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`	9 years ago
chengduoZH	8711a9a22a	refine code	9 years ago
chengduoZH	37671ac053	follow comments	9 years ago
chengduoZH	9e244a8cbe	follow comments	9 years ago
chengduoZH	54f09620cf	code refine	9 years ago
chengduoZH	488908e95b	refine cuda	9 years ago
chengduoZH	fbbfe8b859	code refine	9 years ago
Yu Yang	8ac02279f2	Fix the proformance problem of enforce (#6085 ) * Fix Proformance problem of enforce * Fix missing `;` in code * Fix CI	9 years ago
qijun	9e6404441c	fix elementwise add bug	9 years ago
qiaolongfei	729b2152ae	add include op_registry.h to elementwise_op_function.h	9 years ago
qiaolongfei	0fa4b985a9	split elementwise_op.h into two header files	9 years ago