Chinese GPU Dev Starts Global Sales of $245 RTX 3060 Ti Rival

Moore Threads
(Image credit: Moore Threads)
46

China-based Moore Treads on Friday began sales of its latest MTT S80 graphics card based on the Chunxiao architecture for client PCs. The add-in-board promises compute performance comparable to Nvidia's GeForce RTX 3060 Ti, but its performance in real games remains unknown. Meanwhile, it is available at JD.com, a store that delivers worldwide. However, there is a catch.

A GeForce RTX 3060 Ti-Like GPU from China

Anton Shilov
Contributing Writer

Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.

  • bit_user
    Interestingly, the MTT S80 is the world's first client graphics card with a PCIe 5.0 x16 interface
    Weird. And completely unnecessary. For 3060 Ti-level performance, PCIe 3.0 x16 should be perfectly fine.

    The only reason I can see for doing it is maybe as a test vehicle for debugging their PCIe controller that they plan to reuse in bigger or completely different products.

    Or, if we're cynical, they did it as a way to have some selling-point where they can claim leadership.
    Reply
  • bit_user
    Moore Threads designs GPUs for many applications (except HPC) and seems intent on selling its products outside of China.
    If they try to establish a real market presence in western countries, that means building a distribution channel and those distributors will be vulnerable to patent infringement claims by existing GPU players (Nvidia, AMD, Intel, Imagination, and ARM). That seems likely to limit their penetration of existing markets, where such IP claims get play.
    Reply
  • John Hogan
    Bring it on. As with the car industry and the coming rush of solid Chinese EVs, this sounds like good news. 3060ti performance should cost about $250 retail with a useful margin. I've owned nothing but Nvidia cards since my voodoo 2. But I won't miss that company if it disappears in the next few years. History is littered with companies that got to the top, took their customers for granted and then got eaten by people trying harder. Strange to say in 2022, but I'd rather give my automotive dollars to BYD and if this GPU mob is serious I'll give them a go too.
    Reply
  • artk2219
    As intel is currently finding out, and as AMD and Nvidia learned to varying degrees long ago, it comes down to the drivers. It can be the most powerful GPU ever created, and it wont matter one bit if it cant actually be used by any software because the drivers for it suck.
    Reply
  • daworstplaya
    artk2219 said:
    As intel is currently finding out, and as AMD and Nvidia learned to varying degrees long ago, it comes down to the drivers. It can be the most powerful GPU ever created, and it wont matter one bit if it cant actually be used by any software because the drivers for it suck.

    ^This! That's basically wasted silicon without good drivers. Wonder how much IP theft happened to create a GPU with those specs. Stream processors = AMD ?
    Reply
  • Chung Leong
    Protectionism works, even when the barriers involved are erected by your bone-headed adversary.
    Reply
  • bit_user
    artk2219 said:
    As intel is currently finding out, and as AMD and Nvidia learned to varying degrees long ago, it comes down to the drivers. It can be the most powerful GPU ever created, and it wont matter one bit if it cant actually be used by any software because the drivers for it suck.
    Yes, but I think Intel's problems are also deeper than mere drivers.

    IMO, Intel tried to do too much, in their first gen. They introduced special units for ray tracing and AI inferencing, then had to implement & optimize driver & runtime support for these + XeSS (their DLSS-equivalent). What they missed is that if the core rasterization performance and drivers for it aren't there, nobody cares much about the other stuff. Especially not ray tracing. You could make the case that XeSS can help them squeeze more performance out of their existing rasterization hardware, so I guess I'm really arguing they shouldn't have burned hardware and software resources trying to do ray tracing, also.
    Reply
  • bit_user
    John Hogan said:
    I've owned nothing but Nvidia cards since my voodoo 2. But I won't miss that company if it disappears in the next few years. History is littered with companies that got to the top, took their customers for granted and then got eaten by people trying harder.
    I don't see Nvidia as not trying. They tend to exploit their market leadership with very high margins, though. Also, I don't see the same creativity as AMD has shown, with their features like Infinity Cache. That complacency could be more of a recent thing, because just 2 generations earlier they introduced tensor cores and hardware ray tracing.

    As a company, Nvidia is focusing very hard on datacenter AI, with products like their DPUs, and edge AI. For them, gaming and visualization is still the main money-maker, but no longer central to their mission.

    John Hogan said:
    Strange to say in 2022, but I'd rather give my automotive dollars to BYD and if this GPU mob is serious I'll give them a go too.
    To the extent you're interested in cost-competitiveness, you'd do well to look into how heavily those products are subsidized. And consider that, if those brands ever achieve market dominance, they might cease to be so inexpensive.
    Reply
  • setx
    bit_user said:
    Weird. And completely unnecessary. For 3060 Ti-level performance, PCIe 3.0 x16 should be perfectly fine.
    For useless gaming it's indeed useless. But for compute I'd absolutely love faster interface.
    The cards are obviously more compute-oriented given lackluster list of supported games.
    Reply
  • blacknemesist
    These GPUs will help keep the mid-range in check, Intel could have done that if they weren't so greedy with the 1st gen card that had a lot of issues.
    Maybe in the future we get more GPUs like this to keep NVidia and AMD from going overboard with pricing and rise the demand, PC are probably at the lowest point ever because of how every component is extremely expensive or extremely poor.
    Reply