Saved in:
Bibliographic Details
Main Author: Bikshandi, Ganesh
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918293499019264
author Bikshandi, Ganesh
author_facet Bikshandi, Ganesh
contents Convolutional Neural Networks (CNNs) are central to modern AI, but their performance is often limited by hardware constraints. NVIDIA Tensor Cores, for instance, require input channels to be multiples of 8 and sometimes 512 for efficient execution. {\em oneDNN} framework for CPU imposes such a requirement for the blocked format. Traditional approaches address such alignment issue using zero-padding, which can be inefficient. In this work, we present a first-step, hardware-aware reformulation of CNN computations using rewrite rules, restructuring the underlying math to satisfy hardware alignment entirely {\bf post-training} without modifying network weights. While our current implementation focuses on a single transformation for Tensor Cores, this approach is generalizable, laying the foundation to explore additional transformations for CPU and accelerators. This study represents an initial step toward {\em semantic tuning}, a systematic, hardware-aware optimization strategy for efficient deployment of CNN models on specialized AI hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11608
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hardware-Aware Reformulation of Convolutions for Efficient Execution on Specialized AI Hardware: A Case Study on NVIDIA Tensor Cores
Bikshandi, Ganesh
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Convolutional Neural Networks (CNNs) are central to modern AI, but their performance is often limited by hardware constraints. NVIDIA Tensor Cores, for instance, require input channels to be multiples of 8 and sometimes 512 for efficient execution. {\em oneDNN} framework for CPU imposes such a requirement for the blocked format. Traditional approaches address such alignment issue using zero-padding, which can be inefficient. In this work, we present a first-step, hardware-aware reformulation of CNN computations using rewrite rules, restructuring the underlying math to satisfy hardware alignment entirely {\bf post-training} without modifying network weights. While our current implementation focuses on a single transformation for Tensor Cores, this approach is generalizable, laying the foundation to explore additional transformations for CPU and accelerators. This study represents an initial step toward {\em semantic tuning}, a systematic, hardware-aware optimization strategy for efficient deployment of CNN models on specialized AI hardware.
title Hardware-Aware Reformulation of Convolutions for Efficient Execution on Specialized AI Hardware: A Case Study on NVIDIA Tensor Cores
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
url https://arxiv.org/abs/2601.11608