columbiaibm

When we bring all this information in, we’re essentially applying CPU milliseconds, for the reason that a millisecond is a millisecond. So naturally, a single machine might be more quickly than another machine, and we take that of course into consideration, which is what CPW and rPerf benchmarks do. But when we figure this stuff out as far as how to consolidate all this information, we’re truly applying milliseconds to do some of the math. That’s how we do AIX and Linux, for the reason that a millisecond is a millisecond and regardless of what operating method you are. And...