Submit a New Speed Entry

Just fill out the form below and everything will be taken care of...

The recommended way to generate stats is by running the client benchmark 3 times on an idle system, and taking the best rate of the three. Also, when possible, it is best to run the clients in as idle an environment as possible. Not all UNIX or multi-user machines have that luxury, so there may be some fluctuation between measured and actual speed.

If your processor, operating system, or client version is not one of the available options, then go back to the main speed index page and use the bugzilla link at the bottom to report the value that you need.

Please make an effort to not submit bogus or invalid values. If you know that your speed value is suspiciously higher or lower than any of the other values reported by others for similar hardware, then recheck your values. Similiarly, if you know your system is grinding to a halt and about to crash and the speed reported by the client is totally non-sense, then don't report that value! Additionally, don't report excessively high/low values for favorite/hated operating system. The purpose of this database is provide a useful comparison for other users, not to promote platform advocacy or advertise bizarre values. By not submitting these bad values, you will save us the effort of having to remove it later. Thanks.

Operating System:
Processor Family:
Processor Model:
    If your exact CPU model is not listed, please go back and use the bugzilla report form.
Processor Speed (MHz):
    If your CPU is overclocked, please specify the speed that it is overclocked to, not its original speed. Do not use any punctuation, abbreviations, or symbols. Round to nearest whole number.

    For AMD XP/MP processors, please enter the marketing model number, not the actual core chip frequency.

    For GPU processors, please enter the GPU core frequency. This speed should be displayed by "dnetc -cpuinfo" for CUDA. Otherwise check online references for your GPU model.

Processor count:

    If your computer is a multi-processor or multi-core machine, enter the number of processors or cores you have. Otherwise enter 1.

    For GPU (CUDA/Stream) entries, this should be the number of GPU cores (ie: Nvidia Stream processors or Radeon Vector processors) on a single video card chip. This number should be displayed by "dnetc -cpuinfo" as the number of "MPs" for CUDA. Otherwise check online references for your GPU model.

    This number is generally between 8 and 256, and NOT just 1.

    If you have multiple GPU video cards installed, please benchmark and enter data for only one video card.

distributed.net client version and project:
distributed.net client speed:

    Measured in keys/sec or nodes/sec, as appropriate. Do not use any punctuation, abbreviations, or symbols. Fully specify all trailing zeros. Round to nearest whole number.

    For Multi-Processor/Multi-Core systems, please give combined multiplied client rate of all processors together (but do not multiply the processor clock speed). The speed reported by "dnetc -bench" is for a single CPU/Core.

    For GPU systems, please give the client rate for a single video card chip. The speed reported by "dnetc -bench" is the total for all GPU cores on a single video card chip.

Your e-mail address:
    Your e-mail will not be shown on any pages, but we may ask you to verify your entry if we believe a data entry error exists.