no code implementations • 21 Sep 2023 • Alex Renda, Yi Ding, Michael Carbin
We first characterize the proportion of data to sample from each region of a program's input space (corresponding to different execution paths of the program) based on the complexity of learning a surrogate of the corresponding execution path.
1 code implementation • 14 Feb 2023 • Isha Chaudhary, Alex Renda, Charith Mendis, Gagandeep Singh
We generate and compare COMET's explanations for the popular neural cost model, Ithemal against those for an accurate CPU simulation-based cost model, uiCA.
no code implementations • 1 Dec 2022 • Zachary Ankner, Alex Renda, Gintare Karolina Dziugaite, Jonathan Frankle, Tian Jin
Practitioners prune neural networks for efficiency gains and generalization improvements, but few scrutinize the factors determining the prunability of a neural network the maximum fraction of weights that pruning can remove without compromising the model's test accuracy.
no code implementations • 11 Apr 2022 • Yi Ding, Alex Renda, Ahsan Pervaiz, Michael Carbin, Henry Hoffmann
Our evaluation shows that compared to the state-of-the-art SEML approach in computer systems optimization, Cello improves latency by 1. 19X for minimizing latency under a power constraint, and improves energy by 1. 18X for minimizing energy under a latency constraint.
1 code implementation • 12 Dec 2021 • Alex Renda, Yi Ding, Michael Carbin
With surrogate adaptation, programmers develop a surrogate of a program then retrain that surrogate on a different task.
no code implementations • 1 Jan 2021 • Alex Renda, Joshua Wolff Fromm
Binarized neural networks, networks with weights and activations constrained to lie in a 2-element set, allow for more time- and resource-efficient inference than standard floating-point networks.
2 code implementations • 8 Oct 2020 • Alex Renda, Yishen Chen, Charith Mendis, Michael Carbin
In this paper we present DiffTune, a system for learning the parameters of x86 basic block CPU simulators from coarse-grained end-to-end measurements.
no code implementations • 7 May 2020 • Riyadh Baghdadi, Abdelkader Nadir Debbagh, Kamel Abdous, Fatima Zohra Benhamida, Alex Renda, Jonathan Elliott Frankle, Michael Carbin, Saman Amarasinghe
In this paper, we demonstrate a compiler that can optimize sparse and recurrent neural networks, both of which are currently outside of the scope of existing neural network compilers (sparse neural networks here stand for networks that can be accelerated with sparse tensor algebra techniques).
2 code implementations • ICLR 2020 • Alex Renda, Jonathan Frankle, Michael Carbin
Learning rate rewinding (which we propose) trains the unpruned weights from their final values using the same learning rate schedule as weight rewinding.
3 code implementations • 21 Aug 2018 • Charith Mendis, Alex Renda, Saman Amarasinghe, Michael Carbin
Predicting the number of clock cycles a processor takes to execute a block of assembly instructions in steady state (the throughput) is important for both compiler designers and performance engineers.
no code implementations • 14 Sep 2017 • Alex Renda, Harrison Goldstein, Sarah Bird, Chris Quirk, Adrian Sampson
We propose to treat these challenges as language-design problems.