GPUOptions.Experimental

public static final class GPUOptions.Experimental

Protobuf type tensorflow.GPUOptions.Experimental

Nested Classes

class GPUOptions.Experimental.Builder Protobuf type tensorflow.GPUOptions.Experimental  
class GPUOptions.Experimental.VirtualDevices 
 Configuration for breaking down a visible GPU into multiple "virtual"
 devices. 
interface GPUOptions.Experimental.VirtualDevicesOrBuilder  

Constants

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

Public Methods

boolean
equals(Object obj)
String
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.
static GPUOptions.Experimental
getDefaultInstance()
GPUOptions.Experimental
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()
boolean
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()
boolean
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.
List<GPUOptions.Experimental.VirtualDevices>
getVirtualDevicesList() 
 The multi virtual device settings.
GPUOptions.Experimental.VirtualDevicesOrBuilder
getVirtualDevicesOrBuilder(int index) 
 The multi virtual device settings.
List<? extends GPUOptions.Experimental.VirtualDevicesOrBuilder>
getVirtualDevicesOrBuilderList() 
 The multi virtual device settings.
int
hashCode()
final boolean
isInitialized()
static GPUOptions.Experimental.Builder
newBuilder(GPUOptions.Experimental prototype)
static GPUOptions.Experimental.Builder
newBuilder()
GPUOptions.Experimental.Builder
newBuilderForType()
static GPUOptions.Experimental
parseDelimitedFrom(InputStream input)
static GPUOptions.Experimental
parseDelimitedFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
static GPUOptions.Experimental
parseFrom(ByteBuffer data)
static GPUOptions.Experimental
parseFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
static GPUOptions.Experimental
parseFrom(ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
static GPUOptions.Experimental
parseFrom(com.google.protobuf.CodedInputStream input)
static GPUOptions.Experimental
parseFrom(byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
static GPUOptions.Experimental
parseFrom(com.google.protobuf.ByteString data)
static GPUOptions.Experimental
parseFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
static GPUOptions.Experimental
parseFrom(com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
static
parser()
GPUOptions.Experimental.Builder
toBuilder()
void
writeTo(com.google.protobuf.CodedOutputStream output)

Inherited Methods

Constants

public static final int COLLECTIVE_RING_ORDER_FIELD_NUMBER

Constant Value: 4

public static final int KERNEL_TRACKER_MAX_BYTES_FIELD_NUMBER

Constant Value: 8

public static final int KERNEL_TRACKER_MAX_INTERVAL_FIELD_NUMBER

Constant Value: 7

public static final int KERNEL_TRACKER_MAX_PENDING_FIELD_NUMBER

Constant Value: 9

public static final int NUM_DEV_TO_DEV_COPY_STREAMS_FIELD_NUMBER

Constant Value: 3

public static final int TIMESTAMPED_ALLOCATOR_FIELD_NUMBER

Constant Value: 5

public static final int USE_UNIFIED_MEMORY_FIELD_NUMBER

Constant Value: 2

public static final int VIRTUAL_DEVICES_FIELD_NUMBER

Constant Value: 1

Public Methods

public boolean equals (Object obj)

public String 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;

public getParserForType ()

public int getSerializedSize ()

public boolean 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.
bool timestamped_allocator = 5;

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

public boolean getUseUnifiedMemory () 

 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;

public GPUOptions.Experimental.VirtualDevices getVirtualDevices (int index) 

 The multi virtual device settings. If empty (not set), it will create
 single virtual device on each visible GPU, according to the settings
 in "visible_device_list" above. Otherwise, the number of elements in the
 list must be the same as the number of visible GPUs (after
 "visible_device_list" filtering if it is set), and the string represented
 device names (e.g. /device:GPU:<id>) will refer to the virtual
 devices and have the <id> field assigned sequentially starting from 0,
 according to the order they appear in this list and the "memory_limit"
 list inside each element. For example,
   visible_device_list = "1,0"
   virtual_devices { memory_limit: 1GB memory_limit: 2GB }
   virtual_devices {}
 will create three virtual devices as:
   /device:GPU:0 -> visible GPU 1 with 1GB memory
   /device:GPU:1 -> visible GPU 1 with 2GB memory
   /device:GPU:2 -> visible GPU 0 with all available memory
 NOTE:
 1. It's invalid to set both this and "per_process_gpu_memory_fraction"
    at the same time.
 2. Currently this setting is per-process, not per-session. Using
    different settings in different sessions within same process will
    result in undefined behavior.
repeated .tensorflow.GPUOptions.Experimental.VirtualDevices virtual_devices = 1;

public int getVirtualDevicesCount () 

 The multi virtual device settings. If empty (not set), it will create
 single virtual device on each visible GPU, according to the settings
 in "visible_device_list" above. Otherwise, the number of elements in the
 list must be the same as the number of visible GPUs (after
 "visible_device_list" filtering if it is set), and the string represented
 device names (e.g. /device:GPU:<id>) will refer to the virtual
 devices and have the <id> field assigned sequentially starting from 0,
 according to the order they appear in this list and the "memory_limit"
 list inside each element. For example,
   visible_device_list = "1,0"
   virtual_devices { memory_limit: 1GB memory_limit: 2GB }
   virtual_devices {}
 will create three virtual devices as:
   /device:GPU:0 -> visible GPU 1 with 1GB memory
   /device:GPU:1 -> visible GPU 1 with 2GB memory
   /device:GPU:2 -> visible GPU 0 with all available memory
 NOTE:
 1. It's invalid to set both this and "per_process_gpu_memory_fraction"
    at the same time.
 2. Currently this setting is per-process, not per-session. Using
    different settings in different sessions within same process will
    result in undefined behavior.
repeated .tensorflow.GPUOptions.Experimental.VirtualDevices virtual_devices = 1;

public List<GPUOptions.Experimental.VirtualDevices> getVirtualDevicesList () 

 The multi virtual device settings. If empty (not set), it will create
 single virtual device on each visible GPU, according to the settings
 in "visible_device_list" above. Otherwise, the number of elements in the
 list must be the same as the number of visible GPUs (after
 "visible_device_list" filtering if it is set), and the string represented
 device names (e.g. /device:GPU:<id>) will refer to the virtual
 devices and have the <id> field assigned sequentially starting from 0,
 according to the order they appear in this list and the "memory_limit"
 list inside each element. For example,
   visible_device_list = "1,0"
   virtual_devices { memory_limit: 1GB memory_limit: 2GB }
   virtual_devices {}
 will create three virtual devices as:
   /device:GPU:0 -> visible GPU 1 with 1GB memory
   /device:GPU:1 -> visible GPU 1 with 2GB memory
   /device:GPU:2 -> visible GPU 0 with all available memory
 NOTE:
 1. It's invalid to set both this and "per_process_gpu_memory_fraction"
    at the same time.
 2. Currently this setting is per-process, not per-session. Using
    different settings in different sessions within same process will
    result in undefined behavior.
repeated .tensorflow.GPUOptions.Experimental.VirtualDevices virtual_devices = 1;

public GPUOptions.Experimental.VirtualDevicesOrBuilder getVirtualDevicesOrBuilder (int index) 

 The multi virtual device settings. If empty (not set), it will create
 single virtual device on each visible GPU, according to the settings
 in "visible_device_list" above. Otherwise, the number of elements in the
 list must be the same as the number of visible GPUs (after
 "visible_device_list" filtering if it is set), and the string represented
 device names (e.g. /device:GPU:<id>) will refer to the virtual
 devices and have the <id> field assigned sequentially starting from 0,
 according to the order they appear in this list and the "memory_limit"
 list inside each element. For example,
   visible_device_list = "1,0"
   virtual_devices { memory_limit: 1GB memory_limit: 2GB }
   virtual_devices {}
 will create three virtual devices as:
   /device:GPU:0 -> visible GPU 1 with 1GB memory
   /device:GPU:1 -> visible GPU 1 with 2GB memory
   /device:GPU:2 -> visible GPU 0 with all available memory
 NOTE:
 1. It's invalid to set both this and "per_process_gpu_memory_fraction"
    at the same time.
 2. Currently this setting is per-process, not per-session. Using
    different settings in different sessions within same process will
    result in undefined behavior.
repeated .tensorflow.GPUOptions.Experimental.VirtualDevices virtual_devices = 1;

public List<? extends GPUOptions.Experimental.VirtualDevicesOrBuilder> getVirtualDevicesOrBuilderList () 

 The multi virtual device settings. If empty (not set), it will create
 single virtual device on each visible GPU, according to the settings
 in "visible_device_list" above. Otherwise, the number of elements in the
 list must be the same as the number of visible GPUs (after
 "visible_device_list" filtering if it is set), and the string represented
 device names (e.g. /device:GPU:<id>) will refer to the virtual
 devices and have the <id> field assigned sequentially starting from 0,
 according to the order they appear in this list and the "memory_limit"
 list inside each element. For example,
   visible_device_list = "1,0"
   virtual_devices { memory_limit: 1GB memory_limit: 2GB }
   virtual_devices {}
 will create three virtual devices as:
   /device:GPU:0 -> visible GPU 1 with 1GB memory
   /device:GPU:1 -> visible GPU 1 with 2GB memory
   /device:GPU:2 -> visible GPU 0 with all available memory
 NOTE:
 1. It's invalid to set both this and "per_process_gpu_memory_fraction"
    at the same time.
 2. Currently this setting is per-process, not per-session. Using
    different settings in different sessions within same process will
    result in undefined behavior.
repeated .tensorflow.GPUOptions.Experimental.VirtualDevices virtual_devices = 1;

public int hashCode ()

public final boolean isInitialized ()

public static GPUOptions.Experimental.Builder newBuilder (GPUOptions.Experimental prototype)

public static GPUOptions.Experimental.Builder newBuilder ()

public GPUOptions.Experimental.Builder newBuilderForType ()

public static GPUOptions.Experimental parseDelimitedFrom (InputStream input)

Throws
IOException

public static GPUOptions.Experimental parseDelimitedFrom (InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Throws
IOException

public static GPUOptions.Experimental parseFrom (ByteBuffer data)

Throws
InvalidProtocolBufferException

public static GPUOptions.Experimental parseFrom (com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Throws
IOException

public static GPUOptions.Experimental parseFrom (ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Throws
InvalidProtocolBufferException

public static GPUOptions.Experimental parseFrom (com.google.protobuf.CodedInputStream input)

Throws
IOException

public static GPUOptions.Experimental parseFrom (byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Throws
InvalidProtocolBufferException

public static GPUOptions.Experimental parseFrom (com.google.protobuf.ByteString data)

Throws
InvalidProtocolBufferException

public static GPUOptions.Experimental parseFrom (InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Throws
IOException

public static GPUOptions.Experimental parseFrom (com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Throws
InvalidProtocolBufferException

public static parser ()

public GPUOptions.Experimental.Builder toBuilder ()

public void writeTo (com.google.protobuf.CodedOutputStream output)

Throws
IOException