#asahi-gpu · 2023-07-14 02:22
linahttps://github.com/AsahiLinux/m1n1/blob/main/proxyclient/m1n1/fw/dcp/ipc.py#L521#asahi-gpu · 2023-07-14 02:20
linaBut also in general we know there's more compression types, stuff used for the video decoders and stuff... would be interesting to scrape that and see if we find other fun formats#asahi-gpu · 2023-07-14 02:20
linaIt's just a little extra blob with more parameters#asahi-gpu · 2023-07-14 02:20
linaBut also I already looked at the DCP side and have the structures worked out, it's boring#asahi-gpu · 2023-07-14 02:20
linaalyssa: Oh whoops you're right, I accidentally built the right tool for that ^^;;#asahi-gpu · 2023-07-07 15:01
linaGuess it's just more heisen for me...#asahi-gpu · 2023-07-07 15:00
lina204 repeat(s) until fail#asahi-gpu · 2023-07-07 14:54
linaNow running 13.5 with the latest kernel, same mesa, no hypervisor#asahi-gpu · 2023-07-07 14:51
lina250 repeat(s) until fail#asahi-gpu · 2023-07-07 04:55
linar3muxd: It's a software thing, on Asahi you can use as much as you want until things start crashing#asahi-gpu · 2023-07-05 13:39
linaalyssa: Well the one jannau ran into with the TVB size at least... and I'm pretty sure I fixed other stuff too, yes ^^#asahi-gpu · 2023-07-05 12:19
linaI got through GLES3 in that mode but GLES31 deadlocked or something, I'll look into it later with lockdep (might be a regression with synctvb, if so we don't care). Without any overrides things work ^^#asahi-gpu · 2023-07-05 12:19
linaTL;DR today I fixed a bunch of kernel stuff, both more sizing/param issues (I have testable test data for it now!) and also implemented the sync TVB growth event though I don't think we actually use/need it now, it was getting triggered by some bad settings I think. But you can test it with ASAHI_MESA_DEBUG=synctvb if you want (see open MR).#asahi-gpu · 2023-07-05 11:51
linadEQP-GLES31.functional.image_load_store.early_fragment_tests.no_early_fragment_tests_depth,Fail#asahi-gpu · 2023-07-05 11:51
linadEQP-GLES31.functional.image_load_store.early_fragment_tests.early_fragment_tests_stencil,Fail#asahi-gpu · 2023-07-05 11:51
linadEQP-GLES31.functional.compute.indirect_dispatch.upload_buffer.multiple_groups,Fail#asahi-gpu · 2023-07-05 11:51
linadEQP-GLES31.functional.compute.indirect_dispatch.gen_in_compute.multiple_groups,Fail#asahi-gpu · 2023-07-05 11:51
linadEQP-GLES31.functional.compute.basic.ssbo_cmd_barrier_multiple,Fail#asahi-gpu · 2023-07-05 11:51
linadEQP-GLES31.functional.compute.basic.image_barrier_multiple,Fail#asahi-gpu · 2023-07-05 11:50
linaThese are the tests that failed without "atomic" in the name but I think they're related?#asahi-gpu · 2023-07-05 11:38
linaDo you remember if it was dEQP-GLES3 or dEQP-GLES31 or something else?#asahi-gpu · 2023-07-05 11:36
linajannau: Do you remember what test was failing with the TVB thing?#asahi-gpu · 2023-07-05 03:50
linaLooks like my previous kernel fix didn't fix the Firefox hangs, it just made them not spin a CPU core... ;;#asahi-gpu · 2023-06-30 13:33
linaGood to know ^^#asahi-gpu · 2023-06-30 13:32
linaHa!#asahi-gpu · 2023-06-29 13:41
linaWhat is failing?#asahi-gpu · 2023-06-29 13:00
linajannau: Okay, so it's the TVB size thing... what machine is this?#asahi-gpu · 2023-06-29 08:12
linaAlso I know the initial TVB size is different with clustering, so it wouldn't surprise me if this breaks on Ultra only (or on the whole Pro/Max/Ultra series)#asahi-gpu · 2023-06-29 08:09
linaI think Ultra really is mostly the same execution path when it comes to rendering, just initialization is probably different.#asahi-gpu · 2023-06-29 08:09
linaRe CTS runs, I think it's largely the same execution paths for all of a series, plus it's not like we're submitting conformance separately for each firmware version either...#asahi-gpu · 2023-06-29 08:07
linaDo you know if the hanging test uses MSAA? I wouldn't be surprised if I need a *sample_count factor in there or something#asahi-gpu · 2023-06-29 08:06
linaI think the logic to compute the minimum initial TVB size is not complete#asahi-gpu · 2023-06-29 08:05
linaIs it reproducible if you increase asahi.initial_tvb_size=64 or something like that?#asahi-gpu · 2023-06-29 08:04
linajannau: "Unknown event" is something we can't handle, usually dynamic TVB allocation or similar, so it's no surprise it would hang after that.#asahi-gpu · 2023-06-29 03:29
linaThe actual driver codepath there is just a GFP_KERNEL alloc with lots of memory free/cached is failing, which is definitely not a problem with the driver itself, but I wouldn't be surprised if the 4K/16K shmem thing is breaking memory management...#asahi-gpu · 2023-06-29 03:28
linaAlso conclusion about that OOM thing is that it was the 4K kernel... which is not very surprising since it has known bugs.#asahi-gpu · 2023-06-29 03:26
lina(We agreed we only need one each of t8103, t600x, t8112, and eventually t602x)#asahi-gpu · 2023-06-29 03:26
linaI can do M2 and M1 Pro, which given our call earlier sounds like all we need with your M1? Or if jannau runs M2 and M1 Max, that covers it as well, or any other combination.#asahi-gpu · 2023-06-15 13:28
linaSee signal...#asahi-gpu · 2023-06-15 13:27
linaBut I'm more worried about whether I'll be in a state to kick off CTS runs and fix the remaining M2 Pro/Max things...#asahi-gpu · 2023-06-15 13:26
linaThe machines are not going in boxes ^^#asahi-gpu · 2023-06-15 13:19
linaHey I know you enjoyed my mesa fault decoding code ^^#asahi-gpu · 2023-06-15 13:18
linawwwwwwwww#asahi-gpu · 2023-06-15 13:17
linaAnd yeah, fair ^^#asahi-gpu · 2023-06-15 13:17
linaI suspect that setting only affects stuff fetched from shader cores (textures and device loads), so I think we'll still get hard faults for other brokenness like bad command streams or TVB problems#asahi-gpu · 2023-06-15 13:16
linaTBH I want to enable softfault by default, it's going to make things a lot more stable for people I bet, since hard faults can kill unrelated jobs and also trigger other existing bugs...#asahi-gpu · 2023-06-15 13:15
linaOK ^^#asahi-gpu · 2023-06-15 13:13
linaYou could try adding this to the kernel yourself, maybe try a bit of kernel rust~ ✨