Saved in:
Bibliographic Details
Main Authors: Khizbullin, Dmitrii, de Andrade, Eduardo Rocha, Nguyen, Thanh Hau, Ferreira, Matheus Pedroza, Pugh, David R.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.16623
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • With the recent popularity of neural networks comes the need for efficient serving of inference workloads. A neural network inference workload can be represented as a computational graph with nodes as operators transforming multidimensional tensors. The tensors can be transposed and/or tiled in a combinatorially large number of ways, some configurations leading to accelerated inference. We propose TGraph, a neural graph architecture that allows screening for fast configurations of the target computational graph, thus representing an artificial intelligence (AI) tensor compiler in contrast to the traditional heuristics-based compilers. The proposed solution improves mean Kendall's $τ$ across layout collections of TpuGraphs from 29.8% of the reliable baseline to 67.4% of TGraph. We estimate the potential CO$_2$ emission reduction associated with our work to be equivalent to over 50% of the total household emissions in the areas hosting AI-oriented data centers.