Learning to Optimize Tensor Programs · HackerPapers discussions

Learning to Optimize Tensor Programs — mentioned by lamchob

Mon, 15 Jun 2020 06:52:23 GMT

In the area of AutoTuning some machine learning methods are used. The goal is to optimize throughput or latency for compute intensive workloads. The machine learning model is trained with performance measurements on the hardware and then use it as proxy for real execution to try out different configurations. Notable works: AutoTVM - https://arxiv.org/abs/1805.08166 CHAMELEON - https://deepai.org/publication/chameleon-adaptive-code-optim... GPU-Warp Scheduling - https://deepai.org/publication/rlws-a-reinforcement-learning...

Paper and discussion history. A mention is not an endorsement.

Learning to Optimize Tensor Programs — mentioned by sanxiyn

Mon, 20 Jan 2020 11:17:24 GMT

You may enjoy the paper "Learning to Optimize Tensor Programs": https://arxiv.org/abs/1805.08166

Paper and discussion history. A mention is not an endorsement.

Learning to Optimize Tensor Programs — HN submission

Tue, 22 May 2018 18:05:32 GMT

Learning to Optimize Tensor Programs

106 points; 13 discussion replies on HN. Paper and source history. A submission is not an endorsement.