Why BOINC should trash whole GPU cache if GPU was not found at current BOINC start ? Why tasks just can't be put in waiting or suspended (to not participate in scheduling decisions) state until GPU will be available again ?
_______________________________________________ boinc_dev mailing list [email protected] http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev To unsubscribe, visit the above URL and (near bottom of page) enter your email address.
