... (at least in the networking case).  It may well be that "benchmark" performance is irrelevant, but I think its atleast worth reviewing other-OS research from the last 20 years to seewhat we can learn.  It may be the case that we have cut ourabstractions too high to take advantage of some architectural features present in modern microprocessors -- it may be that we want to ...

...you run your code on a faster or slower computer? Your count will be wrong and your execution speed will be wrong. Try to run an old DOS Game on a modern machine and you will seewhat I mean. Many of them still used hardcoded delay loops instead of timers.... Learn how to use QueryPerformanceCounter to do your timing. Plenty of tutorials out there on how to use it. ...

... you run your code on a faster or slower computer? Your count will be wrong and your execution speed will be wrong. Try to run an old DOS Game on a modern machine and you will seewhat I mean. Many of them still used hardcoded delay loops instead of timers.... Learn how to use QueryPerformanceCounter to do your timing. Plenty of tutorials out there on how to use it. I agree...

...if you run your code on a faster or slower computer? Your count will be wrong and your execution speed will be wrong. Try to run an old DOS Game on a modern machine and you will seewhat I mean. Many of them still used hardcoded delay loops instead of timers.... Learn how to use QueryPerformanceCounter to do your timing. Plenty of tutorials out there on how to use it. That way, your code...