Stormwind_mobile has joined #glasgow
<marcan> whitequark: for reference, my JACK buffer size is 16ms right now.
<whitequark> aha
<marcan> I do get underruns on discontinuities, but steady-state it's pretty good, though not perfect depending on what I'm doing
<marcan> I use the linux-rt patches but realtime on x86 is a shitshow anyway
* whitequark looks at `insmod nvidia`
<marcan> lol.
<whitequark> i mean
<whitequark> i don't use it at the same time as rt stuff
<whitequark> it *probably* shouldn't fuck things up if there's no actual GPU in the system
<marcan> if it compiles for RT
<whitequark> it does need an undocumented environment variable to even build with preempt-rt
<whitequark> export IGNORE_PREEMPT_RT_PRESENCE=1
<marcan> lol.
<whitequark> seems to work tho?
<whitequark> whatever horrifying hack it's using works
<whitequark> i think the reason that thing even exists is because of all the machine vision people using tegra
<whitequark> which i mean, actually what the fuck???
<marcan> hahahaha
<whitequark> sure i'm fucking around on my desk and so that's fine
<whitequark> but you assholes run some sort of a robot on it or whatever
<_whitenotifier> [GlasgowEmbedded/glasgow] whitequark pushed 2 commits to master [+0/-0/±2] https://git.io/JeRfZ
<_whitenotifier> [GlasgowEmbedded/glasgow] whitequark 0471275 - applet.audio.yamaha_opx: fix OPL3 reset.
<_whitenotifier> [GlasgowEmbedded/glasgow] whitequark fd25ade - applet.audio.yamaha_opx: allow user-defined command stream filters.
pg12 has quit [Quit: pg12]
pg12 has joined #glasgow
pg12 has quit [Client Quit]
pg12 has joined #glasgow
pg12 has quit [Client Quit]
pg12 has joined #glasgow
pg12 has quit [Client Quit]
pg12 has joined #glasgow
pg12 has quit [Client Quit]
pg12 has joined #glasgow
pg12 has quit [Client Quit]
pg12 has joined #glasgow
thaytan has quit [Ping timeout: 265 seconds]
thaytan has joined #glasgow
pie_ has joined #glasgow
pie__ has quit [Ping timeout: 246 seconds]
craigo has quit [Ping timeout: 265 seconds]
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 245 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
mwk has quit [Ping timeout: 240 seconds]
Stary has quit [Ping timeout: 265 seconds]
mwk has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
ExeciN has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 246 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stary has joined #glasgow
<emily> marcan: are the realtime patches actually worth it?
<emily> also by "realtime on x86 is a shitshow" do you mean architecturally (because agreed ofc) or linux specifically?
Stormwind_mobile has quit [Ping timeout: 276 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
<whitequark> both
Stormwind_mobile has joined #glasgow
<whitequark> the realtime patches are sufficiently worth it that they'll be mainline soon
carl0s has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 245 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Exec1N has joined #glasgow
Stormwind_mobile has joined #glasgow
ExeciN has quit [Ping timeout: 268 seconds]
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
<marcan> emily: architecturally
<marcan> but also just in general there is Too Much Crap on a modern OS
<marcan> the RT patches do help though
<marcan> e.g. I've run emerge compiles while doing realtime audio stuff and it was fine
<marcan> but the devil of RT stuff is that the exceptional cases are what kill you
<marcan> sure, you can peg the CPUs with compute garbage and the RT side won't feel anything (as long as CPU throttling or the like don't screw you over)
<marcan> heck if anything the lack of idle modes will *help* RT stuff
<marcan> RT latencies go down when you burn CPU
<marcan> but then it's the little glitches where something holds the wrong mutex or something waits on something it shouldn't or some hardware misbehaves that get you
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
<grazfather> sorear you asked two weeks ago where I had heard of glasgow. I think someone tweeted it.
<grazfather> to some article that mentioned it and the new bus pirate
<sorear> mm
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
<Stormwind_mobile> Can someone tell me the max dara rate one can get piped through Glasgow?
<whitequark> about 30 MB/s
<whitequark> (sum in both directions)
<whitequark> that requires some real good alignment of stars though, and is only possible on Linux
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
craigo has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Read error: Connection reset by peer]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 268 seconds]
Stormwind_mobile has joined #glasgow
Stormwind_mobile has quit [Ping timeout: 240 seconds]
Stormwind_mobile has joined #glasgow
<electronic_eel> Stormwind_mobile: I constantly get numbers around 41 and 42 MByte/s when running "glasgow run benchmark"
<electronic_eel> this is on linux with a several years old cpu/mainboard (core i7-4771)
nicexe has joined #glasgow
Exec1N has quit [Ping timeout: 240 seconds]
Stormwind_mobile has quit [Ping timeout: 240 seconds]
<ktemkin> (those are on LUNA; my forthcoming FPGA analyzer/multitool)
* gruetzkopf wonders how many people actually get that
<tnt> I definitely didn't get it before it was explicitely mentionned here ...
mwk has quit [Ping timeout: 265 seconds]
<ZirconiumX> I mean, the colours are pretty obvious to me, but then I have a three foot long flag with those colours on
<davidc__> I only realized after grumbling about assembly costs + feeder counts (but, then again, I was looking at a BOM without any placement info)
carl0s has quit [Remote host closed the connection]
Stormwind_mobile has joined #glasgow
mwk has joined #glasgow