“Article” said:On the other end of the spectrum are Intel’s ultra-high performance CPU designs which sacrifice power/area for very high performance. Those 10nm cells target frequencies greater than 5 GHz under 100% usage conditions.
GT3 is a 2-slice configuration, doubling GT2. So Ice Lake GT3 is up to 128 EUs or 1024 cores. I do not see it happening without HBM.
It has been abandon for GDDRx/HBMx by Micron.What about HMC? Is that completely MiA?
The success of HMC is apparent by the wide adoption across a variety of technology industries. This includes:
- futuristic applications in data science as exemplified by the Square Kilometer Array (SKA) program,
- unparalleled high-performance compute (HPC) solutions from companies such as Fujitsu(PRIMEHPC FX100),
- delivering 400G and beyond in high-performance network routers and data center switches, such as Juniper and other networking customers.
HMC enablement required developing a supportive ecosystem, where academia such as the University of Heidelberg created the openHMC IP, enabling FPGA-based designs to become a reality. Collaboration of Industry leaders co-developed multiple specifications of HMC through the open Hybrid Memory Cube Consortium (HMCC). The value of this teamwork and engagement should continue to harness the creativity to deliver new technology to solve future market requirements.
Now, as the volume projects that drove HMC success begin to reach maturity, at Micron we are now turning our attention to the needs of the next generation of high-performance compute and networking solutions. We continue to leverage our successful Graphics memory product line (GDDR) beyond the traditional graphics market and for extreme performance applications, Micron is investing in HBM (High-Bandwidth Memory) development programs which we recently made public.
That’s where the Micron SB-852 board comes in. The board, powered by 512GB of top-of-the-line DDR4 DRAM and 2GB of Hybrid Memory Cube, is being tested as a means to further machine-learning capabilities at one of the four main LHC experiments, CMS. Micron’s memory solutions that combine neural network capabilities will be tested in the data-acquisition systems of the experiment Scientists working at CERN are looking to deploy leading-edge technologies that can support their experiments’ computing and data processing requirements. Memory plays a vital role by processing vast amounts of data, helping researchers gain valuable insights from data generated by the experiments.
It's interesting that Intel is very specifically saying 15W for Icelake: https://www.anandtech.com/show/13775/ces-2019-intel-consumer-10nm-is-coming-with-ice-lake Not "7-15W", just 15W. I wonder if Lakefield will entirely take the low power end of the market, and we won't see a Y-series Icelake?
http://ranker.sisoftware.net/show_s...d1e0c6ae93a680f8c5f4d2b7d2efdff98ab786b6&l=enIt's interesting that Intel is very specifically saying 15W for Icelake: https://www.anandtech.com/show/13775/ces-2019-intel-consumer-10nm-is-coming-with-ice-lake Not "7-15W", just 15W. I wonder if Lakefield will entirely take the low power end of the market, and we won't see a Y-series Icelake?
It's interesting that Intel is very specifically saying 15W for Icelake: https://www.anandtech.com/show/13775/ces-2019-intel-consumer-10nm-is-coming-with-ice-lake Not "7-15W", just 15W. I wonder if Lakefield will entirely take the low power end of the market, and we won't see a Y-series Icelake?
at 1,9GHz that result is nice, at 2,3GHz it is just a minor IPC bump
I think the low single core scores indicate it was running at 1.4ghz.
Not sure where 1.9 came from?
Shouldn't this be in the video section ?Intel is disclosing their Gen11 Graphics Architecture at GDC 2019 (March 18th-22nd)
https://schedule.gdconf.com/session...ssor-graphics-gen11-presented-by-intel/864304