דף זה תורגם על ידי Cloud Translation API.

GPUOptions.Experimental

מחלקה סופית סטטית ציבורית GPUOptions.ניסוי

סוג Protobuf tensorflow.GPUOptions.Experimental

כיתות מקוננות

מַחלָקָה	GPUOptions.Experimental.Builder	סוג Protobuf `tensorflow.GPUOptions.Experimental`
מַחלָקָה	GPUOptions.Experimental.VirtualDevices	Configuration for breaking down a visible GPU into multiple "virtual" devices.
מִמְשָׁק	GPUOptions.Experimental.VirtualDevicesOrBuilder

קבועים

int	COLLECTIVE_RING_ORDER_FIELD_NUMBER
int	KERNEL_TRACKER_MAX_BYTES_FIELD_NUMBER
int	KERNEL_TRACKER_MAX_INTERVAL_FIELD_NUMBER
int	KERNEL_TRACKER_MAX_PENDING_FIELD_NUMBER
int	NUM_DEV_TO_DEV_COPY_STREAMS_FIELD_NUMBER
int	TIMESTAMPED_ALLOCATOR_FIELD_NUMBER
int	USE_UNIFIED_MEMORY_FIELD_NUMBER
int	VIRTUAL_DEVICES_FIELD_NUMBER

שיטות ציבוריות

בוליאני	שווה (Object obj)
חוּט	getCollectiveRingOrder () If non-empty, defines a good GPU ring order on a single worker based on device interconnect.
com.google.protobuf.ByteString	getCollectiveRingOrderBytes () If non-empty, defines a good GPU ring order on a single worker based on device interconnect.
סטטי GPUOptions. ניסוי	getDefaultInstance ()
GPUOptions.ניסיוני	getDefaultInstanceForType ()
final static com.google.protobuf.Descriptors.Descriptor	getDescriptor ()
int	getKernelTrackerMaxBytes () If kernel_tracker_max_bytes = n > 0, then a tracking event is inserted after every series of kernels allocating a sum of memory >= n.
int	getKernelTrackerMaxInterval () Parameters for GPUKernelTracker.
int	getKernelTrackerMaxPending () If kernel_tracker_max_pending > 0 then no more than this many tracking events can be outstanding at a time.
int	getNumDevToDevCopyStreams () If > 1, the number of device-to-device copy streams to create for each GPUDevice.
	getParserForType ()
int	getSerializedSize ()
בוליאני	getTimestampedAllocator () If true then extra work is done by GPUDevice and GPUBFCAllocator to keep track of when GPU memory is freed and when kernels actually complete so that we can know when a nominally free memory chunk is really not subject to pending use.
final com.google.protobuf.UnknownFieldSet	getUnknownFields ()
בוליאני	getUseUnifiedMemory () If true, uses CUDA unified memory for memory allocations.
GPUOptions.Experimental.VirtualDevices	getVirtualDevices (int index) The multi virtual device settings.
int	getVirtualDevicesCount () The multi virtual device settings.
רשימה< GPUOptions.Experimental.VirtualDevices >	getVirtualDevicesList () The multi virtual device settings.
GPUOptions.Experimental.VirtualDevicesOrBuilder	getVirtualDevicesOrBuilder (int index) The multi virtual device settings.
רשימה<? מרחיב את GPUOptions.Experimental.VirtualDevicesOrBuilder >	getVirtualDevicesOrBuilderList () The multi virtual device settings.
int	hashcode ()
בוליאנית סופית	isinitialized ()
סטטי GPUOptions.Experimental.Builder	newBuilder (אבטיפוס GPUOptions.Experimental )
סטטי GPUOptions.Experimental.Builder	newBuilder ()
GPUOptions.Experimental.Builder	newBuilderForType ()
סטטי GPUOptions. ניסוי	parseDelimitedFrom (קלט InputStream)
סטטי GPUOptions. ניסוי	parseDelimitedFrom (קלט InputStream, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
סטטי GPUOptions. ניסוי	parseFrom (נתוני ByteBuffer)
סטטי GPUOptions. ניסוי	parseFrom (קלט com.google.protobuf.CodedInputStream, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
סטטי GPUOptions. ניסוי	parseFrom (נתוני ByteBuffer, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
סטטי GPUOptions. ניסוי	parseFrom (קלט com.google.protobuf.CodedInputStream)
סטטי GPUOptions. ניסוי	parseFrom (נתוני byte[], com.google.protobuf.ExtensionRegistryLite extensionRegistry)
סטטי GPUOptions. ניסוי	parseFrom (נתוני com.google.protobuf.ByteString)
סטטי GPUOptions. ניסוי	parseFrom (קלט InputStream, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
סטטי GPUOptions. ניסוי	parseFrom (נתוני com.google.protobuf.ByteString, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
סטָטִי	מנתח ()
GPUOptions.Experimental.Builder	toBuilder ()
בָּטֵל	writeTo (פלט com.google.protobuf.CodedOutputStream)

שיטות בירושה

מכיתה java.lang.Object

בוליאני	שווה (Object arg0)
כיתה אחרונה<?>	getClass ()
int	hashcode ()
ריק סופי	להודיע ()
ריק סופי	הודע הכל ()
חוּט	toString ()
ריק סופי	המתן (ארג0 ארוך, אינט arg1)
ריק סופי	חכה (ארג0 ארוך)
ריק סופי	חכה ()

מהממשק org.tensorflow.proto.framework.GPUOptions.ExperimentalOrBuilder

מחרוזת מופשטת	getCollectiveRingOrder () If non-empty, defines a good GPU ring order on a single worker based on device interconnect.
תקציר com.google.protobuf.ByteString	getCollectiveRingOrderBytes () If non-empty, defines a good GPU ring order on a single worker based on device interconnect.
מופשט int	getKernelTrackerMaxBytes () If kernel_tracker_max_bytes = n > 0, then a tracking event is inserted after every series of kernels allocating a sum of memory >= n.
מופשט int	getKernelTrackerMaxInterval () Parameters for GPUKernelTracker.
מופשט int	getKernelTrackerMaxPending () If kernel_tracker_max_pending > 0 then no more than this many tracking events can be outstanding at a time.
מופשט int	getNumDevToDevCopyStreams () If > 1, the number of device-to-device copy streams to create for each GPUDevice.
בוליאני מופשט	getTimestampedAllocator () If true then extra work is done by GPUDevice and GPUBFCAllocator to keep track of when GPU memory is freed and when kernels actually complete so that we can know when a nominally free memory chunk is really not subject to pending use.
בוליאני מופשט	getUseUnifiedMemory () If true, uses CUDA unified memory for memory allocations.
אבסטרקט GPUOptions.Experimental.VirtualDevices	getVirtualDevices (int index) The multi virtual device settings.
מופשט int	getVirtualDevicesCount () The multi virtual device settings.
רשימת תקציר< GPUOptions.Experimental.VirtualDevices >	getVirtualDevicesList () The multi virtual device settings.
מופשט GPUOptions.Experimental.VirtualDevicesOrBuilder	getVirtualDevicesOrBuilder (int index) The multi virtual device settings.
רשימה מופשטת<? מרחיב את GPUOptions.Experimental.VirtualDevicesOrBuilder >	getVirtualDevicesOrBuilderList () The multi virtual device settings.

קבועים

גמר סטטי ציבורי COLLECTIVE_RING_ORDER_FIELD_NUMBER

ערך קבוע: 4

גמר סטטי ציבורי KERNEL_TRACKER_MAX_BYTES_FIELD_NUMBER

ערך קבוע: 8

גמר סטטי ציבורי KERNEL_TRACKER_MAX_INTERVAL_FIELD_NUMBER

ערך קבוע: 7

גמר סטטי ציבורי KERNEL_TRACKER_MAX_PENDING_FIELD_NUMBER

ערך קבוע: 9

גמר סטטי ציבורי NUM_DEV_TO_DEV_COPY_STREAMS_FIELD_NUMBER

ערך קבוע: 3

גמר סטטי ציבורי TIMESTAMPED_ALLOCATOR_FIELD_NUMBER

ערך קבוע: 5

גמר סטטי ציבורי USE_UNIFIED_MEMORY_FIELD_NUMBER

ערך קבוע: 2

גמר סטטי ציבורי VIRTUAL_DEVICES_FIELD_NUMBER

ערך קבוע: 1

שיטות ציבוריות

שווה ערך בוליאני ציבורי (Object obj)

מחרוזת ציבורית getCollectiveRingOrder ()

 If non-empty, defines a good GPU ring order on a single worker based on
 device interconnect.  This assumes that all workers have the same GPU
 topology.  Specify as a comma-separated string, e.g. "3,2,1,0,7,6,5,4".
 This ring order is used by the RingReducer implementation of
 CollectiveReduce, and serves as an override to automatic ring order
 generation in OrderTaskDeviceMap() during CollectiveParam resolution.

string collective_ring_order = 4;

public com.google.protobuf.ByteString getCollectiveRingOrderBytes ()

 If non-empty, defines a good GPU ring order on a single worker based on
 device interconnect.  This assumes that all workers have the same GPU
 topology.  Specify as a comma-separated string, e.g. "3,2,1,0,7,6,5,4".
 This ring order is used by the RingReducer implementation of
 CollectiveReduce, and serves as an override to automatic ring order
 generation in OrderTaskDeviceMap() during CollectiveParam resolution.

string collective_ring_order = 4;

Public static GPUOptions.Experimental getDefaultInstance ()

public GPUOptions.Experimental getDefaultInstanceForType ()

public static final com.google.protobuf.Descriptors.Descriptor getDescriptor ()

public int getKernelTrackerMaxBytes ()

 If kernel_tracker_max_bytes = n > 0, then a tracking event is
 inserted after every series of kernels allocating a sum of
 memory >= n.  If one kernel allocates b * n bytes, then one
 event will be inserted after it, but it will count as b against
 the pending limit.

int32 kernel_tracker_max_bytes = 8;

public int getKernelTrackerMaxInterval ()

 Parameters for GPUKernelTracker.  By default no kernel tracking is done.
 Note that timestamped_allocator is only effective if some tracking is
 specified.
 If kernel_tracker_max_interval = n > 0, then a tracking event
 is inserted after every n kernels without an event.

int32 kernel_tracker_max_interval = 7;

public int getKernelTrackerMaxPending ()

 If kernel_tracker_max_pending > 0 then no more than this many
 tracking events can be outstanding at a time.  An attempt to
 launch an additional kernel will stall until an event
 completes.

int32 kernel_tracker_max_pending = 9;

public int getNumDevToDevCopyStreams ()

 If > 1, the number of device-to-device copy streams to create
 for each GPUDevice.  Default value is 0, which is automatically
 converted to 1.

int32 num_dev_to_dev_copy_streams = 3;

פּוּמְבֵּי getParserForType ()

public int getSerializedSize ()

getTimestampedAllocator בוליאני ציבורי ()

 If true then extra work is done by GPUDevice and GPUBFCAllocator to
 keep track of when GPU memory is freed and when kernels actually
 complete so that we can know when a nominally free memory chunk
 is really not subject to pending use.

bool timestamped_allocator = 5;

public final com.google.protobuf.UnknownFieldSet getUnknownFields ()

getUseUnifiedMemory בוליאני ציבורי ()

 If true, uses CUDA unified memory for memory allocations. If
 per_process_gpu_memory_fraction option is greater than 1.0, then unified
 memory is used regardless of the value for this field. See comments for
 per_process_gpu_memory_fraction field for more details and requirements
 of the unified memory. This option is useful to oversubscribe memory if
 multiple processes are sharing a single GPU while individually using less
 than 1.0 per process memory fraction.

bool use_unified_memory = 2;