Re: gfortran, g95, and dual-core

Richard Maine wrote:


So computing time is not simply a matter of counting "flops"

Nope. Hasn't been for decades.

For my present hardware, using a benchmark for "flops" that simply multiplies large dense matrices, I have:

2/2003 desktop 100 Mflop/2.4GHz = 0.04 flop/Hz g77 with -fbounds-check
4/2006 laptop 40 Mflop/1.7GHz = 0.02 flop/Hz g77 with -bounds-check

Timing was not very accurate, done by stopwatch for portability of the benchmark program, and these were short runs. The laptop, though newer, is less efficient, presumably due to the factors you mention. It was a low-end machine.
.

Relevant Pages

  • Re: Timer in AppleSoft BASIC with ProDOS
    ... magazine benchmark and times for various Commodore machines. ... Yup, that thread is the driver behind this question, but I don't own a stopwatch, and I don't feel like rearranging my office to get a computer that does have a stopwatch program close enough to the Apple to make it work. ... When you finish timing, read the two-byte counter again into another 16-bit variable and subtract the first reading ...
    (comp.sys.apple2.programmer)
  • Re: Deltic 55016 for GCR?
    ... Well, back in the day, I used to log trains according to the mileposts, ... who is timing either runners at a track or mileposts speeding by is able ... I wasn't using a stopwatch - at least not in later days. ... window shelf. ...
    (uk.railway)
  • Re: using a current to measure a time interval
    ... >>these wires link to a stopclock/watch (i can give the model name if you ... >>it stops. ... This isn't useful because I need it to start timing when it ... > If you can provide a link to the stopwatch that would help. ...
    (sci.electronics.design)
  • Re: speed of execution
    ... he had been timing programs ... running in the simulator with a stopwatch!!! ... timing was way out. ...
    (comp.lang.c)