The performance of the Cortex-R82 prefetcher and the intensity of prefetching required across different application areas using various industry standard benchmarks to measure the performance of the processor.
High-performance processors employ hardware data prefetching to reduce the negative performance impact of large main memory latencies. An effective prefetching mechanism can improve cache hit rate significantly. Data prefetching boosts the execution performance by fetching data before it is needed. While prefetching improves performance substantially on many programs, it can significantly reduce performance on others. Therefore, even though Cortex-R82 has some control over the prefetchers, how it should be enabled is an implementation choice. This can be done by using different control options to configure the prefetcher capabilities. In this paper, the investigation has been done on prefetcher capabilities of Cortex-R82 with a baseline where no prefetching is present. The investigation demonstrates the performance of the Cortex-R82 prefetcher in the following domains: no prefetching, minimum prefetching (conservative), moderate prefetching, and maximum prefetching (aggressive). This study also illustrates the intensity of prefetching required across different application areas using various industry standard benchmarks to measure the performance of the processor.
Click here to read more.
Leave a Reply