PaperNotes
PaperNotes copied to clipboard
记录阅读各类paper的想法笔记(关注体系结构,机器学习系统,深度学习,计算机视觉)
[FireSim PAPER](https://sagark.org/assets/pubs/firesim-isca2018.pdf) https://github.com/firesim/firesim
[Integrating NVIDIA Deep Learning Accelerator (NVDLA) with RISC-V SoC on FireSim EMC2’19](https://www.emc2-workshop.com/assets/docs/hpca-19/paper3.pdf) > Integrating Verilog designs into FireSim
[PyMTLv3:Mamba: Closing the Performance Gap in Productive Hardware Development Frameworks (DAC)](http://www.csl.cornell.edu/~cbatten/pdfs/jiang-mamba-dac2018.pdf)
[Co-Designing Accelerators and SoC Interfaces using gem5-Aladdin(MICRO2016](https://ysshao.github.io/assets/papers/shao2016-micro.pdf)
[Scalable LLVM-Based Accelerator Modeling in gem5](https://ieeexplore.ieee.org/abstract/document/8621036) 发表在IEEE Computer Architecture Letters中,这在CECA中是A类, 没有纳入CCF中 这是篇关于 LLVM-BASEDDATA-PATHSIMULATION的论文
[GANAX: A UnifiedMIMD-SIMD Acceleration for Generative Adversarial Networks](https://arxiv.org/pdf/1806.01107.pdf)
[Cambricon: An Instruction Set Architecture for Neural Networks](https://pdfs.semanticscholar.org/09ba/89e7feb19e2a064236df08e1e01c6cf49309.pdf)
[ShiDianNao: Shifting vision processing closer to the sensor](https://lap.epfl.ch/wp-content/uploads/2018/05/DuJun15_ShiDianNaoShiftingVisionProcessingCloserToTheSensor_ISCA15.pdf) 这篇论文在创新方面比不上 Diannao , Cambricon等等, 但是相对于之前论文,**他在加速器设计细节上讲的非常详细!!**
Exploiting Locality in Graph Analytics through Hardware-Accelerated Traversal Scheduling(MICRO2018)
[Exploiting Locality in Graph Analytics through Hardware-Accelerated Traversal Scheduling](https://www.pdl.cmu.edu/PDL-FTP/associated/2018.hats.micro.pdf) 
[An Architectural Framework for Accelerating Dynamic Parallel Algorithms on Reconfigurable Hardware](https://cpb-us-w2.wpmucdn.com/sites.coecis.cornell.edu/dist/7/89/files/2016/08/parallelxl-micro2018-10bi0tp.pdf) 