RE: [Deinterlace-discuss] Problems fixed

[Rob M. <rob...@gm...>]

At 15:19 11-06-05, John Adcock wrote:
>It does look pretty odd, probably should be a straight conversion to use
>the high frequency timer,

I have done some testing and there seems to be a real good reason why it 
was done this way. On a P2 350 MHz QueryPerformanceCounter() can be 
executed about 200,000 times per second, this is not fast enough to 
accurately measure a 50 kHz event. Some more testing reveals that the rdtsc 
instruction can be executed about 10 million times per second on the same 
machine.

Maybe we should directly use the rdtsc instruction? If so, would it be safe 
to assume that this instruction does exist on the hardware and returns 
valid results? I guess so since we never check if QueryPerformanceCounter() 
returns a valid result.

Rob