Debugger API :: CUDA Toolkit Documentation

4.1. CUDBGAPI_st 结构体参考

公共变量

CUDBGResult ( *acknowledgeEvent30 )( CUDBGEvent30* event ): Inform the debugger API that the event has been processed.
CUDBGResult ( *acknowledgeEvents42 )( ): Inform the debugger API that synchronous events have been processed.
CUDBGResult ( *acknowledgeSyncEvents )( ): Inform the debugger API that synchronous events have been processed.
CUDBGResult ( *clearAttachState )( ): Clear attach-specific state prior to detach.
CUDBGResult ( *disassemble )( uint32_t dev, uint64_t addr, uint32_t* instSize, char* buf, uint32_t sz ): Disassemble instruction at instruction address.
CUDBGResult ( *finalize )( ): Finalize the API and free all memory.
CUDBGResult ( *generateCoredump )( const char* filename, CUDBGCoredumpGenerationFlags flags ): Generates a coredump for the current GPU state.
CUDBGResult ( *getAdjustedCodeAddress )( uint32_t devId, uint64_t address, uint64_t* adjustedAddress, CUDBGAdjAddrAction adjAction ): The client must call this function before inserting a breakpoint, or when the previous or next code address is needed. Returns the adjusted code address for a given code address for a given device.
CUDBGResult ( *getBlockDim )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* blockDim ): Get the number of threads in the given block.
CUDBGResult ( *getClusterDim )( uint32_t dev, uint64_t gridId64, CuDim3* clusterDim ): Get the number of blocks in the given cluster.
CUDBGResult ( *getConstBankAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t bank, uint32_t offset, uint64_t* address ): Convert constant bank number and offset into GPU VA.
CUDBGResult ( *getDeviceName )( uint32_t dev, char* buf, uint32_t sz ): Get the device name string.
CUDBGResult ( *getDevicePCIBusInfo )( uint32_t devId, uint32_t* pciBusId, uint32_t* pciDevId ): Get PCI bus and device ids associated with device devId.
CUDBGResult ( *getDeviceType )( uint32_t dev, char* buf, uint32_t sz ): Get the string description of the device.
CUDBGResult ( *getElfImage )( uint32_t dev, uint32_t sm, uint32_t wp, bool relocated, void* *elfImage, uint64_t* size ): Get the relocated or non-relocated ELF image and size for the grid on the given device.
CUDBGResult ( *getElfImage32 )( uint32_t dev, uint32_t sm, uint32_t wp, bool relocated, void* *elfImage, uint32_t* size ): Get the relocated or non-relocated ELF image and size for the grid on the given device.
CUDBGResult ( *getElfImageByHandle )( uint32_t devId, uint64_t handle, CUDBGElfImageType type, void* elfImage, uint64_t size ): Get the relocated or non-relocated ELF image for the given handle on the given device.
CUDBGResult ( *getErrorStringEx )( char* buf, uint32_t bufSz, uint32_t* msgSz ): Fills a user-provided buffer with an error message encoded as a null-terminated ASCII string. The error message is specific to the last failed API call and is invalidated after every API call.
CUDBGResult ( *getGridAttribute )( uint32_t dev, uint32_t sm, uint32_t wp, CUDBGAttribute attr, uint64_t* value ): Get the value of a grid attribute.
CUDBGResult ( *getGridAttributes )( uint32_t dev, uint32_t sm, uint32_t wp, CUDBGAttributeValuePair* pairs, uint32_t numPairs ): Get several grid attribute values in a single API call.
CUDBGResult ( *getGridDim )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* gridDim ): Get the number of blocks in the given grid.
CUDBGResult ( *getGridDim32 )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim2* gridDim ): Get the number of blocks in the given grid.
CUDBGResult ( *getGridInfo )( uint32_t dev, uint64_t gridId64, CUDBGGridInfo* gridInfo ): Get information about the specified grid. If the context of the grid has already been destroyed, the function will return CUDBG_ERROR_INVALID_GRID, although the grid id is correct.
CUDBGResult ( *getGridInfo55 )( uint32_t dev, uint64_t gridId64, CUDBGGridInfo55* gridInfo ): Get information about the specified grid. If the context of the grid has already been destroyed, the function will return CUDBG_ERROR_INVALID_GRID, although the grid id is correct.
CUDBGResult ( *getGridStatus )( uint32_t dev, uint64_t gridId64, CUDBGGridStatus* status ): Check whether the grid corresponding to the given gridId is still present on the device.
CUDBGResult ( *getGridStatus50 )( uint32_t dev, uint32_t gridId, CUDBGGridStatus* status ): Check whether the grid corresponding to the given gridId is still present on the device.
CUDBGResult ( *getHostAddrFromDeviceAddr )( uint32_t dev, uint64_t device_addr, uint64_t* host_addr ): given a device virtual address, return a corresponding system memory virtual address.
CUDBGResult ( *getLoadedFunctionInfo )( uint32_t devId, uint64_t handle, CUDBGLoadedFunctionInfo* info, uint32_t startIndex, uint32_t numEntries ): Get the section number and address of loaded functions for a given module.
CUDBGResult ( *getLoadedFunctionInfo118 )( uint32_t devId, uint64_t handle, CUDBGLoadedFunctionInfo* info, uint32_t numEntries ): Get the section number and address of loaded functions for a given module.
CUDBGResult ( *getManagedMemoryRegionInfo )( uint64_t startAddress, CUDBGMemoryInfo* memoryInfo, uint32_t memoryInfo_size, uint32_t* numEntries ): Returns a sorted list of managed memory regions The sorted list of memory regions starts from a region containing the specified starting address. If the starting address is set to 0, a sorted list of managed memory regions is returned which starts from the managed memory region with the lowest start address.
CUDBGResult ( *getNextAsyncEvent50 )( CUDBGEvent50* event ): Copies the next available event in the asynchronous event queue into 'event' and removes it from the queue. The asynchronous event queue is held separate from the normal event queue, and does not require acknowledgement from the debug client.
CUDBGResult ( *getNextAsyncEvent55 )( CUDBGEvent55* event ): Copies the next available event in the asynchronous event queue into 'event' and removes it from the queue. The asynchronous event queue is held separate from the normal event queue, and does not require acknowledgement from the debug client.
CUDBGResult ( *getNextEvent )( CUDBGEventQueueType type, CUDBGEvent* event ): Copies the next available event into 'event' and removes it from the queue.
CUDBGResult ( *getNextEvent30 )( CUDBGEvent30* event ): Copies the next available event in the event queue into 'event' and removes it from the queue.
CUDBGResult ( *getNextEvent32 )( CUDBGEvent32* event ): Copies the next available event in the event queue into 'event' and removes it from the queue.
CUDBGResult ( *getNextEvent42 )( CUDBGEvent42* event ): Copies the next available event in the event queue into 'event' and removes it from the queue.
CUDBGResult ( *getNextSyncEvent50 )( CUDBGEvent50* event )
CUDBGResult ( *getNextSyncEvent55 )( CUDBGEvent55* event ): Copies the next available event in the synchronous event queue into 'event' and removes it from the queue.
CUDBGResult ( *getNumDevices )( uint32_t* numDev ): Get the number of installed CUDA devices.
CUDBGResult ( *getNumLanes )( uint32_t dev, uint32_t* numLanes ): Get the number of lanes per warp on the device.
CUDBGResult ( *getNumPredicates )( uint32_t dev, uint32_t* numPredicates ): Get the number of predicate registers per lane on the device.
CUDBGResult ( *getNumRegisters )( uint32_t dev, uint32_t* numRegs ): Get the number of registers per lane on the device.
CUDBGResult ( *getNumSMs )( uint32_t dev, uint32_t* numSMs ): Get the total number of SMs on the device.
CUDBGResult ( *getNumUniformPredicates )( uint32_t dev, uint32_t* numPredicates ): Get the number of uniform predicate registers per warp on the device.
CUDBGResult ( *getNumUniformRegisters )( uint32_t dev, uint32_t* numRegs ): Get the number of uniform registers per warp on the device.
CUDBGResult ( *getNumWarps )( uint32_t dev, uint32_t* numWarps ): Get the number of warps per SM on the device.
CUDBGResult ( *getPhysicalRegister30 )( uint64_t pc, char* reg, uint32_t* buf, uint32_t sz, uint32_t* numPhysRegs, CUDBGRegClass* regClass ): Get the physical register number(s) assigned to a virtual register name 'reg' at a given PC, if 'reg' is live at that PC.
CUDBGResult ( *getPhysicalRegister40 )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t pc, char* reg, uint32_t* buf, uint32_t sz, uint32_t* numPhysRegs, CUDBGRegClass* regClass ): Get the physical register number(s) assigned to a virtual register name 'reg' at a given PC, if 'reg' is live at that PC.
CUDBGResult ( *getSmType )( uint32_t dev, char* buf, uint32_t sz ): Get the SM type of the device.
CUDBGResult ( *getTID )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* tid ): Get the ID of the Linux thread hosting the context of the grid.
CUDBGResult ( *initialize )( ): Initialize the API.
CUDBGResult ( *initializeAttachStub )( ): Initialize the attach stub.
CUDBGResult ( *isDeviceCodeAddress )( uintptr_t addr, bool* isDeviceAddress ): Determines whether a virtual address resides within device code.
CUDBGResult ( *isDeviceCodeAddress55 )( uintptr_t addr, bool* isDeviceAddress ): Determines whether a virtual address resides within device code. This API is strongly deprecated. Use CUDBGAPI_st::isDeviceCodeAddress instead.
CUDBGResult ( *lookupDeviceCodeSymbol )( char* symName, bool* symFound, uintptr_t* symAddr ): Determines whether a symbol represents a function in device code and returns its virtual address.
CUDBGResult ( *memcheckReadErrorAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t* address, ptxStorageKind* storage ): Get the address that memcheck detected an error on.
CUDBGResult ( *readActiveLanes )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* activeLanesMask ): Reads the bitmask of active lanes on a valid warp.
CUDBGResult ( *readBlockIdx )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* blockIdx ): Reads the CUDA block index running on a valid warp.
CUDBGResult ( *readBlockIdx32 )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim2* blockIdx ): Reads the two-dimensional CUDA block index running on a valid warp.
CUDBGResult ( *readBrokenWarps )( uint32_t dev, uint32_t sm, uint64_t* brokenWarpsMask ): Reads the bitmask of warps that are at a breakpoint on a given SM.
CUDBGResult ( *readCCRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t* val ): Reads the hardware CC register.
CUDBGResult ( *readCallDepth )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t* depth ): Reads the call depth (number of calls) for a given lane.
CUDBGResult ( *readCallDepth32 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* depth ): Reads the call depth (number of calls) for a given warp.
CUDBGResult ( *readClusterIdx )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* clusterIdx ): Reads the CUDA cluster index running on a valid warp.
CUDBGResult ( *readCodeMemory )( uint32_t dev, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the code memory segment.
CUDBGResult ( *readConstMemory )( uint32_t dev, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the constant memory segment.
CUDBGResult ( *readDeviceExceptionState )( uint32_t devId, uint64_t* mask, uint32_t numWords ): Get the exception state of the SMs on the device.
CUDBGResult ( *readDeviceExceptionState80 )( uint32_t devId, uint64_t* exceptionSMMask ): Get the exception state of the SMs on the device.
CUDBGResult ( *readErrorPC )( uint32_t devId, uint32_t sm, uint32_t wp, uint64_t* errorPC, bool* errorPCValid ): Get the hardware reported error PC if it exists.
CUDBGResult ( *readGenericMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, void* buf, uint32_t sz ): Reads content at an address in the generic address space. This function determines if the given address falls into the local, shared, or global memory window. It then accesses memory taking into account the hardware co-ordinates provided as inputs.
CUDBGResult ( *readGlobalMemory )( uint64_t addr, void* buf, uint32_t sz ): Reads content at an address in the global address space. If the address is valid on more than one device and one of those devices does not support UVA, an error is returned.
CUDBGResult ( *readGlobalMemory31 )( uint32_t dev, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the global memory segment.
CUDBGResult ( *readGlobalMemory55 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the global memory segment (entire 40-bit VA on Fermi+).
CUDBGResult ( *readGridId )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t* gridId64 ): Reads the 64-bit CUDA grid index running on a valid warp.
CUDBGResult ( *readGridId50 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* gridId ): Reads the CUDA grid index running on a valid warp.
CUDBGResult ( *readLaneException )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, CUDBGException_t* exception ): Reads the exception type for a given lane.
CUDBGResult ( *readLaneStatus )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, bool* error ): Reads the status of the given lane. For specific error values, use readLaneException.
CUDBGResult ( *readLocalMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the local memory segment.
CUDBGResult ( *readPC )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t* pc ): Reads the PC on the given active lane.
CUDBGResult ( *readParamMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the param memory segment.
CUDBGResult ( *readPinnedMemory )( uint64_t addr, void* buf, uint32_t sz ): Reads content at pinned address in system memory.
CUDBGResult ( *readPredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t predicates_size, uint32_t* predicates ): Reads content of hardware predicate registers.
CUDBGResult ( *readRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t regno, uint32_t* val ): Reads content of a hardware register.
CUDBGResult ( *readRegisterRange )( uint32_t devId, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t index, uint32_t registers_size, uint32_t* registers ): Reads content of a hardware range of hardware registers.
CUDBGResult ( *readReturnAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t level, uint64_t* ra ): Reads the physical return address for a call level.
CUDBGResult ( *readReturnAddress32 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t level, uint64_t* ra ): Reads the physical return address for a call level.
CUDBGResult ( *readSharedMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, void* buf, uint32_t sz ): Reads content at address in the shared memory segment.
CUDBGResult ( *readSyscallCallDepth )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t* depth ): Reads the call depth of syscalls for a given lane.
CUDBGResult ( *readTextureMemory )( uint32_t devId, uint32_t vsm, uint32_t wp, uint32_t id, uint32_t dim, uint32_t* coords, void* buf, uint32_t sz ): This method is no longer supported since CUDA 12.0.
CUDBGResult ( *readTextureMemoryBindless )( uint32_t devId, uint32_t vsm, uint32_t wp, uint32_t texSymtabIndex, uint32_t dim, uint32_t* coords, void* buf, uint32_t sz ): This method is no longer supported since CUDA 12.0.
CUDBGResult ( *readThreadIdx )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, CuDim3* threadIdx ): Reads the CUDA thread index running on valid lane.
CUDBGResult ( *readUniformPredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t predicates_size, uint32_t* predicates ): Reads contents of uniform predicate registers.
CUDBGResult ( *readUniformRegisterRange )( uint32_t devId, uint32_t sm, uint32_t wp, uint32_t regno, uint32_t registers_size, uint32_t* registers ): Reads a range of uniform registers.
CUDBGResult ( *readValidLanes )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* validLanesMask ): Reads the bitmask of valid lanes on a given warp.
CUDBGResult ( *readValidWarps )( uint32_t dev, uint32_t sm, uint64_t* validWarpsMask ): Reads the bitmask of valid warps on a given SM.
CUDBGResult ( *readVirtualPC )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t* pc ): Reads the virtual PC on the given active lane.
CUDBGResult ( *readVirtualReturnAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t level, uint64_t* ra ): Reads the virtual return address for a call level.
CUDBGResult ( *readVirtualReturnAddress32 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t level, uint64_t* ra ): Reads the virtual return address for a call level.
CUDBGResult ( *readWarpState )( uint32_t dev, uint32_t sm, uint32_t wp, CUDBGWarpState* state ): Get state of a given warp.
CUDBGResult ( *readWarpState60 )( uint32_t devId, uint32_t sm, uint32_t wp, CUDBGWarpState60* state ): Get state of a given warp.
CUDBGResult ( *requestCleanupOnDetach )( uint32_t appResumeFlag ): Request for cleanup of driver state when detaching.
CUDBGResult ( *requestCleanupOnDetach55 )( ): Request for cleanup of driver state when detaching.
CUDBGResult ( *resumeDevice )( uint32_t dev ): Resume a suspended CUDA device.
CUDBGResult ( *resumeWarpsUntilPC )( uint32_t devId, uint32_t sm, uint64_t warpMask, uint64_t virtPC ): Inserts a temporary breakpoint at the specified virtual PC, and resumes all warps in the specified bitmask on a given SM. As compared to CUDBGAPI_st::resumeDevice, CUDBGAPI_st::resumeWarpsUntilPC provides finer-grain control by resuming a selected set of warps on the same SM. The main intended usage is to accelerate the single-stepping process when the target PC is known in advance. Instead of single-stepping each warp individually until the target PC is hit, the client can issue this API. When this API is used, errors within CUDA kernels will no longer be reported precisely. In the situation where resuming warps is not possible, this API will return CUDBG_ERROR_WARP_RESUME_NOT_POSSIBLE. The client should then fall back to using CUDBGAPI_st::singleStepWarp or CUDBGAPI_st::resumeDevice.
CUDBGResult ( *setBreakpoint )( uint32_t dev, uint64_t addr ): Sets a breakpoint at the given instruction address for the given device. Before setting a breakpoint, CUDBGAPI_st::getAdjustedCodeAddress should be called to get the adjusted breakpoint address.
CUDBGResult ( *setBreakpoint31 )( uint64_t addr ): Sets a breakpoint at the given instruction address.
CUDBGResult ( *setKernelLaunchNotificationMode )( CUDBGKernelLaunchNotifyMode mode ): Set the launch notification policy.
CUDBGResult ( *setNotifyNewEventCallback )( CUDBGNotifyNewEventCallback callback ): Provides the API with the function to call to notify the debugger of a new application or device event.
CUDBGResult ( *setNotifyNewEventCallback31 )( CUDBGNotifyNewEventCallback31 callback, void* data ): Provides the API with the function to call to notify the debugger of a new application or device event.
CUDBGResult ( *setNotifyNewEventCallback40 )( CUDBGNotifyNewEventCallback40 callback ): Provides the API with the function to call to notify the debugger of a new application or device event.
CUDBGResult ( *singleStepWarp )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t nsteps, uint64_t* warpMask ): Single step an individual warp nsteps times on a suspended CUDA device. Only the last instruction in a range should be a control flow instruction.
CUDBGResult ( *singleStepWarp40 )( uint32_t dev, uint32_t sm, uint32_t wp ): Single step an individual warp on a suspended CUDA device.
CUDBGResult ( *singleStepWarp41 )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t* warpMask ): Single step an individual warp on a suspended CUDA device.
CUDBGResult ( *suspendDevice )( uint32_t dev ): Suspends a running CUDA device.
CUDBGResult ( *unsetBreakpoint )( uint32_t dev, uint64_t addr ): Unsets a breakpoint at the given instruction address for the given device.
CUDBGResult ( *unsetBreakpoint31 )( uint64_t addr ): Unsets a breakpoint at the given instruction address.
CUDBGResult ( *writeCCRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t val ): Writes the hardware CC register.
CUDBGResult ( *writeGenericMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, const void* buf, uint32_t sz ): Writes content to an address in the generic address space. This function determines if the given address falls into the local, shared, or global memory window. It then accesses memory taking into account the hardware co-ordinates provided as inputs.
CUDBGResult ( *writeGlobalMemory )( uint64_t addr, const void* buf, uint32_t sz ): Writes content to an address in the global address space. If the address is valid on more than one device and one of those devices does not support UVA, an error is returned.
CUDBGResult ( *writeGlobalMemory31 )( uint32_t dev, uint64_t addr, const void* buf, uint32_t sz ): Writes content to address in the global memory segment.
CUDBGResult ( *writeGlobalMemory55 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, const void* buf, uint32_t sz ): Writes content to address in the global memory segment (entire 40-bit VA on Fermi+).
CUDBGResult ( *writeLocalMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, const void* buf, uint32_t sz ): Writes content to address in the local memory segment.
CUDBGResult ( *writeParamMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, const void* buf, uint32_t sz ): Writes content to address in the param memory segment.
CUDBGResult ( *writePinnedMemory )( uint64_t addr, const void* buf, uint32_t sz ): Writes content to pinned address in system memory.
CUDBGResult ( *writePredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t predicates_size, const uint32_t* predicates ): Writes content to hardware predicate registers.
CUDBGResult ( *writeRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t regno, uint32_t val ): Writes content to a hardware register.
CUDBGResult ( *writeSharedMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, const void* buf, uint32_t sz ): Writes content to address in the shared memory segment.
CUDBGResult ( *writeUniformPredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t predicates_size, const uint32_t* predicates ): Writes to uniform predicate registers.
CUDBGResult ( *writeUniformRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t regno, uint32_t val ): Writes content to a uniform register.

变量

CUDBGResult ( *CUDBGAPI_st::acknowledgeEvent30 )( CUDBGEvent30* event )

通知调试器API该事件已处理完毕。自CUDA 3.0起。

参数

event: - pointer to the event that has been processed

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::acknowledgeEvents42 )( )

通知调试器API同步事件已处理完毕。自CUDA 3.1起。

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::acknowledgeSyncEvents )( )

通知调试器API同步事件已处理完毕。自CUDA 5.0起。

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::clearAttachState )( )

在分离前清除特定附加状态。自CUDA 5.0起。

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::disassemble )( uint32_t dev, uint64_t addr, uint32_t* instSize, char* buf, uint32_t sz )

反汇编指定指令地址处的指令。自CUDA 3.0起支持。

参数

dev: - device index
addr: - instruction address
instSize: - instruction size (32 or 64 bits)
buf: - disassembled instruction buffer
sz: - disassembled instruction buffer size

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::finalize )( )

完成API并释放所有内存。自CUDA 3.0起。

另请参阅：

initialize

CUDBG_SUCCESS, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_COMMUNICATION_FAILURE, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::generateCoredump )( const char* filename, CUDBGCoredumpGenerationFlags flags )

为当前GPU状态生成核心转储文件。自CUDA 12.3起

参数

filename: - target coredump file name
flags: - coredump generation flags/options

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_NOT_SUPPORTED

CUDBGResult ( *CUDBGAPI_st::getAdjustedCodeAddress )( uint32_t devId, uint64_t address, uint64_t* adjustedAddress, CUDBGAdjAddrAction adjAction )

客户端在插入断点或需要获取前一个/下一个代码地址时，必须调用此函数。该函数会返回针对指定设备调整后的给定代码地址。自CUDA 5.5版本起支持此功能。

另请参阅：

unsetBreakpoint

参数

devId: - the device index
address
adjustedAddress: - adjusted address
adjAction: - whether the adjusted next, previous or current address is needed

CUDBG_SUCCESS, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_INVALID_ADDRESS, CUDBG_ERROR_INVALID_DEVICE

CUDBGResult ( *CUDBGAPI_st::getBlockDim )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* blockDim )

获取给定块中的线程数。自CUDA 3.0起。

另请参阅：

getGridDim

参数

dev: - device index
sm: - SM index
wp: - warp index
blockDim: - the returned number of threads in the block

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getClusterDim )( uint32_t dev, uint64_t gridId64, CuDim3* clusterDim )

获取给定集群中的块数量。自 CUDA 12.0 起。

另请参阅：

getBlockDim

getGridDim

参数

dev: - device index
gridId64: - grid ID
clusterDim: - the returned number of blocks in the cluster

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getConstBankAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t bank, uint32_t offset, uint64_t* address )

将常量存储区编号和偏移量转换为GPU虚拟地址。自CUDA 12.3起

参数

dev: - device index
sm: - SM index
wp: - warp index
bank: - constant bank number
offset: - offset within the bank
address: - (output) GPU VA

CUDBG_ERROR_NOT_SUPPORTED

CUDBGResult ( *CUDBGAPI_st::getDeviceName )( uint32_t dev, char* buf, uint32_t sz )

获取设备名称字符串。自CUDA 6.5起。

另请参阅：

获取SM类型

getDeviceType

参数

dev: - device index
buf: - the destination buffer
sz: - the size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_BUFFER_TOO_SMALL, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getDevicePCIBusInfo )( uint32_t devId, uint32_t* pciBusId, uint32_t* pciDevId )

获取与设备devId关联的PCI总线和设备ID。

参数

devId: - the cuda device id
pciBusId: - pointer where corresponding PCI BUS ID would be stored
pciDevId: - pointer where corresponding PCI DEVICE ID would be stored

CUDBG_ERROR_INVALID_ARGS, CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE

CUDBGResult ( *CUDBGAPI_st::getDeviceType )( uint32_t dev, char* buf, uint32_t sz )

获取设备的字符串描述。自CUDA 3.0起。

另请参阅：

获取SM类型

参数

dev: - device index
buf: - the destination buffer
sz: - the size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_BUFFER_TOO_SMALL, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getElfImage )( uint32_t dev, uint32_t sm, uint32_t wp, bool relocated, void* *elfImage, uint64_t* size )

获取指定设备上网格的重定位或非重定位ELF镜像及其大小。自CUDA 4.0起支持。

参数

dev: - device index
sm: - SM index
wp: - warp index
relocated: - set to true to specify the relocated ELF image, false otherwise
*elfImage: - pointer to the ELF image
size: - size of the ELF image (64 bits)

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getElfImage32 )( uint32_t dev, uint32_t sm, uint32_t wp, bool relocated, void* *elfImage, uint32_t* size )

获取指定设备上网格的重定位或非重定位ELF映像及其大小。自CUDA 3.0起支持。

参数

dev: - device index
sm: - SM index
wp: - warp index
relocated: - set to true to specify the relocated ELF image, false otherwise
*elfImage: - pointer to the ELF image
size: - size of the ELF image (32 bits)

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getElfImageByHandle )( uint32_t devId, uint64_t handle, CUDBGElfImageType type, void* elfImage, uint64_t size )

获取给定设备上指定句柄的重定位或非重定位ELF映像。该句柄由ELF映像加载通知事件提供。

自 CUDA 6.0 起。

参数

devId: - device index
handle: - elf image handle
type: - type of the requested ELF image
elfImage: - pointer to the ELF image
size

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getErrorStringEx )( char* buf, uint32_t bufSz, uint32_t* msgSz )

使用以空字符结尾的ASCII字符串编码的错误消息填充用户提供的缓冲区。该错误消息针对最近失败的API调用，并在每次API调用后失效。自CUDA 12.2起。

另请参阅：

获取错误字符串

参数

buf: - the destination buffer
bufSz: - the size of the destination buffer in bytes
msgSz: - the size of an error message including the terminating null character.

CUDBG_SUCCESS, CUDBG_ERROR_BUFFER_TOO_SMALL CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getGridAttribute )( uint32_t dev, uint32_t sm, uint32_t wp, CUDBGAttribute attr, uint64_t* value )

获取网格属性的值。自CUDA 3.1起。

参数

dev: - device index
sm: - SM index
wp: - warp index
attr: - the attribute
value: - the returned value of the attribute

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_INVALID_ATTRIBUTE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getGridAttributes )( uint32_t dev, uint32_t sm, uint32_t wp, CUDBGAttributeValuePair* pairs, uint32_t numPairs )

通过单次API调用获取多个网格属性值。自CUDA 3.1起支持。

参数

dev: - device index
sm: - SM index
wp: - warp index
pairs: - array of attribute/value pairs
numPairs: - the number of attribute/values pairs in the array

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_INVALID_ATTRIBUTE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getGridDim )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* gridDim )

获取给定网格中的块数量。自CUDA 4.0起。

另请参阅：

getBlockDim

参数

dev: - device index
sm: - SM index
wp: - warp index
gridDim: - the returned number of blocks in the grid

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getGridDim32 )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim2* gridDim )

获取给定网格中的块数量。自CUDA 3.0起。

另请参阅：

getBlockDim

参数

dev: - device index
sm: - SM index
wp: - warp index
gridDim: - the returned number of blocks in the grid

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getGridInfo )( uint32_t dev, uint64_t gridId64, CUDBGGridInfo* gridInfo )

获取指定网格(grid)的信息。如果该网格的上下文已被销毁，即使网格ID正确，函数也将返回CUDBG_ERROR_INVALID_GRID。自CUDA 12.0起生效。

参数

dev
gridId64
gridInfo: - pointer to a client allocated structure in which grid info will be returned.

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::getGridInfo55 )( uint32_t dev, uint64_t gridId64, CUDBGGridInfo55* gridInfo )

获取指定网格(grid)的信息。如果该网格的上下文已被销毁，即使网格ID正确，函数也将返回CUDBG_ERROR_INVALID_GRID。自CUDA 5.5版本起生效。

参数

dev
gridId64
gridInfo: - pointer to a client allocated structure in which grid info will be returned.

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::getGridStatus )( uint32_t dev, uint64_t gridId64, CUDBGGridStatus* status )

检查给定gridId对应的网格是否仍存在于设备上。自CUDA 5.5起。

参数

dev
gridId64: - 64-bit grid ID
status: - enum indicating whether the grid status is INVALID, PENDING, ACTIVE, SLEEPING, TERMINATED or UNDETERMINED

CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_INTERNAL

CUDBGResult ( *CUDBGAPI_st::getGridStatus50 )( uint32_t dev, uint32_t gridId, CUDBGGridStatus* status )

检查给定gridId对应的网格是否仍存在于设备上。自CUDA 5.0起。

参数

dev
gridId: - grid ID
status: - enum indicating whether the grid status is INVALID, PENDING, ACTIVE, SLEEPING, TERMINATED or UNDETERMINED

CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_INTERNAL

CUDBGResult ( *CUDBGAPI_st::getHostAddrFromDeviceAddr )( uint32_t dev, uint64_t device_addr, uint64_t* host_addr )

给定一个设备虚拟地址，返回对应的系统内存虚拟地址。自CUDA 4.1起。

另请参阅：

readGenericMemory

writeGenericMemory

参数

dev: - device index
device_addr: - device memory address
host_addr: - returned system memory address

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_CONTEXT, CUDBG_ERROR_INVALID_MEMORY_SEGMENT

CUDBGResult ( *CUDBGAPI_st::getLoadedFunctionInfo )( uint32_t devId, uint64_t handle, CUDBGLoadedFunctionInfo* info, uint32_t startIndex, uint32_t numEntries )

获取给定模块中已加载函数的节编号和地址。自CUDA 11.8起

参数

devId
handle: - ELF/cubin image handle
info
startIndex
numEntries: - number of function load entries to read

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_NOT_SUPPORTED

CUDBGResult ( *CUDBGAPI_st::getLoadedFunctionInfo118 )( uint32_t devId, uint64_t handle, CUDBGLoadedFunctionInfo* info, uint32_t numEntries )

获取给定模块中已加载函数的节编号和地址。自CUDA 11.8起

参数

devId
handle: - ELF/cubin image handle
info
numEntries: - number of function load entries to read

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_NOT_SUPPORTED

CUDBGResult ( *CUDBGAPI_st::getManagedMemoryRegionInfo )( uint64_t startAddress, CUDBGMemoryInfo* memoryInfo, uint32_t memoryInfo_size, uint32_t* numEntries )

返回一个已排序的托管内存区域列表。排序后的内存区域列表从包含指定起始地址的区域开始。如果起始地址设置为0，则返回从最低起始地址的托管内存区域开始的排序列表。自CUDA 6.0起支持此功能。

参数

startAddress: - The address that the first region in the list must contain. If the starting address is set to 0, the list of managed memory regions returned starts from the managed memory region with the lowest start address.
memoryInfo: - Client-allocated array of memory region records of type CUDBGMemoryInfo.
memoryInfo_size: - Number of records of type CUDBGMemoryInfo that memoryInfo can hold.
numEntries: - Pointer to a client-allocated variable holding the number of valid entries retured in memoryInfo. Valid entries are continguous and start from memoryInfo[0].

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_ADDRESS, CUDBG_ERROR_INTERNAL

CUDBGResult ( *CUDBGAPI_st::getNextAsyncEvent50 )( CUDBGEvent50* event )

将异步事件队列中的下一个可用事件复制到'event'中，并将其从队列中移除。异步事件队列与普通事件队列分开维护，不需要调试客户端的确认。自CUDA 5.0起。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextAsyncEvent55 )( CUDBGEvent55* event )

将异步事件队列中的下一个可用事件复制到'event'中，并将其从队列中移除。异步事件队列与常规事件队列分开维护，不需要调试客户端的确认。自CUDA 5.5起。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextEvent )( CUDBGEventQueueType type, CUDBGEvent* event )

将下一个可用事件复制到'event'中，并将其从队列中移除。自CUDA 6.0起。

参数

type: - application event queue type
event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextEvent30 )( CUDBGEvent30* event )

将事件队列中的下一个可用事件复制到'event'中，并将其从队列中移除。自CUDA 3.0起。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextEvent32 )( CUDBGEvent32* event )

将事件队列中的下一个可用事件复制到'event'中，并将其从队列中移除。自CUDA 3.1版本起支持。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextEvent42 )( CUDBGEvent42* event )

将事件队列中的下一个可用事件复制到'event'中，并将其从队列中移除。自CUDA 4.0起。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextSyncEvent50 )( CUDBGEvent50* event )

自 CUDA 5.0 起。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNextSyncEvent55 )( CUDBGEvent55* event )

将同步事件队列中的下一个可用事件复制到'event'中，并将其从队列中移除。自CUDA 5.5起。

参数

event: - pointer to an event container where to copy the event parameters

CUDBG_SUCCESS, CUDBG_ERROR_NO_EVENT_AVAILABLE, CUDBG_ERROR_INVALID_ARGS

CUDBGResult ( *CUDBGAPI_st::getNumDevices )( uint32_t* numDev )

获取已安装的CUDA设备数量。自CUDA 3.0起。

另请参阅：

参数

numDev: - the returned number of devices

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumLanes )( uint32_t dev, uint32_t* numLanes )

获取设备上每个warp的lane数量。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
numLanes: - the returned number of lanes

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumPredicates )( uint32_t dev, uint32_t* numPredicates )

获取设备上每个通道的谓词寄存器数量。自CUDA 6.5起。

另请参阅：

参数

dev: - device index
numPredicates: - the returned number of predicate registers

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumRegisters )( uint32_t dev, uint32_t* numRegs )

获取设备上每个通道的寄存器数量。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
numRegs: - the returned number of registers

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumSMs )( uint32_t dev, uint32_t* numSMs )

获取设备上的SM总数。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
numSMs: - the returned number of SMs

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumUniformPredicates )( uint32_t dev, uint32_t* numPredicates )

获取设备上每个warp的统一谓词寄存器数量。自CUDA 10.0起。

另请参阅：

getNumUniformPredicates

参数

dev: - device index
numPredicates: - the returned number of uniform predicate registers

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumUniformRegisters )( uint32_t dev, uint32_t* numRegs )

获取设备上每个warp的统一寄存器数量。自CUDA 10.0起。

另请参阅：

getNumRegisters

参数

dev: - device index
numRegs: - the returned number of uniform registers

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getNumWarps )( uint32_t dev, uint32_t* numWarps )

获取设备上每个SM的warp数量。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
numWarps: - the returned number of warps

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getPhysicalRegister30 )( uint64_t pc, char* reg, uint32_t* buf, uint32_t sz, uint32_t* numPhysRegs, CUDBGRegClass* regClass )

获取在给定程序计数器(PC)位置分配给虚拟寄存器名称'reg'的物理寄存器编号，前提是该寄存器在该PC位置处于活跃状态。自CUDA 3.0起支持此功能。

参数

pc: - Program counter
reg: - virtual register index
buf: - physical register name(s)
sz: - the physical register name buffer size
numPhysRegs: - number of physical register names returned
regClass: - the class of the physical registers

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UKNOWN_FUNCTION, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::getPhysicalRegister40 )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t pc, char* reg, uint32_t* buf, uint32_t sz, uint32_t* numPhysRegs, CUDBGRegClass* regClass )

获取在给定PC处分配给虚拟寄存器名称'reg'的物理寄存器编号（如果'reg'在该PC处是活跃的）。获取在给定PC处分配给虚拟寄存器名称'reg'的物理寄存器编号（如果'reg'在该PC处是活跃的）。如果一个虚拟寄存器名称映射到多个物理寄存器，则具有最低物理寄存器索引的物理寄存器将包含虚拟寄存器的最高位，而具有最高物理寄存器索引的物理寄存器将包含虚拟寄存器的最低位。

自 CUDA 3.1 起。

参数

dev: - device index
sm: - SM index
wp: - warp indx
pc: - Program counter
reg: - virtual register index
buf: - physical register name(s)
sz: - the physical register name buffer size
numPhysRegs: - number of physical register names returned
regClass: - the class of the physical registers

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UKNOWN_FUNCTION, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::getSmType )( uint32_t dev, char* buf, uint32_t sz )

获取设备的SM类型。自CUDA 3.0起。

另请参阅：

getDeviceType

参数

dev: - device index
buf: - the destination buffer
sz: - the size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_BUFFER_TOO_SMALL, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::getTID )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* tid )

获取托管网格上下文的Linux线程ID。自CUDA 3.0起。

参数

dev: - device index
sm: - SM index
wp: - warp index
tid: - the returned thread id

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::initialize )( )

初始化API。自CUDA 3.0起。

另请参阅：

finalize

CUDBG_SUCCESS, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::initializeAttachStub )( )

初始化附加存根。自 CUDA 5.0 起。

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::isDeviceCodeAddress )( uintptr_t addr, bool* isDeviceAddress )

判断虚拟地址是否位于设备代码内。自CUDA 3.0起。

参数

addr: - virtual address
isDeviceAddress: - true if address resides within device code

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UNINITIALIZED, CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::isDeviceCodeAddress55 )( uintptr_t addr, bool* isDeviceAddress )

判断一个虚拟地址是否位于设备代码中。此API已强烈不建议使用。请改用CUDBGAPI_st::isDeviceCodeAddress。自CUDA 3.0起。

参数

addr: - virtual address
isDeviceAddress: - true if address resides within device code

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UNINITIALIZED, CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::lookupDeviceCodeSymbol )( char* symName, bool* symFound, uintptr_t* symAddr )

确定一个符号是否表示设备代码中的函数并返回其虚拟地址。自CUDA 3.0起。

参数

symName: - symbol name
symFound: - set to true if the symbol is found
symAddr: - the symbol virtual address if found

CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_UNINITIALIZED, CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::memcheckReadErrorAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t* address, ptxStorageKind* storage )

获取memcheck检测到错误的地址。自CUDA 5.0起。

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
address: - returned address detected by memcheck
storage: - returned address class of address

CUDBG_ERROR_NOT_SUPPORTED,

CUDBGResult ( *CUDBGAPI_st::readActiveLanes )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* activeLanesMask )

读取有效线程束中活动通道的位掩码。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
activeLanesMask: - the returned bitmask of active lanes

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readBlockIdx )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* blockIdx )

读取运行在有效warp上的CUDA块索引。自CUDA 4.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
blockIdx: - the returned CUDA block index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readBlockIdx32 )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim2* blockIdx )

读取运行在有效warp上的二维CUDA块索引。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
blockIdx: - the returned CUDA block index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readBrokenWarps )( uint32_t dev, uint32_t sm, uint64_t* brokenWarpsMask )

读取指定SM上处于断点的warp位掩码。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
sm: - SM index
brokenWarpsMask: - the returned bitmask of broken warps

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readCCRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t* val )

读取硬件CC寄存器。自CUDA 6.5起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
val: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readCallDepth )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t* depth )

读取给定通道的调用深度（调用次数）。自CUDA 4.0起。

另请参阅：

readReturnAddress

readVirtualReturnAddress

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
depth: - the returned call depth

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readCallDepth32 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* depth )

读取给定warp的调用深度（调用次数）。自CUDA 3.1起支持。

另请参阅：

readReturnAddress32

readVirtualReturnAddress32

参数

dev: - device index
sm: - SM index
wp: - warp index
depth: - the returned call depth

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readClusterIdx )( uint32_t dev, uint32_t sm, uint32_t wp, CuDim3* clusterIdx )

读取运行在有效warp上的CUDA集群索引。自CUDA 12.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
clusterIdx: - the returned CUDA cluster index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readCodeMemory )( uint32_t dev, uint64_t addr, void* buf, uint32_t sz )

读取代码内存段中指定地址的内容。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::readConstMemory )( uint32_t dev, uint64_t addr, void* buf, uint32_t sz )

读取常量内存段中指定地址的内容。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::readDeviceExceptionState )( uint32_t devId, uint64_t* mask, uint32_t numWords )

获取设备上SM（流式多处理器）的异常状态。自CUDA 9.0起

另请参阅：

getNumSMs

参数

devId: - the cuda device id
mask: - Arbitrarily sized bit field containing a 1 at (1 << i) if SM i hit an exception
numWords

CUDBG_ERROR_INVALID_ARGS, CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE

CUDBGResult ( *CUDBGAPI_st::readDeviceExceptionState80 )( uint32_t devId, uint64_t* exceptionSMMask )

获取设备上SM（流式多处理器）的异常状态。自CUDA 5.5版本起支持

参数

devId: - the cuda device id
exceptionSMMask: - Bit field containing a 1 at (1 << i) if SM i hit an exception

CUDBG_ERROR_INVALID_ARGS, CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE

CUDBGResult ( *CUDBGAPI_st::readErrorPC )( uint32_t devId, uint32_t sm, uint32_t wp, uint64_t* errorPC, bool* errorPCValid )

获取硬件报告的错误PC（如果存在）。自CUDA 6.0起

参数

devId: - the device index
sm: - the SM index
wp
errorPC: - PC ofthe exception
errorPCValid: - boolean to indicate that the returned error PC is valid

CUDBG_SUCCESS CUDBG_ERROR_UNINITIALIZED CUDBG_ERROR_INVALID_DEVICE CUDBG_ERROR_INVALID_SM CUDBG_ERROR_INVALID_WARP CUDBG_ERROR_INVALID_ARGS CUDBG_ERROR_UNKNOWN_FUNCTION

CUDBGResult ( *CUDBGAPI_st::readGenericMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, void* buf, uint32_t sz )

读取通用地址空间中某个地址的内容。此函数会判断给定地址是否位于本地、共享或全局内存窗口内，然后根据提供的硬件坐标输入访问内存。自CUDA 6.0起支持该功能。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
addr: - memory address
buf: - buffer
sz

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED, CUDBG_ERROR_ADDRESS_NOT_IN_DEVICE_MEM

CUDBGResult ( *CUDBGAPI_st::readGlobalMemory )( uint64_t addr, void* buf, uint32_t sz )

读取全局地址空间中某个地址的内容。如果该地址在多个设备上有效且其中某个设备不支持UVA，则会返回错误。自CUDA 6.0起。

另请参阅：

参数

addr: - memory address
buf: - buffer
sz

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED, CUDBG_ERROR_INVALID_MEMORY_ACCESS, CUDBG_ERROR_ADDRESS_NOT_IN_DEVICE_MEM CUDBG_ERROR_AMBIGUOUS_MEMORY_ADDRESS_

CUDBGResult ( *CUDBGAPI_st::readGlobalMemory31 )( uint32_t dev, uint64_t addr, void* buf, uint32_t sz )

读取全局内存段中指定地址的内容。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::readGlobalMemory55 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, void* buf, uint32_t sz )

读取全局内存段中指定地址的内容（Fermi及以上架构支持完整的40位虚拟地址）。自CUDA 3.2版本起支持。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBGResult ( *CUDBGAPI_st::readGridId )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t* gridId64 )

读取运行在有效warp上的64位CUDA网格索引。自CUDA 5.5起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
gridId64

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readGridId50 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* gridId )

读取运行在有效warp上的CUDA网格索引。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
gridId: - the returned CUDA grid index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readLaneException )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, CUDBGException_t* exception )

读取给定通道的异常类型。自 CUDA 3.1 起。

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
exception: - the returned exception type

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readLaneStatus )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, bool* error )

读取给定通道的状态。如需获取具体的错误值，请使用readLaneException。自CUDA 3.0起支持该功能。

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
error: - true if there is an error

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readLocalMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, void* buf, uint32_t sz )

读取本地内存段中指定地址的内容。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBGResult ( *CUDBGAPI_st::readPC )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t* pc )

读取给定活动通道上的PC（程序计数器）。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
pc: - the returned PC

CUDBGResult ( *CUDBGAPI_st::readParamMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, void* buf, uint32_t sz )

读取参数内存段中指定地址的内容。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::readPinnedMemory )( uint64_t addr, void* buf, uint32_t sz )

读取系统内存中固定地址的内容。自CUDA 3.2起。

另请参阅：

参数

addr: - system memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_MEMORY_MAPPING_FAILED, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readPredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t predicates_size, uint32_t* predicates )

读取硬件谓词寄存器的内容。自CUDA 6.5起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
predicates_size: - number of predicate registers to read
predicates: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t regno, uint32_t* val )

读取硬件寄存器的内容。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
regno: - register index
val: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readRegisterRange )( uint32_t devId, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t index, uint32_t registers_size, uint32_t* registers )

读取硬件寄存器范围内内容。自CUDA 6.0起。

另请参阅：

参数

devId
sm: - SM index
wp: - warp index
ln: - lane index
index: - index of the first register to read
registers_size: - number of registers to read
registers: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readReturnAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t level, uint64_t* ra )

读取调用层级的物理返回地址。自CUDA 4.0起。

另请参阅：

readCallDepth

readVirtualReturnAddress

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
level: - the specified call level
ra: - the returned return address for level

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_INVALID_CALL_LEVEL, CUDBG_ERROR_ZERO_CALL_DEPTH, CUDBG_ERROR_UNKNOWN_FUNCTION, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readReturnAddress32 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t level, uint64_t* ra )

读取调用层级的物理返回地址。自CUDA 3.1起支持。

另请参阅：

readCallDepth32

readVirtualReturnAddress32

参数

dev: - device index
sm: - SM index
wp: - warp index
level: - the specified call level
ra: - the returned return address for level

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_INVALID_GRID, CUDBG_ERROR_INVALID_CALL_LEVEL, CUDBG_ERROR_ZERO_CALL_DEPTH, CUDBG_ERROR_UNKNOWN_FUNCTION, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readSharedMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, void* buf, uint32_t sz )

读取共享内存段中指定地址的内容。自CUDA 3.0起支持。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::readSyscallCallDepth )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t* depth )

读取给定通道的系统调用深度。自CUDA 4.1起。

另请参阅：

readReturnAddress

readVirtualReturnAddress

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
depth: - the returned call depth

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readTextureMemory )( uint32_t devId, uint32_t vsm, uint32_t wp, uint32_t id, uint32_t dim, uint32_t* coords, void* buf, uint32_t sz )

该方法自CUDA 12.0起不再受支持。

另请参阅：

参数

devId: - device index
vsm: - SM index
wp: - warp index
id: - texture id (the value of DW_AT_location attribute in the relocated ELF image)
dim: - texture dimension (1 to 4)
coords: - array of coordinates of size dim
buf: - result buffer
sz: - size of the buffer

CUDBG_ERROR_NOT_SUPPORTED,

CUDBGResult ( *CUDBGAPI_st::readTextureMemoryBindless )( uint32_t devId, uint32_t vsm, uint32_t wp, uint32_t texSymtabIndex, uint32_t dim, uint32_t* coords, void* buf, uint32_t sz )

该方法自CUDA 12.0起不再受支持。

另请参阅：

参数

devId: - device index
vsm: - SM index
wp: - warp index
texSymtabIndex: - global symbol table index of the texture symbol
dim: - texture dimension (1 to 4)
coords: - array of coordinates of size dim
buf: - result buffer
sz: - size of the buffer

CUDBG_ERROR_NOT_SUPPORTED

CUDBGResult ( *CUDBGAPI_st::readThreadIdx )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, CuDim3* threadIdx )

读取运行在有效通道上的CUDA线程索引。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
threadIdx: - the returned CUDA thread index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readUniformPredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t predicates_size, uint32_t* predicates )

读取统一谓词寄存器的内容。自 CUDA 10.0 起。

另请参阅：

readPredicates

参数

dev: - device index
sm: - SM index
wp: - warp index
predicates_size: - number of predicate registers to read
predicates: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readUniformRegisterRange )( uint32_t devId, uint32_t sm, uint32_t wp, uint32_t regno, uint32_t registers_size, uint32_t* registers )

读取一组统一寄存器。自 CUDA 10.0 起。

另请参阅：

readRegister

参数

devId
sm: - SM index
wp: - warp index
regno: - starting index into uniform register file
registers_size: - number of bytes to read
registers: - pointer to buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readValidLanes )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t* validLanesMask )

读取给定warp中有效通道的位掩码。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
validLanesMask: - the returned bitmask of valid lanes

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readValidWarps )( uint32_t dev, uint32_t sm, uint64_t* validWarpsMask )

读取给定SM上有效warp的位掩码。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
validWarpsMask: - the returned bitmask of valid warps

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::readVirtualPC )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t* pc )

读取指定活动通道上的虚拟PC。自CUDA 3.0起。

另请参阅：

readPC

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
pc: - the returned PC

CUDBGResult ( *CUDBGAPI_st::readVirtualReturnAddress )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t level, uint64_t* ra )

读取调用层级的虚拟返回地址。自CUDA 4.0起支持。

另请参阅：

readCallDepth

readReturnAddress

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
level: - the specified call level
ra: - the returned virtual return address for level

CUDBGResult ( *CUDBGAPI_st::readVirtualReturnAddress32 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t level, uint64_t* ra )

读取调用层级的虚拟返回地址。自CUDA 3.1起支持。

另请参阅：

readCallDepth32

readReturnAddress32

参数

dev: - device index
sm: - SM index
wp: - warp index
level: - the specified call level
ra: - the returned virtual return address for level

CUDBGResult ( *CUDBGAPI_st::readWarpState )( uint32_t dev, uint32_t sm, uint32_t wp, CUDBGWarpState* state )

获取指定warp的状态。自CUDA 12.0起支持。

参数

dev: - device index
sm: - SM index
wp: - warp index
state: - pointer to structure that contains warp status

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED,

CUDBGResult ( *CUDBGAPI_st::readWarpState60 )( uint32_t devId, uint32_t sm, uint32_t wp, CUDBGWarpState60* state )

获取指定warp的状态。自CUDA 6.0起。

参数

devId
sm: - SM index
wp: - warp index
state: - pointer to structure that contains warp status

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED,

CUDBGResult ( *CUDBGAPI_st::requestCleanupOnDetach )( uint32_t appResumeFlag )

请求在分离时清理驱动程序状态。自CUDA 6.0起。

参数

appResumeFlag: - value of CUDBG_RESUME_FOR_ATTACH_DETACH as read from the application's process space.

CUDBG_SUCCESS CUDBG_ERROR_COMMUNICATION_FAILURE CUDBG_ERROR_INVALID_ARGS CUDBG_ERROR_INTERNAL

CUDBGResult ( *CUDBGAPI_st::requestCleanupOnDetach55 )( )

请求在分离时清理驱动程序状态。自 CUDA 5.0 起。

CUDBG_SUCCESS CUDBG_ERROR_COMMUNICATION_FAILURE CUDBG_ERROR_INVALID_ARGS CUDBG_ERROR_INTERNAL

CUDBGResult ( *CUDBGAPI_st::resumeDevice )( uint32_t dev )

恢复一个被挂起的CUDA设备。自CUDA 3.0起。

另请参阅：

suspendDevice

singleStepWarp

参数

dev: - device index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_RUNNING_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::resumeWarpsUntilPC )( uint32_t devId, uint32_t sm, uint64_t warpMask, uint64_t virtPC )

在指定的虚拟PC处插入一个临时断点，并在给定的SM上恢复指定位掩码中的所有warp。与CUDBGAPI_st::resumeDevice相比，CUDBGAPI_st::resumeWarpsUntilPC通过在同一SM上恢复选定的warp集合提供了更精细的控制。其主要用途是当目标PC已知时加速单步执行过程。客户端可以调用此API，而不必逐个warp单步执行直到命中目标PC。使用此API时，CUDA内核中的错误将不再被精确报告。在无法恢复warp的情况下，此API将返回CUDBG_ERROR_WARP_RESUME_NOT_POSSIBLE。此时客户端应回退使用CUDBGAPI_st::singleStepWarp或CUDBGAPI_st::resumeDevice。自CUDA 6.0起支持此功能。

另请参阅：

resumeDevice

参数

devId: - device index
sm: - the SM index
warpMask: - the bitmask of warps to resume (1 = resume, 0 = do not resume)
virtPC: - the virtual PC where the temporary breakpoint will be inserted

CUDBG_SUCCESS CUDBG_ERROR_INVALID_ARGS CUDBG_ERROR_INVALID_DEVICE CUDBG_ERROR_INVALID_SM CUDBG_ERROR_INVALID_WARP_MASK CUDBG_ERROR_WARP_RESUME_NOT_POSSIBLE CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::setBreakpoint )( uint32_t dev, uint64_t addr )

在指定设备的给定指令地址处设置断点。在设置断点前，应先调用CUDBGAPI_st::getAdjustedCodeAddress获取调整后的断点地址。自CUDA 3.2版本起支持此功能。

另请参阅：

unsetBreakpoint

参数

dev: - the device index
addr: - instruction address

CUDBG_SUCCESS, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_INVALID_ADDRESS, CUDBG_ERROR_INVALID_DEVICE

CUDBGResult ( *CUDBGAPI_st::setBreakpoint31 )( uint64_t addr )

在给定的指令地址设置断点。自 CUDA 3.0 起支持。

另请参阅：

unsetBreakpoint31

参数

addr: - instruction address

CUDBG_SUCCESS, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_INVALID_ADDRESS

CUDBGResult ( *CUDBGAPI_st::setKernelLaunchNotificationMode )( CUDBGKernelLaunchNotifyMode mode )

设置启动通知策略。自CUDA 5.5起。

参数

mode: - mode to deliver kernel launch notifications in

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::setNotifyNewEventCallback )( CUDBGNotifyNewEventCallback callback )

提供API功能，用于通知调试器有新应用程序或设备事件。自CUDA 4.1起支持。

参数

callback: - the callback function

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::setNotifyNewEventCallback31 )( CUDBGNotifyNewEventCallback31 callback, void* data )

提供API功能，用于通知调试器有新应用程序或设备事件。自CUDA 3.0起。

参数

callback: - the callback function
data: - a pointer to be passed to the callback when called

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::setNotifyNewEventCallback40 )( CUDBGNotifyNewEventCallback40 callback )

提供API功能，用于通知调试器有新应用程序或设备事件。自CUDA 3.2起。

参数

callback: - the callback function

CUDBG_SUCCESS

CUDBGResult ( *CUDBGAPI_st::singleStepWarp )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t nsteps, uint64_t* warpMask )

在挂起的CUDA设备上单步执行单个warp nsteps次。范围中的最后一条指令应为控制流指令。自CUDA 7.5起。

另请参阅：

resumeDevice

suspendDevice

参数

dev: - device index
sm: - SM index
wp: - warp index
nsteps: - number of single steps
warpMask: - the warps that have been single-stepped

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_RUNNING_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::singleStepWarp40 )( uint32_t dev, uint32_t sm, uint32_t wp )

在挂起的CUDA设备上单步执行一个独立的warp。自CUDA 3.0起支持。

另请参阅：

resumeDevice

suspendDevice

singleStepWarp

参数

dev: - device index
sm: - SM index
wp: - warp index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_RUNNING_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_UNKNOWN, CUDBG_ERROR_WARP_RESUME_NOT_POSSIBLE

CUDBGResult ( *CUDBGAPI_st::singleStepWarp41 )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t* warpMask )

在挂起的CUDA设备上单步执行单个warp。自CUDA 4.1起支持。

另请参阅：

resumeDevice

suspendDevice

参数

dev: - device index
sm: - SM index
wp: - warp index
warpMask: - the warps that have been single-stepped

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_RUNNING_DEVICE, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_UNKNOWN

CUDBGResult ( *CUDBGAPI_st::suspendDevice )( uint32_t dev )

暂停正在运行的CUDA设备。自CUDA 3.0起支持。

另请参阅：

resumeDevice

singleStepWarp

参数

dev: - device index

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_RUNNING_DEVICE, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::unsetBreakpoint )( uint32_t dev, uint64_t addr )

在指定设备的给定指令地址处取消断点设置。自CUDA 3.2起支持。

另请参阅：

setBreakpoint

参数

dev: - the device index
addr: - instruction address

CUDBG_SUCCESS, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_INVALID_ADDRESS, CUDBG_ERROR_INVALID_DEVICE

CUDBGResult ( *CUDBGAPI_st::unsetBreakpoint31 )( uint64_t addr )

在给定的指令地址取消断点设置。自 CUDA 3.0 起支持。

另请参阅：

setBreakpoint31

参数

addr: - instruction address

CUDBG_SUCCESS, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::writeCCRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t val )

写入硬件CC寄存器。自CUDA 6.5起。

另请参阅：

写入常量内存

写入纹理内存

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
val: - value to write to the CC register

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::writeGenericMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, const void* buf, uint32_t sz )

将内容写入通用地址空间中的某个地址。此函数会判断给定地址是否位于本地、共享或全局内存窗口内，然后根据作为输入提供的硬件坐标访问内存。自CUDA 6.0起支持该功能。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
addr: - memory address
buf: - buffer
sz

CUDBGResult ( *CUDBGAPI_st::writeGlobalMemory )( uint64_t addr, const void* buf, uint32_t sz )

将内容写入全局地址空间中的某个地址。如果该地址在多个设备上有效，且其中某个设备不支持UVA，则会返回错误。自CUDA 6.0起。

另请参阅：

参数

addr: - memory address
buf: - buffer
sz

CUDBGResult ( *CUDBGAPI_st::writeGlobalMemory31 )( uint32_t dev, uint64_t addr, const void* buf, uint32_t sz )

将内容写入全局内存段中的地址。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBGResult ( *CUDBGAPI_st::writeGlobalMemory55 )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, const void* buf, uint32_t sz )

将内容写入全局内存段中的地址（Fermi+架构上为完整的40位虚拟地址）。自CUDA 3.2起支持该功能。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBGResult ( *CUDBGAPI_st::writeLocalMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint64_t addr, const void* buf, uint32_t sz )

将内容写入本地内存段的地址。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBGResult ( *CUDBGAPI_st::writeParamMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, const void* buf, uint32_t sz )

将内容写入参数内存段中的地址。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::writePinnedMemory )( uint64_t addr, const void* buf, uint32_t sz )

将内容写入系统内存中的固定地址。自CUDA 3.2起。

另请参阅：

参数

addr: - system memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_MEMORY_MAPPING_FAILED, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::writePredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t predicates_size, const uint32_t* predicates )

将内容写入硬件谓词寄存器。自CUDA 6.5起。

另请参阅：

写入常量内存

写入纹理内存

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
predicates_size: - number of predicate registers to write
predicates: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::writeRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t ln, uint32_t regno, uint32_t val )

将内容写入硬件寄存器。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
ln: - lane index
regno: - register index
val: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_LANE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::writeSharedMemory )( uint32_t dev, uint32_t sm, uint32_t wp, uint64_t addr, const void* buf, uint32_t sz )

将内容写入共享内存段中的地址。自CUDA 3.0起。

另请参阅：

参数

dev: - device index
sm: - SM index
wp: - warp index
addr: - memory address
buf: - buffer
sz: - size of the buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED, CUDBG_ERROR_MEMORY_MAPPING_FAILED

CUDBGResult ( *CUDBGAPI_st::writeUniformPredicates )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t predicates_size, const uint32_t* predicates )

写入统一谓词寄存器。自 CUDA 10.0 起。

另请参阅：

readUniformPredicate

writeRegister

参数

dev: - device index
sm: - SM index
wp: - warp index
predicates_size: - number of predicate registers to write
predicates: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED

CUDBGResult ( *CUDBGAPI_st::writeUniformRegister )( uint32_t dev, uint32_t sm, uint32_t wp, uint32_t regno, uint32_t val )

将内容写入统一寄存器。自 CUDA 10.0 起。

另请参阅：

writeRegister

readUniformRegisterRange

参数

dev: - device index
sm: - SM index
wp: - warp index
regno: - register index
val: - buffer

CUDBG_SUCCESS, CUDBG_ERROR_INVALID_ARGS, CUDBG_ERROR_INVALID_DEVICE, CUDBG_ERROR_INVALID_SM, CUDBG_ERROR_INVALID_WARP, CUDBG_ERROR_UNINITIALIZED