#asahi-gpu · 2021-04-21 01:54
bloomThat's good for efficiency but makes it harder to grep for what I'm looking for in a 67k line hexdump!#asahi-gpu · 2021-04-21 01:54
bloomWas unnecessarily hard... the texture descriptor in particular is tightly packed#asahi-gpu · 2021-04-21 01:53
bloomFound the texture/sampler descriptors.#asahi-gpu · 2021-04-20 23:54
bloomnice 👍#asahi-gpu · 2021-04-20 23:54
bloomalthough I would be entirely unsurpirsed if the TODO.writeout instructions functioned as barriers#asahi-gpu · 2021-04-20 23:53
bloomnope.#asahi-gpu · 2021-04-20 23:37
chrisfbloom: do we know anything about thread ordering wrt previous writers to the same pixel?#asahi-gpu · 2021-04-20 23:24
bloompikachu#asahi-gpu · 2021-04-20 23:24
bloomsurprised_pickachu.jpg#asahi-gpu · 2021-04-20 23:24
bloomBlending seems to be 100% in software (in the fragment shader).#asahi-gpu · 2021-04-20 04:10
bloomDepth/stencil state done.#asahi-gpu · 2021-04-20 02:09
bloomI suppose I should poke cmdstream#asahi-gpu · 2021-04-19 18:05
bloomyeah, dougall pointed out similar issues.. working theory is that it's dual-issue ALU, with memory loads as messagepassing (quick)#asahi-gpu · 2021-04-19 13:27
Yuzuand if anything, the stuff in the linked presentation sounds in-order (the optimizations in slide 57, for instance, would be of fairly limited use in a true OoO machine, since independent ops would happily execute while waiting for blocked ops)#asahi-gpu · 2021-04-19 13:19
Yuzuit seems like the structures needed to support OoO would be expensive when architectural state is as large as it tends to be in GPUs#asahi-gpu · 2021-04-19 13:18
Yuzui was wondering about the same thing#asahi-gpu · 2021-04-19 13:11
radexbloom: huh, I thought "superscalar" just means "can issue multiple instructions in one cycle" and is orthogonal to OoO#asahi-gpu · 2021-04-19 12:22
bloomAlso, the linked LLVM presentation from Apple has a brief discussion on their scheduling.#asahi-gpu · 2021-04-19 12:21
bloomand we know it's not the first two.. and we know AGX perf is unparalleled..#asahi-gpu · 2021-04-19 12:21
bloomradex: Heuristic argument.. we know GPUs need some form of perthread SIMD or VLIW or multi-issue or straight up superscalar for high perf#asahi-gpu · 2021-04-19 09:29
radexbloom: just curious, how do we know that AGX has "some form of out of order execution"? I thought OoO isn't really a thing in GPUs, and instead, heavy multithreading is used to hide latency, but I'm probably uninformed#asahi-gpu · 2021-04-19 00:22
JTLcool, will check it out#asahi-gpu · 2021-04-19 00:18
bloomJTL: ^ there you go :p#asahi-gpu · 2021-04-19 00:17
bloombut the code has a bunch of hacks in it .. again, all cleaned up in time#asahi-gpu · 2021-04-19 00:17
bloomThe frontend is a fork of the usual demo app https://github.com/AsahiLinux/gpu/tree/wip#asahi-gpu · 2021-04-19 00:16
bloomhttps://gist.github.com/alyssarosenzweig/4dc380184a4959fe609bfa26bf96dd6c are the shaders, from which you'll learn, knowing how to write a shader compiler does *not* mean you know how to write shaders that don't suck :p#asahi-gpu · 2021-04-19 00:16
bloom(Disclaimer: all the code for that is published but it's split across 3 repos and it'd probably be hard to reproduce as-is. This will be rectified over time..)#asahi-gpu · 2021-04-19 00:15
bloomHave a field day y'all :)#asahi-gpu · 2021-04-19 00:15
bloomhttps://rosenzweig.io/blog/asahi-gpu-part-3.html#asahi-gpu · 2021-04-18 22:43
bloomHoping to get it out tonight... the work is done, but administrivia is hard.#asahi-gpu · 2021-04-18 22:43
bloomDraft is written, editing now.#asahi-gpu · 2021-04-18 22:43
bloomYep#asahi-gpu · 2021-04-18 22:42
JTLregarding M1 GPU progress?#asahi-gpu · 2021-04-18 22:32
bloomBlog post incoming :)#asahi-gpu · 2021-04-17 15:46
bloomhandles the core floating point stuff#asahi-gpu · 2021-04-17 15:46
bloomspun up an optimizer for agx#asahi-gpu · 2021-04-17 15:34
bloomLikewise using mov_imm as a 32-bit thing#asahi-gpu · 2021-04-17 15:33
bloomI bet so.#asahi-gpu · 2021-04-17 15:32
bloomIf two 16-bit values are in a packed register (r0l/r0h say) can we use bitop_mov on the 32-bit register (r0) for vectorization?#asahi-gpu · 2021-04-17 15:31
bloomOh, theres's a cute optimization I need to check the legitimacy of#asahi-gpu · 2021-04-17 12:00
glibcoh, they don't use a fast sin at all? That's interesting indeed#asahi-gpu · 2021-04-17 04:57
blooma lot of this stuff is irrelevant/invisible to software#asahi-gpu · 2021-04-17 04:57
bloomor not#asahi-gpu · 2021-04-17 04:56
dougallyeah, i'm sure it'll make more sense as we figure more out, but definitely plenty of puzzles left :)#asahi-gpu · 2021-04-17 04:56
method_interesting#asahi-gpu · 2021-04-17 04:54
bloomOh, I see.#asahi-gpu · 2021-04-17 04:54
dougall(that's from the announcement video iirc)#asahi-gpu · 2021-04-17 04:53
dougallhttps://www.anandtech.com/show/16252/mac-mini-apple-m1-tested/3 <- the slide#asahi-gpu · 2021-04-17 04:53
bloomsome of that is speculation from anandtech