IRC logs for #openrisc Monday, 2014-08-25

--- Log opened Mon Aug 25 00:00:22 2014
stekernhmm, briefly looking at the github repo with the or1200->mor1kx fpu it seems like the fpu used a bsd-like license18:44
olofkohdl is pretty bsd-like too, isn't it?18:49
stekernI think I've figured out this snooping bug (aka, the bug formerly known as spinlock bug)19:12
stekernI believe it's a corner case where a snoop hit happens at the same time as a refill is just about to start19:13
stekernand the tags are saved away, since we only have one tag mem for all ways19:14
stekernthen when the refill is done, the saved tag is written over the invalidation caused by the snoop19:15
stekern...all this is just a result of a bad design choice I made to just use one tag mem...19:15
stekernI should change that and have a seperate tag mem for each way19:16
olofkIs anything set in stone, or is it just a matter of reimplementing it?19:28
stekernit's just an implementation detail, so 'just' reimplementing it19:29
olofkWhich kernel repo is in best shape? Is upstream usable for single core19:29
olofkYeah, I considered putting '' around just :)19:29
stekernbut I think I'll work-around it for a quick fix right now. but it makes me changing that a bit more high prio.19:31
stekernupstream kernel is almost usable19:32
stekernthere are a couple of bug-fixing patches that hasn't made it there though...19:34
stekernI keep them around in my smp branch, and afaik that should be in pretty good shape19:35
olofkgithub or
olofkfound i19:37
olofkah crap... pushed to the wrong branch again20:42
stekernat least this smp setup is a lot more stable after I added the refill abortion on snoop hits20:47
stekernit always crashed ~1 minute of running the gcc execute regression tests20:48
stekernnow it's been running for 10 minutes already20:48
poke53281Great worl. 10 minutes is already fantastic. But that means, that the next problems will be harder to find.21:30
poke53281Are you sure, that the kernel is not the problem? At the moment you seem to have two construction sites and both of them could be responsible.21:44
--- Log closed Tue Aug 26 00:00:23 2014

Generated by 2.15.2 by Marius Gedminas - find it at!