Searched refs:LAUNCH_CUDA_KERNEL (Results 1 – 6 of 6) sorted by relevance
/external/eigen/unsupported/Eigen/CXX11/src/Tensor/ |
D | TensorReductionCuda.h | 300 LAUNCH_CUDA_KERNEL((FullReductionKernel<block_size, num_per_thread, Self, Op, Index>), 326 LAUNCH_CUDA_KERNEL((ReductionInitFullReduxKernelHalfFloat<Self, Op, Index>), 330 LAUNCH_CUDA_KERNEL((FullReductionKernelHalfFloat<block_size, num_per_thread, Self, Op, Index>), 334 LAUNCH_CUDA_KERNEL((ReductionCleanupKernelHalfFloat<Op>), 573 LAUNCH_CUDA_KERNEL((ReductionInitKernel<OutputType, Index>), 578 LAUNCH_CUDA_KERNEL((InnerReductionKernel<num_per_thread, Self, Op, Index>), 619 LAUNCH_CUDA_KERNEL((ReductionInitKernelHalfFloat<Self, Op, Index>), 623 LAUNCH_CUDA_KERNEL((InnerReductionKernelHalfFloat<num_per_thread, Self, Op, Index>), 732 LAUNCH_CUDA_KERNEL((ReductionInitKernel<float, Index>), 737 LAUNCH_CUDA_KERNEL((OuterReductionKernel<num_per_thread, Self, Op, Index>),
|
D | TensorConvolution.h | 909 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel1D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 913 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel1D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 917 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel1D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 970 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 974 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 983 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 987 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 994 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu… 1040 …LAUNCH_CUDA_KERNEL((EigenConvolutionKernel3D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
|
D | TensorDeviceCuda.h | 317 #define LAUNCH_CUDA_KERNEL(kernel, gridsize, blocksize, sharedmem, device, ...) \ in initializeDeviceProp() macro
|
D | TensorExecutor.h | 260 LAUNCH_CUDA_KERNEL(
|
D | TensorScan.h | 280 …LAUNCH_CUDA_KERNEL((ScanKernel<Self, Reducer>), num_blocks, block_size, 0, self.device(), self, to…
|
D | TensorContractionCuda.h | 1322 …LAUNCH_CUDA_KERNEL((EigenContractionKernel<Scalar, Index, LhsMapper, RhsMapper, OutputMapper>), nu… 1333 …LAUNCH_CUDA_KERNEL((EigenFloatContractionKernel16x16<Index, LhsMapper, RhsMapper, OutputMapper>), … 1339 …LAUNCH_CUDA_KERNEL((EigenFloatContractionKernel<Index, LhsMapper, RhsMapper, OutputMapper>), num_b…
|