HomeSort by relevance Sort by last modified time
    Searched refs:LAUNCH_CUDA_KERNEL (Results 1 - 6 of 6) sorted by null

  /external/eigen/unsupported/Eigen/CXX11/src/Tensor/
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>)
    [all...]
TensorConvolution.h     [all...]
TensorDeviceCuda.h 317 #define LAUNCH_CUDA_KERNEL(kernel, gridsize, blocksize, sharedmem, device, ...) \
TensorExecutor.h 260 LAUNCH_CUDA_KERNEL(
TensorScan.h 280 LAUNCH_CUDA_KERNEL((ScanKernel<Self, Reducer>), num_blocks, block_size, 0, self.device(), self, total_size, data);
TensorContractionCuda.h     [all...]

Completed in 496 milliseconds