Originally posted by boxie
View Post
Announcement
Collapse
No announcement yet.
Marek Working On 32-bit GPU Pointers For RadeonSI
Collapse
X
-
Originally posted by boxie View Post
i wonder if this gets enabled for only 4GiB < cards (as you would need the 64bit pointers for accessing the large memory areas).
BTW I purchased Sapphire RX-580 Nitro+ and it works like a charm with KDE Plasma its my first AMD GPU and i enjoy the tear free plasma experience and nice open source drivers working out of box.
- Likes 1
Comment
-
32-bit pointers will only be used internally by the driver for passing pointers to shaders. Older GCN has 64 bytes (and Vega has 128 bytes) of shader input storage. 32-bit pointers will help use that storage more effectively. For example, in Vulkan, the pointers typically point to descriptor pools. In OpenGL, the pointers point to texture/UBO/TBO/SSBO/etc. descriptor lists.
- Likes 7
Comment
-
Originally posted by Azrael5 View Postmessage to Marek: 32 bit is dead, don't waste your time in useless activities.
- Likes 5
Comment
-
Originally posted by marek View Post32-bit pointers will only be used internally by the driver for passing pointers to shaders. Older GCN has 64 bytes (and Vega has 128 bytes) of shader input storage. 32-bit pointers will help use that storage more effectively. For example, in Vulkan, the pointers typically point to descriptor pools. In OpenGL, the pointers point to texture/UBO/TBO/SSBO/etc. descriptor lists.
- Likes 1
Comment
-
Originally posted by M@yeulC View Post
Most likely you can use two addressing modes... Then I am just speculating, I must admit that I didn't bother researching. Another possibility *could* be addressing larger chunks of memory.
Edit: it does look like there are some new heap flags, so you can most certainly use it along with 64bit addressing for other parts of the program. Mesa code certainly looks like a treasure trove to anyone interested in GPUs, I'll have to have a deep look at it one of these days
Comment
-
Comment