| 17 May 2025 |
 Tristan Ross | 329 derivations left now | 14:30:47 |
 @winston:milli.ng | That's a heck of a long compile time! | 14:53:48 |
| Tristan Ross | In reply to @winston:milli.ng
That's a heck of a long compile time! It's been a week, I estimated about 8 days and it looks like it'll take that long | 14:54:36 |
 dramforever | @rosscomputerguy:matrix.org one week continuous building? best advertisement for visionfive 2 i've heard | 16:52:24 |
 Alex | I have sometimes had >1w up times, but I've never seen 2w uptimes.
I'm not sure if it would die because of overheating (passive cooling at 1.5 GHz and non-working thermal throttling) or instability. | 16:54:01 |
| dramforever | passive cooling is sufficient for jh7110 unless your nvme is absolutely toasty | 16:54:35 |
| dramforever | you can also just monitor the temps | 16:58:13 |
| Alex | Hm I think I did once and saw that it wasn't an overheat that killed it.
It was a while ago so I can't remember very well.
At the moment, I having bigger problems to deal with (like extremely inconsistent booting, possibly due to broken kernels). | 16:59:33 |
| dramforever | i'd check if the power supply is sufficient/reliable | 17:00:28 |
| Alex | It's a laptop USB-C charger, so it should be alright.
Not sure how I'd check it, but I do have a multimetre if that's all it takes. | 17:01:12 |
 @lotte:chir.rs | In reply to @dramforever:matrix.org
@rosscomputerguy:matrix.org one week continuous building? best advertisement for visionfive 2 i've heard i have run a small benchmark earlier today and their perf figures are just Wrong | 17:02:08 |
| dramforever | hmm, i'd just look at the wattage and ballpark it. 65W should be fine | 17:02:08 |
| dramforever | how are you booting | 17:02:09 |
| dramforever | ... perf figures? | 17:02:43 |
| Alex | Flash (with manual customisations to boot from NVMe) | 17:02:47 |
| @lotte:chir.rs | In reply to @dramforever:matrix.org
... perf figures? on the kickstarter they raccompared themselves to the pi 4 | 17:03:15 |
| @lotte:chir.rs | racclaiming it was ~similar speed | 17:03:22 |
| Alex | In reply to @lotte:chir.rs
i have run a small benchmark earlier today and their perf figures are just Wrong Wrong as in worse than advertised?
Could be a difference in flags if you're not enabling _Zba_Zbb and PGO. | 17:03:37 |
| @lotte:chir.rs | yeah tbf i didn’t enable Zba_Zbb | 17:04:06 |
| @lotte:chir.rs | but the raccode i was testing did not make use of those instructions | 17:04:29 |
| dramforever | In reply to @lotte:chir.rs
on the kickstarter they raccompared themselves to the pi 4 ... it's just not possible | 17:04:50 |
| dramforever | the 4 cores on the pi4 are simply way better | 17:05:13 |
| Alex | Maybe they were just comparing the clock rates?
(Very scientific benchmark that.) | 17:05:50 |
| dramforever | both are 1.5GHz | 17:08:00 |
| dramforever | i went to check the kickstarter page and it claims to be a chunk slower than the pi4 | 17:08:18 |
| Alex | Exactly. Comparable performance. /s | 17:08:24 |
| dramforever | which may be true | 17:08:25 |
| @lotte:chir.rs | the first test was 128 bit ID generation (nanosecond system clock, 128 bit multiply, and an atomic memory raccess), the cm4 did it in 140ns average, the vf2 in 1.114μs average (~8x slower)
1MB of base64 encoding? 4.383ms on the cm4, 12.122ms on the vf2 (~3x slower) | 17:08:38 |
| dramforever | it also just does not have vector instructions | 17:09:00 |
| @lotte:chir.rs | lemme try openssl speed | 17:09:02 |
