Associate
APU + HBM bandwidth is gonna be pretty beast for those not wanting a dedicated GPU
If they're going to do it like that,
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
APU + HBM bandwidth is gonna be pretty beast for those not wanting a dedicated GPU
APU + HBM bandwidth is gonna be pretty beast for those not wanting a dedicated GPU
If they get the IPC even roughly up to modern levels, then that's good enough for me - What I really need for my development work is memory bandwidth and storage.
It seems Zen launches in October with an 8C/16T chip is supposed to be between Broadwell and Haswell IPC:
http://wccftech.com/amd-zen-cpu-8-core-summit-ridge-launching-october/
Not sure if I can believe the IPC claim though!! It would be awesome if true!!
It seems Zen launches in October with an 8C/16T chip is supposed to be between Broadwell and Haswell IPC:
http://wccftech.com/amd-zen-cpu-8-core-summit-ridge-launching-october/
Not sure if I can believe the IPC claim though!! It would be awesome if true!!
It seems Zen launches in October with an 8C/16T chip is supposed to be between Broadwell and Haswell IPC:
http://wccftech.com/amd-zen-cpu-8-core-summit-ridge-launching-october/
Not sure if I can believe the IPC claim though!! It would be awesome if true!!
It seems that unlike with Bulldozer, AMD has created separate dies for server and consumer parts. The server version of the die has twice the cores, L3 cache and additional I/O controllers per die. I haven´t been able to disassemble one yet, however judging from the package size it is a MCM part. 14nm LPP process.
The relative power consumption is roughly the same as on Intel 14nm parts with similar configuration, but the clocks are quite low :/
40501415
For a long time I actually like what I see. I´d say as long as the consumer Zen parts can reach high enough clocks (min. 3.5GHz), everything will be pretty good
Opterons for enthusiasts again?
Be nice to be able to actually buy a high-end version of a new AMD chip again...
Saw this on SA forums(after it was mentioned on AT forums) but OFC take with bucketloads of salt:
https://semiaccurate.com/forums/showpost.php?p=257682&postcount=2112
Apparently the poster who made the posts had some information on Carrizo which was correct according to that thread.
Sounds like Zen has a problem with clock rates.
But he is testing a commercial high core count CPU using an MCM. So it could be something like a 32 core chip.
Perhaps I'm reading too much into it but, he mentioned power consumption as level with Similar Intel parts but at lower clock rates and goes on to say the desktop parts should be good provided they can get reasonable clocks out of them.
It reads like he is sceptical of that.
Relative power consumption and another poster with a reasonable track record said around Broadwell levels of efficiency and I have seen that chap post sometimes,and they tend to be quite careful in what they say.
The other post he made was quite interesting - it means IPC might be a bit better than what we thing. I was estimating IB level at most.
However,hopefully we will see more leaks closer the date.
Struggling with clocks should come as no surprise, it's using a 1st-gen finfet node from a 3rd-rate foundry. It was never going to be a speed demon.