They can only achieve 3Ghz because that is the absolute highest clock speed you can set it to in the BIOS. I'm sure you can push it to go even faster if that limit was removed.
of course, we will see if Loongson open it up more in the future.
That explains how the 3A6000 can have the same performance as the Intel i3 processor despite having a lower clock rate. It is 50% more wide.
The problem is, if they already hit the limits in terms of width of the architecture, how are they going to increase performance further to compete against latest generation US processors? Make a processor with a longer pipeline so they can reach a higher clockspeed? Further increasing issue width requires a compiler good enough to extract ILP from the code in the first place.
If they want to design a new core again with same process first that explains why they don't expect it to happen until 2 years have passed. They want to design the processor with the new core in same process first and deliver that next year, then shrink that processor the year after that.
They are continually improving design of core and CPU. Case in point here about 3B6000, which is also going to be octa-core
2024 年龙芯将流片首款大小核协同芯片。龙芯 3A6000 的下一代将是 3B6000，四大四小八个核，内置自研 GPGPU。大核争取通过结构优化再提高性能 20% 以上（挺难的）。在 3B6000 的基础上，采用更先进工艺研制 3A7000 或 3B7000 下半年将会开展更先进工艺的技术准备工作
so they are adopting the 4 large and 4 small core design. Not only that, they are looking for 20% improvement in large core performance. I assume large core here is referring to LA664, so maybe 4xImproved LA664 + 4xLA364
Adding more core and improving existing cores require a lot of design work.
And then they are moving to designing 3A7000 and 3B7000 at end of 2024, presumably for unveiling in 2025. And that's when they get to 7nm
That probably means they improved the design somehow. Perhaps by using more modern layout tools or smaller area cache memory cells. Since the width has increased by 50% and they added SMT (2 threads per core) there should have been some increase in chip size. Since there isn't, they must have improved design or process in some way.
Yes, they previously mentioned improved core & CPU design. The first iteration also involved creating new ISA, so it probably had room for a lot of improvement
The Intel processor has more cores. Just replicating the cores with their associated cache will lead to a total processor cache increase.
All this takes work. I mean they are doing that with 3B6000. But again, they are already spending more on R&D than their entire revenue for the last quarter. I wish they get a little more support here.
It took them a lot to even get 16 core/32 virtual core 3C6000 designed. 3D6000 is just 2 chiplet using 龙链技术 (loong chain link tech)
3E6000 is just 4 chiplet connected with that
would be nice if they designed it to be 32 core right out of box, but nope.
As far as I'm concerned, there are real strategic value around for having Loongson.
It would be nice if they figured out a way to reduce the size of the transistors and memory cells similar to what TSMC did for AMD with Zen 4c. But this would require work by SMIC which I doubt they will do.
Huawei has SMIC totally booked and it also seems to be entirely committed to its own forked version of ARM
I wish hisilicon can get involved here
They do get some government support. They must, since Loongson is used for example in the Beidou satellites. I wouldn't be surprised if it was used in military and machine control systems as well.
That's still minimal. All the Chinese chipmakers get govt orders.
The Chinese commercial market hasn't responded because of cost/performance issues. But the Chinese government uses their products. With the increase in demand for Chinese designed and made computer hardware in recent years due to Chinese government orders, there has been a shortage of components to make government computers, which is why I think the Chinese government stopped the export of Loongson's chips. This wasn't targeted at Russia, the export ban was just to meet government demand. But I guess that Loongson and the Russian companies or government lobbied the Chinese government hard enough that they allowed exports to Russia to resume. This is a good thing, I think, since it might allow Loongson to gain traction in the export market. Something which thus far they have failed to do.
If Loongson also wants to reach higher market share worldwide I think they should license their ISA to 3rd parties. Otherwise I think a lot of non-US customers will eventually just move to RISC-V regardless of how good their chip implementations are. Even then long term success is hardly guaranteed.
I mean, they are doing that with domestic firms and also I would presume Russian firms in the future.
They are also trying to develop their own GPGPU. There is just a lot going on there. See here
目前正开发9A1000等GPU，9A1000的INT8性能可达32TOPS，支持多个GPU通过龙链互连，可降低延迟提升带宽，提高多片协同工作的性能。龙芯9A1000 GPU计划在2024年Q3流片，对标AMD RX550。
Do we really need a GPU with just 32TOPS and at same level as AMD RX550? Probably not, but work done on this allows them to say everything is domestic and to integrate a better GPU into the SoC they are developing. They are stubbornly independent
already finding the site in many cases is not trivial...