Efficient Prefix Scan for the GPU-Based Implementation of Random Forest

The random forest ensemble learning with the Graphics Processing Unit (GPU) version of prefix scan method is presented. The efficiency of the implementation of the random forest algorithm depends critically on the scan (prefix sum) algorithm. The prefix scan is used in the depth-first implementation of optimal split point computation. Described are different implementations of the prefix scan algorithms. The speeds of the algorithms depend on three factors: the algorithm itself, which could be improved, the programming skills, and the compiler. In parallel environments, things are even more complicated and depend on the programmer´s knowledge of the Central Processing Unit (CPU) or the GPU architecture. An efficient parallel scan algorithm that avoids bank conflicts is crucial for the prefix scan implementation. In our tests, multicore CPU and GPU implementation based on NVIDIA´s CUDA is compared.

Changing Direction Parallel Scan Path Generating Method through Matching Scan Space for Metal Laser Deposition Shaping

Those ultimate reasons of over-cladding and under-cladding are indicated through analyzing between the existing parallel scan mode and the characteristic of metal laser deposition shaping. A kind of scan path generating method is presented, firstly, scan path is generated base on grouping internal parallel filling scan according to the set scan space in the same layer, then, scan direction is changed base on matching different scan space in different layer. Practical application shows that the scan path can effectively enhance the flatness of shaping layer and the fabrication quality, ensure to shape successfully.