http://jens.ayton.se/blag/performance-comparisons-of-common-operations-ppc-edition/ Cocoa coding stuff, when I can be bothered. Sun, 05 Sep 2010 17:14:39 +0000 hourly 1 http://wordpress.org/?v=3.0.1 http://jens.ayton.se/blag/performance-comparisons-of-common-operations-ppc-edition/comment-page-1/#comment-9 hachu Thu, 27 Sep 2007 18:41:51 +0000 http://jens.ayton.se/blag/performance-comparisons-of-common-operations-ppc-edition/#comment-9 Your memory ops that seem faster than Mike's are most likely actually faster. Mike used a Mac Pro which uses FBDIMMS which are not predictable in terms of latency and bandwidth. He should have used a Core 2 iMac or something to get more reliable numbers. Your memory ops that seem faster than Mike’s are most likely actually faster. Mike used a Mac Pro which uses FBDIMMS which are not predictable in terms of latency and bandwidth. He should have used a Core 2 iMac or something to get more reliable numbers.

]]> http://jens.ayton.se/blag/performance-comparisons-of-common-operations-ppc-edition/comment-page-1/#comment-5 David Smith Tue, 28 Aug 2007 23:34:09 +0000 http://jens.ayton.se/blag/performance-comparisons-of-common-operations-ppc-edition/#comment-5 Some things to consider with the divide loop timings are the processor's out of order execution, caching, branch prediction, and memory prefetching facilities. If you're doing predictable accesses and huge loop iteration counts you can bet the processor will hide most of it. Core 2 can even hoist loads past stores in many places. As such, trying to figure out timings by counting instructions is somewhat futile. Some things to consider with the divide loop timings are the processor’s out of order execution, caching, branch prediction, and memory prefetching facilities. If you’re doing predictable accesses and huge loop iteration counts you can bet the processor will hide most of it. Core 2 can even hoist loads past stores in many places. As such, trying to figure out timings by counting instructions is somewhat futile.

]]>