00:22:46 -!- nyef [~nyef@pool-64-222-178-106.man.east.myfairpoint.net] has quit [Quit: G'night all.] 01:37:01 -!- jweiss [~weissj@cpe-069-134-025-078.nc.res.rr.com] has quit [Ping timeout: 276 seconds] 01:37:01 -!- pkhuong [~pkhuong@gravelga.xen.prgmr.com] has quit [Ping timeout: 276 seconds] 01:37:01 -!- foom [~jknight@ita4fw1.itasoftware.com] has quit [Ping timeout: 276 seconds] 01:38:03 jweiss [~weissj@cpe-069-134-025-078.nc.res.rr.com] has joined #sbcl 01:39:00 pkhuong_ [~pkhuong@gravelga.xen.prgmr.com] has joined #sbcl 01:41:40 foom [~jknight@ita4fw1.itasoftware.com] has joined #sbcl 02:46:59 -!- jweiss [~weissj@cpe-069-134-025-078.nc.res.rr.com] has quit [Ping timeout: 276 seconds] 04:22:45 nikodemus [~nikodemus@cs181199216.pp.htv.fi] has joined #sbcl 04:22:45 -!- ChanServ has set mode +o nikodemus 04:46:32 good morning 05:39:37 -!- _3b``` [foobar@cpe-72-179-19-4.austin.res.rr.com] has quit [Ping timeout: 272 seconds] 05:53:15 _3b``` [foobar@cpe-72-179-19-4.austin.res.rr.com] has joined #sbcl 06:58:50 -!- Krystof [~csr21@csrhodes.plus.com] has quit [Ping timeout: 264 seconds] 07:11:20 mega1 [~quassel@catv4E5CABA2.pool.t-online.hu] has joined #sbcl 07:58:36 -!- mbohun [~mbohun@ppp115-156.static.internode.on.net] has quit [Remote host closed the connection] 08:12:05 tcr [~tcr@cpc5-bour5-2-0-cust340.15-1.cable.virginmedia.com] has joined #sbcl 08:18:25 Krystof [~csr21@158.223.161.73] has joined #sbcl 08:18:25 -!- ChanServ has set mode +o Krystof 08:56:59 -!- Krystof [~csr21@158.223.161.73] has quit [Ping timeout: 276 seconds] 08:57:45 What is the default FP exception mask in sbcl? 09:13:11 Krystof [~csr21@158.223.161.73] has joined #sbcl 09:13:11 -!- ChanServ has set mode +o Krystof 09:13:33 angavrilov: depends on the platforms 10:23:38 sb-sprof is not loadable from asdf? 10:30:25 i don't remember 10:30:37 not all contribs are 10:30:58 https://bugs.launchpad.net/sbcl/+bug/393309 10:54:23 -!- Krystof [~csr21@158.223.161.73] has quit [Ping timeout: 255 seconds] 11:09:51 -!- nikodemus [~nikodemus@cs181199216.pp.htv.fi] has quit [Quit: This computer has gone to sleep] 11:20:04 nyef [~nyef@pool-64-222-178-106.man.east.myfairpoint.net] has joined #sbcl 11:20:26 G'morning all. 11:24:55 hi nyef 11:32:34 stassats [~stassats@wikipedia/stassats] has joined #sbcl 11:34:09 attila_lendvai [~attila_le@4d6f5d3b.adsl.enternet.hu] has joined #sbcl 11:47:15 -!- attila_lendvai [~attila_le@4d6f5d3b.adsl.enternet.hu] has quit [Ping timeout: 265 seconds] 11:57:17 mbohun [~mbohun@ppp115-156.static.internode.on.net] has joined #sbcl 12:07:20 Krystof [~csr21@158.223.161.73] has joined #sbcl 12:07:20 -!- ChanServ has set mode +o Krystof 12:28:07 -!- Krystof [~csr21@158.223.161.73] has quit [Ping timeout: 272 seconds] 12:50:21 nikodemus [~nikodemus@cs181058025.pp.htv.fi] has joined #sbcl 12:50:21 -!- ChanServ has set mode +o nikodemus 12:50:41 -!- tsuru [~charlie@c-174-50-217-160.hsd1.tn.comcast.net] has quit [Remote host closed the connection] 13:07:46 -!- stassats [~stassats@wikipedia/stassats] has quit [Remote host closed the connection] 13:34:37 Krystof [~csr21@158.223.161.73] has joined #sbcl 13:34:37 -!- ChanServ has set mode +o Krystof 14:06:08 hargettp [~hargettp@dhcp-162.mirrorimage.net] has joined #sbcl 14:16:25 -!- tcr [~tcr@cpc5-bour5-2-0-cust340.15-1.cable.virginmedia.com] has quit [Ping timeout: 252 seconds] 14:18:47 tcr [~tcr@cpc1-bour2-0-0-cust414.15-1.cable.virginmedia.com] has joined #sbcl 14:23:36 -!- hargettp [~hargettp@dhcp-162.mirrorimage.net] has quit [Remote host closed the connection] 14:33:00 -!- Krystof [~csr21@158.223.161.73] has quit [Read error: Operation timed out] 14:36:26 attila_lendvai [~attila_le@4d6f5d3b.adsl.enternet.hu] has joined #sbcl 14:47:14 The_Jon_Smith [~The_Jon_S@ip24-250-13-137.ri.ri.cox.net] has joined #sbcl 14:54:40 stassats [~stassats@wikipedia/stassats] has joined #sbcl 14:55:21 hargettp [~hargettp@dhcp-162.mirrorimage.net] has joined #sbcl 15:02:09 cmpitg [~cmpitg@113.22.101.69] has joined #sbcl 15:05:35 kjbrock [~kevin@173-11-106-193-SFBA.hfc.comcastbusiness.net] has joined #sbcl 15:09:49 -!- mbohun [~mbohun@ppp115-156.static.internode.on.net] has quit [Quit: Leaving] 15:10:19 nyef: was there a reason you didn't want out-of-line error traps? 15:10:42 (or rather more importantly, coalesced error traps) 15:10:51 Table-based unwind. 15:11:31 are you working on it already? 15:12:29 I did some looking-into of it about a week or so ago. 15:12:42 (Week and a half or so?) 15:13:12 But then I took a priority change and started looking at DX closure value-cells instead. 15:13:27 I'll probably be getting back to it soon, though. 15:18:29 -!- kjbrock [~kevin@173-11-106-193-SFBA.hfc.comcastbusiness.net] has quit [Quit: kjbrock] 15:41:20 ok. i'll probably commit the merged traps for x86 and x86-64, but ripping them out again will be easy 15:41:30 by the way, which is the problem: coalescing or out-of-line-ness? (and why?) 15:42:27 or is it just that coalescing will also require that all traps are used with stack in consistent state? 15:44:23 It's the loss of information on the currently-active PHYSENV. 15:44:49 ok 15:45:01 Or the currently-active dynamic contour, but they correspond fairly well with PHYSENVs. 15:45:17 So CALLing the traps would possibly suffice to retain the information. 15:45:29 right 15:49:00 Krystof [~csr21@158.223.161.73] has joined #sbcl 15:49:09 -!- ChanServ has set mode +o Krystof 15:55:58 -!- Krystof [~csr21@158.223.161.73] has quit [Ping timeout: 245 seconds] 15:58:07 -!- cmpitg [~cmpitg@113.22.101.69] has quit [Quit: leaving] 15:59:05 tsuru [~charlie@c-174-50-217-160.hsd1.tn.comcast.net] has joined #sbcl 16:04:51 -!- hargettp [~hargettp@dhcp-162.mirrorimage.net] has quit [Remote host closed the connection] 16:12:59 Krystof [~csr21@howells.doc.gold.ac.uk] has joined #sbcl 16:13:00 -!- ChanServ has set mode +o Krystof 16:22:50 hargettp [~hargettp@dhcp-162.mirrorimage.net] has joined #sbcl 16:26:34 -!- attila_lendvai [~attila_le@4d6f5d3b.adsl.enternet.hu] has quit [Ping timeout: 252 seconds] 16:59:08 kclifton [~kclifton@s198-166-45-245.ab.hsia.telus.net] has joined #sbcl 17:05:40 -!- Krystof [~csr21@howells.doc.gold.ac.uk] has quit [Read error: Operation timed out] 17:13:24 kjbrock [~kevin@173-11-106-193-SFBA.hfc.comcastbusiness.net] has joined #sbcl 17:14:33 -!- nikodemus [~nikodemus@cs181058025.pp.htv.fi] has quit [Quit: Leaving] 17:35:12 -!- kjbrock [~kevin@173-11-106-193-SFBA.hfc.comcastbusiness.net] has quit [Quit: kjbrock] 17:37:23 -!- stassats [~stassats@wikipedia/stassats] has quit [Remote host closed the connection] 17:59:47 stassats [~stassats@wikipedia/stassats] has joined #sbcl 18:27:21 jga [~gajon@189.253.56.122] has joined #sbcl 18:49:53 Migs [~Migs@205.122.50.75] has joined #sbcl 18:50:19 -!- Migs [~Migs@205.122.50.75] has left #sbcl 19:32:08 -!- kclifton [~kclifton@s198-166-45-245.ab.hsia.telus.net] has quit [Quit: kclifton] 20:31:15 maybe-find-stack-top-hint (actually find-call-name-and-frame) makes ERROR have *considerable* overhead 20:34:02 ... Why are we /still/ finding major inefficiencies like this? 20:34:27 I mean, surely we should run out of them at some point, right? 20:34:56 nyef: we're as fast as C, why look for inefficiencies ;) 20:35:43 Explain why ITA uses some C components for their number crunching again, then? 20:36:07 hit the philistines over the head with the SBCL manual, I guess 20:36:36 No, our compiler just plain sucks at some things. 20:36:44 well, that too 20:37:33 such as writing a 32bit hash function. you basically can't do that at all in 64bit sbcl, because it tries to do everything in fixnum arithmetic instead of 32bit raw ops. 20:40:00 Processing 8mio packets, 3000 of them are malformed resulting in an error (which is then caught by an handler-case somewhat up the stack); the call to error makes up 25% of the total time if I'm not reading sb-sprof incorrectly 20:40:28 that sounds so incredible I can't even persuade myself to believe it :-) 20:40:52 that sounds a little ridiculous 20:41:47 You want to look at the sb-sprof output? 20:41:54 Why is that even happening prior to debugger entry? 20:42:11 tcr: don't use error? (: 20:42:52 fixing it looks easy enough, though 20:43:02 nyef: well, I was thinking we could convert IR2 to gcc ;) 20:43:03 Sure 20:44:34 tcr: might as well paste the output 20:44:54 args to error and cerror could profitably be dynamic-extent, too 20:45:45 Say, are the closures for the condition handlers and restarts marked as DX yet? 20:47:33 paste too large :-) 20:47:53 even just top 100 contributors from the flat output 20:49:32 http://common-lisp.net/~trittweiler/prof.txt 20:49:38 first flat, then graph 20:49:51 I'm going to delete the file again in a couple of minutes 20:50:33 I'd like to receive comments on the pthread_sigmask thing; that comes from GC? 20:53:03 tcr: I think that's correct, yes 20:53:20 yup 20:53:23 Wouldn't it also come from the normal signal-handling path? 20:53:40 it wouldn't consume as much cpu 20:54:03 Even if it keeps hitting the deferred case? 20:54:04 is sigmask also used in unithreaded builds? 20:54:14 I'm calling gc manually, quite a lot 20:54:33 tcr: can you frob ERROR to do (let ((*sb!debug:*stack-top-hint* nil)) (signal condition) (setf *sb!debug:*stack-top-hint* (maybe-find-stack-top-hint)) (invoke-debugger)) and see if that has any effect? 20:55:26 not easily I mean it's not hard but I'd have to get the appropriate setup and I'd rather spend my time else :-) 20:55:40 fair enough 20:55:59 wow, nikodemus was right; we call error 'simple-type-error all over the place 21:38:19 -!- _3b``` [foobar@cpe-72-179-19-4.austin.res.rr.com] has quit [Ping timeout: 240 seconds] 21:58:49 -!- tcr [~tcr@cpc1-bour2-0-0-cust414.15-1.cable.virginmedia.com] has quit [Quit: Leaving.] 21:59:40 _3b``` [foobar@cpe-72-179-19-4.austin.res.rr.com] has joined #sbcl 22:06:41 -!- mega1 [~quassel@catv4E5CABA2.pool.t-online.hu] has quit [Ping timeout: 264 seconds] 22:07:40 tcr [~tcr@cpc5-bour5-2-0-cust340.15-1.cable.virginmedia.com] has joined #sbcl 22:15:36 attila_lendvai [~attila_le@4d6f5d3b.adsl.enternet.hu] has joined #sbcl 22:36:29 -!- joshe [~joshe@opal.elsasser.org] has quit [Ping timeout: 276 seconds] 22:36:40 joshe [~joshe@opal.elsasser.org] has joined #sbcl 22:47:34 -!- attila_lendvai [~attila_le@4d6f5d3b.adsl.enternet.hu] has quit [Quit: Leaving.] 23:06:16 -!- tcr [~tcr@cpc5-bour5-2-0-cust340.15-1.cable.virginmedia.com] has quit [Quit: Leaving.] 23:51:06 -!- rbarraud [~rbarraud@118-93-187-24.dsl.dyn.ihug.co.nz] has quit [Read error: Connection reset by peer]