31–40 of 86 posts
I wonder what Jim Keller has to say about this, wasn't he hired to oversee the introduction of the 10nm manufacturing process?
It's so strange how this is all playing out almost exactly like the Athlon XP days except with lots of cores and clouds.
Does anyone believe there's another core duo type massive leap out there to even be had this time around though? AMD is going to slowly pull a bit ahead of intel, especially in bang for buck, but i don't see how they can catch back up. As it is, last time intel jumped ahead it was by repackaging and souping up an a mobile arch that in and of itself was based on the old pentium 3 arch. They can't really mine the parts…
Of course, Intel also appears to be forgetting that they have the ultimate advantage in getting to accelerators--they can dump the accelerator in the same socket, Nvidia can't--since they keep trying to compete by using expansion cards despite that being the worst limiting factor for offload.
It used to be that Intel was undisputed king of the silicon race. It's kind of shocking that they've fallen so far behind. TSMC is already doing 7nm mass production right now: https://www.digitimes.com/news/a20180622PD204.html (arguably, what they call "7nm" isn't quite that, but still...)
It used to be that Intel was undisputed king of the silicon race. It's kind of shocking that they've fallen so far behind. TSMC is already doing 7nm mass production right now: https://www.digitimes.com/news/a20180622PD204.html (arguably, what they call "7nm" isn't quite that, but still...)
Every single time an article comes up about this someone says this, and every single time someone refutes this saying that 7nm is a lie. Intel 10nm is supposed to be more dense than TSMC 7nm (if they ever get there).
Yes, intel's 10nm absolutely smashes Samsung, GF and TSMC's 10nm processes. Yes Intel's 10nm should be very competitive/comparable with Samsung/GF/TSMC's 7nm processes. But all of the Intel 10nm metrics are slightly worse than the 7nm processes its now competing with.
To cherrypick one metric as an example -
* TSMC 10nm sram bitcell size: 0.042 µm²
* Intel 10nm sram bitcell size: 0.031 µm²
* TSMC 7nm sram bitcell size: 0.027 µm²I wonder how cloud computing providers feel about this. On the one hand, competition between Intel and AMD for the cloud probably means cheaper chips for them. On the other hand, they were probably looking forward to the power savings from Intel's 10nm chips.
AMD be like "C'mon Intel, you're making this too easy."
Earlier quoted context omitted.
They both manufacture silicon gates.. what does it matter if the production infrastructure on top is different.
the way they measure size is different
https://seekingalpha.com/article/4190920-intel-intc-q2-2018-... what was actually said is this:
> we continue to make progress on 10-nanometer. Yields are improving consistent with the timeline we shared in April, and we expect systems on shelves for the 2019 holiday season.
This article guesses this to mean Cannon Lake.
In reality, it almost surely means Ice Lake.
Earlier quoted context omitted.
the way they measure size is different
Ah. What confused me was the word “process” which typically refers to the stack of things that take a high level description of a circuit and turn it into instructions for the machine to execute to make the wafer.