Device Management

Device Management#

HIP Runtime API Reference: Device Management

Collaboration diagram for Device Management:

Functions
hipError_t	hipDeviceSynchronize (void)
	Waits on all active streams on current device.

hipError_t	hipDeviceReset (void)
	The state of current device is discarded and updated to a fresh state.

hipError_t	hipSetDevice (int deviceId)
	Set default device to be used for subsequent hip API calls from this thread.

hipError_t	hipGetDevice (int *deviceId)
	Return the default device id for the calling host thread.

hipError_t	hipGetDeviceCount (int *count)
	Return number of compute-capable devices.

hipError_t	hipDeviceGetAttribute (int *pi, hipDeviceAttribute_t attr, int deviceId)
	Query for a specific device attribute.

hipError_t	hipDeviceGetDefaultMemPool (hipMemPool_t *mem_pool, int device)
	Returns the default memory pool of the specified device.

hipError_t	hipDeviceSetMemPool (int device, hipMemPool_t mem_pool)
	Sets the current memory pool of a device.

hipError_t	hipDeviceGetMemPool (hipMemPool_t *mem_pool, int device)
	Gets the current memory pool for the specified device.

hipError_t	hipGetDeviceProperties (hipDeviceProp_t *prop, int deviceId)
	Returns device properties.

hipError_t	hipDeviceSetCacheConfig (hipFuncCache_t cacheConfig)
	Set L1/Shared cache partition.

hipError_t	hipDeviceGetCacheConfig (hipFuncCache_t *cacheConfig)
	Get Cache configuration for a specific Device.

hipError_t	hipDeviceGetLimit (size_t *pValue, enum hipLimit_t limit)
	Get Resource limits of current device.

hipError_t	hipDeviceSetLimit (enum hipLimit_t limit, size_t value)
	Set Resource limits of current device.

hipError_t	hipDeviceGetSharedMemConfig (hipSharedMemConfig *pConfig)
	Returns bank width of shared memory for current device.

hipError_t	hipGetDeviceFlags (unsigned int *flags)
	Gets the flags set for current device.

hipError_t	hipDeviceSetSharedMemConfig (hipSharedMemConfig config)
	The bank width of shared memory on current device is set.

hipError_t	hipSetDeviceFlags (unsigned flags)
	The current device behavior is changed according the flags passed.

hipError_t	hipChooseDevice (int device, const hipDeviceProp_t prop)
	Device which matches hipDeviceProp_t is returned.

hipError_t	hipExtGetLinkTypeAndHopCount (int device1, int device2, uint32_t linktype, uint32_t hopcount)
	Returns the link type and hop count between two devices.

hipError_t	hipIpcGetMemHandle (hipIpcMemHandle_t handle, void devPtr)
	Gets an interprocess memory handle for an existing device memory allocation.

hipError_t	hipIpcOpenMemHandle (void **devPtr, hipIpcMemHandle_t handle, unsigned int flags)
	Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.

hipError_t	hipIpcCloseMemHandle (void *devPtr)
	Close memory mapped with hipIpcOpenMemHandle.

hipError_t	hipIpcGetEventHandle (hipIpcEventHandle_t *handle, hipEvent_t event)
	Gets an opaque interprocess handle for an event.

hipError_t	hipIpcOpenEventHandle (hipEvent_t *event, hipIpcEventHandle_t handle)
	Opens an interprocess event handles.

Detailed Description

This section describes the device management functions of HIP runtime API.

Function Documentation

◆ hipChooseDevice()

hipError_t hipChooseDevice	(	int *	device,
		const hipDeviceProp_t *	prop
	)

Device which matches hipDeviceProp_t is returned.

Parameters

[out]	device	ID
[in]	device	properties pointer

Returns: hipSuccess, hipErrorInvalidValue

◆ hipDeviceGetAttribute()

hipError_t hipDeviceGetAttribute	(	int *	pi,
		hipDeviceAttribute_t	attr,
		int	deviceId
	)

Query for a specific device attribute.

Parameters

[out]	pi	pointer to value to return
[in]	attr	attribute to query
[in]	deviceId	which device to query for information

Returns: hipSuccess, hipErrorInvalidDevice, hipErrorInvalidValue

◆ hipDeviceGetCacheConfig()

hipError_t hipDeviceGetCacheConfig ( hipFuncCache_t * cacheConfig )

Get Cache configuration for a specific Device.

Parameters

[out] cacheConfig

Returns: hipSuccess, hipErrorNotInitialized Note: AMD devices and some Nvidia GPUS do not support reconfigurable cache. This hint is ignored on those architectures.

◆ hipDeviceGetDefaultMemPool()

hipError_t hipDeviceGetDefaultMemPool	(	hipMemPool_t *	mem_pool,
		int	device
	)

Returns the default memory pool of the specified device.

Parameters

[out]	mem_pool	Default memory pool to return
[in]	device	Device index for query the default memory pool

Returns: #chipSuccess, hipErrorInvalidDevice, hipErrorInvalidValue, hipErrorNotSupported

See also: hipDeviceGetDefaultMemPool, hipMallocAsync, hipMemPoolTrimTo, hipMemPoolGetAttribute, hipDeviceSetMemPool, hipMemPoolSetAttribute, hipMemPoolSetAccess, hipMemPoolGetAccess

Warning: : This API is marked as beta, meaning, while this is feature complete, it is still open to changes and may have outstanding issues.

◆ hipDeviceGetLimit()

hipError_t hipDeviceGetLimit	(	size_t *	pValue,
		enum hipLimit_t	limit
	)

Get Resource limits of current device.

Parameters

[out]	pValue
[in]	limit

Returns: hipSuccess, hipErrorUnsupportedLimit, hipErrorInvalidValue Note: Currently, only hipLimitMallocHeapSize is available

◆ hipDeviceGetMemPool()

hipError_t hipDeviceGetMemPool	(	hipMemPool_t *	mem_pool,
		int	device
	)

Gets the current memory pool for the specified device.

Returns the last pool provided to hipDeviceSetMemPool for this device or the device's default memory pool if hipDeviceSetMemPool has never been called. By default the current mempool is the default mempool for a device, otherwise the returned pool must have been set with hipDeviceSetMemPool.

Parameters

[out]	mem_pool	Current memory pool on the specified device
[in]	device	Device index to query the current memory pool

Returns: hipSuccess, hipErrorInvalidValue, hipErrorNotSupported

See also: hipDeviceGetDefaultMemPool, hipMallocAsync, hipMemPoolTrimTo, hipMemPoolGetAttribute, hipDeviceSetMemPool, hipMemPoolSetAttribute, hipMemPoolSetAccess, hipMemPoolGetAccess

Warning: : This API is marked as beta, meaning, while this is feature complete, it is still open to changes and may have outstanding issues.

◆ hipDeviceGetSharedMemConfig()

hipError_t hipDeviceGetSharedMemConfig ( hipSharedMemConfig * pConfig )

Returns bank width of shared memory for current device.

Parameters

[out] pConfig

Returns: hipSuccess, hipErrorInvalidValue, hipErrorNotInitialized

Note: AMD devices and some Nvidia GPUS do not support shared cache banking, and the hint is ignored on those architectures.

◆ hipDeviceReset()

hipError_t hipDeviceReset ( void )

The state of current device is discarded and updated to a fresh state.

Calling this function deletes all streams created, memory allocated, kernels running, events created. Make sure that no other thread is using the device or streams, memory, kernels, events associated with the current device.

Returns: hipSuccess

See also: hipDeviceSynchronize

◆ hipDeviceSetCacheConfig()

hipError_t hipDeviceSetCacheConfig ( hipFuncCache_t cacheConfig )

Set L1/Shared cache partition.

Parameters

[in] cacheConfig

Returns: hipSuccess, hipErrorNotInitialized Note: AMD devices and some Nvidia GPUS do not support reconfigurable cache. This hint is ignored on those architectures.

◆ hipDeviceSetLimit()

hipError_t hipDeviceSetLimit	(	enum hipLimit_t	limit,
		size_t	value
	)

Set Resource limits of current device.

Parameters

[in]	limit
[in]	value

Returns: hipSuccess, hipErrorUnsupportedLimit, hipErrorInvalidValue

◆ hipDeviceSetMemPool()

hipError_t hipDeviceSetMemPool	(	int	device,
		hipMemPool_t	mem_pool
	)

Sets the current memory pool of a device.

The memory pool must be local to the specified device. hipMallocAsync allocates from the current mempool of the provided stream's device. By default, a device's current memory pool is its default memory pool.

Note: Use hipMallocFromPoolAsync for asynchronous memory allocations from a device different than the one the stream runs on.

Parameters

[in]	device	Device index for the update
[in]	mem_pool	Memory pool for update as the current on the specified device

Returns: hipSuccess, hipErrorInvalidValue, hipErrorInvalidDevice, hipErrorNotSupported

See also: hipDeviceGetDefaultMemPool, hipMallocAsync, hipMemPoolTrimTo, hipMemPoolGetAttribute, hipDeviceSetMemPool, hipMemPoolSetAttribute, hipMemPoolSetAccess, hipMemPoolGetAccess

Warning: : This API is marked as beta, meaning, while this is feature complete, it is still open to changes and may have outstanding issues.

◆ hipDeviceSetSharedMemConfig()

hipError_t hipDeviceSetSharedMemConfig ( hipSharedMemConfig config )

The bank width of shared memory on current device is set.

Parameters

[in] config

Returns: hipSuccess, hipErrorInvalidValue, hipErrorNotInitialized

Note: AMD devices and some Nvidia GPUS do not support shared cache banking, and the hint is ignored on those architectures.

◆ hipDeviceSynchronize()

hipError_t hipDeviceSynchronize ( void )

Waits on all active streams on current device.

When this command is invoked, the host thread gets blocked until all the commands associated with streams associated with the device. HIP does not support multiple blocking modes (yet!).

Returns: hipSuccess

See also: hipSetDevice, hipDeviceReset

◆ hipExtGetLinkTypeAndHopCount()

hipError_t hipExtGetLinkTypeAndHopCount	(	int	device1,
		int	device2,
		uint32_t *	linktype,
		uint32_t *	hopcount
	)

Returns the link type and hop count between two devices.

Parameters

[in]	device1	Ordinal for device1
[in]	device2	Ordinal for device2
[out]	linktype	Returns the link type (See hsa_amd_link_info_type_t) between the two devices
[out]	hopcount	Returns the hop count between the two devices

Queries and returns the HSA link type and the hop count between the two specified devices.

Returns: hipSuccess, #hipInvalidDevice, hipErrorRuntimeOther

◆ hipGetDevice()

hipError_t hipGetDevice ( int * deviceId )

Return the default device id for the calling host thread.

Parameters

[out] device *device is written with the default device

HIP maintains an default device for each thread using thread-local-storage. This device is used implicitly for HIP runtime APIs called by this thread. hipGetDevice returns in * device the default device for the calling host thread.

Returns: hipSuccess, hipErrorInvalidDevice, hipErrorInvalidValue

See also: hipSetDevice, hipGetDevicesizeBytes

◆ hipGetDeviceCount()

hipError_t hipGetDeviceCount ( int * count )

Return number of compute-capable devices.

Parameters

[output] count Returns number of compute-capable devices.

Returns: hipSuccess, hipErrorNoDevice

Returns in *count the number of devices that have ability to run compute commands. If there are no such devices, then hipGetDeviceCount will return hipErrorNoDevice. If 1 or more devices can be found, then hipGetDeviceCount returns hipSuccess.

◆ hipGetDeviceFlags()

hipError_t hipGetDeviceFlags ( unsigned int * flags )

Gets the flags set for current device.

Parameters

[out] flags

Returns: hipSuccess, hipErrorInvalidDevice, hipErrorInvalidValue

◆ hipGetDeviceProperties()

hipError_t hipGetDeviceProperties	(	hipDeviceProp_t *	prop,
		int	deviceId
	)

Returns device properties.

Parameters

[out]	prop	written with device properties
[in]	deviceId	which device to query for information

Returns: hipSuccess, hipErrorInvalidDevice

Bug:

HCC always returns 0 for maxThreadsPerMultiProcessor

HCC always returns 0 for regsPerBlock

HCC always returns 0 for l2CacheSize

Populates hipGetDeviceProperties with information for the specified device.

◆ hipIpcCloseMemHandle()

hipError_t hipIpcCloseMemHandle ( void * devPtr )

Close memory mapped with hipIpcOpenMemHandle.

Unmaps memory returnd by hipIpcOpenMemHandle. The original allocation in the exporting process as well as imported mappings in other processes will be unaffected.

Any resources used to enable peer access will be freed if this is the last mapping using them.

Parameters

devPtr - Device pointer returned by hipIpcOpenMemHandle

Returns: hipSuccess, hipErrorMapFailed, hipErrorInvalidHandle,

◆ hipIpcGetEventHandle()

hipError_t hipIpcGetEventHandle	(	hipIpcEventHandle_t *	handle,
		hipEvent_t	event
	)

Gets an opaque interprocess handle for an event.

This opaque handle may be copied into other processes and opened with hipIpcOpenEventHandle. Then hipEventRecord, hipEventSynchronize, hipStreamWaitEvent and hipEventQuery may be used in either process. Operations on the imported event after the exported event has been freed with hipEventDestroy will result in undefined behavior.

Parameters

[out]	handle	Pointer to hipIpcEventHandle to return the opaque event handle
[in]	event	Event allocated with hipEventInterprocess and hipEventDisableTiming flags

Returns: hipSuccess, hipErrorInvalidConfiguration, hipErrorInvalidValue

◆ hipIpcGetMemHandle()

hipError_t hipIpcGetMemHandle	(	hipIpcMemHandle_t *	handle,
		void *	devPtr
	)

Gets an interprocess memory handle for an existing device memory allocation.

Takes a pointer to the base of an existing device memory allocation created with hipMalloc and exports it for use in another process. This is a lightweight operation and may be called multiple times on an allocation without adverse effects.

If a region of memory is freed with hipFree and a subsequent call to hipMalloc returns memory with the same device address, hipIpcGetMemHandle will return a unique handle for the new memory.

Parameters

handle	- Pointer to user allocated hipIpcMemHandle to return the handle in.
devPtr	- Base pointer to previously allocated device memory

Returns: hipSuccess, hipErrorInvalidHandle, hipErrorOutOfMemory, hipErrorMapFailed,

◆ hipIpcOpenEventHandle()

hipError_t hipIpcOpenEventHandle	(	hipEvent_t *	event,
		hipIpcEventHandle_t	handle
	)

Opens an interprocess event handles.

Opens an interprocess event handle exported from another process with cudaIpcGetEventHandle. The returned hipEvent_t behaves like a locally created event with the hipEventDisableTiming flag specified. This event need be freed with hipEventDestroy. Operations on the imported event after the exported event has been freed with hipEventDestroy will result in undefined behavior. If the function is called within the same process where handle is returned by hipIpcGetEventHandle, it will return hipErrorInvalidContext.

Parameters

[out]	event	Pointer to hipEvent_t to return the event
[in]	handle	The opaque interprocess handle to open

Returns: hipSuccess, hipErrorInvalidValue, hipErrorInvalidContext

◆ hipIpcOpenMemHandle()

hipError_t hipIpcOpenMemHandle	(	void **	devPtr,
		hipIpcMemHandle_t	handle,
		unsigned int	flags
	)

Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.

Maps memory exported from another process with hipIpcGetMemHandle into the current device address space. For contexts on different devices hipIpcOpenMemHandle can attempt to enable peer access between the devices as if the user called hipDeviceEnablePeerAccess. This behavior is controlled by the hipIpcMemLazyEnablePeerAccess flag. hipDeviceCanAccessPeer can determine if a mapping is possible.

Contexts that may open hipIpcMemHandles are restricted in the following way. hipIpcMemHandles from each device in a given process may only be opened by one context per device per other process.

Memory returned from hipIpcOpenMemHandle must be freed with hipIpcCloseMemHandle.

Calling hipFree on an exported memory region before calling hipIpcCloseMemHandle in the importing context will result in undefined behavior.

Parameters

devPtr	- Returned device pointer
handle	- hipIpcMemHandle to open
flags	- Flags for this operation. Must be specified as hipIpcMemLazyEnablePeerAccess

Returns: hipSuccess, hipErrorMapFailed, hipErrorInvalidHandle, hipErrorTooManyPeers

Note: No guarantees are made about the address returned in *devPtr. In particular, multiple processes may not receive the same address for the same handle.

◆ hipSetDevice()

hipError_t hipSetDevice ( int deviceId )

Set default device to be used for subsequent hip API calls from this thread.

Parameters

[in] deviceId Valid device in range 0...hipGetDeviceCount().

Sets device as the default device for the calling host thread. Valid device id's are 0... (hipGetDeviceCount()-1).

Many HIP APIs implicitly use the "default device" :

Any device memory subsequently allocated from this host thread (using hipMalloc) will be allocated on device.
Any streams or events created from this host thread will be associated with device.
Any kernels launched from this host thread (using hipLaunchKernel) will be executed on device (unless a specific stream is specified, in which case the device associated with that stream will be used).

This function may be called from any host thread. Multiple host threads may use the same device. This function does no synchronization with the previous or new device, and has very little runtime overhead. Applications can use hipSetDevice to quickly switch the default device before making a HIP runtime call which uses the default device.

The default device is stored in thread-local-storage for each thread. Thread-pool implementations may inherit the default device of the previous thread. A good practice is to always call hipSetDevice at the start of HIP coding sequency to establish a known standard device.

Returns: hipSuccess, hipErrorInvalidDevice, #hipErrorDeviceAlreadyInUse

See also: hipGetDevice, hipGetDeviceCount

◆ hipSetDeviceFlags()

hipError_t hipSetDeviceFlags ( unsigned flags )

The current device behavior is changed according the flags passed.

Parameters

[in] flags

The schedule flags impact how HIP waits for the completion of a command running on a device. hipDeviceScheduleSpin : HIP runtime will actively spin in the thread which submitted the work until the command completes. This offers the lowest latency, but will consume a CPU core and may increase power. hipDeviceScheduleYield : The HIP runtime will yield the CPU to system so that other tasks can use it. This may increase latency to detect the completion but will consume less power and is friendlier to other tasks in the system. hipDeviceScheduleBlockingSync : On ROCm platform, this is a synonym for hipDeviceScheduleYield. hipDeviceScheduleAuto : Use a hueristic to select between Spin and Yield modes. If the number of HIP contexts is greater than the number of logical processors in the system, use Spin scheduling. Else use Yield scheduling.

hipDeviceMapHost : Allow mapping host memory. On ROCM, this is always allowed and the flag is ignored. hipDeviceLmemResizeToMax :

Warning: ROCm silently ignores this flag.

Returns: hipSuccess, hipErrorInvalidDevice, hipErrorSetOnActiveProcess

Device Management

Device Management#

Functions

Detailed Description

Function Documentation

◆ hipChooseDevice()

◆ hipDeviceGetAttribute()

◆ hipDeviceGetCacheConfig()

◆ hipDeviceGetDefaultMemPool()

◆ hipDeviceGetLimit()

◆ hipDeviceGetMemPool()

◆ hipDeviceGetSharedMemConfig()

◆ hipDeviceReset()

◆ hipDeviceSetCacheConfig()

◆ hipDeviceSetLimit()

◆ hipDeviceSetMemPool()

◆ hipDeviceSetSharedMemConfig()

◆ hipDeviceSynchronize()

◆ hipExtGetLinkTypeAndHopCount()

◆ hipGetDevice()

◆ hipGetDeviceCount()

◆ hipGetDeviceFlags()

◆ hipGetDeviceProperties()

◆ hipIpcCloseMemHandle()

◆ hipIpcGetEventHandle()

◆ hipIpcGetMemHandle()

◆ hipIpcOpenEventHandle()

◆ hipIpcOpenMemHandle()

◆ hipSetDevice()

◆ hipSetDeviceFlags()