public static final class GPUOptions.Experimental extends com.google.protobuf.GeneratedMessageV3 implements GPUOptions.ExperimentalOrBuilder
tensorflow.GPUOptions.Experimental| Modifier and Type | Class and Description |
|---|---|
static class |
GPUOptions.Experimental.Builder
Protobuf type
tensorflow.GPUOptions.Experimental |
static class |
GPUOptions.Experimental.VirtualDevices
Configuration for breaking down a visible GPU into multiple "virtual"
devices.
|
static interface |
GPUOptions.Experimental.VirtualDevicesOrBuilder |
com.google.protobuf.GeneratedMessageV3.BuilderParent, com.google.protobuf.GeneratedMessageV3.ExtendableBuilder<MessageType extends com.google.protobuf.GeneratedMessageV3.ExtendableMessage,BuilderType extends com.google.protobuf.GeneratedMessageV3.ExtendableBuilder<MessageType,BuilderType>>, com.google.protobuf.GeneratedMessageV3.ExtendableMessage<MessageType extends com.google.protobuf.GeneratedMessageV3.ExtendableMessage>, com.google.protobuf.GeneratedMessageV3.ExtendableMessageOrBuilder<MessageType extends com.google.protobuf.GeneratedMessageV3.ExtendableMessage>, com.google.protobuf.GeneratedMessageV3.FieldAccessorTable, com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter| Modifier and Type | Field and Description |
|---|---|
static int |
COLLECTIVE_RING_ORDER_FIELD_NUMBER |
static int |
KERNEL_TRACKER_MAX_BYTES_FIELD_NUMBER |
static int |
KERNEL_TRACKER_MAX_INTERVAL_FIELD_NUMBER |
static int |
KERNEL_TRACKER_MAX_PENDING_FIELD_NUMBER |
static int |
NUM_DEV_TO_DEV_COPY_STREAMS_FIELD_NUMBER |
static int |
TIMESTAMPED_ALLOCATOR_FIELD_NUMBER |
static int |
USE_UNIFIED_MEMORY_FIELD_NUMBER |
static int |
VIRTUAL_DEVICES_FIELD_NUMBER |
| Modifier and Type | Method and Description |
|---|---|
boolean |
equals(java.lang.Object obj) |
java.lang.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() |
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.
|
com.google.protobuf.Parser<GPUOptions.Experimental> |
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.
|
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.
|
java.util.List<GPUOptions.Experimental.VirtualDevices> |
getVirtualDevicesList()
The multi virtual device settings.
|
GPUOptions.Experimental.VirtualDevicesOrBuilder |
getVirtualDevicesOrBuilder(int index)
The multi virtual device settings.
|
java.util.List<? extends GPUOptions.Experimental.VirtualDevicesOrBuilder> |
getVirtualDevicesOrBuilderList()
The multi virtual device settings.
|
int |
hashCode() |
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable |
internalGetFieldAccessorTable() |
boolean |
isInitialized() |
static GPUOptions.Experimental.Builder |
newBuilder() |
static GPUOptions.Experimental.Builder |
newBuilder(GPUOptions.Experimental prototype) |
GPUOptions.Experimental.Builder |
newBuilderForType() |
protected GPUOptions.Experimental.Builder |
newBuilderForType(com.google.protobuf.GeneratedMessageV3.BuilderParent parent) |
protected java.lang.Object |
newInstance(com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter unused) |
static GPUOptions.Experimental |
parseDelimitedFrom(java.io.InputStream input) |
static GPUOptions.Experimental |
parseDelimitedFrom(java.io.InputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static GPUOptions.Experimental |
parseFrom(byte[] data) |
static GPUOptions.Experimental |
parseFrom(byte[] data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static GPUOptions.Experimental |
parseFrom(java.nio.ByteBuffer data) |
static GPUOptions.Experimental |
parseFrom(java.nio.ByteBuffer data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static GPUOptions.Experimental |
parseFrom(com.google.protobuf.ByteString data) |
static GPUOptions.Experimental |
parseFrom(com.google.protobuf.ByteString data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static GPUOptions.Experimental |
parseFrom(com.google.protobuf.CodedInputStream input) |
static GPUOptions.Experimental |
parseFrom(com.google.protobuf.CodedInputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static GPUOptions.Experimental |
parseFrom(java.io.InputStream input) |
static GPUOptions.Experimental |
parseFrom(java.io.InputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static com.google.protobuf.Parser<GPUOptions.Experimental> |
parser() |
GPUOptions.Experimental.Builder |
toBuilder() |
void |
writeTo(com.google.protobuf.CodedOutputStream output) |
canUseUnsafe, computeStringSize, computeStringSizeNoTag, emptyBooleanList, emptyDoubleList, emptyFloatList, emptyIntList, emptyLongList, getAllFields, getDescriptorForType, getField, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, hasField, hasOneof, internalGetMapField, makeExtensionsImmutable, mergeFromAndMakeImmutableInternal, mutableCopy, mutableCopy, mutableCopy, mutableCopy, mutableCopy, newBooleanList, newBuilderForType, newDoubleList, newFloatList, newIntList, newLongList, parseDelimitedWithIOException, parseDelimitedWithIOException, parseUnknownField, parseUnknownFieldProto3, parseWithIOException, parseWithIOException, parseWithIOException, parseWithIOException, serializeBooleanMapTo, serializeIntegerMapTo, serializeLongMapTo, serializeStringMapTo, writeReplace, writeString, writeStringNoTagfindInitializationErrors, getInitializationErrorString, hashBoolean, hashEnum, hashEnumList, hashFields, hashLong, toStringaddAll, addAll, checkByteStringIsUtf8, toByteArray, toByteString, writeDelimitedTo, writeToclone, finalize, getClass, notify, notifyAll, wait, wait, waitpublic static final int VIRTUAL_DEVICES_FIELD_NUMBER
public static final int USE_UNIFIED_MEMORY_FIELD_NUMBER
public static final int NUM_DEV_TO_DEV_COPY_STREAMS_FIELD_NUMBER
public static final int COLLECTIVE_RING_ORDER_FIELD_NUMBER
public static final int TIMESTAMPED_ALLOCATOR_FIELD_NUMBER
public static final int KERNEL_TRACKER_MAX_INTERVAL_FIELD_NUMBER
public static final int KERNEL_TRACKER_MAX_BYTES_FIELD_NUMBER
public static final int KERNEL_TRACKER_MAX_PENDING_FIELD_NUMBER
protected java.lang.Object newInstance(com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter unused)
newInstance in class com.google.protobuf.GeneratedMessageV3public final com.google.protobuf.UnknownFieldSet getUnknownFields()
getUnknownFields in interface com.google.protobuf.MessageOrBuildergetUnknownFields in class com.google.protobuf.GeneratedMessageV3public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessageV3public java.util.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;getVirtualDevicesList in interface GPUOptions.ExperimentalOrBuilderpublic java.util.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;getVirtualDevicesOrBuilderList in interface GPUOptions.ExperimentalOrBuilderpublic 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;getVirtualDevicesCount in interface GPUOptions.ExperimentalOrBuilderpublic 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;getVirtualDevices in interface GPUOptions.ExperimentalOrBuilderpublic 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;getVirtualDevicesOrBuilder in interface GPUOptions.ExperimentalOrBuilderpublic 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;getUseUnifiedMemory in interface GPUOptions.ExperimentalOrBuilderpublic 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;getNumDevToDevCopyStreams in interface GPUOptions.ExperimentalOrBuilderpublic java.lang.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;getCollectiveRingOrder in interface GPUOptions.ExperimentalOrBuilderpublic 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;getCollectiveRingOrderBytes in interface GPUOptions.ExperimentalOrBuilderpublic 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;getTimestampedAllocator in interface GPUOptions.ExperimentalOrBuilderpublic 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;getKernelTrackerMaxInterval in interface GPUOptions.ExperimentalOrBuilderpublic 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;getKernelTrackerMaxBytes in interface GPUOptions.ExperimentalOrBuilderpublic 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;getKernelTrackerMaxPending in interface GPUOptions.ExperimentalOrBuilderpublic final boolean isInitialized()
isInitialized in interface com.google.protobuf.MessageLiteOrBuilderisInitialized in class com.google.protobuf.GeneratedMessageV3public void writeTo(com.google.protobuf.CodedOutputStream output)
throws java.io.IOException
writeTo in interface com.google.protobuf.MessageLitewriteTo in class com.google.protobuf.GeneratedMessageV3java.io.IOExceptionpublic int getSerializedSize()
getSerializedSize in interface com.google.protobuf.MessageLitegetSerializedSize in class com.google.protobuf.GeneratedMessageV3public boolean equals(java.lang.Object obj)
equals in interface com.google.protobuf.Messageequals in class com.google.protobuf.AbstractMessagepublic int hashCode()
hashCode in interface com.google.protobuf.MessagehashCode in class com.google.protobuf.AbstractMessagepublic static GPUOptions.Experimental parseFrom(java.nio.ByteBuffer data) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static GPUOptions.Experimental parseFrom(java.nio.ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static GPUOptions.Experimental parseFrom(com.google.protobuf.ByteString data) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static GPUOptions.Experimental parseFrom(com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static GPUOptions.Experimental parseFrom(byte[] data) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static GPUOptions.Experimental parseFrom(byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static GPUOptions.Experimental parseFrom(java.io.InputStream input) throws java.io.IOException
java.io.IOExceptionpublic static GPUOptions.Experimental parseFrom(java.io.InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws java.io.IOException
java.io.IOExceptionpublic static GPUOptions.Experimental parseDelimitedFrom(java.io.InputStream input) throws java.io.IOException
java.io.IOExceptionpublic static GPUOptions.Experimental parseDelimitedFrom(java.io.InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws java.io.IOException
java.io.IOExceptionpublic static GPUOptions.Experimental parseFrom(com.google.protobuf.CodedInputStream input) throws java.io.IOException
java.io.IOExceptionpublic static GPUOptions.Experimental parseFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws java.io.IOException
java.io.IOExceptionpublic GPUOptions.Experimental.Builder newBuilderForType()
newBuilderForType in interface com.google.protobuf.MessagenewBuilderForType in interface com.google.protobuf.MessageLitepublic static GPUOptions.Experimental.Builder newBuilder()
public static GPUOptions.Experimental.Builder newBuilder(GPUOptions.Experimental prototype)
public GPUOptions.Experimental.Builder toBuilder()
toBuilder in interface com.google.protobuf.MessagetoBuilder in interface com.google.protobuf.MessageLiteprotected GPUOptions.Experimental.Builder newBuilderForType(com.google.protobuf.GeneratedMessageV3.BuilderParent parent)
newBuilderForType in class com.google.protobuf.GeneratedMessageV3public static GPUOptions.Experimental getDefaultInstance()
public static com.google.protobuf.Parser<GPUOptions.Experimental> parser()
public com.google.protobuf.Parser<GPUOptions.Experimental> getParserForType()
getParserForType in interface com.google.protobuf.MessagegetParserForType in interface com.google.protobuf.MessageLitegetParserForType in class com.google.protobuf.GeneratedMessageV3public GPUOptions.Experimental getDefaultInstanceForType()
getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuildergetDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder