Benchmark Archaeology
Read OriginalThe article examines a historical performance benchmark from the R mailing list, comparing the speed of R, S, and compiled C code for a loop-intensive statistical algorithm. It revisits the benchmark on modern Apple M1 hardware, showing significant speed gains but less than predicted by Moore's Law, and discusses reasons like single-threaded execution and cache utilization.
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser
Top of the Week
No top articles yet