemmStridedBatched
    • 2.6.6. cublasIamaxEx
    • 2.6.7. cublasIaminEx
    • 2.6.8. cublasAsumEx
    • 2.6.9. cublasAxpyEx
    • 2.6.10. cublasCopyEx
    • 2.6.11. cublasDotEx
    • 2.6.12. cublasDotcEx
    • 2.6.13. cublasNrm2Ex
    • 2.6.14. cublasRotEx
    • 2.6.15. cublasRotgEx
    • 2.6.16. cublasRotmEx
    • 2.6.17. cublasRotmgEx
    • 2.6.18. cublasScalEx
    • 2.6.19. cublasSwapEx
    • 2.6.20. cublasGemmEx
    • 2.6.21. cublasGemmBatchedEx
    • 2.6.22. cublasGemmStridedBatchedEx
  • 2.7. CUBLAS V2 Module Functions
    • 2.7.1. Single Precision Functions and Subroutines
      • 2.7.1.1. isamax
      • 2.7.1.2. isamin
      • 2.7.1.3. sasum
      • 2.7.1.4. saxpy
      • 2.7.1.5. scopy
      • 2.7.1.6. sdot
      • 2.7.1.7. snrm2
      • 2.7.1.8. srot
      • 2.7.1.9. srotg
      • 2.7.1.10. srotm
      • 2.7.1.11. srotmg
      • 2.7.1.12. sscal
      • 2.7.1.13. sswap
      • 2.7.1.14. sgbmv
      • 2.7.1.15. sgemv
      • 2.7.1.16. sger
      • 2.7.1.17. ssbmv
      • 2.7.1.18. sspmv
      • 2.7.1.19. sspr
      • 2.7.1.20. sspr2
      • 2.7.1.21. ssymv
      • 2.7.1.22. ssyr
      • 2.7.1.23. ssyr2
      • 2.7.1.24. stbmv
      • 2.7.1.25. stbsv
      • 2.7.1.26. stpmv
      • 2.7.1.27. stpsv
      • 2.7.1.28. strmv
      • 2.7.1.29. strsv
      • 2.7.1.30. sgemm
      • 2.7.1.31. ssymm
      • 2.7.1.32. ssyrk
      • 2.7.1.33. ssyr2k
      • 2.7.1.34. ssyrkx
      • 2.7.1.35. strmm
      • 2.7.1.36. strsm
    • 2.7.2. Double Precision Functions and Subroutines
      • 2.7.2.1. idamax
      • 2.7.2.2. idamin
      • 2.7.2.3. dasum
      • 2.7.2.4. daxpy
      • 2.7.2.5. dcopy
      • 2.7.2.6. ddot
      • 2.7.2.7. dnrm2
      • 2.7.2.8. drot
      • 2.7.2.9. drotg
      • 2.7.2.10. drotm
      • 2.7.2.11. drotmg
      • 2.7.2.12. dscal
      • 2.7.2.13. dswap
      • 2.7.2.14. dgbmv
      • 2.7.2.15. dgemv
      • 2.7.2.16. dger
      • 2.7.2.17. dsbmv
      • 2.7.2.18. dspmv
      • 2.7.2.19. dspr
      • 2.7.2.20. dspr2
      • 2.7.2.21. dsymv
      • 2.7.2.22. dsyr
      • 2.7.2.23. dsyr2
      • 2.7.2.24. dtbmv
      • 2.7.2.25. dtbsv
      • 2.7.2.26. dtpmv
      • 2.7.2.27. dtpsv
      • 2.7.2.28. dtrmv
      • 2.7.2.29. dtrsv
      • 2.7.2.30. dgemm
      • 2.7.2.31. dsymm
      • 2.7.2.32. dsyrk
      • 2.7.2.33. dsyr2k
      • 2.7.2.34. dsyrkx
      • 2.7.2.35. dtrmm
      • 2.7.2.36. dtrsm
    • 2.7.3. Single Precision Complex Functions and Subroutines
      • 2.7.3.1. icamax
      • 2.7.3.2. icamin
      • 2.7.3.3. scasum
      • 2.7.3.4. caxpy
      • 2.7.3.5. ccopy
      • 2.7.3.6. cdotc
      • 2.7.3.7. cdotu
      • 2.7.3.8. scnrm2
      • 2.7.3.9. crot
      • 2.7.3.10. csrot
      • 2.7.3.11. crotg
      • 2.7.3.12. cscal
      • 2.7.3.13. csscal
      • 2.7.3.14. cswap
      • 2.7.3.15. cgbmv
      • 2.7.3.16. cgemv
      • 2.7.3.17. cgerc
      • 2.7.3.18. cgeru
      • 2.7.3.19. csymv
      • 2.7.3.20. csyr
      • 2.7.3.21. csyr2
      • 2.7.3.22. ctbmv
      • 2.7.3.23. ctbsv
      • 2.7.3.24. ctpmv
      • 2.7.3.25. ctpsv
      • 2.7.3.26. ctrmv
      • 2.7.3.27. ctrsv
      • 2.7.3.28. chbmv
      • 2.7.3.29. chemv
      • 2.7.3.30. chpmv
      • 2.7.3.31. cher
      • 2.7.3.32. cher2
      • 2.7.3.33. chpr
      • 2.7.3.34. chpr2
      • 2.7.3.35. cgemm
      • 2.7.3.36. csymm
      • 2.7.3.37. csyrk
      • 2.7.3.38. csyr2k
      • 2.7.3.39. csyrkx
      • 2.7.3.40. ctrmm
      • 2.7.3.41. ctrsm
      • 2.7.3.42. chemm
      • 2.7.3.43. cherk
      • 2.7.3.44. cher2k
      • 2.7.3.45. cherkx
    • 2.7.4. Double Precision Complex Functions and Subroutines
      • 2.7.4.1. izamax
      • 2.7.4.2. izamin
      • 2.7.4.3. dzasum
      • 2.7.4.4. zaxpy
      • 2.7.4.5. zcopy
      • 2.7.4.6. zdotc
      • 2.7.4.7. zdotu
      • 2.7.4.8. dznrm2
      • 2.7.4.9. zrot
      • 2.7.4.10. zsrot
      • 2.7.4.11. zrotg
      • 2.7.4.12. zscal
      • 2.7.4.13. zdscal
      • 2.7.4.14. zswap
      • 2.7.4.15. zgbmv
      • 2.7.4.16. zgemv
      • 2.7.4.17. zgerc
      • 2.7.4.18. zgeru
      • 2.7.4.19. zsymv
      • 2.7.4.20. zsyr
      • 2.7.4.21. zsyr2
      • 2.7.4.22. ztbmv
      • 2.7.4.23. ztbsv
      • 2.7.4.24. ztpmv
      • 2.7.4.25. ztpsv
      • 2.7.4.26. ztrmv
      • 2.7.4.27. ztrsv
      • 2.7.4.28. zhbmv
      • 2.7.4.29. zhemv
      • 2.7.4.30. zhpmv
      • 2.7.4.31. zher
      • 2.7.4.32. zher2
      • 2.7.4.33. zhpr
      • 2.7.4.34. zhpr2
      • 2.7.4.35. zgemm
      • 2.7.4.36. zsymm
      • 2.7.4.37. zsyrk
      • 2.7.4.38. zsyr2k
      • 2.7.4.39. zsyrkx
      • 2.7.4.40. ztrmm
      • 2.7.4.41. ztrsm
      • 2.7.4.42. zhemm
      • 2.7.4.43. zherk
      • 2.7.4.44. zher2k
      • 2.7.4.45. zherkx
  • 2.8. CUBLAS XT Module Functions
    • 2.8.1. cublasXtCreate
    • 2.8.2. cublasXtDestroy
    • 2.8.3. cublasXtDeviceSelect
    • 2.8.4. cublasXtSetBlockDim
    • 2.8.5. cublasXtGetBlockDim
    • 2.8.6. cublasXtSetCpuRoutine
    • 2.8.7. cublasXtSetCpuRatio
    • 2.8.8. cublasXtSetPinningMemMode
    • 2.8.9. cublasXtGetPinningMemMode
    • 2.8.10. cublasXtSgemm
    • 2.8.11. cublasXtSsymm
    • 2.8.12. cublasXtSsyrk
    • 2.8.13. cublasXtSsyr2k
    • 2.8.14. cublasXtSsyrkx
    • 2.8.15. cublasXtStrmm
    • 2.8.16. cublasXtStrsm
    • 2.8.17. cublasXtSspmm
    • 2.8.18. cublasXtCgemm
    • 2.8.19. cublasXtChemm
    • 2.8.20. cublasXtCherk
    • 2.8.21. cublasXtCher2k
    • 2.8.22. cublasXtCherkx
    • 2.8.23. cublasXtCsymm
    • 2.8.24. cublasXtCsyrk
    • 2.8.25. cublasXtCsyr2k
    • 2.8.26. cublasXtCsyrkx
    • 2.8.27. cublasXtCtrmm
    • 2.8.28. cublasXtCtrsm
    • 2.8.29. cublasXtCspmm
    • 2.8.30. cublasXtDgemm
    • 2.8.31. cublasXtDsymm
    • 2.8.32. cublasXtDsyrk
    • 2.8.33. cublasXtDsyr2k
    • 2.8.34. cublasXtDsyrkx
    • 2.8.35. cublasXtDtrmm
    • 2.8.36. cublasXtDtrsm
    • 2.8.37. cublasXtDspmm
    • 2.8.38. cublasXtZgemm
    • 2.8.39. cublasXtZhemm
    • 2.8.40. cublasXtZherk
    • 2.8.41. cublasXtZher2k
    • 2.8.42. cublasXtZherkx
    • 2.8.43. cublasXtZsymm
    • 2.8.44. cublasXtZsyrk
    • 2.8.45. cublasXtZsyr2k
    • 2.8.46. cublasXtZsyrkx
    • 2.8.47. cublasXtZtrmm
    • 2.8.48. cublasXtZtrsm
    • 2.8.49. cublasXtZspmm
  • 2.9. CUBLAS MP Module Functions
    • 2.9.1. cublasMpCreate
    • 2.9.2. cublasMpDestroy
    • 2.9.3. cublasMpStreamSet
    • 2.9.4. cublasMpStreamGet
    • 2.9.5. cublasMpGetVersion
    • 2.9.6. cublasMpGridCreate
    • 2.9.7. cublasMpGridDestroy
    • 2.9.8. cublasMpMatrixDescriptorCreate
    • 2.9.9. cublasMpMatrixDescriptorDestroy
    • 2.9.10. cublasMpMatrixDescriptorInit
    • 2.9.11. cublasMpNumroc
    • 2.9.12. cublasMpMatmulDescriptorCreate
    • 2.9.13. cublasMpMatmulDescriptorDestroy
    • 2.9.14. cublasMpMatmulDescriptorAttributeSet
    • 2.9.15. cublasMpMatmulDescriptorAttributeGet
    • 2.9.16. cublasMpGemr2D_bufferSize
    • 2.9.17. cublasMpGemr2D
    • 2.9.18. cublasMpTrmr2D_bufferSize
    • 2.9.19. cublasMpTrmr2D
    • 2.9.20. cublasMpGemm_bufferSize
    • 2.9.21. cublasMpGemm
    • 2.9.22. cublasMpMatmul_bufferSize
    • 2.9.23. cublasMpMatmul
    • 2.9.24. cublasMpSyrk
    • 2.9.25. cublasMpSyrk
    • 2.9.26. cublasMpTrsm_bufferSize
    • 2.9.27. cublasMpTrsm
    • 2.9.28. cublasMpGeadd_bufferSize
    • 2.9.29. cublasMpGeadd
    • 2.9.30. cublasMpTradd_bufferSize
    • 2.9.31. cublasMpTradd
    • 2.9.32. cublasMpLoggerSetFile
    • 2.9.33. cublasMpLoggerOpenFile
    • 2.9.34. cublasMpLoggerSetLevel
    • 2.9.35. cublasMpLoggerSetMask
    • 2.9.36. cublasMpLoggerForceDisable
• 3. FFT Runtime Library APIs
  • 3.1. CUFFT Definitions and Helper Functions
    • 3.1.1. cufftSetCompatibilityMode
    • 3.1.2. cufftSetStream
    • 3.1.3. cufftGetVersion
    • 3.1.4. cufftSetAutoAllocation
    • 3.1.5. cufftSetWorkArea
    • 3.1.6. cufftDestroy
  • 3.2. CUFFT Plans and Estimated Size Functions
    • 3.2.1. cufftPlan1d
    • 3.2.2. cufftPlan2d
    • 3.2.3. cufftPlan3d
    • 3.2.4. cufftPlanMany
    • 3.2.5. cufftCreate
    • 3.2.6. cufftMakePlan1d
    • 3.2.7. cufftMakePlan2d
    • 3.2.8. cufftMakePlan3d
    • 3.2.9. cufftMakePlanMany
    • 3.2.10. cufftEstimate1d
    • 3.2.11. cufftEstimate2d
    • 3.2.12. cufftEstimate3d
    • 3.2.13. cufftEstimateMany
    • 3.2.14. cufftGetSize1d
    • 3.2.15. cufftGetSize2d
    • 3.2.16. cufftGetSize3d
    • 3.2.17. cufftGetSizeMany
    • 3.2.18. cufftGetSize
  • 3.3. CUFFT Execution Functions
    • 3.3.1. cufftExecC2C
    • 3.3.2. cufftExecR2C
    • 3.3.3. cufftExecC2R
    • 3.3.4. cufftExecZ2Z
    • 3.3.5. cufftExecD2Z
    • 3.3.6. cufftExecZ2D
  • 3.4. CUFFTXT Definitions and Helper Functions
    • 3.4.1. cufftXtSetGPUs
    • 3.4.2. cufftXtMalloc
    • 3.4.3. cufftXtFree
    • 3.4.4. cufftXtMemcpy
  • 3.5. CUFFTXT Plans and Work Area Functions
    • 3.5.1. cufftXtMakePlanMany
    • 3.5.2. cufftXtQueryPlan
    • 3.5.3. cufftXtSetWorkAreaPolicy
    • 3.5.4. cufftXtGetSizeMany
    • 3.5.5. cufftXtSetWorkArea
    • 3.5.6. cufftXtSetDistribution
  • 3.6. CUFFTXT Execution Functions
    • 3.6.1. cufftXtExec
    • 3.6.2. cufftXtExecDescriptor
    • 3.6.3. cufftXtExecDescriptorC2C
    • 3.6.4. cufftXtExecDescriptorZ2Z
    • 3.6.5. cufftXtExecDescriptorR2C
    • 3.6.6. cufftXtExecDescriptorD2Z
    • 3.6.7. cufftXtExecDescriptorC2R
    • 3.6.8. cufftXtExecDescriptorZ2D
  • 3.7. CUFFTMP Functions
    • 3.7.1. cufftMpNvshmemMalloc
    • 3.7.2. cufftMpNvshmemFree
    • 3.7.3. cufftMpAttachComm
    • 3.7.4. cufftMpCreateReshape
    • 3.7.5. cufftMpAttachReshapeComm
    • 3.7.6. cufftMpGetReshapeSize
    • 3.7.7. cufftMpMakeReshape
    • 3.7.8. cufftMpExecReshapeAsync
    • 3.7.9. cufftMpDestroyReshape
• 4. Random Number Runtime Library APIs
  • 4.1. CURAND Definitions and Helper Functions
    • 4.1.1. curandCreateGenerator
    • 4.1.2. curandCreateGeneratorHost
    • 4.1.3. curandDestroyGenerator
    • 4.1.4. curandGetVersion
    • 4.1.5. curandSetStream
    • 4.1.6. curandSetPseudoRandomGeneratorSeed
    • 4.1.7. curandSetGeneratorOffset
    • 4.1.8. curandSetGeneratorOrdering
    • 4.1.9. curandSetQuasiRandomGeneratorDimensions
  • 4.2. CURAND Generator Functions
    • 4.2.1. curandGenerate
    • 4.2.2. curandGenerateLongLong
    • 4.2.3. curandGenerateUniform
    • 4.2.4. curandGenerateUniformDouble
    • 4.2.5. curandGenerateNormal
    • 4.2.6. curandGenerateNormalDouble
    • 4.2.7. curandGeneratePoisson
    • 4.2.8. curandGenerateSeeds
    • 4.2.9. curandGenerateLogNormal
    • 4.2.10. curandGenerateLogNormalDouble
  • 4.3. CURAND Device Definitions and Functions
    • 4.3.1. curand_Init
      • 4.3.1.1. curandInitXORWOW
      • 4.3.1.2. curandInitMRG32k3a
      • 4.3.1.3. curandInitPhilox4_32_10
      • 4.3.1.4. curandInitSobol32
      • 4.3.1.5. curandInitScrambledSobol32
      • 4.3.1.6. curandInitSobol64
      • 4.3.1.7. curandInitScrambledSobol64
    • 4.3.2. curand
      • 4.3.2.1. curandGetXORWOW
      • 4.3.2.2. curandGetMRG32k3a
      • 4.3.2.3. curandGetPhilox4_32_10
      • 4.3.2.4. curandGetSobol32
      • 4.3.2.5. curandGetScrambledSobol32
      • 4.3.2.6. curandGetSobol64
      • 4.3.2.7. curandGetScrambledSobol64
    • 4.3.3. Curand_Normal
      • 4.3.3.1. curandNormalXORWOW
      • 4.3.3.2. curandNormalMRG32k3a
      • 4.3.3.3. curandNormalPhilox4_32_10
      • 4.3.3.4. curandNormalSobol32
      • 4.3.3.5. curandNormalScrambledSobol32
      • 4.3.3.6. curandNormalSobol64
      • 4.3.3.7. curandNormalScrambledSobol64
    • 4.3.4. Curand_Normal_Double
      • 4.3.4.1. curandNormalDoubleXORWOW
      • 4.3.4.2. curandNormalDoubleMRG32k3a
      • 4.3.4.3. curandNormalDoublePhilox4_32_10
      • 4.3.4.4. curandNormalDoubleSobol32
      • 4.3.4.5. curandNormalDoubleScrambledSobol32
      • 4.3.4.6. curandNormalDoubleSobol64
      • 4.3.4.7. curandNormalDoubleScrambledSobol64
    • 4.3.5. Curand_Log_Normal
      • 4.3.5.1. curandLogNormalXORWOW
      • 4.3.5.2. curandLogNormalMRG32k3a
      • 4.3.5.3. curandLogNormalPhilox4_32_10
      • 4.3.5.4. curandLogNormalSobol32
      • 4.3.5.5. curandLogNormalScrambledSobol32
      • 4.3.5.6. curandLogNormalSobol64
      • 4.3.5.7. curandLogNormalScrambledSobol64
    • 4.3.6. Curand_Log_Normal_Double
      • 4.3.6.1. curandLogNormalDoubleXORWOW
      • 4.3.6.2. curandLogNormalDoubleMRG32k3a
      • 4.3.6.3. curandLogNormalDoublePhilox4_32_10
      • 4.3.6.4. curandLogNormalDoubleSobol32
      • 4.3.6.5. curandLogNormalDoubleScrambledSobol32
      • 4.3.6.6. curandLogNormalDoubleSobol64
      • 4.3.6.7. curandLogNormalDoubleScrambledSobol64
    • 4.3.7. Curand_Uniform
      • 4.3.7.1. curandUniformXORWOW
      • 4.3.7.2. curandUniformMRG32k3a
      • 4.3.7.3. curandUniformPhilox4_32_10
      • 4.3.7.4. curandUniformSobol32
      • 4.3.7.5. curandUniformScrambledSobol32
      • 4.3.7.6. curandUniformSobol64
      • 4.3.7.7. curandUniformScrambledSobol64
    • 4.3.8. Curand_Uniform_Double
      • 4.3.8.1. curandUniformDoubleXORWOW
      • 4.3.8.2. curandUniformDoubleMRG32k3a
      • 4.3.8.3. curandUniformDoublePhilox4_32_10
      • 4.3.8.4. curandUniformDoubleSobol32
      • 4.3.8.5. curandUniformDoubleScrambledSobol32
      • 4.3.8.6. curandUniformDoubleSobol64
      • 4.3.8.7. curandUniformDoubleScrambledSobol64
• 5. SPARSE Matrix Runtime Library APIs
  • 5.1. CUSPARSE Definitions and Helper Functions
    • 5.1.1. cusparseCreate
    • 5.1.2. cusparseDestroy
    • 5.1.3. cusparseGetErrorName
    • 5.1.4. cusparseGetErrorString
    • 5.1.5. cusparseGetVersion
    • 5.1.6. cusparseSetStream
    • 5.1.7. cusparseGetStream
    • 5.1.8. cusparseGetPointerMode
    • 5.1.9. cusparseSetPointerMode
    • 5.1.10. cusparseCreateMatDescr
    • 5.1.11. cusparseDestroyMatDescr
    • 5.1.12. cusparseSetMatType
    • 5.1.13. cusparseGetMatType
    • 5.1.14. cusparseSetMatFillMode
    • 5.1.15. cusparseGetMatFillMode
    • 5.1.16. cusparseSetMatDiagType
    • 5.1.17. cusparseGetMatDiagType
    • 5.1.18. cusparseSetMatIndexBase
    • 5.1.19. cusparseGetMatIndexBase
    • 5.1.20. cusparseCreateSolveAnalysisInfo
    • 5.1.21. cusparseDestroySolveAnalysisInfo
    • 5.1.22. cusparseGetLevelInfo
    • 5.1.23. cusparseCreateHybMat
    • 5.1.24. cusparseDestroyHybMat
    • 5.1.25. cusparseCreateCsrsv2Info
    • 5.1.26. cusparseDestroyCsrsv2Info
    • 5.1.27. cusparseCreateCsric02Info
    • 5.1.28. cusparseDestroyCsric02Info
    • 5.1.29. cusparseCreateCsrilu02Info
    • 5.1.30. cusparseDestroyCsrilu02Info
    • 5.1.31. cusparseCreateBsrsv2Info
    • 5.1.32. cusparseDestroyBsrsv2Info
    • 5.1.33. cusparseCreateBsric02Info
    • 5.1.34. cusparseDestroyBsric02Info
    • 5.1.35. cusparseCreateBsrilu02Info
    • 5.1.36. cusparseDestroyBsrilu02Info
    • 5.1.37. cusparseCreateBsrsm2Info
    • 5.1.38. cusparseDestroyBsrsm2Info
    • 5.1.39. cusparseCreateCsrgemm2Info
    • 5.1.40. cusparseDestroyCsrgemm2Info
    • 5.1.41. cusparseCreateColorInfo
    • 5.1.42. cusparseDestroyColorInfo
    • 5.1.43. cusparseCreateCsru2csrInfo
    • 5.1.44. cusparseDestroyCsru2csrInfo
  • 5.2. CUSPARSE Level 1 Functions
    • 5.2.1. cusparseSaxpyi
    • 5.2.2. cusparseDaxpyi
    • 5.2.3. cusparseCaxpyi
    • 5.2.4. cusparseZaxpyi
    • 5.2.5. cusparseSdoti
    • 5.2.6. cusparseDdoti
    • 5.2.7. cusparseCdoti
    • 5.2.8. cusparseZdoti
    • 5.2.9. cusparseCdotci
    • 5.2.10. cusparseZdotci
    • 5.2.11. cusparseSgthr
    • 5.2.12. cusparseDgthr
    • 5.2.13. cusparseCgthr
    • 5.2.14. cusparseZgthr
    • 5.2.15. cusparseSgthrz
    • 5.2.16. cusparseDgthrz
    • 5.2.17. cusparseCgthrz
    • 5.2.18. cusparseZgthrz
    • 5.2.19. cusparseSsctr
    • 5.2.20. cusparseDsctr
    • 5.2.21. cusparseCsctr
    • 5.2.22. cusparseZsctr
    • 5.2.23. cusparseSroti
    • 5.2.24. cusparseDroti
  • 5.3. CUSPARSE Level 2 Functions
    • 5.3.1. cusparseSbsrmv
    • 5.3.2. cusparseDbsrmv
    • 5.3.3. cusparseCbsrmv
    • 5.3.4. cusparseZbsrmv
    • 5.3.5. cusparseSbsrxmv
    • 5.3.6. cusparseDbsrxmv
    • 5.3.7. cusparseCbsrxmv
    • 5.3.8. cusparseZbsrxmv
    • 5.3.9. cusparseScsrmv
    • 5.3.10. cusparseDcsrmv
    • 5.3.11. cusparseCcsrmv
    • 5.3.12. cusparseZcsrmv
    • 5.3.13. cusparseScsrsv_analysis
    • 5.3.14. cusparseDcsrsv_analysis
    • 5.3.15. cusparseCcsrsv_analysis
    • 5.3.16. cusparseZcsrsv_analysis
    • 5.3.17. cusparseScsrsv_solve
    • 5.3.18. cusparseDcsrsv_solve
    • 5.3.19. cusparseCcsrsv_solve
    • 5.3.20. cusparseZcsrsv_solve
    • 5.3.21. cusparseSgemvi_bufferSize
    • 5.3.22. cusparseDgemvi_bufferSize
    • 5.3.23. cusparseCgemvi_bufferSize
    • 5.3.24. cusparseZgemvi_bufferSize
    • 5.3.25. cusparseSgemvi
    • 5.3.26. cusparseDgemvi
    • 5.3.27. cusparseCgemvi
    • 5.3.28. cusparseZgemvi
    • 5.3.29. cusparseShybmv
    • 5.3.30. cusparseDhybmv
    • 5.3.31. cusparseChybmv
    • 5.3.32. cusparseZhybmv
    • 5.3.33. cusparseShybsv_analysis
    • 5.3.34. cusparseDhybsv_analysis
    • 5.3.35. cusparseChybsv_analysis
    • 5.3.36. cusparseZhybsv_analysis
    • 5.3.37. cusparseShybsv_solve
    • 5.3.38. cusparseDhybsv_solve
    • 5.3.39. cusparseChybsv_solve
    • 5.3.40. cusparseZhybsv_solve
    • 5.3.41. cusparseSbsrsv2_bufferSize
    • 5.3.42. cusparseDbsrsv2_bufferSize
    • 5.3.43. cusparseCbsrsv2_bufferSize
    • 5.3.44. cusparseZbsrsv2_bufferSize
    • 5.3.45. cusparseSbsrsv2_analysis
    • 5.3.46. cusparseDbsrsv2_analysis
    • 5.3.47. cusparseCbsrsv2_analysis
    • 5.3.48. cusparseZbsrsv2_analysis
    • 5.3.49. cusparseSbsrsv2_solve
    • 5.3.50. cusparseDbsrsv2_solve
    • 5.3.51. cusparseCbsrsv2_solve
    • 5.3.52. cusparseZbsrsv2_solve
    • 5.3.53. cusparseXbsrsv2_zeroPivot
    • 5.3.54. cusparseScsrsv2_bufferSize
    • 5.3.55. cusparseDcsrsv2_bufferSize
    • 5.3.56. cusparseCcsrsv2_bufferSize
    • 5.3.57. cusparseZcsrsv2_bufferSize
    • 5.3.58. cusparseScsrsv2_analysis
    • 5.3.59. cusparseDcsrsv2_analysis
    • 5.3.60. cusparseCcsrsv2_analysis
    • 5.3.61. cusparseZcsrsv2_analysis
    • 5.3.62. cusparseScsrsv2_solve
    • 5.3.63. cusparseDcsrsv2_solve
    • 5.3.64. cusparseCcsrsv2_solve
    • 5.3.65. cusparseZcsrsv2_solve
    • 5.3.66. cusparseXcsrsv2_zeroPivot
  • 5.4. CUSPARSE Level 3 Functions
    • 5.4.1. cusparseScsrmm
    • 5.4.2. cusparseDcsrmm
    • 5.4.3. cusparseCcsrmm
    • 5.4.4. cusparseZcsrmm
    • 5.4.5. cusparseScsrmm2
    • 5.4.6. cusparseDcsrmm2
    • 5.4.7. cusparseCcsrmm2
    • 5.4.8. cusparseZcsrmm2
    • 5.4.9. cusparseScsrsm_analysis
    • 5.4.10. cusparseDcsrsm_analysis
    • 5.4.11. cusparseCcsrsm_analysis
    • 5.4.12. cusparseZcsrsm_analysis
    • 5.4.13. cusparseScsrsm_solve
    • 5.4.14. cusparseDcsrsm_solve
    • 5.4.15. cusparseCcsrsm_solve
    • 5.4.16. cusparseZcsrsm_solve
    • 5.4.17. cusparseScsrsm2_bufferSizeExt
    • 5.4.18. cusparseDcsrsm2_bufferSizeExt
    • 5.4.19. cusparseCcsrsm2_bufferSizeExt
    • 5.4.20. cusparseZcsrsm2_bufferSizeExt
    • 5.4.21. cusparseScsrsm2_analysis
    • 5.4.22. cusparseDcsrsm2_analysis
    • 5.4.23. cusparseCcsrsm2_analysis
    • 5.4.24. cusparseZcsrsm2_analysis
    • 5.4.25. cusparseScsrsm2_solve
    • 5.4.26. cusparseDcsrsm2_solve
    • 5.4.27. cusparseCcsrsm2_solve
    • 5.4.28. cusparseZcsrsm2_solve
    • 5.4.29. cusparseXcsrsm2_zeroPivot
    • 5.4.30. cusparseSbsrmm
    • 5.4.31. cusparseDbsrmm
    • 5.4.32. cusparseCbsrmm
    • 5.4.33. cusparseZbsrmm
    • 5.4.34. cusparseSbsrsm2_bufferSize
    • 5.4.35. cusparseDbsrsm2_bufferSize
    • 5.4.36. cusparseCbsrsm2_bufferSize
    • 5.4.37. cusparseZbsrsm2_bufferSize
    • 5.4.38. cusparseSbsrsm2_analysis
    • 5.4.39. cusparseDbsrsm2_analysis
    • 5.4.40. cusparseCbsrsm2_analysis
    • 5.4.41. cusparseZbsrsm2_analysis
    • 5.4.42. cusparseSbsrsm2_solve
    • 5.4.43. cusparseDbsrsm2_solve
    • 5.4.44. cusparseCbsrsm2_solve
    • 5.4.45. cusparseZbsrsm2_solve
    • 5.4.46. cusparseXbsrsm2_zeroPivot
    • 5.4.47. cusparseSgemmi
    • 5.4.48. cusparseDgemmi
    • 5.4.49. cusparseCgemmi
    • 5.4.50. cusparseZgemmi
  • 5.5. CUSPARSE Extra Functions
    • 5.5.1. cusparseXcsrgeamNnz
    • 5.5.2. cusparseScsrgeam
    • 5.5.3. cusparseDcsrgeam
    • 5.5.4. cusparseCcsrgeam
    • 5.5.5. cusparseZcsrgeam
    • 5.5.6. cusparseScsrgeam2_bufferSizeExt
    • 5.5.7. cusparseDcsrgeam2_bufferSizeExt
    • 5.5.8. cusparseCcsrgeam2_bufferSizeExt
    • 5.5.9. cusparseZcsrgeam2_bufferSizeExt
    • 5.5.10. cusparseXcsrgeam2Nnz
    • 5.5.11. cusparseScsrgeam2
    • 5.5.12. cusparseDcsrgeam2
    • 5.5.13. cusparseCcsrgeam2
    • 5.5.14. cusparseZcsrgeam2
    • 5.5.15. cusparseXcsrgemmNnz
    • 5.5.16. cusparseScsrgemm
    • 5.5.17. cusparseDcsrgemm
    • 5.5.18. cusparseCcsrgemm
    • 5.5.19. cusparseZcsrgemm
    • 5.5.20. cusparseScsrgemm2_bufferSizeExt
    • 5.5.21. cusparseDcsrgemm2_bufferSizeExt
    • 5.5.22. cusparseCcsrgemm2_bufferSizeExt
    • 5.5.23. cusparseZcsrgemm2_bufferSizeExt
    • 5.5.24. cusparseXcsrgemm2Nnz
    • 5.5.25. cusparseScsrgemm2
    • 5.5.26. cusparseDcsrgemm2
    • 5.5.27. cusparseCcsrgemm2
    • 5.5.28. cusparseZcsrgemm2
  • 5.6. CUSPARSE Preconditioning Functions
    • 5.6.1. cusparseScsric0
    • 5.6.2. cusparseDcsric0
    • 5.6.3. cusparseCcsric0
    • 5.6.4. cusparseZcsric0
    • 5.6.5. cusparseScsrilu0
    • 5.6.6. cusparseDcsrilu0
    • 5.6.7. cusparseCcsrilu0
    • 5.6.8. cusparseZcsrilu0
    • 5.6.9. cusparseSgtsv
    • 5.6.10. cusparseDgtsv
    • 5.6.11. cusparseCgtsv
    • 5.6.12. cusparseZgtsv
    • 5.6.13. cusparseSgtsv2_buffersize
    • 5.6.14. cusparseDgtsv2_buffersize
    • 5.6.15. cusparseCgtsv2_buffersize
    • 5.6.16. cusparseZgtsv2_buffersize
    • 5.6.17. cusparseSgtsv2
    • 5.6.18. cusparseDgtsv2
    • 5.6.19. cusparseCgtsv2
    • 5.6.20. cusparseZgtsv2
    • 5.6.21. cusparseSgtsv2_nopivot_buffersize
    • 5.6.22. cusparseDgtsv2_nopivot_buffersize
    • 5.6.23. cusparseCgtsv2_nopivot_buffersize
    • 5.6.24. cusparseZgtsv2_nopivot_buffersize
    • 5.6.25. cusparseSgtsv2_nopivot
    • 5.6.26. cusparseDgtsv2_nopivot
    • 5.6.27. cusparseCgtsv2_nopivot
    • 5.6.28. cusparseZgtsv2_nopivot
    • 5.6.29. cusparseSgtsv2StridedBatch_buffersize
    • 5.6.30. cusparseDgtsv2StridedBatch_buffersize
    • 5.6.31. cusparseCgtsv2StridedBatch_buffersize
    • 5.6.32. cusparseZgtsv2StridedBatch_buffersize
    • 5.6.33. cusparseSgtsv2StridedBatch
    • 5.6.34. cusparseDgtsv2StridedBatch
    • 5.6.35. cusparseCgtsv2StridedBatch
    • 5.6.36. cusparseZgtsv2StridedBatch
    • 5.6.37. cusparseSgtsvInterleavedBatch_buffersize
    • 5.6.38. cusparseDgtsvInterleavedBatch_buffersize
    • 5.6.39. cusparseCgtsvInterleavedBatch_buffersize
    • 5.6.40. cusparseZgtsvInterleavedBatch_buffersize
    • 5.6.41. cusparseSgtsvInterleavedBatch
    • 5.6.42. cusparseDgtsvInterleavedBatch
    • 5.6.43. cusparseCgtsvInterleavedBatch
    • 5.6.44. cusparseZgtsvInterleavedBatch
    • 5.6.45. cusparseSgpsvInterleavedBatch_buffersize
    • 5.6.46. cusparseDgpsvInterleavedBatch_buffersize
    • 5.6.47. cusparseCgpsvInterleavedBatch_buffersize
    • 5.6.48. cusparseZgpsvInterleavedBatch_buffersize
    • 5.6.49. cusparseSgpsvInterleavedBatch
    • 5.6.50. cusparseDgpsvInterleavedBatch
    • 5.6.51. cusparseCgpsvInterleavedBatch
    • 5.6.52. cusparseZgpsvInterleavedBatch
    • 5.6.53. cusparseScsric02_bufferSize
    • 5.6.54. cusparseDcsric02_bufferSize
    • 5.6.55. cusparseCcsric02_bufferSize
    • 5.6.56. cusparseZcsric02_bufferSize
    • 5.6.57. cusparseScsric02_analysis
    • 5.6.58. cusparseDcsric02_analysis
    • 5.6.59. cusparseCcsric02_analysis
    • 5.6.60. cusparseZcsric02_analysis
    • 5.6.61. cusparseScsric02
    • 5.6.62. cusparseDcsric02
    • 5.6.63. cusparseCcsric02
    • 5.6.64. cusparseZcsric02
    • 5.6.65. cusparseXcsric02_zeroPivot
    • 5.6.66. cusparseScsrilu02_numericBoost
    • 5.6.67. cusparseDcsrilu02_numericBoost
    • 5.6.68. cusparseCcsrilu02_numericBoost
    • 5.6.69. cusparseZcsrilu02_numericBoost
    • 5.6.70. cusparseScsrilu02_bufferSize
    • 5.6.71. cusparseDcsrilu02_bufferSize
    • 5.6.72. cusparseCcsrilu02_bufferSize
    • 5.6.73. cusparseZcsrilu02_bufferSize
    • 5.6.74. cusparseScsrilu02_analysis
    • 5.6.75. cusparseDcsrilu02_analysis
    • 5.6.76. cusparseCcsrilu02_analysis
    • 5.6.77. cusparseZcsrilu02_analysis
    • 5.6.78. cusparseScsrilu02
    • 5.6.79. cusparseDcsrilu02
    • 5.6.80. cusparseCcsrilu02
    • 5.6.81. cusparseZcsrilu02
    • 5.6.82. cusparseXcsrilu02_zeroPivot
    • 5.6.83. cusparseSbsric02_bufferSize
    • 5.6.84. cusparseDbsric02_bufferSize
    • 5.6.85. cusparseCbsric02_bufferSize
    • 5.6.86. cusparseZbsric02_bufferSize
    • 5.6.87. cusparseSbsric02_analysis
    • 5.6.88. cusparseDbsric02_analysis
    • 5.6.89. cusparseCbsric02_analysis
    • 5.6.90. cusparseZbsric02_analysis
    • 5.6.91. cusparseSbsric02
    • 5.6.92. cusparseDbsric02
    • 5.6.93. cusparseCbsric02
    • 5.6.94. cusparseZbsric02
    • 5.6.95. cusparseXbsric02_zeroPivot
    • 5.6.96. cusparseSbsrilu02_numericBoost
    • 5.6.97. cusparseDbsrilu02_numericBoost
    • 5.6.98. cusparseCbsrilu02_numericBoost
    • 5.6.99. cusparseZbsrilu02_numericBoost
    • 5.6.100. cusparseSbsrilu02_bufferSize
    • 5.6.101. cusparseDbsrilu02_bufferSize
    • 5.6.102. cusparseCbsrilu02_bufferSize
    • 5.6.103. cusparseZbsrilu02_bufferSize
    • 5.6.104. cusparseSbsrilu02_analysis
    • 5.6.105. cusparseDbsrilu02_analysis
    • 5.6.106. cusparseCbsrilu02_analysis
    • 5.6.107. cusparseZbsrilu02_analysis
    • 5.6.108. cusparseSbsrilu02
    • 5.6.109. cusparseDbsrilu02
    • 5.6.110. cusparseCbsrilu02
    • 5.6.111. cusparseZbsrilu02
    • 5.6.112. cusparseXbsrilu02_zeroPivot
  • 5.7. CUSPARSE Reordering Functions
    • 5.7.1. cusparseScsrColor
    • 5.7.2. cusparseDcsrColor
    • 5.7.3. cusparseCcsrColor
    • 5.7.4. cusparseZcsrColor
  • 5.8. CUSPARSE Format Conversion Functions
    • 5.8.1. cusparseSbsr2csr
    • 5.8.2. cusparseDbsr2csr
    • 5.8.3. cusparseCbsr2csr
    • 5.8.4. cusparseZbsr2csr
    • 5.8.5. cusparseXcoo2csr
    • 5.8.6. cusparseScsc2dense
    • 5.8.7. cusparseDcsc2dense
    • 5.8.8. cusparseCcsc2dense
    • 5.8.9. cusparseZcsc2dense
    • 5.8.10. cusparseScsc2hyb
    • 5.8.11. cusparseDcsc2hyb
    • 5.8.12. cusparseCcsc2hyb
    • 5.8.13. cusparseZcsc2hyb
    • 5.8.14. cusparseXcsr2bsrNnz
    • 5.8.15. cusparseScsr2bsr
    • 5.8.16. cusparseDcsr2bsr
    • 5.8.17. cusparseCcsr2bsr
    • 5.8.18. cusparseZcsr2bsr
    • 5.8.19. cusparseXcsr2coo
    • 5.8.20. cusparseScsr2csc
    • 5.8.21. cusparseDcsr2csc
    • 5.8.22. cusparseCcsr2csc
    • 5.8.23. cusparseZcsr2csc
    • 5.8.24. cusparseCsr2cscEx2_bufferSize
    • 5.8.25. cusparseCsr2cscEx2
    • 5.8.26. cusparseScsr2dense
    • 5.8.27. cusparseDcsr2dense
    • 5.8.28. cusparseCcsr2dense
    • 5.8.29. cusparseZcsr2dense
    • 5.8.30. cusparseScsr2hyb
    • 5.8.31. cusparseDcsr2hyb
    • 5.8.32. cusparseCcsr2hyb
    • 5.8.33. cusparseZcsr2hyb
    • 5.8.34. cusparseSdense2csc
    • 5.8.35. cusparseDdense2csc
    • 5.8.36. cusparseCdense2csc
    • 5.8.37. cusparseZdense2csc
    • 5.8.38. cusparseSdense2csr
    • 5.8.39. cusparseDdense2csr
    • 5.8.40. cusparseCdense2csr
    • 5.8.41. cusparseZdense2csr
    • 5.8.42. cusparseSdense2hyb
    • 5.8.43. cusparseDdense2hyb
    • 5.8.44. cusparseCdense2hyb
    • 5.8.45. cusparseZdense2hyb
    • 5.8.46. cusparseShyb2csc
    • 5.8.47. cusparseDhyb2csc
    • 5.8.48. cusparseChyb2csc
    • 5.8.49. cusparseZhyb2csc
    • 5.8.50. cusparseShyb2csr
    • 5.8.51. cusparseDhyb2csr
    • 5.8.52. cusparseChyb2csr
    • 5.8.53. cusparseZhyb2csr
    • 5.8.54. cusparseShyb2dense
    • 5.8.55. cusparseDhyb2dense
    • 5.8.56. cusparseChyb2dense
    • 5.8.57. cusparseZhyb2dense
    • 5.8.58. cusparseSnnz
    • 5.8.59. cusparseDnnz
    • 5.8.60. cusparseCnnz
    • 5.8.61. cusparseZnnz
    • 5.8.62. cusparseSgebsr2gebsc_bufferSize
    • 5.8.63. cusparseDgebsr2gebsc_bufferSize
    • 5.8.64. cusparseCgebsr2gebsc_bufferSize
    • 5.8.65. cusparseZgebsr2gebsc_bufferSize
    • 5.8.66. cusparseSgebsr2gebsc
    • 5.8.67. cusparseDgebsr2gebsc
    • 5.8.68. cusparseCgebsr2gebsc
    • 5.8.69. cusparseZgebsr2gebsc
    • 5.8.70. cusparseSgebsr2gebsr_bufferSize
    • 5.8.71. cusparseDgebsr2gebsr_bufferSize
    • 5.8.72. cusparseCgebsr2gebsr_bufferSize
    • 5.8.73. cusparseZgebsr2gebsr_bufferSize
    • 5.8.74. cusparseXgebsr2gebsrNnz
    • 5.8.75. cusparseSgebsr2gebsr
    • 5.8.76. cusparseDgebsr2gebsr
    • 5.8.77. cusparseCgebsr2gebsr
    • 5.8.78. cusparseZgebsr2gebsr
    • 5.8.79. cusparseSgebsr2csr
    • 5.8.80. cusparseDgebsr2csr
    • 5.8.81. cusparseCgebsr2csr
    • 5.8.82. cusparseZgebsr2csr
    • 5.8.83. cusparseScsr2gebsr_bufferSize
    • 5.8.84. cusparseDcsr2gebsr_bufferSize
    • 5.8.85. cusparseCcsr2gebsr_bufferSize
    • 5.8.86. cusparseZcsr2gebsr_bufferSize
    • 5.8.87. cusparseXcsr2gebsrNnz
    • 5.8.88. cusparseScsr2gebsr
    • 5.8.89. cusparseDcsr2gebsr
    • 5.8.90. cusparseCcsr2gebsr
    • 5.8.91. cusparseZcsr2gebsr
    • 5.8.92. cusparseCreateIdentityPermutation
    • 5.8.93. cusparseXcoosort_bufferSize
    • 5.8.94. cusparseXcoosortByRow
    • 5.8.95. cusparseXcoosortByColumn
    • 5.8.96. cusparseXcsrsort_bufferSize
    • 5.8.97. cusparseXcsrsort
    • 5.8.98. cusparseXcscsort_bufferSize
    • 5.8.99. cusparseXcscsort
    • 5.8.100. cusparseScsru2csr_bufferSize
    • 5.8.101. cusparseDcsru2csr_bufferSize
    • 5.8.102. cusparseCcsru2csr_bufferSize
    • 5.8.103. cusparseZcsru2csr_bufferSize
    • 5.8.104. cusparseScsru2csr
    • 5.8.105. cusparseDcsru2csr
    • 5.8.106. cusparseCcsru2csr
    • 5.8.107. cusparseZcsru2csr
    • 5.8.108. cusparseScsr2csru
    • 5.8.109. cusparseDcsr2csru
    • 5.8.110. cusparseCcsr2csru
    • 5.8.111. cusparseZcsr2csru
  • 5.9. CUSPARSE Generic API Functions
    • 5.9.1. cusparseDenseToSparse_bufferSize
    • 5.9.2. cusparseDenseToSparse_analysis
    • 5.9.3. cusparseDenseToSparse_convert
    • 5.9.4. cusparseSparseToDense_bufferSize
    • 5.9.5. cusparseSparseToDense
    • 5.9.6. cusparseCreateSpVec
    • 5.9.7. cusparseDestroySpVec
    • 5.9.8. cusparseSpVecGet
    • 5.9.9. cusparseSpVecGetIndexBase
    • 5.9.10. cusparseSpVecGetValues
    • 5.9.11. cusparseSpVecSetValues
    • 5.9.12. cusparseCreateDnVec
    • 5.9.13. cusparseDestroyDnVec
    • 5.9.14. cusparseDnVecGet
    • 5.9.15. cusparseDnVecGetValues
    • 5.9.16. cusparseDnVecSetValues
    • 5.9.17. cusparseCreateCoo
    • 5.9.18. cusparseCreateCooAoS
    • 5.9.19. cusparseCreateCsr
    • 5.9.20. cusparseCreateBlockedEll
    • 5.9.21. cusparseDestroySpMat
    • 5.9.22. cusparseCooGet
    • 5.9.23. cusparseCooAoSGet
    • 5.9.24. cusparseCsrGet
    • 5.9.25. cusparseBlockedEllGet
    • 5.9.26. cusparseCsrSetPointers
    • 5.9.27. cusparseCscSetPointers
    • 5.9.28. cusparseSpMatGetFormat
    • 5.9.29. cusparseSpMatGetIndexBase
    • 5.9.30. cusparseSpMatGetSize
    • 5.9.31. cusparseSpMatGetValues
    • 5.9.32. cusparseSpMatSetValues
    • 5.9.33. cusparseSpMatGetStridedBatch
    • 5.9.34. cusparseSpMatSetStridedBatch
    • 5.9.35. cusparseCooSetStridedBatch
    • 5.9.36. cusparseCsrSetStridedBatch
    • 5.9.37. cusparseBsrSetStridedBatch
    • 5.9.38. cusparseSpMatGetAttribute
    • 5.9.39. cusparseSpMatSetAttribute
    • 5.9.40. cusparseCreateDnMat
    • 5.9.41. cusparseDestroyDnMat
    • 5.9.42. cusparseDnMatGet
    • 5.9.43. cusparseDnMatGetValues
    • 5.9.44. cusparseDnMatSetValues
    • 5.9.45. cusparseDnMatGetStridedBatch
    • 5.9.46. cusparseDnMatSetStridedBatch
    • 5.9.47. cusparseSpVV_bufferSize
    • 5.9.48. cusparseSpVV
    • 5.9.49. cusparseSpMV_bufferSize
    • 5.9.50. cusparseSpMV
    • 5.9.51. cusparseSpSV_CreateDescr
    • 5.9.52. cusparseSpSV_DestroyDescr
    • 5.9.53. cusparseSpSV_bufferSize
    • 5.9.54. cusparseSpSV_analysis
    • 5.9.55. cusparseSpSV_solve
    • 5.9.56. cusparseSpSV_updateMatrix
    • 5.9.57. cusparseSpMM_bufferSize
    • 5.9.58. cusparseSpMM_preprocess
    • 5.9.59. cusparseSpMM
    • 5.9.60. cusparseSpSM_CreateDescr
    • 5.9.61. cusparseSpSM_DestroyDescr
    • 5.9.62. cusparseSpSM_bufferSize
    • 5.9.63. cusparseSpSM_analysis
    • 5.9.64. cusparseSpSM_solve
    • 5.9.65. cusparseSDDMM_bufferSize
    • 5.9.66. cusparseSDDMM_preprocess
    • 5.9.67. cusparseSDDMM
    • 5.9.68. cusparseSpGEMM_CreateDescr
    • 5.9.69. cusparseSpGEMM_DestroyDescr
    • 5.9.70. cusparseSpGEMM_workEstimation
    • 5.9.71. cusparseSpGEMM_getNumProducts
    • 5.9.72. cusparseSpGEMM_estimateMemory
    • 5.9.73. cusparseSpGEMM_compute
    • 5.9.74. cusparseSpGEMM_copy
    • 5.9.75. cusparseSpGEMMreuse_workEstimation
    • 5.9.76. cusparseSpGEMMreuse_nnz
    • 5.9.77. cusparseSpGEMMreuse_copy
    • 5.9.78. cusparseSpGEMMreuse_compute
• 6. Matrix Solver Runtime Library APIs
  • 6.1. CUSOLVER Definitions and Helper Functions
    • 6.1.1. cusolverDnCreate
    • 6.1.2. cusolverDnDestroy
    • 6.1.3. cusolverDnCreateParams
    • 6.1.4. cusolverDnDestroyParams
    • 6.1.5. cusolverDnCreateSyevjInfo
    • 6.1.6. cusolverDnDestroySyevjInfo
    • 6.1.7. cusolverDnSetAdvOptions
    • 6.1.8. cusolverDnGetStream
    • 6.1.9. cusolverDnSetStream
    • 6.1.10. cusolverDnXsyevjSetTolerance
    • 6.1.11. cusolverDnXsyevjSetMaxSweeps
    • 6.1.12. cusolverDnXsyevjSetSortEig
    • 6.1.13. cusolverDnXsyevjGetResidual
    • 6.1.14. cusolverDnXsyevjGetSweeps
  • 6.2. cusolverDn Legacy API
    • 6.2.1. cusolverDnSpotrf_buffersize
    • 6.2.2. cusolverDnDpotrf_buffersize
    • 6.2.3. cusolverDnCpotrf_buffersize
    • 6.2.4. cusolverDnZpotrf_buffersize
    • 6.2.5. cusolverDnSpotrf
    • 6.2.6. cusolverDnDpotrf
    • 6.2.7. cusolverDnCpotrf
    • 6.2.8. cusolverDnZpotrf
    • 6.2.9. cusolverDnSpotrs
    • 6.2.10. cusolverDnDpotrs
    • 6.2.11. cusolverDnCpotrs
    • 6.2.12. cusolverDnZpotrs
    • 6.2.13. cusolverDnSpotrfBatched
    • 6.2.14. cusolverDnDpotrfBatched
    • 6.2.15. cusolverDnCpotrfBatched
    • 6.2.16. cusolverDnZpotrfBatched
    • 6.2.17. cusolverDnSpotrsBatched
    • 6.2.18. cusolverDnDpotrsBatched
    • 6.2.19. cusolverDnCpotrsBatched
    • 6.2.20. cusolverDnZpotrsBatched
    • 6.2.21. cusolverDnSpotri_buffersize
    • 6.2.22. cusolverDnDpotri_buffersize
    • 6.2.23. cusolverDnCpotri_buffersize
    • 6.2.24. cusolverDnZpotri_buffersize
    • 6.2.25. cusolverDnSpotri
    • 6.2.26. cusolverDnDpotri
    • 6.2.27. cusolverDnCpotri
    • 6.2.28. cusolverDnZpotri
    • 6.2.29. cusolverDnStrtri_buffersize
    • 6.2.30. cusolverDnDtrtri_buffersize
    • 6.2.31. cusolverDnCtrtri_buffersize
    • 6.2.32. cusolverDnZtrtri_buffersize
    • 6.2.33. cusolverDnStrtri
    • 6.2.34. cusolverDnDtrtri
    • 6.2.35. cusolverDnCtrtri
    • 6.2.36. cusolverDnZtrtri
    • 6.2.37. cusolverDnSlauum_buffersize
    • 6.2.38. cusolverDnDlauum_buffersize
    • 6.2.39. cusolverDnClauum_buffersize
    • 6.2.40. cusolverDnZlauum_buffersize
    • 6.2.41. cusolverDnSlauum
    • 6.2.42. cusolverDnDlauum
    • 6.2.43. cusolverDnClauum
    • 6.2.44. cusolverDnZlauum
    • 6.2.45. cusolverDnSgetrf_buffersize
    • 6.2.46. cusolverDnDgetrf_buffersize
    • 6.2.47. cusolverDnCgetrf_buffersize
    • 6.2.48. cusolverDnZgetrf_buffersize
    • 6.2.49. cusolverDnSgetrf
    • 6.2.50. cusolverDnDgetrf
    • 6.2.51. cusolverDnCgetrf
    • 6.2.52. cusolverDnZgetrf
    • 6.2.53. cusolverDnSgetrs
    • 6.2.54. cusolverDnDgetrs
    • 6.2.55. cusolverDnCgetrs
    • 6.2.56. cusolverDnZgetrs
    • 6.2.57. cusolverDnSlaswp
    • 6.2.58. cusolverDnDlaswp
    • 6.2.59. cusolverDnClaswp
    • 6.2.60. cusolverDnZlaswp
    • 6.2.61. cusolverDnSgeqrf_buffersize
    • 6.2.62. cusolverDnDgeqrf_buffersize
    • 6.2.63. cusolverDnCgeqrf_buffersize
    • 6.2.64. cusolverDnZgeqrf_buffersize
    • 6.2.65. cusolverDnSgeqrf
    • 6.2.66. cusolverDnDgeqrf
    • 6.2.67. cusolverDnCgeqrf
    • 6.2.68. cusolverDnZgeqrf
    • 6.2.69. cusolverDnSorgqr_buffersize
    • 6.2.70. cusolverDnDorgqr_buffersize
    • 6.2.71. cusolverDnCorgqr_buffersize
    • 6.2.72. cusolverDnZorgqr_buffersize
    • 6.2.73. cusolverDnSorgqr
    • 6.2.74. cusolverDnDorgqr
    • 6.2.75. cusolverDnCorgqr
    • 6.2.76. cusolverDnZorgqr
    • 6.2.77. cusolverDnSormqr_buffersize
    • 6.2.78. cusolverDnDormqr_buffersize
    • 6.2.79. cusolverDnCormqr_buffersize
    • 6.2.80. cusolverDnZormqr_buffersize
    • 6.2.81. cusolverDnSormqr
    • 6.2.82. cusolverDnDormqr
    • 6.2.83. cusolverDnCormqr
    • 6.2.84. cusolverDnZormqr
    • 6.2.85. cusolverDnSsytrf_buffersize
    • 6.2.86. cusolverDnDsytrf_buffersize
    • 6.2.87. cusolverDnCsytrf_buffersize
    • 6.2.88. cusolverDnZsytrf_buffersize
    • 6.2.89. cusolverDnSsytrf
    • 6.2.90. cusolverDnDsytrf
    • 6.2.91. cusolverDnCsytrf
    • 6.2.92. cusolverDnZsytrf
    • 6.2.93. cusolverDnSsytrs_bufferSize
    • 6.2.94. cusolverDnDsytrs_bufferSize
    • 6.2.95. cusolverDnCsytrs_bufferSize
    • 6.2.96. cusolverDnZsytrs_bufferSize
    • 6.2.97. cusolverDnSsytrs
    • 6.2.98. cusolverDnDsytrs
    • 6.2.99. cusolverDnCsytrs
    • 6.2.100. cusolverDnZsytrs
    • 6.2.101. cusolverDnSsytri_bufferSize
    • 6.2.102. cusolverDnDsytri_bufferSize
    • 6.2.103. cusolverDnCsytri_bufferSize
    • 6.2.104. cusolverDnZsytri_bufferSize
    • 6.2.105. cusolverDnSsytri
    • 6.2.106. cusolverDnDsytri
    • 6.2.107. cusolverDnCsytri
    • 6.2.108. cusolverDnZsytri
  • 6.3. cusolverDn Legacy Eigenvalue Solver API
    • 6.3.1. cusolverDnSgebrd_buffersize
    • 6.3.2. cusolverDnDgebrd_buffersize
    • 6.3.3. cusolverDnCgebrd_buffersize
    • 6.3.4. cusolverDnZgebrd_buffersize
    • 6.3.5. cusolverDnSgebrd
    • 6.3.6. cusolverDnDgebrd
    • 6.3.7. cusolverDnCgebrd
    • 6.3.8. cusolverDnZgebrd
    • 6.3.9. cusolverDnSorgbr_buffersize
    • 6.3.10. cusolverDnDorgbr_buffersize
    • 6.3.11. cusolverDnCungbr_buffersize
    • 6.3.12. cusolverDnZungbr_buffersize
    • 6.3.13. cusolverDnSorgbr
    • 6.3.14. cusolverDnDorgbr
    • 6.3.15. cusolverDnCungbr
    • 6.3.16. cusolverDnZungbr
    • 6.3.17. cusolverDnSsytrd_buffersize
    • 6.3.18. cusolverDnDsytrd_buffersize
    • 6.3.19. cusolverDnChetrd_buffersize
    • 6.3.20. cusolverDnZhetrd_buffersize
    • 6.3.21. cusolverDnSsytrd
    • 6.3.22. cusolverDnDsytrd
    • 6.3.23. cusolverDnChetrd
    • 6.3.24. cusolverDnZhetrd
    • 6.3.25. cusolverDnSormtr_buffersize
    • 6.3.26. cusolverDnDormtr_buffersize
    • 6.3.27. cusolverDnCunmtr_buffersize
    • 6.3.28. cusolverDnZunmtr_buffersize
    • 6.3.29. cusolverDnSormtr
    • 6.3.30. cusolverDnDormtr
    • 6.3.31. cusolverDnCunmtr
    • 6.3.32. cusolverDnZunmtr
    • 6.3.33. cusolverDnSorgtr_buffersize
    • 6.3.34. cusolverDnDorgtr_buffersize
    • 6.3.35. cusolverDnCungtr_buffersize
    • 6.3.36. cusolverDnZungtr_buffersize
    • 6.3.37. cusolverDnSorgtr
    • 6.3.38. cusolverDnDorgtr
    • 6.3.39. cusolverDnCungtr
    • 6.3.40. cusolverDnZungtr
    • 6.3.41. cusolverDnSgesvd_buffersize
    • 6.3.42. cusolverDnDgesvd_buffersize
    • 6.3.43. cusolverDnCgesvd_buffersize
    • 6.3.44. cusolverDnZgesvd_buffersize
    • 6.3.45. cusolverDnSgesvd
    • 6.3.46. cusolverDnDgesvd
    • 6.3.47. cusolverDnCgesvd
    • 6.3.48. cusolverDnZgesvd
    • 6.3.49. cusolverDnSsyevd_buffersize
    • 6.3.50. cusolverDnDsyevd_buffersize
    • 6.3.51. cusolverDnCheevd_buffersize
    • 6.3.52. cusolverDnZheevd_buffersize
    • 6.3.53. cusolverDnSsyevd
    • 6.3.54. cusolverDnDsyevd
    • 6.3.55. cusolverDnCheevd
    • 6.3.56. cusolverDnZheevd
    • 6.3.57. cusolverDnSsyevdx_buffersize
    • 6.3.58. cusolverDnDsyevdx_buffersize
    • 6.3.59. cusolverDnCheevdx_buffersize
    • 6.3.60. cusolverDnZheevdx_buffersize
    • 6.3.61. cusolverDnSsyevdx
    • 6.3.62. cusolverDnDsyevdx
    • 6.3.63. cusolverDnCheevdx
    • 6.3.64. cusolverDnZheevdx
    • 6.3.65. cusolverDnSsyevj_buffersize
    • 6.3.66. cusolverDnDsyevj_buffersize
    • 6.3.67. cusolverDnCheevj_buffersize
    • 6.3.68. cusolverDnZheevj_buffersize
    • 6.3.69. cusolverDnSsyevj
    • 6.3.70. cusolverDnDsyevj
    • 6.3.71. cusolverDnCheevj
    • 6.3.72. cusolverDnZheevj
    • 6.3.73. cusolverDnSsyevjBatched_bufferSize
    • 6.3.74. cusolverDnDsyevjBatched_bufferSize
    • 6.3.75. cusolverDnCheevjBatched_bufferSize
    • 6.3.76. cusolverDnZheevjBatched_bufferSize
    • 6.3.77. cusolverDnSsyevjBatched
    • 6.3.78. cusolverDnDsyevjBatched
    • 6.3.79. cusolverDnCheevjBatched
    • 6.3.80. cusolverDnZheevjBatched
    • 6.3.81. cusolverDnSsygvd_buffersize
    • 6.3.82. cusolverDnDsygvd_buffersize
    • 6.3.83. cusolverDnChegvd_buffersize
    • 6.3.84. cusolverDnZhegvd_buffersize
    • 6.3.85. cusolverDnSsygvd
    • 6.3.86. cusolverDnDsygvd
    • 6.3.87. cusolverDnChegvd
    • 6.3.88. cusolverDnZhegvd
    • 6.3.89. cusolverDnSsygvdx_buffersize
    • 6.3.90. cusolverDnDsygvdx_buffersize
    • 6.3.91. cusolverDnChegvdx_buffersize
    • 6.3.92. cusolverDnZhegvdx_buffersize
    • 6.3.93. cusolverDnSsygvdx
    • 6.3.94. cusolverDnDsygvdx
    • 6.3.95. cusolverDnChegvdx
    • 6.3.96. cusolverDnZhegvdx
  • 6.4. cusolverDn 64-bit API
    • 6.4.1. cusolverDnXpotrf_buffersize
    • 6.4.2. cusolverDnXpotrf
    • 6.4.3. cusolverDnXpotrs
    • 6.4.4. cusolverDnXgeqrf_buffersize
    • 6.4.5. cusolverDnXgeqrf
    • 6.4.6. cusolverDnXgetrf_buffersize
    • 6.4.7. cusolverDnXgetrf
    • 6.4.8. cusolverDnXgetrs
    • 6.4.9. cusolverDnXsyevd_buffersize
    • 6.4.10. cusolverDnXsyevd
    • 6.4.11. cusolverDnXsyevdx_buffersize
    • 6.4.12. cusolverDnXsyevdx
    • 6.4.13. cusolverDnXsytrs_bufferSize
    • 6.4.14. cusolverDnXsytrs
    • 6.4.15. cusolverDnXtrtri_bufferSize
    • 6.4.16. cusolverDnXtrtri
    • 6.4.17. cusolverDnXgesvd_buffersize
    • 6.4.18. cusolverDnXgesvd
    • 6.4.19. cusolverDnXgesvdp_buffersize
    • 6.4.20. cusolverDnXgesvdp
    • 6.4.21. cusolverDnXgesvdr_buffersize
    • 6.4.22. cusolverDnXgesvdr
  • 6.5. cusolverMp API
    • 6.5.1. cusolverMpCreate
    • 6.5.2. cusolverMpDestroy
    • 6.5.3. cusolverMpGetStream
    • 6.5.4. cusolverMpGetVersion
    • 6.5.5. cusolverMpCreateDeviceGrid
    • 6.5.6. cusolverMpDestroyGrid
    • 6.5.7. cusolverMpCreateMatrixDesc
    • 6.5.8. cusolverMpDestroyMatrixDesc
    • 6.5.9. cusolverMpNumROC
    • 6.5.10. cusolverMpGetrf_buffersize
    • 6.5.11. cusolverMpGetrf
    • 6.5.12. cusolverMpGetrs_buffersize
    • 6.5.13. cusolverMpGetrs
    • 6.5.14. cusolverMpPotrf_buffersize
    • 6.5.15. cusolverMpPotrf
    • 6.5.16. cusolverMpPotrs_buffersize
    • 6.5.17. cusolverMpPotrs
    • 6.5.18. cusolverMpOrmqr_buffersize
    • 6.5.19. cusolverMpOrmqr
    • 6.5.20. cusolverMpOrmtr_buffersize
    • 6.5.21. cusolverMpOrmtr
    • 6.5.22. cusolverMpGels_buffersize
    • 6.5.23. cusolverMpGels
    • 6.5.24. cusolverMpStedc_buffersize
    • 6.5.25. cusolverMpStedc
    • 6.5.26. cusolverMpGeqrf_buffersize
    • 6.5.27. cusolverMpGeqrf
    • 6.5.28. cusolverMpSytrd_buffersize
    • 6.5.29. cusolverMpSytrd
    • 6.5.30. cusolverMpSyevd_buffersize
    • 6.5.31. cusolverMpSyevd
    • 6.5.32. cusolverMpSygst_buffersize
    • 6.5.33. cusolverMpSygst
    • 6.5.34. cusolverMpSygvd_buffersize
    • 6.5.35. cusolverMpSygvd
    • 6.5.36. cusolverMpLoggerSetFile
    • 6.5.37. cusolverMpLoggerOpenFile
    • 6.5.38. cusolverMpLoggerSetLevel
    • 6.5.39. cusolverMpLoggerSetMask
    • 6.5.40. cusolverMpLoggerForceDisable
  • 6.6. NVLAMATH Runtime Library
    • 6.6.1. NVLAMATH Automatic Drop-In Acceleration
    • 6.6.2. NVLAMATH Usage From CUDA Fortran
    • 6.6.3. NVLAMATH Usage From OpenACC
    • 6.6.4. NVLAMATH Usage From OpenMP
    • 6.6.5. NVLAMATH List of Current Subroutines
    • 6.6.6. NVLAMATH Argument Checks and CPU Fallback
• 7. Tensor Primitives Runtime Library APIs
  • 7.1. CUTENSOR Definitions and Helper Functions
    • 7.1.1. cutensorCreate
    • 7.1.2. cutensorDestroy
    • 7.1.3. cutensorCreateTensorDescriptor
    • 7.1.4. cutensorDestroyTensorDescriptor
    • 7.1.5. cutensorOperationDescriptorGetAttribute
    • 7.1.6. cutensorOperationDescriptorSetAttribute
    • 7.1.7. cutensorDestroyOperationDescriptor
    • 7.1.8. cutensorCreatePlanPreference
    • 7.1.9. cutensorDestroyPlanPreference
    • 7.1.10. cutensorPlanPreferenceSetAttribute
    • 7.1.11. cutensorEstimateWorkspaceSize
    • 7.1.12. cutensorCreatePlan
    • 7.1.13. cutensorDestroyPlan
    • 7.1.14. cutensorGetErrorString
    • 7.1.15. cutensorGetVersion
    • 7.1.16. cutensorGetCudartVersion
  • 7.2. CUTENSOR Element-wise Operations
    • 7.2.1. cutensorCreatePermutation
    • 7.2.2. cutensorPermute
    • 7.2.3. cutensorCreateElementwiseBinary
    • 7.2.4. cutensorElementwiseBinaryExecute
    • 7.2.5. cutensorCreateElementwiseTrinary
    • 7.2.6. cutensorElementwiseTrinaryExecute
  • 7.3. CUTENSOR Reduction Operations
    • 7.3.1. cutensorCreateReduction
    • 7.3.2. cutensorReduce
  • 7.4. CUTENSOR Contraction Operations
    • 7.4.1. cutensorCreateContraction
    • 7.4.2. cutensorContract
  • 7.5. CUTENSOR Fortran Extensions
    • 7.5.1. Fortran Reshape
    • 7.5.2. Fortran Transpose
    • 7.5.3. Fortran Spread
    • 7.5.4. Fortran Element-wise Expressions
    • 7.5.5. Fortran Matmul Operations
    • 7.5.6. Fortran Dot_Product Operations
    • 7.5.7. Supported Element-wise Functions
• 8. NVIDIA Collective Communications Library (NCCL) APIs
  • 8.1. NCCL Definitions and Helper Functions
    • 8.1.1. ncclGetVersion
    • 8.1.2. ncclGetUniqueId
    • 8.1.3. ncclCommInitRank
    • 8.1.4. ncclCommInitRankConfig
    • 8.1.5. ncclCommInitAll
    • 8.1.6. ncclCommDestroy
    • 8.1.7. ncclCommFinalize
    • 8.1.8. ncclCommSplit
    • 8.1.9. ncclCommAbort
    • 8.1.10. ncclCommRegister
    • 8.1.11. ncclCommDeregister
    • 8.1.12. ncclGetErrorString
    • 8.1.13. ncclGetLastError
    • 8.1.14. ncclCommGetAsyncError
    • 8.1.15. ncclCommCount
    • 8.1.16. ncclCommCuDevice
    • 8.1.17. ncclCommUserRank
  • 8.2. NCCL Collective Communication Functions
    • 8.2.1. ncclAllReduce
    • 8.2.2. ncclBroadcast
    • 8.2.3. ncclReduce
    • 8.2.4. ncclAllGather
    • 8.2.5. ncclReduceScatter
  • 8.3. NCCL Point To Point Communication Functions
    • 8.3.1. ncclSend
    • 8.3.2. ncclRecv
  • 8.4. NCCL Group Calls
    • 8.4.1. ncclGroupStart
    • 8.4.2. ncclGroupEnd
• 9. NVSHMEM Communication Library APIs
  • 9.1. NVSHMEM Definitions, Setup, Exit, and Query Functions
    • 9.1.1. nvshmem_init
    • 9.1.2. nvshmemx_init_attr
    • 9.1.3. nvshmem_my_pe
    • 9.1.4. nvshmem_n_pes
    • 9.1.5. nvshmem_team_my_pe
    • 9.1.6. nvshmem_team_n_pes
    • 9.1.7. nvshmem_team_get_config
    • 9.1.8. nvshmem_team_translate_pe
    • 9.1.9. nvshmem_team_split_strided
    • 9.1.10. nvshmem_team_split_2d
    • 9.1.11. nvshmem_team_destroy
    • 9.1.12. nvshmem_info_get_version
    • 9.1.13. nvshmem_info_get_name
    • 9.1.14. nvshmem_finalize
    • 9.1.15. nvshmem_ptr
  • 9.2. NVSHMEM Memory Management Functions
    • 9.2.1. nvshmem_malloc
    • 9.2.2. nvshmem_free
    • 9.2.3. nvshmem_align
    • 9.2.4. nvshmem_calloc
    • 9.2.5. nvshmemx_buffer_register
    • 9.2.6. nvshmemx_buffer_unregister
    • 9.2.7. nvshmemx_buffer_unregister_all
  • 9.3. NVSHMEM Remote Memory Access Functions
    • 9.3.1. nvshmem_put
    • 9.3.2. nvshmem_p
    • 9.3.3. nvshmem_iput
    • 9.3.4. nvshmem_put_nbi
    • 9.3.5. nvshmemx_put_block
    • 9.3.6. nvshmemx_put_warp
    • 9.3.7. nvshmem_get
    • 9.3.8. nvshmem_g
    • 9.3.9. nvshmem_iget
    • 9.3.10. nvshmem_get_nbi
    • 9.3.11. nvshmemx_get_block
    • 9.3.12. nvshmemx_get_warp
  • 9.4. NVSHMEM Collective Communication Functions
    • 9.4.1. nvshmem_barrier, nvshmem_barrier_all
    • 9.4.2. nvshmem_sync, nvshmem_sync_all
    • 9.4.3. nvshmem_alltoall
    • 9.4.4. nvshmem_broadcast
    • 9.4.5. nvshmem_collect
    • 9.4.6. NVSHMEM Reductions
      • 9.4.6.1. nvshmem_and_reduce
      • 9.4.6.2. nvshmem_or_reduce
      • 9.4.6.3. nvshmem_xor_reduce
      • 9.4.6.4. nvshmem_max_reduce
      • 9.4.6.5. nvshmem_min_reduce
      • 9.4.6.6. nvshmem_sum_reduce
      • 9.4.6.7. nvshmem_prod_reduce
  • 9.5. NVSHMEM Point to Point Synchronization Functions
    • 9.5.1. nvshmem_wait_until
    • 9.5.2. nvshmem_wait_until_all
    • 9.5.3. nvshmem_wait_until_any
    • 9.5.4. nvshmem_wait_until_some
    • 9.5.5. nvshmem_wait_until_all_vector
    • 9.5.6. nvshmem_wait_until_any_vector
    • 9.5.7. nvshmem_wait_until_some_vector
    • 9.5.8. nvshmem_test
    • 9.5.9. nvshmem_test_all
    • 9.5.10. nvshmem_test_any
    • 9.5.11. nvshmem_test_some
    • 9.5.12. nvshmem_test_all_vector
    • 9.5.13. nvshmem_test_any_vector
    • 9.5.14. nvshmem_test_some_vector
  • 9.6. NVSHMEM Memory Ordering Functions
    • 9.6.1. nvshmem_fence
    • 9.6.2. nvshmem_quiet
• 10. NVTX Profiling Library APIs
  • 10.1. NVTX Basic Tooling APIs
    • 10.1.1. nvtxStartRange
    • 10.1.2. nvtxEndRange
  • 10.2. NVTX Advanced Tooling APIs
    • 10.2.1. NVTX Definitions and Derived Types
    • 10.2.2. nvtxInitialize
    • 10.2.3. nvtxDomainCreate
    • 10.2.4. nvtxDomainDestroy
    • 10.2.5. nvtxDomainRegisterString
    • 10.2.6. nvtxDomainNameCategory
    • 10.2.7. nvtxNameCategory
    • 10.2.8. nvtxDomainMarkEx
    • 10.2.9. nvtxMarkEx
    • 10.2.10. nvtxMark
    • 10.2.11. nvtxDomainRangeStartEx
    • 10.2.12. nvtxRangeStartEx
    • 10.2.13. nvtxRangeStart
    • 10.2.14. nvtxDomainRangeEnd
    • 10.2.15. nvtxRangeEnd
    • 10.2.16. nvtxDomainRangePushEx
    • 10.2.17. nvtxRangePushEx
    • 10.2.18. nvtxRangePush
    • 10.2.19. nvtxDomainRangePop
    • 10.2.20. nvtxRangePop
  • 10.3. NVTX Automated Instrumentation
• 11. NVIDIA Communication Abstraction Library (CAL) APIs
  • 11.1. CAL API
    • 11.1.1. cal_comm_create_mpi
    • 11.1.2. cal_comm_destroy
    • 11.1.3. cal_stream_sync
    • 11.1.4. cal_comm_barrier
    • 11.1.5. cal_comm_get_rank
    • 11.1.6. cal_comm_get_size
• 12. Examples
  • 12.1. Using cuBLAS from OpenACC Host Code
  • 12.2. Using cuBLAS from CUDA Fortran Host Code
  • 12.3. Using cuFFT from OpenACC Host Code
  • 12.4. Using cuFFT from CUDA Fortran Host Code
  • 12.5. Using cufftXt from CUDA Fortran Host Code
  • 12.6. Using cuFFTMp from either OpenACC or CUDA Fortran
  • 12.7. Using cuRAND from OpenACC Host Code
  • 12.8. Using cuRAND from OpenACC Device Code
  • 12.9. Using cuRAND from CUDA Fortran Host Code
  • 12.10. Using cuRAND from CUDA Fortran Device Code
  • 12.11. Using cuSPARSE from OpenACC Host Code
  • 12.12. Using cuSPARSE from CUDA Fortran Host Code
  • 12.13. Using cuTENSOR from CUDA Fortran Host Code
  • 12.14. Using cuTENSOREX from CUDA Fortran Host Code
  • 12.15. Using cuTENSOR from OpenACC Host Code