以光線追蹤演算法為例之支援非規律型程式可適性異質多核 心執行期軟體函式庫設計

Abstract

異質多核心架構被廣泛地採用於電腦系統中，從手持式裝置、桌上型電腦以致於大型伺服器主機皆有顯著應用。然而，最佳化異質多核心平台，在下列三個面向仍面臨諸多挑戰：首先，執行續內部分歧將使得SIMD元件利用率大幅降低。其次，不同核心裝置間的冗餘資料複製將大幅占用系統頻寬。最後，負載不平衡的問題將造成系統效能低落。本論文針對以上三點問題深入探討，並且提出三種解決方案：中繼資料反饋、動態工作分配以及異質執行續庫加以改善。 我們將上述機制實作於一個衍生自Embree的光線追蹤演算法執行期函式庫中，並且比較兩者之間在不同場景中的效能表現。實驗顯示，在複雜場景中上述的解決方法能帶來顯著的效能提升，特別是當場景中物件眾多以及畫面過於龐大使得CPU無法有效處理的情況下尤其明顯。

Heterogeneous architecture has been widely adopted in various computing systems, from mobile devices to servers. However, optimizing the performance for such platforms remains challenging in three aspects: the control flow divergence decreases the utilization of SIMD components, the significant memory copy overhead between computing devices consuming precious memory bandwidth and the load imbalance that degrades the overall performance. In this paper, we proposed three methodologies: Intermediate Feedback, Dynamic Task Partitioning and Heterogeneous Runtime that work collaboratively to overcome the aforesaid problems. We adopted and implemented these methodologies in a heterogeneous runtime library derived from Intel Embree and compared the performance results of the two frameworks running Ray-Tracing on various scenes. Experiment results have shown that the performance gain from the proposed methods is significant, especially in complex scenes with a large amount of objects or with large input data sizes the CPU cannot handle efficiently.