Apr 082010
 

The popular technology website Bright Side of News* has published an in-depth report I authored comparing an ARM Cortex-A8 microprocessor, used in the Apple iPad’s A4 chip, against a trifecta of x86 CPUs typically found in netbooks, small notebooks and embedded devices.  My report particularly focuses on compute performance.

A major component of that comparison is miniBench, an open source benchmark that I wrote in C++.  I ported miniBench to Linux for both ARM and x86 platforms enabling, for the first time, objective, head-to-head performance comparisons across a wide range of meaningful tests like Dhrystone, Whetstone, FFT, LinPack, MFLOPS, AES, SHA1, SHA256 and many others.

While I worked as head of benchmarking for Centaur Technology, we used miniBench to help isolate performance problems in our microprocessors so that we could optimize out the weakest attributes of our chip designs.

In the BSN* report, I also compare performance across a number of popular JavaScript benchmarks and a few other native tests.

The results surprised me.  It is also worth examinig the relative compute performance between the new Intel Atom N450, the new VIA Nano L3050 and an old AMD Mobile Athlon based upon the Barton core.

You can read my full report here.

I noticed that Theo generously gave me credit for the recall of the 1.13GHz Intel Pentium III.  I want to make it clear that Tom Pabst discovered the speed path defect that manifested when he was trying to compile the Linux kernel.  My part in the recall was representing Tom’s Hardware at Intel.  The representative for the giant chipmaker initially laughed at the issue until I threatened him with an united call to yank the defective part involving a number of major computer hardware ethusiast websites.