从SSE到OpenCL:多核CPU上骨骼动画并行算法对比研究

From SSE to Open CL: Comparison of Parallel Algorithms for Skeletal Animation on Multi-core CPUs

拥有高精度蒙皮和复杂骨骼绑定关系的骨骼动画,渲染时存在很大的性能瓶颈。以往研究采用GPU加速动画,但高端GPU成本过高,而中低端GPU的通用计算性能有时不如高端CPU。为充分挖掘算法在多核CPU上的执行性能,弥补中低端GPU通用计算性能的不足,提出了基于Open CL的针对指令和线程的新兴集成并行方案,并与基于SSE结合Open MP针对指令和线程的传统独立并行方案展开对比。实验结果表明,在多数CPU和多种复杂度的数据上,基于Open CL的新兴并行方案的性能明显高于基于SSE的传统并行方案,并且性能优势随着数据复杂度的增加而提升。

While skeletal animations consist of high fidelity mesh and complex vertex binding, there is a huge performance bottleneck. Previous studies used GPUs to accelerate animation, but the general purpose computing performance of cheap GPUs was lower than high end CPUs. In order to explore the performance for multi-core CPUs to make up the shortfall of cheap GPUs for general purpose computing, the latest parallel scheme based on Open CL which integrated the former two levels of parallelization was proposed, comparing to the traditional parallel scheme formed by SSE and Open MP oriented to instruction parallelization and thread parallelization separately. The experimental results show that on most CPU with different complex data, the performance of the parallel scheme based on Open CL is better than SSE. And the more complex the data is, the greater the performance advantage grows.