hub / github.com/benoitsteiner/tensorflow-opencl / gpu

Method gpu

tensorflow/python/framework/ops.py:722–733 · view source on GitHub ↗

A copy of this Tensor with contents backed by memory on the GPU. Arguments: gpu_index: Identifies which GPU to place the contents on the returned Tensor in. Returns: A GPU-memory backed Tensor object initialized with the same contents as this Tensor.

(self, gpu_index=0)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 15

testGPUMethod · 0.80

testMatMulGPUMethod · 0.80

testOpWithInputsOnDifferentDevicesMethod · 0.80

testOutputOnHostMemoryMethod · 0.80

testSilentCopyMethod · 0.80

testTensorPlacementMethod · 0.80

testCopyBetweenDevicesMethod · 0.80

testNumpyForceCPUMethod · 0.80

testMatMulGPUMethod · 0.80

testOperationWithNoInputsRunsOnDeviceMethod · 0.80

benchmark_matmulFunction · 0.80

fnMethod · 0.80

Calls 2

_copyMethod · 0.95

contextMethod · 0.45

Tested by 15

testGPUMethod · 0.64

testMatMulGPUMethod · 0.64

testOpWithInputsOnDifferentDevicesMethod · 0.64

testOutputOnHostMemoryMethod · 0.64

testSilentCopyMethod · 0.64

testTensorPlacementMethod · 0.64

testCopyBetweenDevicesMethod · 0.64

testNumpyForceCPUMethod · 0.64

testMatMulGPUMethod · 0.64

testOperationWithNoInputsRunsOnDeviceMethod · 0.64

benchmark_matmulFunction · 0.64

fnMethod · 0.64