#dri-devel on 2025-06-07 — irc logs at oftc.catirclogs.org

2024-07-16 04:52 ChanServ changed the topic of #dri-devel to: <ajax> nothing involved with X should ever be unable to find a bar

00:02 Nasina has joined #dri-devel

00:08 kzd has quit [Ping timeout: 480 seconds]

00:11 digetx has quit [Ping timeout: 480 seconds]

01:02 rasterman has quit [Quit: Gettin' stinky!]

01:20 Emantor has quit [Quit: ZNC - http://znc.in]

01:20 Emantor has joined #dri-devel

01:36 The_Company has joined #dri-devel

01:43 Company has quit [Ping timeout: 480 seconds]

02:00 kzd has joined #dri-devel

02:27 Daanct12 has joined #dri-devel

02:32 Nasina has quit [Read error: Connection reset by peer]

02:32 pzanoni has quit [Ping timeout: 480 seconds]

02:32 Nasina has joined #dri-devel

02:36 glennk has joined #dri-devel

02:44 Nasina has quit [Ping timeout: 480 seconds]

03:00 The_Company has quit []

03:09 Nasina has joined #dri-devel

03:21 Nasina has quit [Ping timeout: 480 seconds]

03:37 Nasina has joined #dri-devel

03:42 Nasina has quit [Remote host closed the connection]

03:47 blaztinn has quit [Ping timeout: 480 seconds]

03:47 blaztinn has joined #dri-devel

03:50 Nasina has joined #dri-devel

03:51 Nasina has quit [Read error: Connection reset by peer]

03:52 illwieckz has quit [Read error: Connection reset by peer]

03:52 Company has joined #dri-devel

03:53 illwieckz has joined #dri-devel

03:55 Company has quit []

04:02 nerdopolis has quit [Ping timeout: 480 seconds]

04:07 Nasina has joined #dri-devel

04:07 zsoltiv_ has quit [Ping timeout: 480 seconds]

04:08 Nasina has quit [Remote host closed the connection]

04:23 Nasina has joined #dri-devel

04:35 zzyiwei has joined #dri-devel

04:36 zzyiwei has quit [Read error: Connection reset by peer]

05:13 vliaskov__ has joined #dri-devel

05:14 Nasina has quit [Remote host closed the connection]

05:14 fab has joined #dri-devel

05:34 Nasina has joined #dri-devel

05:35 Nasina has quit [Read error: Connection reset by peer]

05:43 Nasina has joined #dri-devel

05:50 Nasina has quit [Read error: Connection reset by peer]

06:11 kasper93_ has joined #dri-devel

06:11 kasper93 is now known as Guest17728

06:11 kasper93_ is now known as kasper93

06:13 kasper93_ has joined #dri-devel

06:13 kasper93 is now known as Guest17729

06:13 kasper93_ is now known as kasper93

06:14 kasper93_ has joined #dri-devel

06:14 kasper93 is now known as Guest17730

06:14 kasper93_ is now known as kasper93

06:18 Guest17728 has quit [Ping timeout: 480 seconds]

06:20 Guest17729 has quit [Ping timeout: 480 seconds]

06:21 Guest17730 has quit [Ping timeout: 480 seconds]

06:27 fab has quit [Quit: fab]

06:31 Nasina has joined #dri-devel

06:34 Nasina has quit [Read error: Connection reset by peer]

06:36 Duke`` has joined #dri-devel

06:38 fab has joined #dri-devel

06:53 kasper93 has quit [Ping timeout: 480 seconds]

06:57 kzd has quit [Ping timeout: 480 seconds]

06:58 Nasina has joined #dri-devel

07:00 sghuge has quit [Remote host closed the connection]

07:00 fab has quit [Quit: fab]

07:00 sghuge has joined #dri-devel

07:01 fab has joined #dri-devel

07:02 fab has quit []

07:23 Nasina has quit [Read error: Connection reset by peer]

07:26 Nasina has joined #dri-devel

07:35 hikiko_ has joined #dri-devel

07:40 hikiko has quit [Ping timeout: 480 seconds]

07:51 Daanct12 has quit [Quit: WeeChat 4.6.3]

07:54 Daanct12 has joined #dri-devel

07:54 Nasina has quit [Read error: Connection reset by peer]

08:08 rasterman has joined #dri-devel

08:13 Nasina has joined #dri-devel

08:13 Nasina has quit [Read error: Connection reset by peer]

08:28 <karolherbst> Soo.. I might want to do something about resource_from_user_memory. Atm I think most drivers only accept page aligned pointers, iris does internal offset magic to support any. I'm wondering if it's better to move that into the frontends instead. On the OpenGL side it's used through GL_AMD_pinned_memory and GL_EXTERNAL_VIRTUAL_MEMORY_BUFFER_AMD. The

08:28 <karolherbst> GL extension doesn't specify any alignment requirements, just advises to use system page size in the FAQ. The OpenCL side of things can create cl_mem buffers from host memory and doesn't specify an alignment req either, however the request is not allowed to fail in OpenCL, so atm if the driver rejects it, I simply create a shadow buffer and handle

08:28 <karolherbst> it in the frontend.

08:29 <karolherbst> I wonder if we should add a cap where each driver specifies the required alignment of resource_from_user_memory

08:29 <karolherbst> and then make it a frontend problem to make the call reliable

08:35 anholt has joined #dri-devel

08:40 TMM has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]

08:40 TMM has joined #dri-devel

09:08 Nasina has joined #dri-devel

09:22 Nasina has quit [Read error: Connection reset by peer]

09:23 Nasina has joined #dri-devel

09:31 Nasina has quit [Ping timeout: 480 seconds]

09:48 mal has quit [Ping timeout: 480 seconds]

09:51 croissant_ has joined #dri-devel

09:52 <kode54> is geekbench6 known to do bad behavior?

09:56 fab has joined #dri-devel

09:57 fab has quit []

09:57 croissant has quit [Ping timeout: 480 seconds]

10:01 sima has joined #dri-devel

10:04 hikiko has joined #dri-devel

10:07 Duke`` has quit [Ping timeout: 480 seconds]

10:07 hikiko_ has quit [Ping timeout: 480 seconds]

10:10 vliaskov__ has quit [Remote host closed the connection]

10:19 Caterpillar has joined #dri-devel

10:30 fab has joined #dri-devel

10:32 fab has quit []

10:32 fab has joined #dri-devel

10:35 fab has quit []

10:35 sima has quit [Ping timeout: 480 seconds]

10:48 rasterman has quit [Quit: Gettin' stinky!]

10:49 JRepin has joined #dri-devel

10:51 Nasina has joined #dri-devel

11:04 coldfeet has joined #dri-devel

11:07 balrog_ has joined #dri-devel

11:10 balrog has quit [Ping timeout: 480 seconds]

11:19 JRepin has quit []

11:19 JRepin has joined #dri-devel

11:27 kts has joined #dri-devel

11:47 kts has quit [Ping timeout: 480 seconds]

11:47 coldfeet has quit [Quit: Lost terminal]

11:48 lplc has quit [Quit: WeeChat 4.0.4]

11:50 lplc has joined #dri-devel

12:15 kasper93 has joined #dri-devel

12:19 JRepin has quit []

12:19 JRepin has joined #dri-devel

12:33 coldfeet has joined #dri-devel

12:52 lion328 has quit [Quit: Leaving]

12:54 JRepin has quit []

12:57 lion328 has joined #dri-devel

12:58 haaninjo has joined #dri-devel

13:00 JRepin has joined #dri-devel

13:06 kts has joined #dri-devel

13:09 abhinav__ has quit [Quit: The Lounge - https://thelounge.chat]

13:09 stsquad has quit [Quit: ZNC 1.8.1 - https://znc.in]

13:09 akhilpo has quit [Quit: The Lounge - https://thelounge.chat]

13:09 lumag has quit [Quit: ZNC 1.8.1 - https://znc.in]

13:09 bryanodonoghue has quit [Quit: The Lounge - https://thelounge.chat]

13:09 sumits has quit [Quit: ZNC 1.8.1 - https://znc.in]

13:09 jhugo has quit [Quit: The Lounge - https://thelounge.chat]

13:09 jessica_24 has quit [Quit: The Lounge - https://thelounge.chat]

13:09 sgerhold has quit [Quit: :/]

13:09 stsquad has joined #dri-devel

13:09 JRepin has quit []

13:10 cbraga3 has joined #dri-devel

13:10 JRepin has joined #dri-devel

13:10 lumag has joined #dri-devel

13:16 nerdopolis has joined #dri-devel

13:20 JRepin has quit []

13:20 TMM has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]

13:20 TMM has joined #dri-devel

13:42 Daanct12 has quit [Quit: WeeChat 4.6.3]

13:45 <eric_engestrom> hakzsam: sorry the for ~48h late reply, I've been very sporadically on my laptop these last couple of days (and I'm about to be mostly offline for a week)

13:45 <eric_engestrom> hakzsam: I'll make a release right now, although I only have a few minutes before I have to go; if I don't manage now I'll find some time tomorrow

13:46 <eric_engestrom> the release will have no other commit and I'll skip the normal ci round to verify it otherwise I don't have time to wait

13:49 croissant_ has quit []

13:49 hikiko_ has joined #dri-devel

13:50 hikiko has quit [Ping timeout: 480 seconds]

13:50 croissant has joined #dri-devel

13:57 kts has quit [Ping timeout: 480 seconds]

14:08 <robclark> karolherbst: any idea about this (from cts test_conversions):

14:08 <robclark> https://www.irccloud.com/pastebin/rurQwfmt/

14:09 <eric_engestrom> hakzsam: release is out :)

14:09 <karolherbst> robclark: LLVM Translator bug

14:09 <robclark> ok so "not our bug"(TM)

14:09 <karolherbst> robclark: https://github.com/KhronosGroup/SPIRV-LLVM-Translator/pull/3120

14:09 <robclark> and yeah, I would appreciate frontend doing page alignment ;-)

14:10 <karolherbst> already merged and backported, might just need to update your deps or so

14:10 <robclark> (there might be extra fun for asahi with different host vs guest pg size)

14:10 <karolherbst> yeah...

14:10 <karolherbst> I really want the driver to tell me the alignment it expets

14:10 <karolherbst> but

14:10 <robclark> hmm, I just cloned SPIRV-LLVM-Translator yesterday

14:10 <karolherbst> asahi doesn't support resource_from_user_memory yet

14:11 <karolherbst> soo..

14:11 <karolherbst> robclark: ohh.. which llvm branch?

14:11 <karolherbst> maybe it wasn't backported...

14:11 <robclark> (nether does freedreno.. yet.. kernel supports it but not wired up yet)

14:11 <robclark> but yeah, required alignment cap would be a good idea

14:11 <karolherbst> I'm more interested in it in terms of fine-grained buffer SVM support

14:11 <robclark> I think main?

14:12 <karolherbst> which will require from_user_memory to be reliable

14:12 <karolherbst> mhhh

14:12 <karolherbst> mesa doesn't build on llvm main

14:12 <karolherbst> https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35399

14:12 <robclark> oh, hmm

14:12 <robclark> I guess I'm using distro version?

14:13 <karolherbst> possibly

14:13 <robclark> yeah, /lib/aarch64-linux-gnu/libLLVMSPIRVLib.so.19.1

14:14 <karolherbst> ahh

14:14 <karolherbst> let's see

14:14 <karolherbst> https://github.com/KhronosGroup/SPIRV-LLVM-Translator/commit/83052effe3ac1f015b9009ca84e7286254c62754

14:15 <karolherbst> but the translator doesn't do releases in the classical sense

14:15 <karolherbst> ohh it does actually...

14:15 <karolherbst> since when I wonder

14:15 <karolherbst> robclark: anyway.. looks like you'll need 19.1.8 of the translator then

14:16 <karolherbst> I think they just tag whenever llvm tags

14:16 <robclark> this is debian (trixie/13) for $reasons.. looks like it is still on 19.1.6

14:16 <karolherbst> rough

14:16 <karolherbst> wanna have my llvm build script?

14:17 <robclark> no!

14:17 <karolherbst> :D

14:17 <robclark> this thing is slow (basically a watch SoC).. it would take half a century to build llvm ;-)

14:17 <robclark> I'll just note what version it is fixed in and move on

14:17 <karolherbst> okay

14:21 <karolherbst> mhhh

14:21 <karolherbst> the from_user_memory alignment problem could become _interesting_ to support

14:22 <karolherbst> e.g. what if your host has 4k pages, the device needs 16k

14:22 <karolherbst> and now you get a 0x...3100 pointer

14:22 <karolherbst> do you try to map 0x...0000 + (internal offset 0x3100) and hope the driver manages if a page is mapped at 0x...3000 but not before?

14:23 <karolherbst> that's gonna get interesting to support properly...

14:23 <robclark> I assume the same offset tricks as sub-page.. if guest has smaller page size, the guest mapping can still be page aligned.. I think

14:24 <karolherbst> yeah but if the driver says "16k alignment" I can't just try to map 0x...3000 even if it's the start of the page on the host

14:24 <karolherbst> _however_

14:25 <karolherbst> for SVM it doesn't matter, because I do the allocation :)

14:25 <karolherbst> and for non SVM I can still do shadow buffers

14:25 <karolherbst> so guess this is a corner case I'll just ignore

14:25 <robclark> so guest VA doesn't need the same alignment as host VA

14:25 <karolherbst> right, but I map into the GPU's VM space

14:25 <robclark> but buffer size and gpu mapping would need 16k alignment

14:26 <karolherbst> mhhhhhh

14:26 <karolherbst> I _think_ there was an issue with that on asahi... but I can't remember

14:26 <robclark> I guess if you want gpu va to equal guest va then it is 16k alignment

14:26 <karolherbst> I think the physical memory needs alignment

14:27 <karolherbst> but not sure...

14:27 <karolherbst> anyway.. can try to solve this when it becomes necessary 🙃

14:34 digetx has joined #dri-devel

14:35 akhilpo has joined #dri-devel

14:37 hikiko has joined #dri-devel

14:42 hikiko_ has quit [Ping timeout: 480 seconds]

14:50 kzd has joined #dri-devel

14:54 warpme has joined #dri-devel

14:55 Company has joined #dri-devel

15:00 gouchi has joined #dri-devel

15:00 gouchi has quit [Remote host closed the connection]

15:17 mal has joined #dri-devel

15:29 dsimic is now known as Guest17742

15:29 dsimic has joined #dri-devel

15:31 Guest17742 has quit [Ping timeout: 480 seconds]

16:11 Mangix has quit [Read error: Connection reset by peer]

16:12 Mangix has joined #dri-devel

16:36 fab has joined #dri-devel

16:37 warpme has quit []

16:37 coldfeet has quit [Quit: Lost terminal]

16:40 zzyiwei has joined #dri-devel

16:41 zzyiwei has quit [Read error: Connection reset by peer]

16:44 JRepin has joined #dri-devel

16:54 JRepin has quit []

16:54 JRepin has joined #dri-devel

16:58 warpme has joined #dri-devel

17:03 davispuh has joined #dri-devel

17:04 JRepin has quit []

17:12 warpme has quit []

17:21 JRepin has joined #dri-devel

17:34 JRepin has quit []

17:36 cphealy_ has quit [Ping timeout: 480 seconds]

17:48 rasterman has joined #dri-devel

17:48 parthi has joined #dri-devel

17:49 JRepin has joined #dri-devel

17:50 coldfeet has joined #dri-devel

17:54 parthiban has quit [Ping timeout: 480 seconds]

17:56 jessica_24 has joined #dri-devel

17:58 parthi has quit [Ping timeout: 480 seconds]

18:12 parthiban has joined #dri-devel

18:19 JRepin has quit []

18:19 JRepin has joined #dri-devel

18:24 JRepin has quit []

18:24 JRepin has joined #dri-devel

18:29 JRepin has quit []

18:30 JRepin has joined #dri-devel

18:55 phire has quit [Ping timeout: 480 seconds]

18:57 rasterman has quit [Quit: Gettin' stinky!]

19:01 parthi has joined #dri-devel

19:01 parthiban has quit [Remote host closed the connection]

19:13 hikiko has quit [Ping timeout: 480 seconds]

19:13 Nasina has quit [Read error: Connection reset by peer]

19:15 Nasina has joined #dri-devel

19:17 parthi has quit [Ping timeout: 480 seconds]

19:23 cphealy has joined #dri-devel

19:29 alanc has quit [Remote host closed the connection]

19:29 Mangix has quit [Read error: Connection reset by peer]

19:29 Mangix has joined #dri-devel

19:30 alanc has joined #dri-devel

19:37 Jeremy_Rand_Talos__ has quit [Remote host closed the connection]

19:38 Jeremy_Rand_Talos__ has joined #dri-devel

19:39 JRepin has quit []

19:40 JRepin has joined #dri-devel

19:49 rasterman has joined #dri-devel

20:03 hikiko has joined #dri-devel

20:06 fab has quit [Quit: fab]

20:11 hikiko_ has joined #dri-devel

20:13 hikiko has quit [Read error: Connection reset by peer]

20:31 YuGiOhJCJ has joined #dri-devel

20:35 nerdopolis has quit [Ping timeout: 480 seconds]

20:53 lanodan has quit [Ping timeout: 480 seconds]

21:25 coldfeet has quit [Quit: Lost terminal]

21:57 <DemiMarie> karolherbst: confirming that per-GPU-context is (required to be) the security boundary

22:03 haaninjo has quit [Quit: Ex-Chat]

22:32 JRepin has quit []

22:35 rasterman has quit [Quit: Gettin' stinky!]

22:53 nerdopolis has joined #dri-devel

23:03 Nasina has quit [Read error: Connection reset by peer]

23:12 Nasina has joined #dri-devel

23:14 Nasina has quit [Read error: Connection reset by peer]

23:16 glennk has quit [Ping timeout: 480 seconds]

23:18 Nasina has joined #dri-devel

23:24 Nasina has quit [Read error: No route to host]

23:39 Nasina has joined #dri-devel

23:47 calico has joined #dri-devel