|
|
#1 | |
|
Registered User
|
__________________
asus p8z77-v lk mb, 8gb ddr3-1866 mhz ram in dual channel,intel core i7 3770k cpu,gigabyte gtx 560 1gb soc gpu, creative labs sb recon 3d pci-e,2x ocz agility 3 90gb ssd in raid 0,antec 650 watt 80 plus platunum psu,antec atx case, pioneer bdr-208 15x bluray writer,windows 8 64 bit oem, steelseries 6gv2 keyboard ,asus vg278he 27' 3d vision 2 lcd monitor, steelseries 6gv2 keyboard, steelseries sensei mlg editon mouse,xbox 360 wired controller for windows,lexar 16gb usb 3.0 flash drive, 3d vision 2 kit I'd rather walk with God in the Dark than shine in the light alone. coming soon:2x samsung 840 pro 256gb in raid 0,logitech z906 5.1 speakers,,(2x2x8gb) 32gb team xtreem 2666mhz ram, 32gb kingston datatravler workspace usb 3.0 flash drive,sound blaster z sound card, adaptec 6805e pci-e 2.0 4x sata 3 raid controller,lg 16x bd writer, PNY gtx 660 ti 2gb gpu, corsair vengeance k65 keyboard, intel core i7 4770k cpu, gigabyte ga-z87x-d3h mb |
|
|
|
|
|
|
#2 | |
|
Join Date: Apr 2009
Location: EU
Posts: 1,041
|
Not on non-nv gpu's, but on cpu's.
|
|
|
|
|
|
|
#3 |
|
Has a vegetation fetish
Join Date: Jan 2006
Posts: 1,816
|
yea, sounds like nvidia want's to allow apps like the gpu version of folding@ to run on cpu's as well (bad example, but the work units for the CUDA client are different and can't be run one the cpu client atm. this would help allow this).
I am not sure how helpfull this will be performance wise, it would be faster to design a piece of code to run on a cpu and under 2-4 threads then for cuda and then through and interpreter that then stuffs the 100-200 threads under the cpu.
__________________
_________________________________________________ Mobo: EVGA 122-ck-nf68 680i sli, CPU: C2D Quad 6600, Video: EVGA GTX 460 1gb SC, Sound: X-fi gaming, Windows 7, Antec P180b,Thermalright Ultra-120 HSF, Antec TruPower TP3-650, 4 Gigs RAM |
|
|
|
|
|
#4 | |
|
Registered User
Join Date: Mar 2006
Posts: 532
|
Quote:
|
|
|
|
|
![]() |
| Thread Tools | |
|
|