partnership with AWS is going to be huge for AMD
here is the Anandtech live blog (thanks to @cekim)
AMD has made significant changes to their CPU architecture which help deliver twice the throughput of their first generation Zen architecture. The major points include an entirely redesigned execution pipeline, major floating point advances with doubled the floating point to 256-bit and double bandwidth for load/store units. One of the key upgrades for Zen 2 is the doubling of the core density which means we are now looking at 2x the core count for each core complex (CCX) which will now be risen to 8 per CCX compared to 4 per CCX.
Improved Execution Pipeline
Doubled Floating Point (256-bit) and Load/Store (Doubled Bandwidth)
Doubled Core Density
Half the Energy Per Operation
Improved Branch Prediction
Better Instruction Pre-Fetching
Re-Optimized Instruction Cache
Larger Op Cache
Increased Dispatch / Retire Bandwidth
Maintaining High Throughput for All Modes
so ryzen 16 core is on the cards.
So, not pushing for AXV512? Interesting.
I’m of mixed minds on this given how niche that is.
Well, maybe. More importantly it’ll be cheaper to produce 8-core CPUs.
Still waiting for dat 8 core APU.
Lets hope they made the L3 cash more unified so the ful L3 is lag free in a single ccx.
That’s why it was a problem before so yeah, that shouldn’t be an issue on a chip with 8 or less cores.
Now its going on again
nah, apparently it was some guy who re-streamed the event. the event was 7 hours ago
My body is ready for 7nm.
Now someone needs to test that Vega for gaming.
TLDW? I’m at work… So short version?
Zen 2 7nm in 2019, Vega 7nm accelerator now.
Zen 4 in the works.
Machine learning etc.
No word on Navi.
Good… No hype this time. Just make it good and put it out there.
Anand (Cutress) is live blogging as we speak?? (well at least up to 1:24pm Eastern = aka: 4-5 minutes ago)
It’s finished now.
a lot of us are here in the U.S. but the livestream was streamed 7 hours ago.