Posts: 430
Threads: 18
Joined: Dec 2008
Reputation:
4
Location: Germany
okay I have a question: What's actually with the AVX instructions? couldn't it get used to speed up the VU's?
I know that GSdx uses it, but I don't notice any difference compared to SSE4.
Main Rig: i7-3770k @4.5ghz | 16GB DDR3 | Nvidia GTX 980 TI | Win 10 X64
Laptop: MSI GT62VR | i7-6700HQ | 16GB DDR4 | Nvidia GTX 1060 | Win 10 X64
Posts: 20.325
Threads: 405
Joined: Aug 2005
Reputation:
554
Location: England
At the moment the AVX instruction set is very limited, but yes the idea of being able to do multiplies and adds within the same instruction could provide some nice little speed ups on the vu's and the ee core (as there are MADD instructions on that too)
Posts: 3.559
Threads: 21
Joined: Jul 2010
Reputation:
61
Location: Australia
SSE+FMA is faster on BD than AVX+FMA according to limited developer tests.
Posts: 195
Threads: 0
Joined: Feb 2009
Reputation:
5
We'll see if we can get gains from it when someone can test it, okay? (Actually it looks like a bit of a pain on the emitter side. But there's not much point doing anything about it right now.)
Posts: 730
Threads: 29
Joined: Nov 2008
Reputation:
20
FMA instructions aren't really a miracle speedup, they'll just remove 1 instruction from certain VU opcodes.