NVIDIACUDA Toolkit Documentation
Search In:
CUDA Toolkit v13.0.0
CUDA Driver API
  • 1. Difference between the driver and runtime APIs
  • 2. API synchronization behavior
  • 3. Stream synchronization behavior
  • 4. Graph object thread safety
  • 5. Rules for version mixing
  • 6. Modules
    • 6.1. Data types used by CUDA driver
    • 6.2. Error Handling
    • 6.3. Initialization
    • 6.4. Version Management
    • 6.5. Device Management
    • 6.6. Device Management [DEPRECATED]
    • 6.7. Primary Context Management
    • 6.8. Context Management
    • 6.9. Context Management [DEPRECATED]
    • 6.10. Module Management
    • 6.11. Module Management [DEPRECATED]
    • 6.12. Library Management
    • 6.13. Memory Management
    • 6.14. Virtual Memory Management
    • 6.15. Stream Ordered Memory Allocator
    • 6.16. Multicast Object Management
    • 6.17. Unified Addressing
    • 6.18. Stream Management
    • 6.19. Event Management
    • 6.20. External Resource Interoperability
    • 6.21. Stream Memory Operations
    • 6.22. Execution Control
    • 6.23. Execution Control [DEPRECATED]
    • 6.24. Graph Management
    • 6.25. Occupancy
    • 6.26. Texture Reference Management [DEPRECATED]
    • 6.27. Surface Reference Management [DEPRECATED]
    • 6.28. Texture Object Management
    • 6.29. Surface Object Management
    • 6.30. Tensor Map Object Managment
    • 6.31. Peer Context Memory Access
    • 6.32. Graphics Interoperability
    • 6.33. Driver Entry Point Access
    • 6.34. Coredump Attributes Control API
    • 6.35. Green Contexts
    • 6.36. Error Log Management Functions
    • 6.37. CUDA Checkpointing
    • 6.38. Profiler Control [DEPRECATED]
    • 6.39. Profiler Control
    • 6.40. OpenGL Interoperability
      • 6.40.1. OpenGL Interoperability [DEPRECATED]
    • 6.41. Direct3D 9 Interoperability
      • 6.41.1. Direct3D 9 Interoperability [DEPRECATED]
    • 6.42. Direct3D 10 Interoperability
      • 6.42.1. Direct3D 10 Interoperability [DEPRECATED]
    • 6.43. Direct3D 11 Interoperability
      • 6.43.1. Direct3D 11 Interoperability [DEPRECATED]
    • 6.44. VDPAU Interoperability
    • 6.45. EGL Interoperability
  • 7. Data Structures
    • 7.1. CUaccessPolicyWindow_v1
    • 7.2. CUarrayMapInfo_v1
    • 7.3. CUasyncNotificationInfo
    • 7.4. CUcheckpointCheckpointArgs
    • 7.5. CUcheckpointGpuPair
    • 7.6. CUcheckpointLockArgs
    • 7.7. CUcheckpointRestoreArgs
    • 7.8. CUcheckpointUnlockArgs
    • 7.9. CUctxCigParam
    • 7.10. CUctxCreateParams
    • 7.11. CUDA_ARRAY3D_DESCRIPTOR_v2
    • 7.12. CUDA_ARRAY_DESCRIPTOR_v2
    • 7.13. CUDA_ARRAY_MEMORY_REQUIREMENTS_v1
    • 7.14. CUDA_ARRAY_SPARSE_PROPERTIES_v1
    • 7.15. CUDA_BATCH_MEM_OP_NODE_PARAMS_v1
    • 7.16. 
    • 7.17. CUDA_CHILD_GRAPH_NODE_PARAMS
    • 7.18. CUDA_CONDITIONAL_NODE_PARAMS
    • 7.19. CUDA_EVENT_RECORD_NODE_PARAMS
    • 7.20. CUDA_EVENT_WAIT_NODE_PARAMS
    • 7.21. CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_v1
    • 7.22. CUDA_EXT_SEM_SIGNAL_NODE_PARAMS_v2
    • 7.23. CUDA_EXT_SEM_WAIT_NODE_PARAMS_v1
    • 7.24. CUDA_EXT_SEM_WAIT_NODE_PARAMS_v2
    • 7.25. CUDA_EXTERNAL_MEMORY_BUFFER_DESC_v1
    • 7.26. CUDA_EXTERNAL_MEMORY_HANDLE_DESC_v1
    • 7.27. CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC_v1
    • 7.28. CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC_v1
    • 7.29. CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS_v1
    • 7.30. CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS_v1
    • 7.31. CUDA_GRAPH_INSTANTIATE_PARAMS
    • 7.32. CUDA_HOST_NODE_PARAMS_v1
    • 7.33. CUDA_HOST_NODE_PARAMS_v2
    • 7.34. CUDA_KERNEL_NODE_PARAMS_v1
    • 7.35. CUDA_KERNEL_NODE_PARAMS_v2
    • 7.36. CUDA_KERNEL_NODE_PARAMS_v3
    • 7.37. CUDA_LAUNCH_PARAMS_v1
    • 7.38. CUDA_MEM_ALLOC_NODE_PARAMS_v1
    • 7.39. CUDA_MEM_ALLOC_NODE_PARAMS_v2
    • 7.40. CUDA_MEM_FREE_NODE_PARAMS
    • 7.41. CUDA_MEMCPY2D_v2
    • 7.42. CUDA_MEMCPY3D_PEER_v1
    • 7.43. CUDA_MEMCPY3D_v2
    • 7.44. CUDA_MEMCPY_NODE_PARAMS
    • 7.45. CUDA_MEMSET_NODE_PARAMS_v1
    • 7.46. CUDA_MEMSET_NODE_PARAMS_v2
    • 7.47. CUDA_POINTER_ATTRIBUTE_P2P_TOKENS_v1
    • 7.48. CUDA_RESOURCE_DESC_v1
    • 7.49. CUDA_RESOURCE_VIEW_DESC_v1
    • 7.50. CUDA_TEXTURE_DESC_v1
    • 7.51. CUdevprop_v1
    • 7.52. CUdevResource
    • 7.53. CUdevSmResource
    • 7.54. CUeglFrame_v1
    • 7.55. CUexecAffinityParam_v1
    • 7.56. CUexecAffinitySmCount_v1
    • 7.57. CUextent3D_v1
    • 7.58. CUgraphEdgeData
    • 7.59. CUgraphExecUpdateResultInfo_v1
    • 7.60. CUgraphNodeParams
    • 7.61. CUipcEventHandle_v1
    • 7.62. CUipcMemHandle_v1
    • 7.63. CUlaunchAttribute
    • 7.64. CUlaunchAttributeValue
    • 7.65. CUlaunchConfig
    • 7.66. CUlaunchMemSyncDomainMap
    • 7.67. CUmemAccessDesc_v1
    • 7.68. CUmemAllocationProp_v1
    • 7.69. CUmemcpy3DOperand_v1
    • 7.70. CUmemcpyAttributes_v1
    • 7.71. CUmemDecompressParams
    • 7.72. CUmemFabricHandle_v1
    • 7.73. CUmemLocation_v1
    • 7.74. CUmemPoolProps_v1
    • 7.75. CUmemPoolPtrExportData_v1
    • 7.76. CUmulticastObjectProp_v1
    • 7.77. CUoffset3D_v1
    • 7.78. CUstreamBatchMemOpParams_v1
    • 7.79. CUtensorMap
  • 8. Data Fields
  • 9. Deprecated List

Search Results

    < Previous | Next >
    CUDA Driver API (PDF) - v13.0.0 (older) - Last updated August 1, 2025 - Send Feedback

    7.15. CUDA_BATCH_MEM_OP_NODE_PARAMS_v1 Struct Reference

    [Data types used by CUDA driver]

    Batch memory operation node parameters

    Used in the legacy cuGraphAddBatchMemOpNode api. New code should use cuGraphAddNode()

    Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact
    Copyright © 2025 NVIDIA Corporation