Comment by tw1984 | Hacker News Reader

Comment by tw1984 | Hacker News Reader

you don't need a paper from a group of UK developers to understand its performance & potential. The processor is made by a Chinese startup, as China is fighting an all out semiconductor war with the US, there is literally unlimited public & private investments that could be poured into such a 64 cores processor if it is indeed remotely on par with the SOFA of x86. Any Chinese company holding such crown jewel would spend billions of $ on PR to get everyone in China to know its name to further milk more investments.

As someone who live in China and has been in the area for decades, the only reason why I have not heard about it until today is pretty obvious - it is a toy implementation no one cares about. There is actually a dedicated term in Chinese describing such junk - “落后产能”, which means backward production capacity.

They knew the expected performance, they knew it is going to be laughed by peers in the area, but they still did it for a good reason - to just fool certain low IQ investors in China to get a free ride of the whole RISC-V thing. Whoever behind this laughable release should really be ashamed - what is the next move? glue together maybe 1024 of those 8051 "cores" and claim it has built a supercomputer on a chip?

you evidently do need a paper from a group of uk developers to understand that it is not junk; as the abstract explains, it's 5–10 times as fast as other risc-v hardware, and even performs better on some workloads than "the x86 high performance CPUs under test", though it still lags behind them by a factor of 4–8 on average

this is enormous progress, and much more convincing than performance projections from simulations carried out by the chip's own designers

> as the abstract explains, it's 5–10 times as fast as other risc-v hardware

you mean those controllers designed to power your SSDs or the 10 cent RISC-V based microcontroller?

> though it still lags behind them by a factor of 4–8 on average

10x slower when compared to the second gen Epyc processor, which is already 2 generations behind.

that 10x gap is not for some specially picked areas, they are the day to day tasks.

no

Nothing laughable about it.

It's comparable on a core to core basis with the first AWS Graviton server chip that was deployed in 2019, only four years ago -- except this has 64 cores while the Graviton has 16.

It's also comparable to current x86 chips with 16 cores that cost about the same but use a lot more electricity. Each core is about 1/4 the speed of the x86, but you get four times more of them, which is fine for many server or HPC workloads.

> It's comparable on a core to core basis with the first AWS Graviton server chip that was deployed in 2019, only four years ago

you do released that this is not an apple to apple comparison, don't you?

First gen Graviton was created specifically for ec2's A1 instances where performance is not the goal. Amazon designed the chip with a well defined & targeted market in mind, they delivered just that. Tell me which half decent org is going to use this 64 cores junk?

You also realize that Graviton can afford to go from a relatively slow gen1 to the current gen4 in just 4-5 years largely due to the fact that they licensed the cores from ARM which has been building this whole ARM stuff for 30 years. Tell me what makes you to believe that some random & unknown newcomers can duplicate such progress without paying all those extremely expensive & time consuming efforts?

The concerned core is built by a group known for selling fake stuff online, historically and statistically, those people don't build the next gen tech.

> except this has 64 cores while the Graviton has 16.

gluing together more highly inefficient cores is not rocket science.

It is absolutely apples to apples. The SG2042 is the first RISC-V server chip, with much the same goals as the first Graviton.

It's not going to take 4-5 years for RISC-V server chips to match x86 (and Arm). They'll be there three years from now, by the end of 2026.

Those designs are already in the pipeline, made by many of the same people who previously designed the fastest chips at AMD, Intel, and Apple.

Reply on news.ycombinator.com