-
Dynex-Neuromorphic-Chip
Dynex has also developed a proprietary circuit design, the Dynex Neuromorphic Chip, that complements the Dynex ecosystem and turns any modern G into a neuromorphic computing chip by simulating its equations of motion. This implementation proofs the mathematical model.
-
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.
There is a cryptocurrency hype machine pumping a distributed computing based on GPUs. It is supposed to provide a platform performing certain real computing tasks at speeds unheard of. Supposedly they are emulating something known as a memristor on GPUs.
I'm sceptical because if it was such a leap, why would it only be hyped in that scene? I'm clueless on the technical details.
Could someone with more insight take a quick look if is real or not?
A few links:
- Whitepaper on their algorithm: https://anonymfile.com/ZRnZ1/dynexsolve-paper-v10c-3.pdf
- Reference implementation: https://github.com/dynexcoin/Dynex-Neuromorphic-Chip
Related posts
-
New exponent functions that make SiLU and SoftMax 2x faster, at full acc
-
An Empirical Evaluation of Columnar Storage Formats [pdf]
-
Nearly all Nintendo 64 games can now be recompiled into native PC ports
-
Introducing Ripple's Brazil Fund: Fostering XRP Ledger Innovation in Brazil
-
The power of interoperability: Why objects are inevitable (2013) [pdf]