2022-12-26
00:11Hibyehello has joined #asahi-dev
00:17hertz has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
00:46cylm has joined #asahi-dev
00:47cylm_ has quit [Ping timeout: 480 seconds]
00:56hertz has joined #asahi-dev
00:58hertz has quit []
01:06hertz has joined #asahi-dev
01:37hertz has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
01:46hertz has joined #asahi-dev
02:54yamii has quit [Ping timeout: 480 seconds]
03:07marcanjannau: yeah, so we still need a completion or something at some point to block until DCP is properly up
03:08marcanDCP has been doing sRGB, but that's a waste of a default; until we get both options exposed (which will require matrix gooeiness for 10-bit due to the wide gamut weirdness) it makes more sense to just expose native and let people who care do their own color management IMO
03:08marcanwe can't do 10-bit sRGB without either new colorspace/userspace support (ew) or matrix weirdness to compensate
03:09marcanbut also in general fewer conversion steps are preferred, so native is better and should result in less banding/quantization issues, and just let userspace deal with a single color correction step
03:10marcanat some point we'll figure out the ICC profiles to do this all properly, feel free to look into that if you're interested
03:10marcanIIRC macOS has the ICC profiles stashed somewhere in plain view and I imagine those are intended to output at the native colorspace
03:11marcanpractically: I think the only actual use case for non-native colorspaces in DCP is for video playback and such, where you're feeding in frames straight from a video decoder / scaler engine and bypassing the GPU (and normal ICC processing)
04:59greguu has quit [Ping timeout: 480 seconds]
05:15jluthra has quit [Remote host closed the connection]
05:15jluthra has joined #asahi-dev
05:35yamii has joined #asahi-dev
05:41kettenis has quit [Remote host closed the connection]
05:41kettenis has joined #asahi-dev
05:44SSJ_GZ has joined #asahi-dev
06:59greguu has joined #asahi-dev
07:06nicolas17 has quit [Ping timeout: 480 seconds]
07:24hertz has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
07:49Dementor4 has joined #asahi-dev
07:49SSJ_GZ has quit [Read error: No route to host]
07:50SSJ_GZ has joined #asahi-dev
07:54mps has quit [Ping timeout: 480 seconds]
07:55Dementor has quit [Ping timeout: 480 seconds]
07:55Dementor4 is now known as Dementor
08:53mps has joined #asahi-dev
09:01cylm has quit [Ping timeout: 480 seconds]
09:36eiln has joined #asahi-dev
09:40eilni'm using the raw iommu api to 1) allocate iova block 2) walk down gem pages and iommu_map() each page
09:41eiln1) is vm-size a legitimate limit i need a carveout for? there's a vm-base which is bogus so i think it's also bogus?
09:42eilnhttps://developer.arm.com/documentation/102420/0200/Functional-description/Functional-blocks-/DMA-controller
09:42hertz has joined #asahi-dev
09:43eilnbasically the "Command channel" and "Weight channel" equivalent work @ 64 gran but the rest are PAGE_SIZE (technically tile size == page size)
09:43eilnthe "command stream" is tiny and unaligned so what macos likes to do is to pack the weights directly after the cmd
09:43eilnorder doesn't affect function ofc but idk if it's worth the effort to separate and track the dma types
09:44eilnhttps://github.com/ARM-software/ethos-n-driver-stack/blob/main/kernel-module/ethosn_dma_iommu.c
09:44eilnhttps://github.com/ARM-software/ethos-n-driver-stack/blob/main/kernel-module/juno-r2-ethosn-smmu.dts
09:45eilnoh also attached power domains aren't called when dart's probed and dart probes before i can
09:50svenlooks like that thing requires a different iommu for each allocation type, you shouldn’t need that
09:57jannauI suspect vm-size in the ADT is just a configured limit. I haven't looked at vm-base. the only device with an non zero vm-base is dcp on m2 and it's probbaly fine to ignore for now since the managed iommu domain allocates iova top down
10:01jannaufor dcp/disp0 on t8103/t600x as well. vm-size is iirc 0xFC000000 but we start allocating at the top of the 32-bit address space
10:56yumasi has joined #asahi-dev
11:25yumasi_ has joined #asahi-dev
11:29yumasi has quit [Read error: Connection reset by peer]
11:29Dementor has quit [Read error: Connection reset by peer]
11:30Dementor has joined #asahi-dev
11:31___nick___ has joined #asahi-dev
12:01yumasi_ has quit [Remote host closed the connection]
12:03yumasi has joined #asahi-dev
12:05___nick___ has quit []
12:09___nick___ has joined #asahi-dev
12:10yumasi has quit [Remote host closed the connection]
12:11yumasi has joined #asahi-dev
12:24yumasi has quit [Remote host closed the connection]
12:28yumasi has joined #asahi-dev
12:31yumasi has quit [Remote host closed the connection]
12:33yumasi has joined #asahi-dev
13:04psykose has quit [Ping timeout: 480 seconds]
13:09yumasi has quit [Remote host closed the connection]
13:09yumasi has joined #asahi-dev
13:12eiln has quit [Quit: Page closed]
13:17yumasi has quit [Ping timeout: 480 seconds]
13:33bcrumb has joined #asahi-dev
13:41yumasi has joined #asahi-dev
13:50yumasi has quit [Remote host closed the connection]
13:51yumasi has joined #asahi-dev
13:52yumasi has quit [Remote host closed the connection]
13:53nuup has quit [Quit: WeeChat 3.0]
13:53yumasi has joined #asahi-dev
13:58bcrumb has quit [Quit: WeeChat 3.7.1]
14:01yumasi has quit [Ping timeout: 480 seconds]
14:10psykose has joined #asahi-dev
14:24psykose_ has joined #asahi-dev
14:26psykose_ has quit [Remote host closed the connection]
14:27psykose_ has joined #asahi-dev
14:28psykose has quit [Ping timeout: 480 seconds]
16:51bluetail8 has quit [Ping timeout: 480 seconds]
17:23yumasi has joined #asahi-dev
17:51roxfan2 has quit [Remote host closed the connection]
17:56roxfan has joined #asahi-dev
18:05cylm has joined #asahi-dev
18:23bluetail8 has joined #asahi-dev
18:31yumasi has quit [Remote host closed the connection]
18:46tpw_rulesmarcan: do you have the mesa releases tagged or something? i am looking through some of the older PKGBUILDs for mesa-asahi-edge and seeing commits which are not pulled down directly by a "git clone" of the repository, e.g. 08ff98967079a2e43a04f11fc646eef51a9103f1. concerned that they might be eligible for garbage collection
19:00wCPO624365 has quit [Remote host closed the connection]
19:00wCPO624365 has joined #asahi-dev
19:48psykose_ has quit [Remote host closed the connection]
19:48psykose has joined #asahi-dev
20:21nicolas17 has joined #asahi-dev
21:08___nick___ has quit [Ping timeout: 480 seconds]
22:17yumasi has joined #asahi-dev
22:25yumasi has quit [Ping timeout: 480 seconds]
22:52SSJ_GZ has quit [Ping timeout: 480 seconds]
23:24DarkShadow44 has quit [Quit: ZNC - https://znc.in]
23:25DarkShadow44 has joined #asahi-dev
23:30yumasi has joined #asahi-dev
23:38yumasi has quit [Ping timeout: 480 seconds]