• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Intel Iris Pro & L4 cache

Krypton

[H]F Junkie
Joined
Oct 11, 2004
Messages
10,972
Let's face it, Ryzen is a rather messy launch but things could change with optimized drivers, bios updates, micro code updates, maybe revised steppings, etc.. Think best case scenario if Ryzen could actually consistently come out ahead in all benchmarks for a like and kind Intel 8c16t processors.. Where does this leave Intel ?

I was thinking that even with current architecture, Intel could add one or possibly 2 128mb eDram chips to the package as they did for the Iris Pro 6200 variants like the 5775c. So for an 8c16t part, a user with a discrete graphics card would enjoy the benefits of the added 128mb l4 cache...which for the 5775c was a significant performance boost.

https://arstechnica.com/gadgets/201...obbing-us-of-the-performance-king-we-deserve/

I think all of us had our hopes up with the 5775c for future desktop enthusiast parts.. but it seems Intel stepped away from that maybe due to the added expense..


Just speculation here... but I think we all wished Intel would give us all an L4 equipped 8c/16t unlocked option in the market.
 
Last edited:
Ryzen is far behind and no threat at all in any segment. But in terms of EDRAM, most mobile SKUs got it now. And all mainstream CPUs got the EDRAM controller. So they can add it anytime they want.

However I guess the HEDT line is the problem here. Since the "EDRAM" in the HEDT line comes via cache and quad channel. So if the HEDT line didn't exist I think we would have a much better chance of getting EDRAM. Another option is when we move to more cores like with CFL and the memory bandwidth limitation becomes too great. We know SKL/KBL likes fast memory to perform to its potential.
 
Back
Top