Class GPUOptions

java.lang.Object
com.google.protobuf.AbstractMessageLite
com.google.protobuf.AbstractMessage
com.google.protobuf.GeneratedMessage
org.tensorflow.proto.GPUOptions
All Implemented Interfaces:
Message, MessageLite, MessageLiteOrBuilder, MessageOrBuilder, Serializable, GPUOptionsOrBuilder
@Generated public final class GPUOptions extends GeneratedMessage implements GPUOptionsOrBuilder
Protobuf type tensorflow.GPUOptions
See Also:

  • Field Details

    • PER_PROCESS_GPU_MEMORY_FRACTION_FIELD_NUMBER

      public static final int PER_PROCESS_GPU_MEMORY_FRACTION_FIELD_NUMBER
      See Also:

    • ALLOW_GROWTH_FIELD_NUMBER

      public static final int ALLOW_GROWTH_FIELD_NUMBER
      See Also:

    • ALLOCATOR_TYPE_FIELD_NUMBER

      public static final int ALLOCATOR_TYPE_FIELD_NUMBER
      See Also:

    • DEFERRED_DELETION_BYTES_FIELD_NUMBER

      public static final int DEFERRED_DELETION_BYTES_FIELD_NUMBER
      See Also:

    • VISIBLE_DEVICE_LIST_FIELD_NUMBER

      public static final int VISIBLE_DEVICE_LIST_FIELD_NUMBER
      See Also:

    • POLLING_ACTIVE_DELAY_USECS_FIELD_NUMBER

      public static final int POLLING_ACTIVE_DELAY_USECS_FIELD_NUMBER
      See Also:

    • POLLING_INACTIVE_DELAY_MSECS_FIELD_NUMBER

      public static final int POLLING_INACTIVE_DELAY_MSECS_FIELD_NUMBER
      See Also:

    • FORCE_GPU_COMPATIBLE_FIELD_NUMBER

      public static final int FORCE_GPU_COMPATIBLE_FIELD_NUMBER
      See Also:

    • EXPERIMENTAL_FIELD_NUMBER

      public static final int EXPERIMENTAL_FIELD_NUMBER
      See Also:

  • Method Details

    • getDescriptor

      public static final Descriptors.Descriptor getDescriptor()

    • internalGetFieldAccessorTable

      protected GeneratedMessage.FieldAccessorTable internalGetFieldAccessorTable()
      Specified by:
      internalGetFieldAccessorTable in class GeneratedMessage

    • getPerProcessGpuMemoryFraction

      public double getPerProcessGpuMemoryFraction()
      Fraction of the total GPU memory to allocate for each process.
1 means to allocate all of the GPU memory, 0.5 means the process
allocates up to ~50% of the total GPU memory.

GPU memory is pre-allocated unless the allow_growth option is enabled.

If greater than 1.0, uses CUDA unified memory to potentially oversubscribe
the amount of memory available on the GPU device by using host memory as a
swap space. Accessing memory not available on the device will be
significantly slower as that would require memory transfer between the host
and the device. Options to reduce the memory requirement should be
considered before enabling this option as this may come with a negative
performance impact. Oversubscription using the unified memory requires
Pascal class or newer GPUs and it is currently only supported on the Linux
operating system. See
https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#um-requirements
for the detailed requirements.
      double per_process_gpu_memory_fraction = 1;
      Specified by:
      getPerProcessGpuMemoryFraction in interface GPUOptionsOrBuilder
      Returns:
      The perProcessGpuMemoryFraction.

    • getAllowGrowth

      public boolean getAllowGrowth()
      If true, the allocator does not pre-allocate the entire specified
GPU memory region, instead starting small and growing as needed.
      bool allow_growth = 4;
      Specified by:
      getAllowGrowth in interface GPUOptionsOrBuilder
      Returns:
      The allowGrowth.

    • getAllocatorType

      public String getAllocatorType()
      The type of GPU allocation strategy to use.

Allowed values:
"": The empty string (default) uses a system-chosen default
which may change over time.

"BFC": A "Best-fit with coalescing" algorithm, simplified from a
version of dlmalloc.
      string allocator_type = 2;
      Specified by:
      getAllocatorType in interface GPUOptionsOrBuilder
      Returns:
      The allocatorType.

    • getAllocatorTypeBytes

      public ByteString getAllocatorTypeBytes()
      The type of GPU allocation strategy to use.

Allowed values:
"": The empty string (default) uses a system-chosen default
which may change over time.

"BFC": A "Best-fit with coalescing" algorithm, simplified from a
version of dlmalloc.
      string allocator_type = 2;
      Specified by:
      getAllocatorTypeBytes in interface GPUOptionsOrBuilder
      Returns:
      The bytes for allocatorType.

    • getDeferredDeletionBytes

      public long getDeferredDeletionBytes()
      Delay deletion of up to this many bytes to reduce the number of
interactions with gpu driver code.  If 0, the system chooses
a reasonable default (several MBs).
      int64 deferred_deletion_bytes = 3;
      Specified by:
      getDeferredDeletionBytes in interface GPUOptionsOrBuilder
      Returns:
      The deferredDeletionBytes.

    • getVisibleDeviceList

      public String getVisibleDeviceList()
      A comma-separated list of GPU ids that determines the 'visible'
to 'virtual' mapping of GPU devices.  For example, if TensorFlow
can see 8 GPU devices in the process, and one wanted to map
visible GPU devices 5 and 3 as "/device:GPU:0", and "/device:GPU:1",
then one would specify this field as "5,3".  This field is similar in
spirit to the CUDA_VISIBLE_DEVICES environment variable, except
it applies to the visible GPU devices in the process.

NOTE:
1. The GPU driver provides the process with the visible GPUs
in an order which is not guaranteed to have any correlation to
the *physical* GPU id in the machine.  This field is used for
remapping "visible" to "virtual", which means this operates only
after the process starts.  Users are required to use vendor
specific mechanisms (e.g., CUDA_VISIBLE_DEVICES) to control the
physical to visible device mapping prior to invoking TensorFlow.
2. In the code, the ids in this list are also called "platform GPU id"s,
and the 'virtual' ids of GPU devices (i.e. the ids in the device
name "/device:GPU:<id>") are also called "TF GPU id"s. Please
refer to third_party/tensorflow/core/common_runtime/gpu/gpu_id.h
for more information.
3. The visible_device_list is also used for PluggableDevice. And
different types of PluggableDevices share this field. In that case,
the pluggable_device_type is used to distinguish them, making the
visible_device_list a list of <pluggable_device_type>:<device_index>,
e.g. "PluggableDeviceA:0,PluggableDeviceA:1,PluggableDeviceB:0".
      string visible_device_list = 5;
      Specified by:
      getVisibleDeviceList in interface GPUOptionsOrBuilder
      Returns:
      The visibleDeviceList.

    • getVisibleDeviceListBytes

      public ByteString getVisibleDeviceListBytes()
      A comma-separated list of GPU ids that determines the 'visible'
to 'virtual' mapping of GPU devices.  For example, if TensorFlow
can see 8 GPU devices in the process, and one wanted to map
visible GPU devices 5 and 3 as "/device:GPU:0", and "/device:GPU:1",
then one would specify this field as "5,3".  This field is similar in
spirit to the CUDA_VISIBLE_DEVICES environment variable, except
it applies to the visible GPU devices in the process.

NOTE:
1. The GPU driver provides the process with the visible GPUs
in an order which is not guaranteed to have any correlation to
the *physical* GPU id in the machine.  This field is used for
remapping "visible" to "virtual", which means this operates only
after the process starts.  Users are required to use vendor
specific mechanisms (e.g., CUDA_VISIBLE_DEVICES) to control the
physical to visible device mapping prior to invoking TensorFlow.
2. In the code, the ids in this list are also called "platform GPU id"s,
and the 'virtual' ids of GPU devices (i.e. the ids in the device
name "/device:GPU:<id>") are also called "TF GPU id"s. Please
refer to third_party/tensorflow/core/common_runtime/gpu/gpu_id.h
for more information.
3. The visible_device_list is also used for PluggableDevice. And
different types of PluggableDevices share this field. In that case,
the pluggable_device_type is used to distinguish them, making the
visible_device_list a list of <pluggable_device_type>:<device_index>,
e.g. "PluggableDeviceA:0,PluggableDeviceA:1,PluggableDeviceB:0".
      string visible_device_list = 5;
      Specified by:
      getVisibleDeviceListBytes in interface GPUOptionsOrBuilder
      Returns:
      The bytes for visibleDeviceList.

    • getPollingActiveDelayUsecs

      public int getPollingActiveDelayUsecs()
      In the event polling loop sleep this many microseconds between
PollEvents calls, when the queue is not empty.  If value is not
set or set to 0, gets set to a non-zero default.
      int32 polling_active_delay_usecs = 6;
      Specified by:
      getPollingActiveDelayUsecs in interface GPUOptionsOrBuilder
      Returns:
      The pollingActiveDelayUsecs.

    • getPollingInactiveDelayMsecs

      public int getPollingInactiveDelayMsecs()
      This field is deprecated and ignored.
      int32 polling_inactive_delay_msecs = 7;
      Specified by:
      getPollingInactiveDelayMsecs in interface GPUOptionsOrBuilder
      Returns:
      The pollingInactiveDelayMsecs.

    • getForceGpuCompatible

      public boolean getForceGpuCompatible()
      Force all tensors to be gpu_compatible. On a GPU-enabled TensorFlow,
enabling this option forces all CPU tensors to be allocated with Cuda
pinned memory. Normally, TensorFlow will infer which tensors should be
allocated as the pinned memory. But in case where the inference is
incomplete, this option can significantly speed up the cross-device memory
copy performance as long as it fits the memory.
Note that this option is not something that should be
enabled by default for unknown or very large models, since all Cuda pinned
memory is unpageable, having too much pinned memory might negatively impact
the overall host system performance.
      bool force_gpu_compatible = 8;
      Specified by:
      getForceGpuCompatible in interface GPUOptionsOrBuilder
      Returns:
      The forceGpuCompatible.

    • hasExperimental

      public boolean hasExperimental()
      Everything inside experimental is subject to change and is not subject
to API stability guarantees in
https://www.tensorflow.org/guide/versions.
      .tensorflow.GPUOptions.Experimental experimental = 9;
      Specified by:
      hasExperimental in interface GPUOptionsOrBuilder
      Returns:
      Whether the experimental field is set.

    • getExperimental

      public GPUOptions.Experimental getExperimental()
      Everything inside experimental is subject to change and is not subject
to API stability guarantees in
https://www.tensorflow.org/guide/versions.
      .tensorflow.GPUOptions.Experimental experimental = 9;
      Specified by:
      getExperimental in interface GPUOptionsOrBuilder
      Returns:
      The experimental.

    • getExperimentalOrBuilder

      public GPUOptions.ExperimentalOrBuilder getExperimentalOrBuilder()
      Everything inside experimental is subject to change and is not subject
to API stability guarantees in
https://www.tensorflow.org/guide/versions.
      .tensorflow.GPUOptions.Experimental experimental = 9;
      Specified by:
      getExperimentalOrBuilder in interface GPUOptionsOrBuilder

    • isInitialized

      public final boolean isInitialized()
      Specified by:
      isInitialized in interface MessageLiteOrBuilder
      Overrides:
      isInitialized in class GeneratedMessage

    • writeTo

      public void writeTo(CodedOutputStream output) throws IOException
      Specified by:
      writeTo in interface MessageLite
      Overrides:
      writeTo in class GeneratedMessage
      Throws:
      IOException

    • getSerializedSize

      public int getSerializedSize()
      Specified by:
      getSerializedSize in interface MessageLite
      Overrides:
      getSerializedSize in class GeneratedMessage

    • equals

      public boolean equals(Object obj)
      Specified by:
      equals in interface Message
      Overrides:
      equals in class AbstractMessage

    • hashCode

      public int hashCode()
      Specified by:
      hashCode in interface Message
      Overrides:
      hashCode in class AbstractMessage

    • parseFrom

      public static GPUOptions parseFrom(ByteBuffer data) throws InvalidProtocolBufferException
      Throws:
      InvalidProtocolBufferException

    • parseFrom

      public static GPUOptions parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry) throws InvalidProtocolBufferException
      Throws:
      InvalidProtocolBufferException

    • parseFrom

      public static GPUOptions parseFrom(ByteString data) throws InvalidProtocolBufferException
      Throws:
      InvalidProtocolBufferException

    • parseFrom

      public static GPUOptions parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry) throws InvalidProtocolBufferException
      Throws:
      InvalidProtocolBufferException

    • parseFrom

      public static GPUOptions parseFrom(byte[] data) throws InvalidProtocolBufferException
      Throws:
      InvalidProtocolBufferException

    • parseFrom

      public static GPUOptions parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry) throws InvalidProtocolBufferException
      Throws:
      InvalidProtocolBufferException

    • parseFrom

      public static GPUOptions parseFrom(InputStream input) throws IOException
      Throws:
      IOException

    • parseFrom

      public static GPUOptions parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException

    • parseDelimitedFrom

      public static GPUOptions parseDelimitedFrom(InputStream input) throws IOException
      Throws:
      IOException

    • parseDelimitedFrom

      public static GPUOptions parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException

    • parseFrom

      public static GPUOptions parseFrom(CodedInputStream input) throws IOException
      Throws:
      IOException

    • parseFrom

      public static GPUOptions parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException

    • newBuilderForType

      public GPUOptions.Builder newBuilderForType()
      Specified by:
      newBuilderForType in interface Message
      Specified by:
      newBuilderForType in interface MessageLite

    • newBuilder

      public static GPUOptions.Builder newBuilder()

    • newBuilder

      public static GPUOptions.Builder newBuilder(GPUOptions prototype)

    • toBuilder

      public GPUOptions.Builder toBuilder()
      Specified by:
      toBuilder in interface Message
      Specified by:
      toBuilder in interface MessageLite

    • newBuilderForType

      protected GPUOptions.Builder newBuilderForType(AbstractMessage.BuilderParent parent)
      Overrides:
      newBuilderForType in class AbstractMessage

    • getDefaultInstance

      public static GPUOptions getDefaultInstance()

    • parser

      public static Parser<GPUOptions> parser()

    • getParserForType

      public Parser<GPUOptions> getParserForType()
      Specified by:
      getParserForType in interface Message
      Specified by:
      getParserForType in interface MessageLite
      Overrides:
      getParserForType in class GeneratedMessage

    • getDefaultInstanceForType

      public GPUOptions getDefaultInstanceForType()
      Specified by:
      getDefaultInstanceForType in interface MessageLiteOrBuilder
      Specified by:
      getDefaultInstanceForType in interface MessageOrBuilder