Saved in:
Bibliographic Details
Main Authors: Huang, Zhibai, Chen, Chen, Yen, James, Shen, Yihan, Xie, Yongchen, Wei, Zhixiang, Xu, Kailiang, Wang, Yun, Liu, Fangxin, Song, Tao, Xia, Mingyuan, Qi, Zhengwei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.06376
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913021839802368
author Huang, Zhibai
Chen, Chen
Yen, James
Shen, Yihan
Xie, Yongchen
Wei, Zhixiang
Xu, Kailiang
Wang, Yun
Liu, Fangxin
Song, Tao
Xia, Mingyuan
Qi, Zhengwei
author_facet Huang, Zhibai
Chen, Chen
Yen, James
Shen, Yihan
Xie, Yongchen
Wei, Zhixiang
Xu, Kailiang
Wang, Yun
Liu, Fangxin
Song, Tao
Xia, Mingyuan
Qi, Zhengwei
contents Peripheral Component Interconnect Express (PCIe) is the de facto interconnect standard for high-speed peripherals and CPUs. The development of PCIe devices for emerging applications requires realistic Transaction Layer Packet (TLP) traces that accurately simulate device-CPU interactions. While generative AI offers a promising avenue for synthesizing complex TLP sequences, it is prone to a critical challenge inherent in all generation tasks: hallucination. Naively applying these models often produces traces that violate fundamental PCIe protocol rules, such as ordering and causality, rendering them unusable for device simulation. To resolve this, our work introduces a methodology to bridge the gap between generative AI and high-fidelity device simulation. This paper presents Phantom, a framework that systematically addresses AI-generated hallucinations in TLP synthesis. Phantom achieves this by coupling a generative backbone with a novel post-processing filter that enforces PCIe-specific constraints, effectively eliminating invalid TLP sequences. We validate Phantom's effectiveness by synthesizing TLP traces for an actual PCIe network interface card. Experimental results show that Phantom produces practical, large-scale TLP traces, significantly outperforming existing models, with improvements of up to 1000$\times$ in task-specific metrics and up to 2.19$\times$ in Fréchet Inception Distance (FID) compared to backbone-only methods. The prototype implementation has been made open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06376
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Phantom of PCIe: Constraining Generative Artificial Intelligences for Practical Peripherals Trace Synthesizing
Huang, Zhibai
Chen, Chen
Yen, James
Shen, Yihan
Xie, Yongchen
Wei, Zhixiang
Xu, Kailiang
Wang, Yun
Liu, Fangxin
Song, Tao
Xia, Mingyuan
Qi, Zhengwei
Machine Learning
Artificial Intelligence
Hardware Architecture
Peripheral Component Interconnect Express (PCIe) is the de facto interconnect standard for high-speed peripherals and CPUs. The development of PCIe devices for emerging applications requires realistic Transaction Layer Packet (TLP) traces that accurately simulate device-CPU interactions. While generative AI offers a promising avenue for synthesizing complex TLP sequences, it is prone to a critical challenge inherent in all generation tasks: hallucination. Naively applying these models often produces traces that violate fundamental PCIe protocol rules, such as ordering and causality, rendering them unusable for device simulation. To resolve this, our work introduces a methodology to bridge the gap between generative AI and high-fidelity device simulation. This paper presents Phantom, a framework that systematically addresses AI-generated hallucinations in TLP synthesis. Phantom achieves this by coupling a generative backbone with a novel post-processing filter that enforces PCIe-specific constraints, effectively eliminating invalid TLP sequences. We validate Phantom's effectiveness by synthesizing TLP traces for an actual PCIe network interface card. Experimental results show that Phantom produces practical, large-scale TLP traces, significantly outperforming existing models, with improvements of up to 1000$\times$ in task-specific metrics and up to 2.19$\times$ in Fréchet Inception Distance (FID) compared to backbone-only methods. The prototype implementation has been made open-source.
title The Phantom of PCIe: Constraining Generative Artificial Intelligences for Practical Peripherals Trace Synthesizing
topic Machine Learning
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2411.06376