Almost all parameters are unknown
The Chinese company Loongson produces not only some of the most modern Chinese processors, but also GPUs. And its new development is designed to compete with Nvidia accelerators for AI, although they are far from the most productive and modern.
The accelerator (or its GPU) is called LG200. The characteristics of this solution, unfortunately, are unknown. The block diagram shows that the GPU consists of 16 small ALUs, four large ALUs, and one huge ALU or special purpose unit.
But the performance is known, albeit for the whole node: from 256 GFLOPS to 1 TFLOPS. Here, unfortunately, the details are again unknown, so it is unclear for which mode the performance is indicated, but even if it is FP64, the figure is quite modest, since modern monsters Nvidia and AMD offer 50-60 TFLOPS or more.
At the same time, Loongson’s solution is a GPGPU, that is, it supports general-purpose computing. Unfortunately, there are no details here yet.
Separately, we can recall that Loongson promised next year to release a video card that can compete with the Radeon RX 550, whose performance (FP32) is just over 1.1 TFLOPS. It is possible that the LG200 will be a direct relative of this adapter.