nm_test16 and nm

Author	Message
Travis Volunteer moderator Project administrator Project developer Project tester Project scientist Send message Joined: 30 Aug 07 Posts: 2046 Credit: 26,480 RAC: 0	Message 6589 - Posted: 24 Nov 2008, 18:22:07 UTC i've tried dynamically calculating the fpops estimates (nm_test14 wasnt correct i don't think), so let me know if these seem about right, and if these WUs work correctly. ID: 6589 · Rating: 0 · rate: / Reply Quote

Emanuel Send message Joined: 18 Nov 07 Posts: 280 Credit: 2,442,757 RAC: 0	Message 6634 - Posted: 24 Nov 2008, 22:23:43 UTC Last modified: 24 Nov 2008, 22:24:09 UTC Slightly off-topic, but isn't the term 'flops'? (it stands for 'floating point operations', of course, so fpops sort of makes more sense) ID: 6634 · Rating: 0 · rate: / Reply Quote

Alinator Send message Joined: 7 Jun 08 Posts: 464 Credit: 56,639,936 RAC: 0	Message 6635 - Posted: 24 Nov 2008, 22:34:29 UTC Last modified: 24 Nov 2008, 22:42:07 UTC FLOPS is a unit of power, FLoating point Operations Per Second. FPOPS is a unit of work, Floating Point OPerationS. <edit> Now that I got that first part straightened out! ;-) In the BOINC context, you need the FPOPS estimate (the amount of work in the task) in order to calculate the estimated runtime using the host Benchmarks. This also comes into play when the Core Client (CC) goes to make a work request from a project. HTH, Alinator ID: 6635 · Rating: 0 · rate: / Reply Quote

nm_test16 and nm_test17