| /external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
| D | buffer_comparator.cc | 113 stream->ThenMemcpy(&buffer, ref_buffer, ref_buffer.size()); in Create()
152 stream_->ThenMemcpy(&result, result_buffer.root_buffer(), sizeof(result)); in CompareEqualImpl()
167 stream_->ThenMemcpy(host_ref_buffer.data(), ref_buffer_.root_buffer(), in CompareEqual()
169 stream_->ThenMemcpy(host_test_buffer.data(), test_buffer, test_buffer.size()); in CompareEqual()
|
| D | infeed_thunk.cc | 71 stream->ThenMemcpy(&tuple_element_address, in ExecuteOnStream()
92 stream->ThenMemcpy(&tuple_address, in ExecuteOnStream()
109 stream->ThenMemcpy(&top_level_address, infeed_addresses, 2 * sizeof(void*)); in ExecuteOnStream()
|
| D | copy_thunk.cc | 39 stream->ThenMemcpy(&destination_data, source_address_, mem_size_); in ExecuteOnStream()
60 stream->ThenMemcpy(&destination_data, source_data, mem_size_); in ExecuteOnStream()
|
| D | conditional_thunk.cc | 69 stream->ThenMemcpy(&pred, branch_index_address, sizeof(bool)); in ExecuteOnStream()
71 stream->ThenMemcpy(&branch_index, branch_index_address, sizeof(int32)); in ExecuteOnStream()
|
| D | outfeed_thunk.cc | 76 stream->ThenMemcpy(tuple_element_buffer_addresses.data(), in ExecuteOnStream()
90 ->ThenMemcpy((*buffer)->destination()->untyped_data(), data_address, in ExecuteOnStream()
|
| D | buffer_comparator_test.cc | 59 stream.ThenMemcpy(&lhs_buffer, lhs.data(), lhs_buffer.size()); in CompareEqualFloatBuffers()
60 stream.ThenMemcpy(&rhs_buffer, rhs.data(), rhs_buffer.size()); in CompareEqualFloatBuffers()
|
| D | tuple_thunk.cc | 40 ->ThenMemcpy(&dest_buffer_address, in ExecuteOnStream()
|
| D | while_thunk.cc | 67 stream->ThenMemcpy(&condition_result, condition_result_data, sizeof(bool)); in ExecuteOnStream()
|
| D | gpu_transfer_manager.cc | 113 stream->ThenMemcpy(buffer.device_memory(), source, size); in TransferBufferToInfeedInternal()
|
| D | cudnn_conv_algorithm_picker.cc | 197 stream.ThenMemcpy(&left_over, halfs, left_over_bytes); in PickBestAlgorithm()
|
| /external/tensorflow/tensorflow/core/common_runtime/gpu/ |
| D | gpu_util.cc | 162 send_device_to_host_stream->ThenMemcpy(buf, gpu_src_ptr, total_bytes); in SetProtoFromGPU()
232 send_device_to_device_stream->ThenMemcpy(&gpu_dst_ptr, gpu_src_ptr, in DeviceToDeviceCopy()
284 send_device_to_host_stream->ThenMemcpy(dst_ptr, gpu_src_ptr, total_bytes); in CopyGPUTensorToCPU()
330 recv_host_to_device_stream->ThenMemcpy(&gpu_dst_ptr, src_ptr, total_bytes); in CopyCPUTensorToGPU()
443 send_stream->ThenMemcpy(&gpu_dst_ptr, gpu_src_ptr, total_bytes); in CopyGPUTensorToSameGPU()
|
| /external/tensorflow/tensorflow/core/kernels/ |
| D | gpu_device_array.h | 86 stream->ThenMemcpy(&output_values_base, in Finalize()
|
| D | check_numerics_op.cc | 170 ->ThenMemcpy(abnormal_detected_host.flat<int>().data(), in ComputeAsync()
|
| D | where_op.cc | 297 ->ThenMemcpy(num_true_host.mutable_data(), num_true_ptr, in ComputeAsyncType()
|
| D | cuda_solvers.h | 413 stream->ThenMemcpy(copy.mutable_data(), wrapped_src, this->bytes())
|
| D | dynamic_partition_op_gpu.cu.cc | 293 ->ThenMemcpy(cpu_tensor.flat<int32>().data(), wrapped, in ComputeAsync()
|
| D | cudnn_rnn_ops.cc | 884 stream->ThenMemcpy(&data_dst_ptr, data_src_ptr, size_in_bytes); in RestoreParams()
1162 stream->ThenMemcpy(&data_dst_ptr, data_src_ptr, size_in_bytes); in Compute()
1183 stream->ThenMemcpy(&data_dst_ptr, data_src_ptr, size_in_bytes); in Compute()
|
| D | crop_and_resize_op.cc | 797 ->ThenMemcpy( in RunIfBoxIndexIsValid()
|
| D | cuda_solvers.cc | 87 return stream->ThenMemcpy(&wrapped_dst, src, bytes).ok(); in CopyHostToDevice()
|
| D | segment_reduction_ops.cc | 256 ->ThenMemcpy(output_rows_host.mutable_data(), output_rows_device, in ComputeAsync()
|
| /external/tensorflow/tensorflow/compiler/xla/service/ |
| D | transfer_manager.cc | 292 stream->ThenMemcpy(destination, source, size); in TransferBufferFromDevice()
305 stream->ThenMemcpy(destination, source, size); in TransferBufferToDevice()
|
| /external/tensorflow/tensorflow/core/nccl/ |
| D | nccl_manager_test.cc | 129 stream->ThenMemcpy(&in_gpu_mem, in_cpu.flat<Scalar>().data(), in MakeReductionTestCase()
170 stream->ThenMemcpy(&in_gpu_mem, in_cpu.flat<Scalar>().data(), in MakeGatherTestCase()
199 stream->ThenMemcpy(out_cpu.flat<Scalar>().data(), out_gpu_mem, in VerifyResults()
|
| /external/tensorflow/tensorflow/stream_executor/ |
| D | stream.h | 1680 Stream &ThenMemcpy(void *host_dst, const DeviceMemoryBase &gpu_src,
1687 Stream &ThenMemcpy(DeviceMemoryBase *gpu_dst, const void *host_src,
1698 return ThenMemcpy(host_dst.begin(), gpu_src, host_size); in ThenMemcpyD2H()
1709 return ThenMemcpy(gpu_dst, host_src.begin(), host_size); in ThenMemcpyH2D()
1715 Stream &ThenMemcpy(DeviceMemoryBase *gpu_dst, const DeviceMemoryBase &gpu_src,
1723 return ThenMemcpy(gpu_dst, gpu_src, size); in ThenMemcpyD2D()
|
| D | stream.cc | 4780 Stream &Stream::ThenMemcpy(void *host_dst, const DeviceMemoryBase &gpu_src, in ThenMemcpy() function in stream_executor::Stream
4793 Stream &Stream::ThenMemcpy(DeviceMemoryBase *gpu_dst, const void *host_src, in ThenMemcpy() function in stream_executor::Stream
4806 Stream &Stream::ThenMemcpy(DeviceMemoryBase *gpu_dst, in ThenMemcpy() function in stream_executor::Stream
|
| /external/tensorflow/tensorflow/stream_executor/cuda/ |
| D | cuda_blas.cc | 2202 if (!stream->ThenMemcpy(&a, a_raw_ptrs.data(), size).ok() || in DoBlasGemmBatchedInternal()
2203 !stream->ThenMemcpy(&b, b_raw_ptrs.data(), size).ok() || in DoBlasGemmBatchedInternal()
2204 !stream->ThenMemcpy(&c, c_raw_ptrs.data(), size).ok()) { in DoBlasGemmBatchedInternal()
|