Precision of calculations

Author	Message
Dimitris Hatzopoulos Send message Joined: 5 Jan 06 Posts: 336 Credit: 80,939 RAC: 0	Message 10324 - Posted: 1 Feb 2006, 23:45:42 UTC I wonder, what are the Rosetta software requirements on floating point precision? For example, I know other projects are using mostly single precision floating point calcs. Best UFO Resources Wikipedia R@h How-To: Join Distributed Computing projects that benefit humanity ID: 10324 · Rating: 0 · rate: / Reply Quote

Vanita Send message Joined: 21 Oct 05 Posts: 43 Credit: 0 RAC: 0	Message 10430 - Posted: 3 Feb 2006, 19:15:28 UTC Mostly single precision. ID: 10430 · Rating: 0 · rate: / Reply Quote

Dimitris Hatzopoulos Send message Joined: 5 Jan 06 Posts: 336 Credit: 80,939 RAC: 0	Message 10472 - Posted: 5 Feb 2006, 2:58:31 UTC Last modified: 5 Feb 2006, 3:00:03 UTC As you can guess, I was asking about precision in relation to using SSE optimisations when compiling the Rosetta software, to speed things up. There was a relevant thread at F@H: "Also, with SSE, we can do lots of single precision floats and there is no competitive advantage by using integers." -Vijay S. Pande http://forum.folding-community.org/viewtopic.php?t=11533 Best UFO Resources Wikipedia R@h How-To: Join Distributed Computing projects that benefit humanity ID: 10472 · Rating: 0 · rate: / Reply Quote

Carlos_Pfitzner Send message Joined: 22 Dec 05 Posts: 71 Credit: 138,867 RAC: 0	Message 10542 - Posted: 7 Feb 2006, 17:31:21 UTC There is a SSE version of rosetta ? -or- the source code ? Click signature for global team stats ID: 10542 · Rating: 0 · rate: / Reply Quote