Nice grey life

The Origins of GPU Computing

---

This article appears in the “Communications of the ACM” magazine as part of a series devoting to showcasing relevant examples of technologies where federal funding of academic research have resulted in widely impacting, clearly identifiable technological advances that have visibly improved –or, at least, changed– life far beyond the technological arena.

The road leading from the first parallel computing technologies built completely for research, through a phase that was preeminently directed at gaming, and back to leading current GPUs, that are basically massively parallel supercomputers used for LLM training and inference and other IA tasks, is far from trivial, and the authors make a good job outlining it in few pages. The article is written in a clearly divulgatory way, staying as clear of technical language as possible.

The authors present three main enabling technologies for current GPU technologies: Parallel computing, parallel graphics systems, and stream processing.

Coming from a technical formation myself, although clearly better grounded in the software side of Computer Engineering than on the electronics side, the most interesting “nugget of information” I take is that parallel computing was born due to the fact that transistor switching consumes very little energy, whereas communication along wires consumes much more — so the more simultaneous operations can be carried out on-chip at once, the less power will be dissipated as heat (and the less time that will be lost due to data stores and loads).

Graphics systems are a natural match for parallel systems, as rendering realistic images basically requires repeating the same blocks of instructions to a large array of items. Early GPU implementations were built on fixed-function graphics pipelines, but by the turn of the century, when nVidia spinned off the research labs at Stanford and started marketing their product, introducing along the way the Graphical Processing Unit term, product, they enabled it to implement the full OpenGL graphics pipeline on a single chip.

Stream processing is the arrangement of in-chip electronics so that they can better exploit producer-consumer locality between stages, in order to achieve greater arithmetic intensity (this is, a greater computation-to-bandwidth ratio), decreasing the total number of access to memory accesses.

The authors explain in broad terms the described technologies and how they fit together, and how the technology was transferred from the universities to the companies that became the most dynamic companies behind today’s top trending technologies.

I felt the article to be engaging and easy to read. As a technologist, I did miss more details — dates when specific advances were made, how some of the advances joined into further inventions… But I understand the aim of the “Federal Funding of Academic Research” series’ aim is more towards outsiders. And, as such, this work very well explains how trillion-dollar technologies are only the result of decades of funding research ideas.

---