/external/tensorflow/tensorflow/core/common_runtime/sycl/ |
D | sycl_device_context.cc | 113 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 118 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 123 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 128 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 133 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 138 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 143 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 148 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 153 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() 158 device->eigen_sycl_device()->memcpyDeviceToHost( in CopyDeviceTensorToCPU() [all …]
|
/external/eigen/unsupported/test/ |
D | cxx11_tensor_of_float16_cuda.cu | 47 gpu_device.memcpyDeviceToHost(half_prec.data(), d_res_half, num_elem*sizeof(bool)); in test_cuda_numext() 48 gpu_device.memcpyDeviceToHost(full_prec.data(), d_res_float, num_elem*sizeof(bool)); in test_cuda_numext() 87 gpu_device.memcpyDeviceToHost(initial.data(), d_float, num_elem*sizeof(float)); in test_cuda_conversion() 88 gpu_device.memcpyDeviceToHost(final.data(), d_conv, num_elem*sizeof(float)); in test_cuda_conversion() 122 gpu_device.memcpyDeviceToHost(half_prec.data(), d_res_half, num_elem*sizeof(float)); in test_cuda_unary() 123 gpu_device.memcpyDeviceToHost(full_prec.data(), d_res_float, num_elem*sizeof(float)); in test_cuda_unary() 163 gpu_device.memcpyDeviceToHost(half_prec.data(), d_res_half, num_elem*sizeof(float)); in test_cuda_elementwise() 164 gpu_device.memcpyDeviceToHost(full_prec.data(), d_res_float, num_elem*sizeof(float)); in test_cuda_elementwise() 229 gpu_device.memcpyDeviceToHost(input1.data(), d_float1, num_elem*sizeof(float)); in test_cuda_trancendental() 230 gpu_device.memcpyDeviceToHost(input2.data(), d_float2, num_elem*sizeof(float)); in test_cuda_trancendental() [all …]
|
D | cxx11_tensor_sycl.cpp | 56 …sycl_device.memcpyDeviceToHost(in1.data(), gpu_in1_data ,(in1.dimensions().TotalSize())*sizeof(flo… in test_sycl_cpu() 68 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data ,(out.dimensions().TotalSize())*sizeof(flo… in test_sycl_cpu() 82 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,(out.dimensions().TotalSize())*sizeof(floa… in test_sycl_cpu() 96 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,(out.dimensions().TotalSize())*sizeof(floa… in test_sycl_cpu() 110 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,(out.dimensions().TotalSize())*sizeof(floa… in test_sycl_cpu() 124 …sycl_device.memcpyDeviceToHost(out.data(),gpu_out_data,(out.dimensions().TotalSize())*sizeof(float… in test_sycl_cpu() 139 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,(out.dimensions().TotalSize())*sizeof(floa… in test_sycl_cpu()
|
D | cxx11_tensor_reduction_sycl.cpp | 47 sycl_device.memcpyDeviceToHost(full_redux_gpu.data(), gpu_out_data, sizeof(float)); in test_full_reductions_sycl() 82 …sycl_device.memcpyDeviceToHost(redux_gpu.data(), gpu_out_data, redux_gpu.dimensions().TotalSize()*… in test_first_dim_reductions_sycl() 120 …sycl_device.memcpyDeviceToHost(redux_gpu.data(), gpu_out_data, redux_gpu.dimensions().TotalSize()*… in test_last_dim_reductions_sycl()
|
D | cxx11_tensor_cast_float16_cuda.cu | 50 gpu_device.memcpyDeviceToHost(initial.data(), d_float, num_elem*sizeof(float)); in test_cuda_conversion() 51 gpu_device.memcpyDeviceToHost(final.data(), d_conv, num_elem*sizeof(float)); in test_cuda_conversion()
|
D | cxx11_tensor_reduction_cuda.cu | 49 gpu_device.memcpyDeviceToHost(full_redux_gpu.data(), gpu_out_ptr, out_bytes); in test_full_reductions() 87 dev.memcpyDeviceToHost(redux_gpu.data(), out_data, gpu_out.size()*sizeof(Type)); in test_first_dim_reductions() 127 dev.memcpyDeviceToHost(redux_gpu.data(), out_data, gpu_out.size()*sizeof(Type)); in test_last_dim_reductions()
|
D | cxx11_tensor_complex_cuda.cu | 100 gpu_device.memcpyDeviceToHost(full_redux_gpu.data(), gpu_out_ptr, out_bytes); in test_cuda_sum_reductions() 137 gpu_device.memcpyDeviceToHost(full_redux_gpu.data(), gpu_out_ptr, out_bytes); in test_cuda_product_reductions()
|
D | cxx11_tensor_broadcast_sycl.cpp | 54 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,(out.dimensions().TotalSize())*sizeof(floa… in test_broadcast_sycl()
|
D | cxx11_tensor_forced_eval_sycl.cpp | 50 …sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,(out.dimensions().TotalSize())*sizeof(floa… in test_forced_eval_sycl()
|
/external/tensorflow/tensorflow/core/kernels/ |
D | quantize_and_dequantize_op.h | 119 d.memcpyDeviceToHost(&min_range, input_min.data(), sizeof(T)); in Compute() 120 d.memcpyDeviceToHost(&max_range, input_max.data(), sizeof(T)); in Compute()
|
D | reverse_sequence_op.cc | 53 context->eigen_device<Device>().memcpyDeviceToHost( in CheckErrors()
|
D | scatter_op.cc | 209 c->eigen_sycl_device().memcpyDeviceToHost( in DoCompute()
|
D | training_ops.cc | 536 device.memcpyDeviceToHost(&alpha, static_cast<const T*>(src_ptr), size); in Compute() 2944 device.memcpyDeviceToHost(&beta1_power, static_cast<const T*>(src_ptr), in Compute() 2948 device.memcpyDeviceToHost(&beta2_power, static_cast<const T*>(src_ptr), in Compute() 2952 device.memcpyDeviceToHost(&lr, static_cast<const T*>(src_ptr), size); in Compute() 2955 device.memcpyDeviceToHost(&beta1, static_cast<const T*>(src_ptr), size); in Compute() 2958 device.memcpyDeviceToHost(&beta2, static_cast<const T*>(src_ptr), size); in Compute() 2961 device.memcpyDeviceToHost(&epsilon, static_cast<const T*>(src_ptr), size); in Compute()
|
D | scatter_nd_op.cc | 649 device.memcpyDeviceToHost(indices_host_, static_cast<const Index*>(src_ptr), in operator ()()
|
/external/eigen/unsupported/Eigen/CXX11/src/Tensor/ |
D | TensorDeviceDefault.h | 30 …EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE void memcpyDeviceToHost(void* dst, const void* src, size_t n… in memcpyDeviceToHost() function
|
D | TensorDeviceSycl.h | 102 …template<typename T> EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE void memcpyDeviceToHost(T *dst, const T… in memcpyDeviceToHost() function
|
D | TensorDeviceThreadPool.h | 125 EIGEN_STRONG_INLINE void memcpyDeviceToHost(void* dst, const void* src, size_t n) const { in memcpyDeviceToHost() function
|
D | TensorDeviceCuda.h | 231 EIGEN_STRONG_INLINE void memcpyDeviceToHost(void* dst, const void* src, size_t n) const { in initializeDeviceProp() function
|