Paper Reading AI Learner

DRAGON : A suite of Hardware Simulation and Optimization tools for Modern Workloads

2022-04-13 23:57:12
Khushal Sethi
arXiv_AI
   
Abstract

We introduce DRAGON, a suite of hardware simulation and optimization tools that enable hardware designers to simulate hardware designs, and to optimize hardware designs to efficiently execute certain workloads. The DRAGON toolchain provides the following tools: Hardware Model Generator (DGen), Hardware Simulator (DSim) and Hardware Optimizer (DOpt). Our work uses a simulation based method of running algorithms (represented as data-flow graphs) and architectures/technology (represented in a description language) to create the hardware model and then maps the algorithms on the hardware. We are able to generate architectures and circuits that are 5x better than previously published works [6, 7] and provide technology targets for improving to 100x and 1000x better computing systems. In conclusion, a new open-source, fast and explainable toolchain for end-to-end exploration and optimization of technologies and architectures is created.

Abstract (translated)

URL

https://arxiv.org/abs/2204.06676

PDF

https://arxiv.org/pdf/2204.06676.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot