#
#asahi-gpu · 2022-10-27 03:03
phirethat's what I was already wondering. though why is it so keen to avoid writing to the store buffer until the end?
#asahi-gpu · 2022-10-27 03:03
linaSince some could be compressed and not others
#asahi-gpu · 2022-10-27 03:02
linaAnd then similarly the meta buffers are separate
#asahi-gpu · 2022-10-27 03:02
linaNow I wonder if this for separate buffers for load/partial/store
#asahi-gpu · 2022-10-27 03:02
linadepth_buffer_ptr3 = 0x1501c68000
#asahi-gpu · 2022-10-27 03:02
linadepth_buffer_ptr2 = 0x1501750000
#asahi-gpu · 2022-10-27 03:02
linadepth_buffer_ptr1 = 0x1501c68000
#asahi-gpu · 2022-10-27 03:01
linaalyssa: Remember how there is more than one depth buffer?
#asahi-gpu · 2022-10-27 03:01
linaHuh.
#asahi-gpu · 2022-10-27 03:00
linaI see the stencil aux buffers too, so this was good to name those fields...
#asahi-gpu · 2022-10-27 02:59
linaWhat the heck. Well, that's a new one.
#asahi-gpu · 2022-10-27 02:59
linadepth_flags = 0x5000000000c4154
#asahi-gpu · 2022-10-27 02:56
linaopens up WebGL Aquarium
#asahi-gpu · 2022-10-27 02:55
linaSome random webGL demo?
#asahi-gpu · 2022-10-27 02:55
linaWhat's a good macOS app to exercise the depth buffer? I just did boot->safari->youtube and there isn't a single render with depth...
#asahi-gpu · 2022-10-27 02:54
alyssasomething about rendering to a texture with usage Unknown and allowGPU = false
#asahi-gpu · 2022-10-27 02:54
phireand framebuffer compresion *only* cares about reducing memory bandwidth, not buffer size
#asahi-gpu · 2022-10-27 02:54
alyssaI honestly can't remember how I got it do that
#asahi-gpu · 2022-10-27 02:54
linaFB compression isn't about size, it's about bandwidth, so the buffers are actually slightly larger (extra meta)
#asahi-gpu · 2022-10-27 02:54
alyssaNow I want to know what macOS on m1 ultra does with the "do not compress depth" magic with metal
#asahi-gpu · 2022-10-27 02:54
linaYou always need more space any time you use compression, by definition
#asahi-gpu · 2022-10-27 02:54
linaYes, exactly
#asahi-gpu · 2022-10-27 02:53
phireah, makes sense. so you can fallback to uncompressed if compression fails to produce a smaller result
#asahi-gpu · 2022-10-27 02:53
linaThis is pretty typical framebuffer compression stuff
#asahi-gpu · 2022-10-27 02:53
linaThe metadata buffer has one byte per 8x4 pixel block in the main buffer
#asahi-gpu · 2022-10-27 02:53
linaThe main buffer is the same, it just has compressed tiles and the metadata buffer tells it how they were compressed.
#asahi-gpu · 2022-10-27 02:52
phireso that means the buffer has the same layout when compressed?
#asahi-gpu · 2022-10-27 02:52
linaWhich is needed for compression
#asahi-gpu · 2022-10-27 02:52
linaThey aren't separate, the extra buffer is the *metadata* buffer
#asahi-gpu · 2022-10-27 02:51
phirealso, this is a waste of memory, having seperate buffers for the TVB overflows and the final depth
#asahi-gpu · 2022-10-27 02:51
phirehmmm.... weird
#asahi-gpu · 2022-10-27 02:50
linaBut then why is *store* being forced on, but not *load*?
#asahi-gpu · 2022-10-27 02:49
phireunless... what if there is a hardware bug loading non-compressed depth/stencil buffers, and this is a workaround?
#asahi-gpu · 2022-10-27 02:49
phirebut hardware bug would be weirder. how would the PBE know the diffrence between a final store and a TVB flush store?
#asahi-gpu · 2022-10-27 02:48
linaFirmware bug would be kind of weird... especially since it's a shared codebase
#asahi-gpu · 2022-10-27 02:48
phireagx firmware bug? I'd be supprised if it was a hardware bug
#asahi-gpu · 2022-10-27 02:47
LunaFoxgirlVTdata has been squimshed (´・ω・)
#asahi-gpu · 2022-10-27 02:47
linaMaybe this is an outright bug? G13X always does partial depth stores compressed?
#asahi-gpu · 2022-10-27 02:46
alyssaeyes emoji
#asahi-gpu · 2022-10-27 02:46
linaThat's... exactly what you would expect of compressed data loaded as uncompressed
#asahi-gpu · 2022-10-27 02:46
linaActually this fits the image I'm seeing... I get lots of mini-tiles with stuff in the top left.
#asahi-gpu · 2022-10-27 02:45
linaYeah, but not having 0x44 seems to break the overflow, like it stores compressed but loads uncompressed.
#asahi-gpu · 2022-10-27 02:45
alyssaOk, that jives with what i've seen on g
#asahi-gpu · 2022-10-27 02:45
phireseperate control over TVB overflow and final depthbuffer is a useful feature
#asahi-gpu · 2022-10-27 02:45
alyssa02:44 < lina> I see a 1:1 correlation between 0x44 and the accel/meta buffer existing
#asahi-gpu · 2022-10-27 02:44
linaphire: Partially, even!
#asahi-gpu · 2022-10-27 02:44
linaIn old G13G traces (that I now found - there are few of them)
#asahi-gpu · 2022-10-27 02:44
phirealso, who is forcing compression on? the kernel driver, or the agx firmware?
#asahi-gpu · 2022-10-27 02:44
linaI see a 1:1 correlation between 0x44 and the accel/meta buffer existing
#asahi-gpu · 2022-10-27 02:43
linaOK, so this is related to compression... but then why is G13D enabling compression even without them, partially, then breaking?

plus ›