Slashdot Mirror
CERN Engineer Details AMD Zen Processor Confirming 32 Core Implementation, SMT (hothardware.com)
MojoKid writes: AMD is long overdue for a major architecture update, though one is coming later this year. Featuring the codename "Zen," AMD's already provided a few details, such as that it will be built using a 14nm FinFET process. In time, AMD will reveal all there is to know about Zen, but we now have a few additional details to share thanks to a computer engineer at CERN. CERN engineer Liviu Valsan recently gave a presentation on technology and market trends for the data center. At around 2 minutes into the discussion, he brought up AMD's Zen architecture with a slide that contained some previously undisclosed details. One of the more interesting revelations was that upcoming x86 processors based on Zen will feature up to 32 physical cores. To achieve a 32-core design, Valsan says AMD will use two 16-core CPUs on a single die with a next-generation interconnect. It has also been previously reported that Zen will offer up to a 40 percent improvement in IPC compared to its current processors as well as symmetric multithreading or SMT akin to Intel HyperThreading. In a 32-core implementation this would result in 64 logical threads of processing.
This. The A10-7800 in my rig is as power-efficient (at idle) as a similarly spec'd intel i5 box would be, has superior on-die graphics (which admittedly, I barely use) and came in about $300 less for mITX mainboard, proc & memory. I could have paid $1000 or more extra for a high-end intel i7 workstation, which would have given me maybe 30% higher performance (at best), that for the most part I'd never notice. AMD wins as far as I'm concerned, and they should make some inroads in the server space with ZEN.
That's guaranteed.
Surely you weren't saying sizes shrink by half every two years is guaranteed. Intel is already saying they won't be able to reach the process shrink goal in 2 years this time around. Around 5nm the shrink will turn into a research project just as challenging as the clock frequency issue. You can't pack carbon atoms closer than ~0.2nm nevermind features. A small protein molecule is 3nm in diameter. A significant drought of Moore's law is coming.
They could simply go back to the larger die areas we had only 10 years ago. It just means performance won't be "free" as time goes on. If you want a better chip you need a bigger chip and it'll cost more because you get less out of a wafer. There's plenty of fucking room on ATX boards and micro ATX boards and even mini ITX boards. And if you want to stick with tiny footprints like the Intel NUCs or the Google/Amazon/Intel "stick it in your HDMI port" shits, you can stack vertically or incorporate your RAM into the die.
I have a suspicion AMD will produce a part with HBM 2 incorporated into the APU die, resulting in a product that is literally a system on a chip, and finally realizes the shit they've been harping on about with regards to HSA. The GPU and the CPU have buckets of memory and all live together holding hands, sharing resources, talking to each other openly, helping each other build a deck or patch some drywall or whatever else the program asks them to do. Mayb we'll see something at E3 2017.
AMD has a technology they call dual graphics so their APUs could work in conjunction with a discrete GPU, similar to how you can Crossfire two discrete GPUs together already. It's probably more geared towards notebooks where the APU can get by driving the display and the GPU can sit idle. One review found that it could give substantial performance increases for some games, but it depends on driver support as well as where the performance bottleneck is at.
You might want to look up "AMD Zerotech" as its that way right now if you buy an AMD APU/CPU and pair it with an AMD GPU. With Zerotech if you use that particular setup it will turn off the discrete when not needed giving you the lower power usage of the APU and will then fire up the discrete when you have a task the APU cannot handle. Likewise if you have an AMD CPU it will turn down the GPU when not needed and simply use the GPUs baked in video encoder/decoder along with the frame buffer while turning the rest off.
I have an AMD FX-8320E paired with an R9 280 and I'm currently only pulling 8w from the CPU with 5 tabs and a video running and the GPU has idled down to practically nothing (my gauges only go down to 300/150 on GPU/memory speed so I cannot tell you how slow its actually running) with the GPU completely cool to the touch and the entire system completely silent.
I have to say I'm deliriously happy with the performance and power usage of my setup, last time I put it on my Kill-A-Watt it was pulling less than the Q6600 that I had been using at the shop as an office box, and thanks to Zerotech while the system stays nice and frosty and sips power when I'm just surfing and watching vids it can still scale up to 4Ghz on the CPU and 940/1250Mhz on the GPU/memory respectively in less than a second and if I want even more? I just flip on the overclock and can shoot up to 4.4Ghz without breaking a sweat. considering I paid less than $650 for this system with 16GB of RAM,a gaming board, 3TB of HDD, a BD burner, the R9 280 AND an SSD? The bang for the buck is just insane, no way you could build an Intel system with those specs, no way in hell.
ACs don't waste your time replying, your posts are never seen by me.