Home
last modified time | relevance | path

Searched refs:LAUNCH_CUDA_KERNEL (Results 1 – 6 of 6) sorted by relevance

/external/eigen/unsupported/Eigen/CXX11/src/Tensor/
DTensorReductionCuda.h300 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>),
DTensorConvolution.h909LAUNCH_CUDA_KERNEL((EigenConvolutionKernel1D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
913LAUNCH_CUDA_KERNEL((EigenConvolutionKernel1D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
917LAUNCH_CUDA_KERNEL((EigenConvolutionKernel1D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
970LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
974LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
983LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
987LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
994LAUNCH_CUDA_KERNEL((EigenConvolutionKernel2D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
1040LAUNCH_CUDA_KERNEL((EigenConvolutionKernel3D<TensorEvaluator<InputArgType, GpuDevice>, Index, Inpu…
DTensorDeviceCuda.h317 #define LAUNCH_CUDA_KERNEL(kernel, gridsize, blocksize, sharedmem, device, ...) \ in initializeDeviceProp() macro
DTensorExecutor.h260 LAUNCH_CUDA_KERNEL(
DTensorScan.h280LAUNCH_CUDA_KERNEL((ScanKernel<Self, Reducer>), num_blocks, block_size, 0, self.device(), self, to…
DTensorContractionCuda.h1322LAUNCH_CUDA_KERNEL((EigenContractionKernel<Scalar, Index, LhsMapper, RhsMapper, OutputMapper>), nu…
1333LAUNCH_CUDA_KERNEL((EigenFloatContractionKernel16x16<Index, LhsMapper, RhsMapper, OutputMapper>), …
1339LAUNCH_CUDA_KERNEL((EigenFloatContractionKernel<Index, LhsMapper, RhsMapper, OutputMapper>), num_b…