Just curious. Is an ION-2 in any way powerful enough to be used for GPUGRID.net & if is, if an ExpressCard 34 Nvidia ION-2 were to become available, could a netbook with an ExpressCard 34 Slot, fx Lenovo S10e use that to crunch for GPUGRID???

BTW, I love recycling, even when it's close to pointless...

---

The first ION is now powerful enough; following the release of the new application and the shortining of tasks.

http://www.gpugrid.net/show_host_detail.php?hostid=55951

2 Feb 2010 23:15:17 UTC 6 Feb 2010 23:15:20 UTC Completed and validated 333,861.33 27,367.87 3,977.21 5,369.23 ACEMD beta version v6.08 (cuda)

I am running a v6.01 task now and it will complete in time.

4 Days for 24/7. Not bad for an atom, & that was the first ION? A drop in the Ocean is still a drop more than none at all! I really hope someone makes an ExpressCard 34 ION-2 Addon Card! If Asus can make the Asus XG Station external GPU http://www.engadget.com/2007/01/08/hands-on-with-the-asus-xg-station-external-gpu/, & Magma could make the ExpressBox http://www.magma.com/products.html A cheap Nvidia ION-2 ExpressCard 34/54 would make useless laptops useful again...

---

ION(2)'s a chipset, not a discrete GPU part, so isn't what you are looking for.
A box full of ION2 boards would be less cost-effective for GPUGRID than spending the equivalent on fewer higher-performance systems.

MJH

I had another valid task complete on my Ion this morning, but since then it picked up 5 tasks and spat them out.

Valid:
Task 1844525 (347-IBUCH_1000smd_pYEEI_100202-5-10-RND8681_0)
Completed and validated 284,188.17 23,687.57 3,977.21 5,369.23 ACEMD - GPU molecular dynamics v6.01 (cuda) – 3days,3h :)

Failures:
All, SWAN: FATAL : swanMalloc failed

All tasks were on the ACEMD - GPU molecular dynamics v6.01 (cuda) application.
http://www.gpugrid.net/workunit.php?wuid=1169190
http://www.gpugrid.net/workunit.php?wuid=1169719
http://www.gpugrid.net/workunit.php?wuid=1169749
http://www.gpugrid.net/workunit.php?wuid=1169755
http://www.gpugrid.net/workunit.php?wuid=1169758

eg.
Name81-GIANNI_BIND_769-92-100-RND6925_0 Workunit1169758 Created16 Feb 2010 3:24:06 UTC Sent16 Feb 2010 3:25:00 UTC Received16 Feb 2010 3:26:35 UTC Server stateOver OutcomeClient error Client stateCompute error Exit status-40 (0xffffffffffffffd8) Computer ID55951 Report deadline21 Feb 2010 3:25:00 UTC Run time9.359999 CPU time8.751656 stderr out
<core_client_version>6.10.18</core_client_version>
<![CDATA[
<message>
- exit code -40 (0xffffffd8)
</message>
<stderr_txt>
# There is 1 device supporting CUDA
# Device 0: "ION"
# Clock rate: 1.25 GHz
# Total amount of global memory: 268435456 bytes
# Number of multiprocessors: 2
# Number of cores: 16
SWAN: FATAL : swanMalloc failed

</stderr_txt>
]]>
Validate stateInvalid Claimed credit0.0148080580480995 Granted credit0 application versionACEMD - GPU molecular dynamics v6.01 (cuda)


The system has been restarted, but it will not pick up any more tasks until tomorrow.
Should I detach that system from the project?