Paddle

Author	SHA1	Message	Date
QI JUN	61ec0b9516	Refine device context (#6433 ) There are mainly following fixes: - take `DeviceContext` as the template parameter of math functors and OpKernel instead of `Place` - remove `eigen_device` interface in base class `DeviceContext` - remove `GetEigenDevice` interface in `ExecutionContext` and base class `DeviceContext` - remove unused `platform::EigenDeviceConverter` - rename `REGISTER_OP_GPU_KERNEL` to `REGISTER_OP_CUDA_KERNEL` - rename `USE_GPU_ONLY_OP` to `USE_CUDA_ONLY_OP`	7 years ago
Markus Kliegl	d0b601c4a8	address PR feedback	7 years ago
Markus Kliegl	42dd5da0fd	conv shift: fix return before syncthreads	7 years ago
Markus Kliegl	3dc8834209	conv shift op: change to CamelCase	7 years ago
typhoonzero	272f3e6d43	refine get cuda context	7 years ago
Markus Kliegl	a281b38393	Conv Shift Operator (#4591 ) * conv_shift_op: initial implementation using Eigen Limitations: - both gradient outputs must be specified and are always computed - explicit for loops => could be optimized in various ways (e.g., different memory layout) * conv shift - gradient fixes fix case when not all output gradients desired * conv shift: minor cleanup * conv shift - more minor cleanup * conv shift: clean up & initial GPU implementation * fix rebase issue	7 years ago