A History Of Nvidia Stream Multiprocessor
fabiensanglard.net
fabiensanglard.net
2. It's a useful read for people writing GPU code, since even if you're not likely to target the older GPUs, understanding the balance of resources and the rationale for SM structure helps you conceptualize how today's hardware will "really" proceed to do the work you ask it to. Of course, "really" is in quotes since the diagrams are still a partial abstraction and there are a lot of hairy details.
A great example of long term strategic thinking, execution and commitment, that's quite rare in tech today.
People were already using GPUs to solve more general problems than real-time graphics. In particular, folks like Mike Houston or Aaron Lefohn (both now at NVidia) worked to formalize the sorts of computations that could efficiently be mapped onto the limited hardware that existed at the time.
NVidia's management did see that opportunity to expand to the HPC market and spent a good chunk of money for years to become a real contender in that space.
Something I loved about working there was laser focus on one product and finding ways to deliver value to their customers with that one product. It was a very different paradigm from working on SoC (system on a chip) devices like cell phones, where many teams competed to gain silicon area in the chip.