richardlethin
Joined 8 years ago
Karma
2
Submissions
3
Member since
Feb 15
Recent submissions
Comment · 8 years ago
Also, we're hiring:
https://www.reservoir.com/company/careers/
Comment · 8 years ago
The R-Stream Encyclopedia article talks about how to raise to the polyhedral model from SSA; this is no problem especially for the super regular computations in Tensor computations used in deep learning. If you get in touch with me I can also get you a copy of the 2008 paper about R-Stream that described it: https://www.reservoir.com/publication/final-report-r-stream-...
By raising from C you don't need to use or learn a new language. Or one can generate C from a succinct notation or framework, and polyhedral optimize from there. That is what was in the R-Stream-TF paper.
Comment · 8 years ago
The TC paper uses techniques that are in the R-Stream compiler. You can get more information about the R-Stream compiler at https://www.reservoir.com/research/publications/?cat=35 - the first paper there also validates the use of polyhedral compilation for deep learning last year. I particularly recommend the article about R-Stream in the Encyclopedia of Parallel Compilation, David Padua (ed). https://www.reservoir.com/publication/r-stream-compiler-2/