ATI Firestream card

Author	Message
]{LiK`RangerS` Send message Joined: 27 Oct 08 Posts: 39 Credit: 6,552,652 RAC: 0	Message 61130 - Posted: 12 May 2009, 13:17:30 UTC wondering what it would do to help in crunching if at all. ID: 61130 · Rating: 0 · rate: / Reply Quote

Hammeh Send message Joined: 11 Nov 08 Posts: 63 Credit: 211,283 RAC: 0	Message 61131 - Posted: 12 May 2009, 13:22:52 UTC GPUs are not supported in this project and the admins have no intention of writing a new script which would allow them to run the Rosetta@home application because of its complexity. ATI cards are only supported currently under the Milkyway@way project, however it is only for Radeon Cards if I remember correctly. Folding@home has an ATI application however it is a nonBOINC project. ID: 61131 · Rating: 0 · rate: / Reply Quote

Chilean Send message Joined: 16 Oct 05 Posts: 711 Credit: 26,694,507 RAC: 0	Message 61148 - Posted: 12 May 2009, 23:40:19 UTC AMD FireStream™ 9170: Industry's First GPU with Double-Precision Floating Point Features * Powered by next-generation ATI GPU from AMD * Parallel processing architecture with 320 stream cores * Up to 500 GFLOPs single precision performance * 2GB GDDR3 on-board memory * Double Precision Floating Point * PCIe 2.0 x16 interface * < 150W power consumption (LOL) * Memory export * BIOS settings optimized for stream processing * API and OS Support * Windows XP, XP64 * Linux 32 and Linux 64 System Requirements * PCI Express® based server or workstation with available x16 lane graphics slot * 500W or greater power supply * 512MB of system memory Optimized for Computation * Double-precision floating point for scientific and engineering codes * 2GB on-board memory * 320 stream cores drive up to 500 GFLOPS single-precision performance * Asynchronous DMA, allowing data transfers without interrupting streams processor or CPU Pair 4 of these (dunno if ATI can 4x tho...)... and BAM! ID: 61148 · Rating: 0 · rate: / Reply Quote

mikey Send message Joined: 5 Jan 06 Posts: 1895 Credit: 9,208,737 RAC: 2,882	Message 61157 - Posted: 13 May 2009, 9:12:20 UTC - in response to Message 61148. AMD FireStream™ 9170: Industry's First GPU with Double-Precision Floating Point Features * Powered by next-generation ATI GPU from AMD * Parallel processing architecture with 320 stream cores * Up to 500 GFLOPs single precision performance * 2GB GDDR3 on-board memory * Double Precision Floating Point * PCIe 2.0 x16 interface * < 150W power consumption (LOL) * Memory export * BIOS settings optimized for stream processing * API and OS Support * Windows XP, XP64 * Linux 32 and Linux 64 System Requirements * PCI Express® based server or workstation with available x16 lane graphics slot * 500W or greater power supply * 512MB of system memory Optimized for Computation * Double-precision floating point for scientific and engineering codes * 2GB on-board memory * 320 stream cores drive up to 500 GFLOPS single-precision performance * Asynchronous DMA, allowing data transfers without interrupting streams processor or CPU Pair 4 of these (dunno if ATI can 4x tho...)... and BAM! I wonder if that is a thought process too for the different projects...how fast the workunits will be run through using a gpu instead of a cpu? They may have to make more work faster! ID: 61157 · Rating: 0 · rate: / Reply Quote

Chilean Send message Joined: 16 Oct 05 Posts: 711 Credit: 26,694,507 RAC: 0	Message 61174 - Posted: 13 May 2009, 22:58:37 UTC - in response to Message 61157. AMD FireStream™ 9170: Industry's First GPU with Double-Precision Floating Point Features * Powered by next-generation ATI GPU from AMD * Parallel processing architecture with 320 stream cores * Up to 500 GFLOPs single precision performance * 2GB GDDR3 on-board memory * Double Precision Floating Point * PCIe 2.0 x16 interface * < 150W power consumption (LOL) * Memory export * BIOS settings optimized for stream processing * API and OS Support * Windows XP, XP64 * Linux 32 and Linux 64 System Requirements * PCI Express® based server or workstation with available x16 lane graphics slot * 500W or greater power supply * 512MB of system memory Optimized for Computation * Double-precision floating point for scientific and engineering codes * 2GB on-board memory * 320 stream cores drive up to 500 GFLOPS single-precision performance * Asynchronous DMA, allowing data transfers without interrupting streams processor or CPU Pair 4 of these (dunno if ATI can 4x tho...)... and BAM! I wonder if that is a thought process too for the different projects...how fast the workunits will be run through using a gpu instead of a cpu? They may have to make more work faster! Rosetta runs a "loop", you set how long the WU takes... the longer you let it run, the more "models" it predicts. ID: 61174 · Rating: 0 · rate: / Reply Quote