# COMET: Neural Cost Model Explanation Framework

arXiv: https://arxiv.org/abs/2302.06836 · HTML: https://mlsanity.com/paper/2302.06836/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 14 Feb 2023.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Abduction-Based Explanations for Machine Learning Models](https://mlsanity.com/paper/1811.10656/) (2018)
- [Logic-Based Explainability in Machine Learning](https://mlsanity.com/paper/2211.00541/) (2022)
- [Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks](https://mlsanity.com/paper/1808.07412/) (2018)
- [A Deep Learning Based Cost Model for Automatic Code Optimization](https://mlsanity.com/paper/2104.04955/) (2021)
- [Foundations of Symbolic Languages for Model Interpretability](https://mlsanity.com/paper/2110.02376/) (2021)
- [Counterfactual Explanations for Models of Code](https://mlsanity.com/paper/2111.05711/) (2021)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative](https://mlsanity.com/paper/1806.03000/) (2018)
- [GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation](https://mlsanity.com/paper/2210.03894/) (2022)
- [uops.info: Characterizing Latency, Throughput, and Port Usage of Instructions on Intel Microarchitectures](https://mlsanity.com/paper/1810.04610/) (2018)
- [Automated Instruction Stream Throughput Prediction for Intel and AMD Microarchitectures](https://mlsanity.com/paper/1809.00912/) (2018)
- [AnICA: Analyzing Inconsistencies in Microarchitectural Code Analyzers](https://mlsanity.com/paper/2209.05994/) (2022)

## Built on by (most cited first, 1 of 1)

- [Specification Generation for Neural Networks in Systems](https://mlsanity.com/paper/2412.03028/) (2024)

## Abstract (arXiv)

Cost models predict the cost of executing given assembly code basic blocks on a specific microarchitecture. Recently, neural cost models have been shown to be fairly accurate and easy to construct. They can replace heavily engineered analytical cost models used in mainstream compiler workflows. However, their black-box nature discourages their adoption. In this work, we develop the first framework, COMET, for generating faithful, generalizable, and intuitive explanations for neural cost models. 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. Our empirical findings show an inverse correlation between the prediction errors of Ithemal and uiCA and the granularity of basic block features in COMET's explanations for them, thus indicating potential reasons for the higher error of Ithemal with respect to uiCA.