The battle for semiconductor supremacy has taken a fresh turn — there’s a new chip on the block, and it’s China’s first product of its kind.
Shanghai Tianshu Zhixin Semiconductor Co. Ltd., commonly known as Tianshu Zhixin, announced that its Big Island (BI) GPGPU has come to life, tech website tomsHARDWARE reported.
Unlike the Jingjia Micro JM5400 GPUs announced back in 2019, the new BI models are not specifically designed to compete with the gaming Nvidia RTX and AMD Radeon models, as they are more tailored towards AI and HPC applications, plus other general purpose uses for the education, medicine and security sectors.
The BI packs 24 billion transistors, and it’s based on a home-made GPU architecture, the report said, offering an impressive price/performance ratio.
The chip is built with the cutting-edge 7nm process node and 2.5D CoWoS (chip-on-wafer-on-substrate) packaging.
Tianshu Zhixin doesn’t explicitly reveal the foundry that’s responsible for producing the BI, the report said.
However, the description of the node coincides with one of TSMC’s advanced manufacturing processes.
Boosted by the trade wars with the United States started during the tumultuous Trump administration, China is now more than ever eager to prove that it too can produce powerful computer processing tech, NotebookCheck.net reported.
The rise of the Chinese tech was first led by the production of affordable yet powerful smartphones from Huawei, which “coincidentally” became the biggest target for bans.
Nevertheless, China is also striving to diminish the reliance on US tech, and has been trying to produce its own computer processors and GPUs for the past few years.
While the Chinese foundries are still playing catch-up on the node miniaturization side, they are certainly not too far behind industry leaders like TSMC.
As far as performance goes, the X86 CPUs produced in China are admittedly not yet impressive enough and certainly cannot compete with what Intel and AMD currently have, but we are seeing promising results with ARM-based processors and, more recently, with GPUs like the ones produced by Tianshu Zhixin.
According to tomsHARDWARE, Tianshu Zhixin commenced development on its BI chip in 2018.
The company finalized the tapeout for BI back in May 2020 and should have already underwent mass production if Tianshu Zhixin wants to meets its goal of commercializing the chip this year.
The BI solution reportedly provides twice the performance of existing mainstream products on the market, while also offering a very appealing performance-to-cost ratio, the report said.
Its main profile is, of course, machine learning and serving the HPC market, and to this end it also uses TSMC’s CoWoS technology, which puts the memory in an encapsulated graphics card, thus enabling very high memory bandwidth.
This is probably an HBM2 standard, but this has not been specifically explained, the report said.
BI supports a plethora of floating point formats, including FP32, FP16, BF16, INT32, INT16, and INT8, just to mention a few.
Tianshu Zhixin is keeping a tight lip on the BI’s performance, but the company has teased FP16 performance up to 147 TFLOPS (floating point operations per second, in trillions), the report said.
For comparison, the Nvidia A100 and AMD Instinct MI100 deliver FP16 performance figures up to 77.97 TFLOPS and 184.6 TFLOPS, respectively.
While most of the home-grown Chinese processors we have seen thus far under-delivered when it comes to direct performance comparisons with mainstream US models, if China keeps up like this on the performance side and also offers aggressive price schemes, we could be seeing some decent alternatives to the US models in just a few years.
Sources: tekdeeps.com, tomsHARDWARE, Craffic, NoteBookCheck.net