Tensor Comprehensions: einstein-notation like language transpiles to CUDA, and autotuned via evolutionary search to maximize perf.
Know nothing about GPU programming? Still write high-performance deep learning.
@PyTorch integration coming in <3 weeks.
https://research.fb.com/announcing-tensor-comprehensions/ …pic.twitter.com/ucbBMRZQPN
-
-
This Tweet is unavailable.
-
Yes, we released a new primitive StridedBatchedGEMM in cuBLAS 8.0 https://goo.gl/UBbpcQ But we need a higher level interface to automatically pick the best primitive for different index contractions
- Show replies
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.