soresu's latest activity
-
Ssoresu replied to the thread Discussion Zen 7 speculation thread.This is very much a non trivial endeavor if the devs deviate to any significant degree from the "off the shelf" engine code. For...
-
Ssoresu replied to the thread Discussion Zen 7 speculation thread.Priorities changed. They could have kept increasing clock frequency with minimal IPC investment, but the power cost would likely have...
-
Ssoresu replied to the thread Discussion Zen 7 speculation thread.Bad optimisation on the part of game devs and low parallelization of the engine are the causes of that. Epic can fix the latter, and...
-
Ssoresu reacted to poke01's post in the thread Question x86 and ARM architectures comparison thread. with
Haha.
Qualcomm should’ve held off till V3 was ready. Oh well, they totally rushed their WoA launch once again. Hopefully, the 6th times the... -
Ssoresu replied to the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation.Yes, or GFX950 in internal parlance.
-
Ssoresu replied to the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation.I think at the CU level besides gfx specific silicon CDNA will be just a generation behind RDNA going forward. This should mean in...
-
Ssoresu reacted to Kepler_L2's post in the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation with Like.
These are marketing names and not used internally. They either use gfx number or in some cases MIxxx Navix (and now ATx)
-
Ssoresu replied to the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation.It wouldn't be the first time AMD had taken so long between one high end SKU and another. (assuming we are talking 7900 XTX -> RDNA5...
-
Ssoresu replied to the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation.Not what I meant. I meant that it wouldn't surprise me if many/most API features in Vulkan v1 were just lower level equivalent...
-
Ssoresu replied to the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation.Could just as easily mean that the current sw solution(s) that work graphs are designed to replace are pretty suboptimal, such that even...
-
Ssoresu replied to the thread Discussion RDNA4 + CDNA3 Architectures Thread.More likely stacked or 2x density (16 -> 32 gbit) GDDR6.
-
Ssoresu replied to the thread Discussion RDNA4 + CDNA3 Architectures Thread.Waiting for Redstone.....
-
Ssoresu reacted to Vikv1918's post in the thread Discussion RDNA4 + CDNA3 Architectures Thread with Haha.
My kingdom for a FSR Redstone leak
-
Ssoresu replied to the thread Discussion RDNA4 + CDNA3 Architectures Thread.Doesn't necessarily mean Redstone has anything to do with it. It's a research paper so it may well just be using previous studies in...
-
Ssoresu reacted to SolidQ's post in the thread Discussion RDNA 5 / UDNA (CDNA Next) speculation with Like.
Hybrid CNN/Trans Interesting. Maybe Huang also gonna rework RTX 6xxx to Compete with RDNA5, but anyway need comfirmation
Facebook
Twitter