paper-with-me

홈 › Papers

Automatic Generation of Fast and Accurate Performance Models for Deep Neural Network Accelerators

2024-09-13 · Konstantin Lübeck, Alexander Louis-Ferdinand Jung, Felix Wedlich, Mika Markus Müller, Federico Nicolás Peccia, Felix Thömmes, Jannik Steinmetz, Valentin Biermaier, Adrian Frischknecht, Paul Palomero Bernardo, Oliver Bringmann

Implementing Deep Neural Networks (DNNs) on resource-constrained edge devices is a challenging task that requires tailored hardware accelerator architectures and a clear understanding of their performance characteristics when executing the intended AI workload. To facilitate this, we present an automated generation approach for fast performance models to accurately estimate the latency of a DNN mapped onto systematically modeled and concisely described accelerator architectures. Using our accelerator architecture description method, we modeled representative DNN accelerators such as Gemmini, UltraTrail, Plasticine-derived, and a parameterizable systolic array. Together with DNN mappings for those modeled architectures, we perform a combined DNN/hardware dependency graph analysis, which enables us, in the best case, to evaluate only 154 loop kernel iterations to estimate the performance for 4.19 billion instructions achieving a significant speedup. We outperform regression and analytical models in terms of mean absolute percentage error (MAPE) compared to simulation results, while being several magnitudes faster than an RTL simulation.

📄 PDF Abstract BibTeX arXiv:2409.08595

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization

2023-03-29 · Stefan Abi-Karam, Cong Hao

There are plenty of graph neural network (GNN) accelerators being proposed. However, they highly rely on users' hardware expertise and are usually optimized for one specific GNN model, making them challenging for practic…

Code GenerationCPUGPUGraph Neural Network

DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architectures

2020-02-26 · Yang Zhao, Chaojian Li, Yue Wang, Pengfei Xu 외

The recent breakthroughs in deep neural networks (DNNs) have spurred a tremendously increased demand for DNN accelerators. However, designing DNN accelerators is non-trivial as it often takes months/years and requires cr…

A Compilation Flow for the Generation of CNN Inference Accelerators on FPGAs

2022-03-08 · Seung-Hun Chung, Tarek S. Abdelrahman

We present a compilation flow for the generation of CNN inference accelerators on FPGAs. The flow translates a frozen model into OpenCL kernels with the TVM compiler and uses the Intel OpenCL SDK to compile to an FPGA bi…

CPUHigh-Level Synthesis

Searching for Fast Model Families on Datacenter Accelerators

2021-02-10 · CVPR 2021 1 · Sheng Li, Mingxing Tan, Ruoming Pang, Andrew Li 외

Neural Architecture Search (NAS), together with model scaling, has shown remarkable progress in designing high accuracy and fast convolutional architecture families. However, as neither NAS nor model scaling considers su…

modelNeural Architecture Search

Photonic Accelerators for Image Segmentation in Autonomous Driving and Defect Detection

2023-09-28 · Lakshmi Nair, David Widemann, Brad Turcott, Nick Moore 외

Photonic computing promises faster and more energy-efficient deep neural network (DNN) inference than traditional digital hardware. Advances in photonic computing can have profound impacts on applications such as autonom…

Autonomous DrivingDefect DetectionImage SegmentationSegmentation+1