Contents

• 1. Introduction
  • 1.1. cuSolverDN: Dense LAPACK
  • 1.2. cuSolverSP: Sparse LAPACK
  • 1.3. cuSolverRF: Refactorization
  • 1.4. Naming Conventions
  • 1.5. Asynchronous Execution
  • 1.6. Library Property
  • 1.7. High Precision Package
• 2. Using the CUSOLVER API
  • 2.1. General Description
    • 2.1.1. Thread Safety
    • 2.1.2. Scalar Parameters
    • 2.1.3. Parallelism with Streams
    • 2.1.4. How to Link cusolver Library
    • 2.1.5. Link Third-party LAPACK Library
    • 2.1.6. Convention of info
    • 2.1.7. Usage of _bufferSize
    • 2.1.8. cuSOLVERDn Logging
    • 2.1.9. Deterministic Results
    • 2.1.10. Floating Point Emulation
  • 2.2. cuSolver Types Reference
    • 2.2.1. cuSolverDN Types
      • 2.2.1.1. cusolverDnHandle_t
      • 2.2.1.2. cublasFillMode_t
      • 2.2.1.3. cublasOperation_t
      • 2.2.1.4. cusolverEigType_t
      • 2.2.1.5. cusolverEigMode_t
      • 2.2.1.6. cusolverIRSRefinement_t
      • 2.2.1.7. cusolverDnIRSParams_t
      • 2.2.1.8. cusolverDnIRSInfos_t
      • 2.2.1.9. cusolverDnFunction_t
      • 2.2.1.10. cusolverAlgMode_t
      • 2.2.1.11. cusolverStatus_t
      • 2.2.1.12. cusolverDnLoggerCallback_t
      • 2.2.1.13. cusolverDeterministicMode_t
      • 2.2.1.14. cusolverMathMode_t
      • 2.2.1.15. cusolverStorevMode_t
      • 2.2.1.16. cusolverDirectMode_t
    • 2.2.2. cuSolverSP Types
      • 2.2.2.1. cusolverSpHandle_t
      • 2.2.2.2. cusparseMatDescr_t
      • 2.2.2.3. cusolverStatus_t
    • 2.2.3. cuSolverRF Types
      • 2.2.3.1. cusolverRfHandle_t
      • 2.2.3.2. cusolverRfMatrixFormat_t
      • 2.2.3.3. cusolverRfNumericBoostReport_t
      • 2.2.3.4. cusolverRfResetValuesFastMode_t
      • 2.2.3.5. cusolverRfFactorization_t
      • 2.2.3.6. cusolverRfTriangularSolve_t
      • 2.2.3.7. cusolverRfUnitDiagonal_t
      • 2.2.3.8. cusolverStatus_t
  • 2.3. cuSolver Formats Reference
    • 2.3.1. Index Base Format
    • 2.3.2. Vector (Dense) Format
    • 2.3.3. Matrix (Dense) Format
    • 2.3.4. Matrix (CSR) Format
    • 2.3.5. Matrix (CSC) Format
  • 2.4. cuSolverDN: dense LAPACK Function Reference
    • 2.4.1. cuSolverDN Helper Function Reference
      • 2.4.1.1. cusolverDnCreate()
      • 2.4.1.2. cusolverDnDestroy()
      • 2.4.1.3. cusolverDnSetStream()
      • 2.4.1.4. cusolverDnGetStream()
      • 2.4.1.5. cusolverDnLoggerSetCallback()
      • 2.4.1.6. cusolverDnLoggerSetFile()
      • 2.4.1.7. cusolverDnLoggerOpenFile()
      • 2.4.1.8. cusolverDnLoggerSetLevel()
      • 2.4.1.9. cusolverDnLoggerSetMask()
      • 2.4.1.10. cusolverDnLoggerForceDisable()
      • 2.4.1.11. cusolverDnSetDeterministicMode()
      • 2.4.1.12. cusolverDnGetDeterministicMode()
      • 2.4.1.13. cusolverDnSetMathMode()
      • 2.4.1.14. cusolverDnGetMathMode()
      • 2.4.1.15. cusolverDnSetEmulationStrategy()
      • 2.4.1.16. cusolverDnGetEmulationStrategy()
      • 2.4.1.17. cusolverDnCreateSyevjInfo()
      • 2.4.1.18. cusolverDnDestroySyevjInfo()
      • 2.4.1.19. cusolverDnXsyevjSetTolerance()
      • 2.4.1.20. cusolverDnXsyevjSetMaxSweeps()
      • 2.4.1.21. cusolverDnXsyevjSetSortEig()
      • 2.4.1.22. cusolverDnXsyevjGetResidual()
      • 2.4.1.23. cusolverDnXsyevjGetSweeps()
      • 2.4.1.24. cusolverDnCreateGesvdjInfo()
      • 2.4.1.25. cusolverDnDestroyGesvdjInfo()
      • 2.4.1.26. cusolverDnXgesvdjSetTolerance()
      • 2.4.1.27. cusolverDnXgesvdjSetMaxSweeps()
      • 2.4.1.28. cusolverDnXgesvdjSetSortEig()
      • 2.4.1.29. cusolverDnXgesvdjGetResidual()
      • 2.4.1.30. cusolverDnXgesvdjGetSweeps()
      • 2.4.1.31. cusolverDnIRSParamsCreate()
      • 2.4.1.32. cusolverDnIRSParamsDestroy()
      • 2.4.1.33. cusolverDnIRSParamsSetSolverPrecisions()
      • 2.4.1.34. cusolverDnIRSParamsSetSolverMainPrecision()
      • 2.4.1.35. cusolverDnIRSParamsSetSolverLowestPrecision()
      • 2.4.1.36. cusolverDnIRSParamsSetRefinementSolver()
      • 2.4.1.37. cusolverDnIRSParamsSetTol()
      • 2.4.1.38. cusolverDnIRSParamsSetTolInner()
      • 2.4.1.39. cusolverDnIRSParamsSetMaxIters()
      • 2.4.1.40. cusolverDnIRSParamsSetMaxItersInner()
      • 2.4.1.41. cusolverDnIRSParamsEnableFallback()
      • 2.4.1.42. cusolverDnIRSParamsDisableFallback()
      • 2.4.1.43. cusolverDnIRSParamsGetMaxIters()
      • 2.4.1.44. cusolverDnIRSInfosCreate()
      • 2.4.1.45. cusolverDnIRSInfosDestroy()
      • 2.4.1.46. cusolverDnIRSInfosGetMaxIters()
      • 2.4.1.47. cusolverDnIRSInfosGetNiters()
      • 2.4.1.48. cusolverDnIRSInfosGetOuterNiters()
      • 2.4.1.49. cusolverDnIRSInfosRequestResidual()
      • 2.4.1.50. cusolverDnIRSInfosGetResidualHistory()
      • 2.4.1.51. cusolverDnCreateParams()
      • 2.4.1.52. cusolverDnDestroyParams()
      • 2.4.1.53. cusolverDnSetAdvOptions()
    • 2.4.2. Dense Linear Solver Reference (legacy)
      • 2.4.2.1. cusolverDn<t>potrf()
      • 2.4.2.2. cusolverDn<t>potrs()
      • 2.4.2.3. cusolverDn<t>potri()
      • 2.4.2.4. cusolverDn<t>getrf()
      • 2.4.2.5. cusolverDn<t>getrs()
      • 2.4.2.6. cusolverDn<t1><t2>gesv()
      • 2.4.2.7. cusolverDnIRSXgesv()
      • 2.4.2.8. cusolverDn<t>geqrf()
      • 2.4.2.9. cusolverDn<t1><t2>gels()
      • 2.4.2.10. cusolverDnIRSXgels()
      • 2.4.2.11. cusolverDn<t>ormqr()
      • 2.4.2.12. cusolverDn<t>orgqr()
      • 2.4.2.13. cusolverDn<t>sytrf()
      • 2.4.2.14. cusolverDn<t>potrfBatched()
      • 2.4.2.15. cusolverDn<t>potrsBatched()
    • 2.4.3. Dense Eigenvalue Solver Reference (legacy)
      • 2.4.3.1. cusolverDn<t>gebrd()
      • 2.4.3.2. cusolverDn<t>orgbr()
      • 2.4.3.3. cusolverDn<t>sytrd()
      • 2.4.3.4. cusolverDn<t>ormtr()
      • 2.4.3.5. cusolverDn<t>orgtr()
      • 2.4.3.6. cusolverDn<t>gesvd()
      • 2.4.3.7. cusolverDn<t>gesvdj()
      • 2.4.3.8. cusolverDn<t>gesvdjBatched()
      • 2.4.3.9. cusolverDn<t>gesvdaStridedBatched()
      • 2.4.3.10. cusolverDn<t>syevd()
      • 2.4.3.11. cusolverDn<t>syevdx()
      • 2.4.3.12. cusolverDn<t>sygvd()
      • 2.4.3.13. cusolverDn<t>sygvdx()
      • 2.4.3.14. cusolverDn<t>syevj()
      • 2.4.3.15. cusolverDn<t>sygvj()
      • 2.4.3.16. cusolverDn<t>syevjBatched()
    • 2.4.4. Dense Linear Solver Reference (64-bit API)
      • 2.4.4.1. cusolverDnXpotrf()
      • 2.4.4.2. cusolverDnXpotrs()
      • 2.4.4.3. cusolverDnXgetrf()
      • 2.4.4.4. cusolverDnXgetrs()
      • 2.4.4.5. cusolverDnXgeqrf()
      • 2.4.4.6. cusolverDnXsytrs()
      • 2.4.4.7. cusolverDnXtrtri()
      • 2.4.4.8. cusolverDnXlarft()
    • 2.4.5. Dense Eigenvalue Solver Reference (64-bit API)
      • 2.4.5.1. cusolverDnXgesvd()
      • 2.4.5.2. cusolverDnXgesvdp()
      • 2.4.5.3. cusolverDnXgesvdr()
      • 2.4.5.4. cusolverDnXsyevd()
      • 2.4.5.5. cusolverDnXsyevdx()
      • 2.4.5.6. cusolverDnXsyevBatched()
      • 2.4.5.7. cusolverDnXgeev()
  • 2.5. cuSolverSP: sparse LAPACK Function Reference [[DEPRECATED]]
    • 2.5.1. Helper Function Reference
      • 2.5.1.1. cusolverSpCreate() [[DEPRECATED]]
      • 2.5.1.2. cusolverSpDestroy() [[DEPRECATED]]
      • 2.5.1.3. cusolverSpSetStream() [[DEPRECATED]]
      • 2.5.1.4. cusolverSpXcsrissym() [[DEPRECATED]]
    • 2.5.2. High Level Function Reference
      • 2.5.2.1. cusolverSp<t>csrlsvlu() [[DEPRECATED]]
      • 2.5.2.2. cusolverSp<t>csrlsvqr() [[DEPRECATED]]
      • 2.5.2.3. cusolverSp<t>csrlsvchol() [[DEPRECATED]]
      • 2.5.2.4. cusolverSp<t>csrlsqvqr() [[DEPRECATED]]
      • 2.5.2.5. cusolverSp<t>csreigvsi() [[DEPRECATED]]
      • 2.5.2.6. cusolverSp<t>csreigs() [[DEPRECATED]]
    • 2.5.3. Low Level Function Reference
      • 2.5.3.1. cusolverSpXcsrsymrcm() [[DEPRECATED]]
      • 2.5.3.2. cusolverSpXcsrsymmdq() [[DEPRECATED]]
      • 2.5.3.3. cusolverSpXcsrsymamd() [[DEPRECATED]]
      • 2.5.3.4. cusolverSpXcsrmetisnd() [[DEPRECATED]]
      • 2.5.3.5. cusolverSpXcsrzfd() [[DEPRECATED]]
      • 2.5.3.6. cusolverSpXcsrperm() [[DEPRECATED]]
      • 2.5.3.7. cusolverSpXcsrqrBatched() [[DEPRECATED]]
  • 2.6. cuSolverRF: Refactorization Reference [[DEPRECATED]]
    • 2.6.1. cusolverRfAccessBundledFactorsDevice() [[DEPRECATED]]
    • 2.6.2. cusolverRfAnalyze() [[DEPRECATED]]
    • 2.6.3. cusolverRfSetupHost() [[DEPRECATED]]
    • 2.6.4. cusolverRfCreate() [[DEPRECATED]]
    • 2.6.5. cusolverRfExtractBundledFactorsHost() [[DEPRECATED]]
    • 2.6.6. cusolverRfExtractSplitFactorsHost() [[DEPRECATED]]
    • 2.6.7. cusolverRfDestroy() [[DEPRECATED]]
    • 2.6.8. cusolverRfGetMatrixFormat() [[DEPRECATED]]
    • 2.6.9. cusolverRfGetNumericProperties() [[DEPRECATED]]
    • 2.6.10. cusolverRfGetNumericBoostReport() [[DEPRECATED]]
    • 2.6.11. cusolverRfGetResetValuesFastMode() [[DEPRECATED]]
    • 2.6.12. cusolverRfGetAlgs()
    • 2.6.13. cusolverRfRefactor() [[DEPRECATED]]
    • 2.6.14. cusolverRfResetValues() [[DEPRECATED]]
    • 2.6.15. cusolverRfSetMatrixFormat() [[DEPRECATED]]
    • 2.6.16. cusolverRfSetNumericProperties() [[DEPRECATED]]
    • 2.6.17. cusolverRfSetResetValuesFastMode() [[DEPRECATED]]
    • 2.6.18. cusolverRfSetAlgs() [[DEPRECATED]]
    • 2.6.19. cusolverRfSolve() [[DEPRECATED]]
    • 2.6.20. cusolverRfBatchSetupHost() [[DEPRECATED]]
    • 2.6.21. cusolverRfBatchAnalyze() [[DEPRECATED]]
    • 2.6.22. cusolverRfBatchResetValues() [[DEPRECATED]]
    • 2.6.23. cusolverRfBatchRefactor() [[DEPRECATED]]
    • 2.6.24. cusolverRfBatchSolve() [[DEPRECATED]]
    • 2.6.25. cusolverRfBatchZeroPivot() [[DEPRECATED]]
• 3. Using the CUSOLVERMG API
  • 3.1. General Description
    • 3.1.1. Thread Safety
    • 3.1.2. Determinism
    • 3.1.3. Tile Strategy
    • 3.1.4. Global Matrix Versus Local Matrix
    • 3.1.5. Usage of _bufferSize
    • 3.1.6. Synchronization
    • 3.1.7. Context Switch
    • 3.1.8. NVLINK
  • 3.2. cuSolverMG Types Reference
    • 3.2.1. cuSolverMG Types
    • 3.2.2. cusolverMgHandle_t
    • 3.2.3. cusolverMgGridMapping_t
    • 3.2.4. cudaLibMgGrid_t
    • 3.2.5. cudaLibMgMatrixDesc_t
  • 3.3. Helper Function Reference
    • 3.3.1. cusolverMgCreate() [DEPRECATED]
    • 3.3.2. cusolverMgDestroy() [DEPRECATED]
    • 3.3.3. cusolverMgDeviceSelect() [DEPRECATED]
    • 3.3.4. cusolverMgCreateDeviceGrid() [DEPRECATED]
    • 3.3.5. cusolverMgDestroyGrid() [DEPRECATED]
    • 3.3.6. cusolverMgCreateMatrixDesc() [DEPRECATED]
    • 3.3.7. cusolverMgDestroyMatrixDesc() [DEPRECATED]
  • 3.4. Dense Linear Solver Reference
    • 3.4.1. cusolverMgPotrf() [DEPRECATED]
    • 3.4.2. cusolverMgPotrs() [DEPRECATED]
    • 3.4.3. cusolverMgPotri() [DEPRECATED]
    • 3.4.4. cusolverMgGetrf() [DEPRECATED]
    • 3.4.5. cusolverMgGetrs() [DEPRECATED]
  • 3.5. Dense Eigenvalue Solver Reference
    • 3.5.1. cusolverMgSyevd() [DEPRECATED]
• 4. Acknowledgements
• 5. Bibliography
• 6. Notices
  • 6.1. Notice
  • 6.2. OpenCL
  • 6.3. Trademarks