00:20:51 -!- Bike [~Glossina@69.166.47.101] has quit [Ping timeout: 245 seconds] 00:23:35 Bike [~Glossina@69.166.47.101] has joined #sbcl 00:28:45 -!- kwmiebach [~kwmiebach@xdsl-87-78-137-247.netcologne.de] has left #sbcl 00:52:50 kwmiebach [kwmiebach@37.188.127.146] has joined #sbcl 00:57:48 -!- kwmiebach [kwmiebach@37.188.127.146] has quit [Read error: Connection reset by peer] 01:28:55 -!- flip214 [~marek@unaffiliated/flip214] has quit [Ping timeout: 246 seconds] 01:29:29 flip214 [~marek@unaffiliated/flip214] has joined #sbcl 01:34:54 -!- stassats [~stassats@wikipedia/stassats] has quit [Ping timeout: 252 seconds] 02:15:18 attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has joined #sbcl 02:26:30 -!- Bike [~Glossina@69.166.47.101] has quit [Ping timeout: 264 seconds] 02:38:46 -!- christoph_debian [~christoph@host-188-174-203-63.customer.m-online.net] has quit [Ping timeout: 245 seconds] 02:44:50 Bike [~Glossina@gannon-wless-gw.resnet.wsu.edu] has joined #sbcl 02:52:01 christoph_debian [~christoph@ppp-88-217-88-37.dynamic.mnet-online.de] has joined #sbcl 04:03:26 -!- Fare [~fare@cpe-69-203-115-132.nyc.res.rr.com] has quit [Ping timeout: 240 seconds] 04:23:23 -!- Vivitron [~Vivitron@c-50-172-44-193.hsd1.il.comcast.net] has quit [Ping timeout: 240 seconds] 05:12:53 -!- yacks [~py@103.6.159.103] has quit [Quit: Leaving] 06:07:27 angavrilov [~angavrilo@217.71.227.190] has joined #sbcl 06:11:27 -!- drmeister [~drmeister@wsip-174-79-188-132.dc.dc.cox.net] has quit [Remote host closed the connection] 06:38:09 prxq [~mommer@x2f69af6.dyn.telefonica.de] has joined #sbcl 06:41:00 -!- prxq [~mommer@x2f69af6.dyn.telefonica.de] has quit [Remote host closed the connection] 06:41:57 drmeister [~drmeister@wsip-174-79-188-132.dc.dc.cox.net] has joined #sbcl 06:43:04 prxq [~mommer@x2f69af6.dyn.telefonica.de] has joined #sbcl 06:46:07 -!- drmeister [~drmeister@wsip-174-79-188-132.dc.dc.cox.net] has quit [Ping timeout: 240 seconds] 06:55:55 -!- flip214 [~marek@unaffiliated/flip214] has quit [Ping timeout: 256 seconds] 06:56:03 flip214 [~marek@86.59.100.100] has joined #sbcl 06:56:03 -!- flip214 [~marek@86.59.100.100] has quit [Changing host] 06:56:03 flip214 [~marek@unaffiliated/flip214] has joined #sbcl 08:03:06 -!- ehaliewicz [~user@50-0-51-11.dsl.static.sonic.net] has quit [Ping timeout: 264 seconds] 08:11:48 -!- attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has quit [Ping timeout: 240 seconds] 08:24:31 stassats [~stassats@wikipedia/stassats] has joined #sbcl 08:25:46 attila_lendvai [~attila_le@92.47.184.31] has joined #sbcl 08:25:46 -!- attila_lendvai [~attila_le@92.47.184.31] has quit [Changing host] 08:25:46 attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has joined #sbcl 08:35:40 Hydan [~hydan@ip-89-103-110-5.net.upcbroadband.cz] has joined #sbcl 08:41:38 yacks [~py@103.6.159.103] has joined #sbcl 08:55:07 morning 09:05:28 -!- flip214 [~marek@unaffiliated/flip214] has quit [Ping timeout: 240 seconds] 09:13:23 flip214 [~marek@unaffiliated/flip214] has joined #sbcl 09:35:30 -!- kludge` [~comet@unaffiliated/espiral] has quit [Ping timeout: 264 seconds] 09:37:17 kludge` [~comet@unaffiliated/espiral] has joined #sbcl 09:43:38 drmeister [~drmeister@mobile-198-228-227-169.mycingular.net] has joined #sbcl 09:43:40 -!- oleo [~oleo@xdsl-78-35-141-168.netcologne.de] has quit [Read error: Operation timed out] 09:43:42 -!- drmeister [~drmeister@mobile-198-228-227-169.mycingular.net] has quit [Read error: Connection reset by peer] 09:44:17 oleo [~oleo@xdsl-78-35-178-124.netcologne.de] has joined #sbcl 11:17:28 ASau [~user@p5797E592.dip0.t-ipconnect.de] has joined #sbcl 11:30:53 tcr [~tcr@88.250.178.132] has joined #sbcl 11:54:48 -!- echo-area [~user@123.120.243.76] has quit [Ping timeout: 240 seconds] 12:17:49 -!- attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has quit [Ping timeout: 246 seconds] 12:18:42 (logand x #xFFFFFFFF) can be done with MOV EAX, EAX, which is quite smaller due to the usage of inline constants 12:18:46 attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has joined #sbcl 12:19:09 but for fixnums this can be done only with #x7FFFFFFF, otherwise shifts are too slow 12:19:34 drmeister [~drmeister@mobile-198-228-227-169.mycingular.net] has joined #sbcl 12:21:09 -!- flip214 [~marek@unaffiliated/flip214] has quit [Ping timeout: 240 seconds] 12:21:13 though, the right shift doesn't have to be arithmetic 12:22:15 drmeiste_ [~drmeister@mobile-198-228-227-169.mycingular.net] has joined #sbcl 12:23:28 flip214 [~marek@unaffiliated/flip214] has joined #sbcl 12:24:02 but there's no difference here 12:24:36 -!- drmeister [~drmeister@mobile-198-228-227-169.mycingular.net] has quit [Ping timeout: 245 seconds] 12:24:36 -!- drmeiste_ [~drmeister@mobile-198-228-227-169.mycingular.net] has quit [Read error: Connection reset by peer] 12:27:44 but (logand (+ x y) #x7FFFFFFF) can be better done just as ADD EAX, EDX 12:32:53 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Remote host closed the connection] 12:54:21 Fare [~fare@cpe-69-203-115-132.nyc.res.rr.com] has joined #sbcl 12:54:22 kwmiebach [~kwmiebach@xdsl-78-35-240-163.netcologne.de] has joined #sbcl 12:54:42 segv- [~mb@95-91-243-234-dynip.superkabel.de] has joined #sbcl 13:05:36 drmeister [~drmeister@mobile-198-228-227-169.mycingular.net] has joined #sbcl 13:08:00 -!- drmeister [~drmeister@mobile-198-228-227-169.mycingular.net] has quit [Read error: Connection reset by peer] 13:09:26 -!- Bike [~Glossina@gannon-wless-gw.resnet.wsu.edu] has quit [Ping timeout: 240 seconds] 13:09:39 Bike [~Glossina@gannon-wless-gw.resnet.wsu.edu] has joined #sbcl 13:13:04 Vivitron [~Vivitron@c-50-172-44-193.hsd1.il.comcast.net] has joined #sbcl 13:20:29 what happens to the sign bit? 13:20:59 ah, I see what you mean. for fixnums. 13:21:35 you "only" need to create a new class of modular arithmetic VOPs for tagged/31 bit values. 13:23:53 *stassats* noticed that empty function calls are slower on haswell vs sandy bridge, not sure why 13:24:22 probably due to stack manipulations 13:25:38 so add eax, edx zero-extends the high 32 bits? 13:25:43 I mean "zeros" 13:26:04 next question: does this actually happen in real code anywhere? 13:26:04 iirc, some AMD uarch had trouble with back to back call/ret 13:29:37 Krystof: every 32 bit op is zero-extended to 64, but constants are sign extended 13:30:56 fixnum tags significantly limit the usefulness of zero extending 13:32:22 and sbcl is not smart enough to untag once/loop/tag once 13:35:21 Krystof: so, what about replacing (sxhash nil/t) with constants? 13:38:45 i'm not really sure how much slower (sxhash unknown) makes it, the main slow down was from type-list-cache-hash 13:40:25 sure, arbitrary fixed constants should be fine 13:41:17 I'm about to make the cache hash must slower because threads. 13:41:41 the developer giveth, the other developer taketh away 13:41:42 *much 13:41:56 -!- ASau [~user@p5797E592.dip0.t-ipconnect.de] has quit [Remote host closed the connection] 13:42:02 I think only writes need to be modified though 13:44:03 i noticed yesterday that discarded multiple values from inlined functions are still computed if they are before the accepted value, i.e. (nth-value 1 (values (- x 3) (- x 10))), (- x 3) is still computed 13:44:39 but nth-value 0 doesn't 13:45:31 and inlined functions + deftransforms bites again 13:46:07 the transforms for rem mod are not applied, because they are inlined, and the inlined transformation of TRUNCATE suffers from the above 13:47:22 i just need to make transform take precedence 13:47:27 transforms 13:47:52 ASau [~user@p5797E592.dip0.t-ipconnect.de] has joined #sbcl 13:50:16 yes. 13:51:51 though fixing the value thing would be nice too 13:53:21 -!- tcr [~tcr@88.250.178.132] has quit [Quit: Leaving.] 13:53:38 darn, another trailing whitespace slipped up 13:58:51 -!- Fare [~fare@cpe-69-203-115-132.nyc.res.rr.com] has quit [Ping timeout: 248 seconds] 14:00:42 I once had a git hook to check for that. 14:01:06 the build removes them, but i didn't do a build for a simple change 14:02:12 i have show-trailing-whitespace set to t, and the face is pretty ugly 14:03:46 tcr [~tcr@81.214.252.210] has joined #sbcl 14:15:38 making transforms take precedence doesn't appear to be as easy as i expected 14:27:14 source transforms are tried before inline expansions in ir1-convert-srctran, but ir1-optimize-combination, where transforms are handled, is done after that 14:27:22 and by the time everything is inlined 14:31:27 you can delay inline expansion if transforms are defined for the function. 14:33:11 and then there's the question of delayed transforms. it's probably stupid to inline when a transform just noted that it might fire after constraint propagation... but delay inlining too much and you'll just get a lot of bad code that hasn't gone through a single round of IR1opt/constraint/IR1opt. 14:41:47 Fare [fare@nat/google/x-tjsqrtbwfkujygpo] has joined #sbcl 16:03:21 -!- Bike [~Glossina@gannon-wless-gw.resnet.wsu.edu] has quit [Ping timeout: 245 seconds] 16:22:08 -!- Hydan [~hydan@ip-89-103-110-5.net.upcbroadband.cz] has quit [Remote host closed the connection] 16:44:39 -!- fikusz [~fikusz@catv-89-132-137-62.catv.broadband.hu] has quit [Quit: Leaving] 16:50:16 sdemarre [~serge@109.134.153.163] has joined #sbcl 16:52:57 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Remote host closed the connection] 16:55:20 segv- [~mb@95-91-243-234-dynip.superkabel.de] has joined #sbcl 16:55:22 -!- attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has quit [Ping timeout: 246 seconds] 17:09:08 attila_lendvai [~attila_le@92.47.184.31] has joined #sbcl 17:09:08 -!- attila_lendvai [~attila_le@92.47.184.31] has quit [Changing host] 17:09:08 attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has joined #sbcl 17:51:41 -!- attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has quit [Ping timeout: 245 seconds] 17:52:28 attila_lendvai [~attila_le@62-165-243-245.pool.digikabel.hu] has joined #sbcl 17:52:28 -!- attila_lendvai [~attila_le@62-165-243-245.pool.digikabel.hu] has quit [Changing host] 17:52:29 attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has joined #sbcl 18:04:21 -!- stassats [~stassats@wikipedia/stassats] has quit [Ping timeout: 252 seconds] 18:23:18 -!- tcr [~tcr@81.214.252.210] has quit [Quit: Leaving.] 18:26:54 Bike [~Glossina@69.166.47.101] has joined #sbcl 18:41:37 stassats [~stassats@wikipedia/stassats] has joined #sbcl 18:43:20 tcr [~tcr@176.41.67.29] has joined #sbcl 18:45:31 -!- tcr [~tcr@176.41.67.29] has quit [Client Quit] 18:49:31 -!- Bike [~Glossina@69.166.47.101] has quit [Ping timeout: 248 seconds] 18:54:05 tcr [~tcr@176.41.67.29] has joined #sbcl 18:56:25 Bike [~Glossina@69.166.47.101] has joined #sbcl 19:04:38 -!- Bike [~Glossina@69.166.47.101] has quit [Ping timeout: 240 seconds] 19:11:33 Bike [~Glossina@69.166.47.101] has joined #sbcl 19:26:03 -!- tcr [~tcr@176.41.67.29] has quit [Quit: Leaving.] 19:38:57 -!- attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has quit [Ping timeout: 252 seconds] 19:44:01 tcr [~tcr@176.41.67.29] has joined #sbcl 19:44:29 -!- tcr [~tcr@176.41.67.29] has quit [Client Quit] 19:54:08 -!- kwmiebach [~kwmiebach@xdsl-78-35-240-163.netcologne.de] has quit [Ping timeout: 240 seconds] 19:54:27 kwmiebach [~kwmiebach@xdsl-213-168-111-154.netcologne.de] has joined #sbcl 19:56:13 attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has joined #sbcl 19:56:59 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Remote host closed the connection] 20:07:56 -!- attila_lendvai [~attila_le@unaffiliated/attila-lendvai/x-3126965] has quit [Quit: Leaving.] 20:23:33 segv- [~mb@95-91-243-234-dynip.superkabel.de] has joined #sbcl 20:29:59 danlentz0 [~danlentz@c-68-37-70-235.hsd1.nj.comcast.net] has joined #sbcl 20:33:44 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Remote host closed the connection] 20:34:39 segv- [~mb@95-91-243-234-dynip.superkabel.de] has joined #sbcl 20:38:47 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Read error: Connection reset by peer] 20:39:41 segv- [~mb@95-91-243-234-dynip.superkabel.de] has joined #sbcl 20:42:28 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Remote host closed the connection] 20:47:26 segv- [~mb@95-91-243-234-dynip.superkabel.de] has joined #sbcl 21:10:54 -!- prxq [~mommer@x2f69af6.dyn.telefonica.de] has quit [Remote host closed the connection] 21:17:33 -!- danlentz0 [~danlentz@c-68-37-70-235.hsd1.nj.comcast.net] has quit [Quit: Dan Lentz ... Out.] 21:20:07 -!- angavrilov [~angavrilo@217.71.227.190] has quit [Remote host closed the connection] 21:43:06 ehaliewicz [~user@50-0-51-11.dsl.static.sonic.net] has joined #sbcl 21:50:50 -!- oleo [~oleo@xdsl-78-35-178-124.netcologne.de] has quit [Quit: Leaving] 21:51:30 -!- sdemarre [~serge@109.134.153.163] has quit [Ping timeout: 252 seconds] 22:04:53 -!- stassats [~stassats@wikipedia/stassats] has quit [Read error: Connection reset by peer] 22:06:17 stassats [~stassats@wikipedia/stassats] has joined #sbcl 22:24:36 Hydan [~hydan@ip-89-103-110-5.net.upcbroadband.cz] has joined #sbcl 22:34:46 -!- Fare [fare@nat/google/x-tjsqrtbwfkujygpo] has quit [Ping timeout: 245 seconds] 22:42:29 Fare [fare@nat/google/x-apmeqczuxkgeotsp] has joined #sbcl 23:06:38 -!- segv- [~mb@95-91-243-234-dynip.superkabel.de] has quit [Remote host closed the connection] 23:11:15 -!- Bike [~Glossina@69.166.47.101] has quit [Ping timeout: 260 seconds] 23:13:50 -!- stassats [~stassats@wikipedia/stassats] has quit [Ping timeout: 240 seconds] 23:18:48 davazp [~user@92.251.186.129.threembb.ie] has joined #sbcl 23:29:48 Bike [~Glossina@wl-nat99.it.wsu.edu] has joined #sbcl