public final class
GPUOptions
Protobuf type tensorflow.GPUOptions
Nested Classes
class | GPUOptions.Builder | Protobuf type tensorflow.GPUOptions
|
|
class | GPUOptions.Experimental | Protobuf type tensorflow.GPUOptions.Experimental
|
|
interface | GPUOptions.ExperimentalOrBuilder |
Constants
Public Methods
boolean |
equals(Object obj)
|
String |
getAllocatorType()
The type of GPU allocation strategy to use. |
com.google.protobuf.ByteString |
getAllocatorTypeBytes()
The type of GPU allocation strategy to use. |
boolean |
getAllowGrowth()
If true, the allocator does not pre-allocate the entire specified GPU memory region, instead starting small and growing as needed. |
static GPUOptions | |
GPUOptions | |
long |
getDeferredDeletionBytes()
Delay deletion of up to this many bytes to reduce the number of interactions with gpu driver code. |
final static com.google.protobuf.Descriptors.Descriptor | |
GPUOptions.Experimental |
getExperimental()
Everything inside experimental is subject to change and is not subject to API stability guarantees in https://www.tensorflow.org/guide/version_compat. |
GPUOptions.ExperimentalOrBuilder |
getExperimentalOrBuilder()
Everything inside experimental is subject to change and is not subject to API stability guarantees in https://www.tensorflow.org/guide/version_compat. |
boolean |
getForceGpuCompatible()
Force all tensors to be gpu_compatible. |
|
|
double |
getPerProcessGpuMemoryFraction()
Fraction of the available GPU memory to allocate for each process. |
int |
getPollingActiveDelayUsecs()
In the event polling loop sleep this many microseconds between PollEvents calls, when the queue is not empty. |
int |
getPollingInactiveDelayMsecs()
This field is deprecated and ignored. |
int | |
final com.google.protobuf.UnknownFieldSet | |
String |
getVisibleDeviceList()
A comma-separated list of GPU ids that determines the 'visible' to 'virtual' mapping of GPU devices. |
com.google.protobuf.ByteString |
getVisibleDeviceListBytes()
A comma-separated list of GPU ids that determines the 'visible' to 'virtual' mapping of GPU devices. |
boolean |
hasExperimental()
Everything inside experimental is subject to change and is not subject to API stability guarantees in https://www.tensorflow.org/guide/version_compat. |
int |
hashCode()
|
final boolean | |
static GPUOptions.Builder |
newBuilder(GPUOptions prototype)
|
static GPUOptions.Builder | |
GPUOptions.Builder | |
static GPUOptions |
parseDelimitedFrom(InputStream input)
|
static GPUOptions |
parseDelimitedFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
|
static GPUOptions |
parseFrom(ByteBuffer data)
|
static GPUOptions |
parseFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
|
static GPUOptions |
parseFrom(ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
|
static GPUOptions |
parseFrom(com.google.protobuf.CodedInputStream input)
|
static GPUOptions |
parseFrom(byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
|
static GPUOptions |
parseFrom(com.google.protobuf.ByteString data)
|
static GPUOptions |
parseFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
|
static GPUOptions |
parseFrom(com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
|
static
|
parser()
|
GPUOptions.Builder | |
void |
writeTo(com.google.protobuf.CodedOutputStream output)
|
Inherited Methods
Constants
public static final int ALLOCATOR_TYPE_FIELD_NUMBER
Constant Value:
2
public static final int ALLOW_GROWTH_FIELD_NUMBER
Constant Value:
4
public static final int DEFERRED_DELETION_BYTES_FIELD_NUMBER
Constant Value:
3
public static final int EXPERIMENTAL_FIELD_NUMBER
Constant Value:
9
public static final int FORCE_GPU_COMPATIBLE_FIELD_NUMBER
Constant Value:
8
public static final int PER_PROCESS_GPU_MEMORY_FRACTION_FIELD_NUMBER
Constant Value:
1
public static final int POLLING_ACTIVE_DELAY_USECS_FIELD_NUMBER
Constant Value:
6
public static final int POLLING_INACTIVE_DELAY_MSECS_FIELD_NUMBER
Constant Value:
7
public static final int VISIBLE_DEVICE_LIST_FIELD_NUMBER
Constant Value:
5
Public Methods
public boolean equals (Object obj)
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;
public com.google.protobuf.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;
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;
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;
public static final com.google.protobuf.Descriptors.Descriptor getDescriptor ()
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/version_compat.
.tensorflow.GPUOptions.Experimental experimental = 9;
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/version_compat.
.tensorflow.GPUOptions.Experimental experimental = 9;
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;
public
getParserForType
()
public double getPerProcessGpuMemoryFraction ()
Fraction of the available 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 available 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;
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;
public int getPollingInactiveDelayMsecs ()
This field is deprecated and ignored.
int32 polling_inactive_delay_msecs = 7;
public int getSerializedSize ()
public final com.google.protobuf.UnknownFieldSet getUnknownFields ()
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.
string visible_device_list = 5;
public com.google.protobuf.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.
string visible_device_list = 5;
public boolean hasExperimental ()
Everything inside experimental is subject to change and is not subject to API stability guarantees in https://www.tensorflow.org/guide/version_compat.
.tensorflow.GPUOptions.Experimental experimental = 9;
public int hashCode ()
public final boolean isInitialized ()
public static GPUOptions parseDelimitedFrom (InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
Throws
IOException |
---|
public static GPUOptions parseFrom (com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
Throws
IOException |
---|
public static GPUOptions parseFrom (ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
Throws
InvalidProtocolBufferException |
---|
public static GPUOptions parseFrom (byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
Throws
InvalidProtocolBufferException |
---|
public static GPUOptions parseFrom (com.google.protobuf.ByteString data)
Throws
InvalidProtocolBufferException |
---|
public static GPUOptions parseFrom (InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
Throws
IOException |
---|
public static GPUOptions parseFrom (com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
Throws
InvalidProtocolBufferException |
---|
public
static
parser
()
public void writeTo (com.google.protobuf.CodedOutputStream output)
Throws
IOException |
---|