#asahi · 2022-02-23 17:58
axboeI kind of take the approach of ensuring Joerg provides a reviwed-by and then just send it in yourself for the merge window with Robin on CC#asahi · 2022-02-23 17:57
axboeis he replying in general?#asahi · 2022-02-23 17:57
axboeomg november#asahi · 2022-02-23 17:55
axboeok#asahi · 2022-02-23 17:55
axboemarcan: where's the last posting of the IOMMU patches? I'm quite happy to help drive some of these forward...#asahi · 2022-02-23 17:45
axboeI too look forward to the day where I don't need a special branch :)#asahi · 2022-02-23 17:45
axboeso he'll be receptive to get everything upstream#asahi · 2022-02-23 17:45
axboelinus was balking at the pricing of the laptops, but sounds like he wants to go get a mini#asahi · 2022-02-19 23:52
axboekov: E cores disabled on the 12900k, all cores enabled on the m1#asahi · 2022-02-19 22:32
axboekov: same conclusion, just a bit closer#asahi · 2022-02-19 22:32
axboekov: using g++11 to be more fair#asahi · 2022-02-19 22:32
axboekov: 5950x (8:16) 1.96x#asahi · 2022-02-19 22:28
axboeain't nobody got time for that#asahi · 2022-02-19 22:23
axboeoh 5950x g++ was 9.x, let's redo with 11.x like the others...#asahi · 2022-02-19 22:22
axboerougly same ratio as kernel compile for 12900k, m1 does proportionally better on rust c++ compile than the 5950x compared to the kernel C compile#asahi · 2022-02-19 22:22
axboekov: hence 5950x 1.82x, 12900k 1.64x#asahi · 2022-02-19 22:21
axboekov: 5950x (8:53), m1 (16:11), 12900k (9:51)#asahi · 2022-02-19 22:00
axboekov: oh nevermind, you literally wrote that#asahi · 2022-02-19 21:59
axboekov: what's the make clean equiv there?#asahi · 2022-02-19 21:59
axboekov: ok, will do a prime run, then a timed one#asahi · 2022-02-19 21:58
axboeGlanzmann: no ecc here either#asahi · 2022-02-19 21:57
axboeGlanzmann: hm#asahi · 2022-02-19 21:56
axboekov: ok let's try it then#asahi · 2022-02-19 21:55
axboeGlanzmann: 5950x gets me ~25GB/sec here#asahi · 2022-02-19 21:55
axboeGlanzmann: 12900k is only ~23GB/sec#asahi · 2022-02-19 21:53
axboekov: guess we can do native, probably close enough#asahi · 2022-02-19 21:53
axboekov: easy to cross compile?#asahi · 2022-02-19 21:52
axboeGlanzmann: 6.7088s, 19533.98 MiB/sec <- E core#asahi · 2022-02-19 21:52
axboeGlanzmann: ;)#asahi · 2022-02-19 21:52
axboeGlanzmann: 2.7906s, 46962.77 MiB/sec#asahi · 2022-02-19 21:51
axboeGlanzmann: on the E core?#asahi · 2022-02-19 21:50
axboepartial to doing kernel compiles as a) that's what I do, and b) no real external requirements for cross compiling#asahi · 2022-02-19 21:49
axboekov: I should try that :)#asahi · 2022-02-19 21:49
axboekov: that just makes it even nuttier...#asahi · 2022-02-19 21:45
axboethe allmodconfig does turn it in after 5 min or so, but it's still way less fan than on an x1 or (god forbid, I had one of these before) a p1#asahi · 2022-02-19 21:45
axboemy experience on my m1 laptop is that a "normal" compile (which is ~3 min) doesn't spin the fan at all#asahi · 2022-02-19 21:43
axboej`ey: but hot!#asahi · 2022-02-19 21:43
axboe(71.78 min for the x1 that finally finishes, fwiw)#asahi · 2022-02-19 21:16
axboeiirc#asahi · 2022-02-19 21:15
axboesorry 2x16g#asahi · 2022-02-19 21:15
axboeGlanzmann: yep, 2x8g#asahi · 2022-02-19 21:14
axboeGlanzmann: oh actually yours are running 2600, mine a 3200#asahi · 2022-02-19 21:13
axboeGlanzmann: figured you would have it right ;)#asahi · 2022-02-19 21:05
axboeGlanzmann: nvme#asahi · 2022-02-19 21:05
axboeGlanzmann: hmm, is your ram clock right? sad to say I ran mine for quite a while before figuring out the bios set the ram speed way too low#asahi · 2022-02-19 21:04
axboewhat they run, I mean#asahi · 2022-02-19 21:04
axboeGlanzmann: these are test boxes, and I use them for peak runs hence disable mitigations, prune config etc#asahi · 2022-02-19 21:03
axboeand -j32#asahi · 2022-02-19 21:03
axboethis is my for-next branch, fwiw#asahi · 2022-02-19 21:03
axboeGlanzmann: 541.5 secs here