Nvidia is one of the major GPU suppliers (as well as AMD and others) as there are more compute needs in autonomous vehicles, robotics, etc. For future demand, will there be more increases in demand for CPU's (or decrease here in favor of GPU's), GPU's or some development other favorable processing unit?
Google had TPU's mentioned a few years back as one example. So curious to know what market segments would likely increase, which would require such processors to fill the increased demand for those units.
For dedicated neural network use cases like vehicles, robots, and datacenters, dedicated accelerator chips are going to be huge. Tesla's been shipping custom silicon for a while, I'd be surprised if Waymo cars didn't have a TPU in them, and there's like a dozen companies making AI accelerators but as far as I know, none of them are for sale yet.
In general computing, FPGAs will likely see a rise in popularity (latest mac pro offers an FPGA card as an option). In task specific computing, GPUs and ASICs will likely lead.
Tesla replaced their Nvidia GPUs over a year ago with a custom chip (I believe they hired a chip designer away from Apple to develop their own silicon).
Google had TPU's mentioned a few years back as one example. So curious to know what market segments would likely increase, which would require such processors to fill the increased demand for those units.