PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives

1 code implementation • 2 Jun 2020 • Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Gagandeep Goyal, Ramakrishna Upadrasta, Bharat Kaul

However, given the constant emergence of new DNN architectures, creating hand optimized code is expensive, slow and is not scalable.

speech-recognition Speech Recognition +2

PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives

no code implementations • 6 Feb 2020 • Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Gagandeep Goyal, Ramakrishna Upadrasta, Bharat Kaul

In this paper, we develop a hybrid solution to the development of deep learning kernels that achieves the best of both worlds: the expert coded microkernels are utilized for the innermost loops of kernels and we use the advanced polyhedral technology to automatically tune the outer loops for performance.