SoylentNews is people
SoylentNews
Fudzilla have 'obtained' a slide showing details of a forthcoming APU from AMD based on their new "Zen" architecture.
The highest end compute HSA part has up to 16 Zen x86 cores and supports 32 threads, or two threads per core. This is something we saw on Intel architectures for a while, and it seems to be working just fine. This will be the first exciting processor from the house of AMD in the server / HSA market in years, and in case AMD delivers it on time it might be a big break for the company.
Each Zen core gets 512 KB of L2 cache and each cluster or four Zen cores is sharing 8MB L3 cache. In case we are talking about a 16-core, 32-thread next generation Zen based x86 processor, the total amount of L2 cache gets to a whopping 8MB, backed by 32MB of L3 cache.
This new APU also comes with the Greenland Graphics and Multimedia Engine that comes with HBM memory on the side. The specs we saw indicate that there can be up to 16GB of HBM memory with 512GB/s speed packed on the interposer. This is definitely a lot of memory for an APU GPU, and it also comes with 1/2 rate double precision compute, enhanced ECC and RAS and HSA support.
The new APU sports quad-channel DDR4 support, with up to 256GB per channel at speeds of up to 3.2GHz. No information yet on which processor socket this APU will use, but it's safe to assume the DDR4 support alone will render it incompatible with all AMD's current motherboards. Support is also included for secure boot and AMD's encryption co-processor.
(Score: 3, Interesting) by kaszz on Tuesday April 14 2015, @11:04PM
I did compare myself some personal computing CPUs for a processing task that is quite integer and memory access intensive as it trash the cache. The outcome was that on average Intel CPUs where approximately 33% faster than AMD CPUs. So even if the tests are rigged. Intel has an advantage, at least if cache and memory speed is critical. (I didn't say anything in regards to floating math, pipelines, cores, threads etc)
So which sources has proven reliable regarding information on CPU performance?
It's crap that Intel behaves like assholes. But perhaps ARM can chew a painful part of their market. It's on x86 that Intel really has a leverage on the market, and chip manufacturing.
(Score: 0) by Anonymous Coward on Wednesday April 15 2015, @11:24AM
Don't worry. His always spews the same nonsense everywhere. The benches aren't rigged at all, they just used ICC as a compiler just like the real app and the compiler favors their own chips. That also means the Intel chips perform better with these real-life apps.
And of course, he's never quoted anything even remotely intelligent. His only "proof" is a youtube video by a n00b that benchmarks CPUs on a heavily GPU-bound computer, which of course finds any old CPU doesn't make a damn difference (therefore the cheaper AMD chip is like soooo much better, right?). Benches done by competent people have different results strangely... But of course he won't cite those because it goes against his blind fanboyism. Intel very much has the upper hand in terms of speed. AMD hasn't been anywhere near competitive (in perf/$) or relevant since the Core 2 Duo era.