-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
These chipsandcheese articles are fantastic, they really go into depth.
Last week I had occasion to dig deeply into the microarchitecture of the Apple M1 and M2 GPUs (which are very similar to the A series on mobile). I found the metal-benchmarks[1] repo to be very useful, and, relevant to this article, it contains a comparison to the RDNA generations. From that it appears that GPU microarchitectures are starting to converge, even if terminology is not. The standard configuration these days seems to be blocks of 128 threads (WGP's in AMD terminology, "cores" in Apple), organized into 4 SIMDs. Resources like workgroup memory (LDS in AMD lingo) are shared among each of these 128-blocks.
The linked repo also has links to other resources, including the incredible work being done by the Asahi Linux people to reverse engineer M1 and deliver working open source GPU drivers.
[1]: https://github.com/philipturner/metal-benchmarks