| *** TheDot <TheDot!~TheDot@d66-244-245-228.abol1.o-net.ca> has joined #libre-soc | 00:02 | |
| sadoon[m]1 | <programmerjake> "latest and greatest side-channel..." <- > <@programmerjake:matrix.org> latest and greatest side-channel: power leds and rolling shutter | 01:21 |
|---|---|---|
| sadoon[m]1 | > https://arstechnica.com/information-technology/2023/06/hackers-can-steal-cryptographic-keys-by-video-recording-connected-power-leds-60-feet-away/ | 01:21 |
| sadoon[m]1 | Oh boy.. | 01:21 |
| *** ghostmansd[pc] <ghostmansd[pc]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 02:11 | |
| *** openpowerbot <openpowerbot!~openpower@94-226-187-44.access.telenet.be> has quit IRC | 02:11 | |
| *** WhyNotHugo <WhyNotHugo!bc7d0f0b52@2604:bf00:561:2000::28> has quit IRC | 02:14 | |
| *** alethkit <alethkit!23bd17ddc6@sourcehut/user/alethkit> has quit IRC | 02:16 | |
| *** yambo <yambo!~yambo@069-145-110-003.biz.spectrum.com> has quit IRC | 02:17 | |
| *** rsc <rsc!~robert@fedora/rsc> has quit IRC | 02:17 | |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 02:20 | |
| *** ghostmansd[pc] is now known as 042AAA2J9 | 02:20 | |
| *** ghostmansd[pc] <ghostmansd[pc]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 02:20 | |
| *** ghostmansd[hex] <ghostmansd[hex]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 02:20 | |
| *** 042AAA2J9 <042AAA2J9!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 02:20 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 02:20 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 02:22 | |
| *** ghostmansd[pc] <ghostmansd[pc]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 02:23 | |
| *** rsc <rsc!~robert@linuxnetz.de> has joined #libre-soc | 02:23 | |
| *** rsc <rsc!~robert@linuxnetz.de> has quit IRC | 02:23 | |
| *** rsc <rsc!~robert@fedora/rsc> has joined #libre-soc | 02:23 | |
| *** yambo <yambo!~yambo@069-145-110-003.biz.spectrum.com> has joined #libre-soc | 02:27 | |
| *** openpowerbot <openpowerbot!~openpower@94-226-187-44.access.telenet.be> has joined #libre-soc | 02:31 | |
| *** alethkit <alethkit!23bd17ddc6@sourcehut/user/alethkit> has joined #libre-soc | 02:33 | |
| *** WhyNotHugo <WhyNotHugo!bc7d0f0b52@2604:bf00:561:2000::28> has joined #libre-soc | 02:36 | |
| *** lxo <lxo!~lxo@gateway/tor-sasl/lxo> has quit IRC | 02:51 | |
| *** lxo <lxo!~lxo@gateway/tor-sasl/lxo> has joined #libre-soc | 02:53 | |
| *** openpowerbot <openpowerbot!~openpower@94-226-187-44.access.telenet.be> has quit IRC | 03:00 | |
| *** openpowerbot <openpowerbot!~openpower@94-226-187-44.access.telenet.be> has joined #libre-soc | 03:01 | |
| programmerjake | luke: I found out why creating a power decoder is really slow: there's a stray gc.collect() call in there! commenting that out made it go several times faster | 06:00 |
| programmerjake | ghostmansd: SVP64Instruction.Prefix is really slow to construct, so I had to add a cached instance. it'd be nice if it were faster and didn't need to duplicate the whole field hierarchy each time you construct an instance. | 07:14 |
| programmerjake | https://git.libre-soc.org/?p=openpower-isa.git;a=commitdiff;h=3947ab6d3d2e12e94638ef11f3c4126b67ed7280 | 07:14 |
| programmerjake | I used py-spy with speedscope to profile running tests, which worked out nicely, once I installed libunwind-dev | 07:17 |
| programmerjake | ci went from 52min to 35min thanks to the optimizations i did | 08:07 |
| *** ghostmansd[hex] <ghostmansd[hex]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 08:37 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 08:40 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.54.36> has joined #libre-soc | 08:40 | |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 10:11 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.54.36> has quit IRC | 10:48 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 10:48 | |
| markos_ | lkcl, just got the loongson board | 11:28 |
| markos_ | missing a case and PSU though, so will have to wait to get it powered on | 11:29 |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 11:41 | |
| lkcl | markos_, awesome! | 14:34 |
| lkcl | programmerjake, fantastic! | 14:34 |
| lkcl | let me see how long it takes here, i'll time all tests in decoder/isa | 14:35 |
| lkcl | hmm my laptop's in "powersave" mode so all cores are limited to 1.5 ghz if using parallel pytest | 14:37 |
| lkcl | https://slashdot.org/story/23/06/13/2057209/researchers-warn-of-model-collapse-as-ai-trains-on-ai-generated-content | 14:39 |
| * lkcl facepalm | 14:39 | |
| markos_ | some people misread what "eating your own dogfood" really means | 14:39 |
| lkcl | well it's supposed to be "fit for human consumption" | 14:40 |
| lkcl | a fact that turned out to be really important when an Indian Restaurant in London was raided in the 1980s... | 14:40 |
| programmerjake | well, training against an AI *does* work in GANs, where one neural net is producing increasingly realistic fakes and the other neural net is getting increasingly good at distinguishing the fakes from the real thing: https://en.wikipedia.org/wiki/Generative_adversarial_network | 14:46 |
| markos_ | But there is a clear separation of the roles in this case, one is trained with real data only -to generate the fakes- and the other is trained on both -to distinguish | 14:49 |
| markos_ | the problem is when you don't know if it's a fake | 14:49 |
| markos_ | which is the case argued in the slashdot post | 14:49 |
| markos_ | what if you have eg. midjourney trained on its own data at one point, the results will be insane | 14:50 |
| markos_ | they're already insanely looking images | 14:50 |
| markos_ | but then they will make absolutely no sense at all | 14:50 |
| *** psydroid <psydroid!~psydroid@user/psydroid> has quit IRC | 14:51 | |
| *** pangelo[m] <pangelo[m]!~pangeloma@2001:470:69fc:105::3ec5> has quit IRC | 14:51 | |
| *** cesar <cesar!~cesar@2001:470:69fc:105::76c> has quit IRC | 14:51 | |
| *** vaino[m] <vaino[m]!~vainomatr@2001:470:69fc:105::3:5474> has quit IRC | 14:51 | |
| *** sadoon[m]1 <sadoon[m]1!~sadoonalb@2001:470:69fc:105::3:5f7c> has quit IRC | 14:51 | |
| *** sadoon[m] <sadoon[m]!~sadoonsou@2001:470:69fc:105::2:bab8> has quit IRC | 14:51 | |
| *** programmerjake <programmerjake!~programme@2001:470:69fc:105::172f> has quit IRC | 14:51 | |
| *** Ryuno-KiAndrJaen <Ryuno-KiAndrJaen!~ryuno-kim@2001:470:69fc:105::14ed> has quit IRC | 14:51 | |
| lkcl | the difference between fake-detection and training-on-training is that the fake-detection is *not* just on training-on-training, it is training on the *difference* between real and fake | 14:57 |
| *** programmerjake <programmerjake!~programme@2001:470:69fc:105::172f> has joined #libre-soc | 14:58 | |
| *** psydroid <psydroid!~psydroid@user/psydroid> has joined #libre-soc | 15:19 | |
| *** sadoon[m] <sadoon[m]!~sadoonsou@2001:470:69fc:105::2:bab8> has joined #libre-soc | 15:19 | |
| *** pangelo[m] <pangelo[m]!~pangeloma@2001:470:69fc:105::3ec5> has joined #libre-soc | 15:19 | |
| *** Ryuno-KiAndrJaen <Ryuno-KiAndrJaen!~ryuno-kim@2001:470:69fc:105::14ed> has joined #libre-soc | 15:19 | |
| *** sadoon[m]1 <sadoon[m]1!~sadoonalb@2001:470:69fc:105::3:5f7c> has joined #libre-soc | 15:19 | |
| *** cesar <cesar!~cesar@2001:470:69fc:105::76c> has joined #libre-soc | 15:19 | |
| *** vaino[m] <vaino[m]!~vainomatr@2001:470:69fc:105::3:5474> has joined #libre-soc | 15:19 | |
| lkcl | real 22m29.469s | 15:46 |
| lkcl | that's at 1.5 ghz with 8 processes | 15:46 |
| lkcl | so... 7 minutes @ 4.8 ghz... | 15:46 |
| lkcl | i remember it being more like 12-15 so that's damn good programmerjake | 15:47 |
| programmerjake | i expect it doesn't scale with frequency 1:1 | 15:47 |
| programmerjake | though otoh it will likely go faster if it uses 16 threads on your 8 core laptop | 15:49 |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 15:52 | |
| lkcl | i can't risk it overheating, otherwise i would | 15:54 |
| lkcl | currently 25C and that's hot enough | 15:54 |
| programmerjake | intel cpus are generally designed to be able to run at like 90C normally, and hotter when thermal throttling | 15:56 |
| programmerjake | though laptops with poor cooling may be limited by max case temperature instead | 15:58 |
| markos_ | 25C? that's not hot :) | 16:05 |
| markos_ | that's the definition of cool :) | 16:05 |
| markos_ | my 11th gen i5 laptop is currently at 50C and I find that acceptable given the load | 16:07 |
| markos_ | unless this measurement is reporting something else and not the cpu | 16:12 |
| markos_ | check lm-sensors package | 16:12 |
| markos_ | but tbh, this does not look a normal temperature of an intel cpu under load, unless your laptop is really special | 16:13 |
| *** yambo <yambo!~yambo@069-145-110-003.biz.spectrum.com> has quit IRC | 16:55 | |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 17:07 | |
| ghostmansd[m] | programmerjake, nice catch! Thank you! | 17:39 |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 17:49 | |
| ghostmansd[m] | I think this should be hidden somewhere in Field class. I'll take a look at it later. | 17:53 |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 17:58 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has quit IRC | 18:07 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.57.248> has joined #libre-soc | 18:12 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@176.59.57.248> has quit IRC | 18:16 | |
| *** ghostmansd[m] <ghostmansd[m]!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 18:17 | |
| *** ghostmansd <ghostmansd!~ghostmans@broadband-109-173-83-100.ip.moscow.rt.ru> has joined #libre-soc | 18:31 | |
| *** tplaten <tplaten!~tplaten@195.52.51.97> has joined #libre-soc | 19:28 | |
| lkcl | markos_, ahh | 21:06 |
| lkcl | Package id 0: +57.0°C (high = +100.0°C, crit = +100.0°C) ALARM (CRIT) | 21:06 |
| lkcl | Core 0: +57.0°C (high = +100.0°C, crit = +100.0°C) ALARM (CRIT) | 21:06 |
| markos_ | yeah, 25C looked suspiciously low | 21:10 |
| *** tplaten <tplaten!~tplaten@195.52.51.97> has quit IRC | 21:24 | |
Generated by irclog2html.py 2.17.1 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!