Mighty-morphing power-SIMD

In modern wireless devices, two broad classes of compute-intensive applications are common: those with high amounts of data-level parallelism, such as signal processing used in wireless baseband applications, and those that have little data-level parallelism, such as encryption. Wide single-instruction multiple-data (SIMD) processors have become popular for providing high performance, yet power efficient data engines for applications with abundant data parallelism. However, the non-data-parallel applications are relegated to a low-performance scalar datapath on these data engines while the SIMD resources are left idle. To accelerate both types of applications, we propose the design of a more flexible SIMD datapath called SIMD-Morph. In SIMD-Morph, code with datalevel parallelism can be executed across the lanes in the traditional manner, but the lanes can be morphed into a feed-forward subgraph accelerator to execute scalar applications more efficiently. The morphed SIMD lanes form an...

• Type: Journal
• Year: 2010
• Where: CASES
• Authors: Ganesh S. Dasika, Mark Woh, Sangwon Seo, Nathan Clark, Trevor N. Mudge, Scott A. Mahlke
• Keywords: CASES 2010, Data Engines, Data-level Parallelism, SIMD, System Software