# Reference Paper
###### tags: `Accelerator`

#### 5-1. DLRM - Characterization
##### Architecture
1. 2020 HPCA, [The Architectural Implications of Facebook’s DNN-based Personalized Recommendation](https://arxiv.org/pdf/1906.03109.pdf)
2. 2019, [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://arxiv.org/pdf/1906.00091.pdf)
##### Training
1. 2022, [Building a Performance Model for Deep Learning Recommendation Model Training on GPUs](https://arxiv.org/pdf/2201.07821.pdf)
2. [<i class="fa fa-file" aria-hidden="true"></i>](https://hackmd.io/@accelerator/rki1-s54q) 2020, [Optimizing Deep Learning Recommender Systems’ Training On CPU Cluster Architectures](https://arxiv.org/pdf/2005.04680.pdf)
3. 2020, [Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems](https://arxiv.org/pdf/2003.09518.pdf)
##### Inference
1. 2020 IEEE, [Cross-Stack Workload Characterization of Deep Recommendation Systems](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9251259)
2. 2020 ISCA, [DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9138960)
3. 2018, [Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications](https://arxiv.org/pdf/1811.09886.pdf)

#### 5-2. DLRM - Existing Solutions
##### Near-Memory
1. 2021 ACM, [MERCI: Efficient Embedding Reduction on Commodity Hardware via Sub-query Memoization](https://dl.acm.org/doi/pdf/10.1145/3445814.3446717)
2. 2019 ISCA, [RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing](https://arxiv.org/pdf/1912.12953.pdf)
3. 2019, MICRO, [TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning](https://arxiv.org/pdf/1908.03072.pdf)
##### In-Storage
1. 2022 HPCA, [RM-SSD: In-Storage Computing for Large-Scale Recommendation Inference](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9773272)
2. 2021 ACM, [FlashEmbedding: Storing Embedding Tables in SSD for Large-Scale Recommender Systems](https://www.cs.cityu.edu.hk/~huwan2/files/apsys21_wan.pdf)
3. [<i class="fa fa-file" aria-hidden="true"></i>](https://hackmd.io/@accelerator/rJtEYQfl9) 2021 ACM, [RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference](https://arxiv.org/pdf/2102.00075.pdf)
4. 2020 ACM, [EMB-SSD: Reducing Tail Latency of DNN-based Recommender Systems using In-storage Processing](https://dl.acm.org/doi/pdf/10.1145/3409963.3410501)
5. 2018, [Bandana: Using Non-volatile Memory for Storing Deep Learning Models](https://arxiv.org/pdf/1811.05922.pdf)
##### Other
1. 2020 ACM, [Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations](https://arxiv.org/pdf/2005.05968.pdf)
2. 2020, [ZnG: Architecting GPU Multi-Processors with New Flash for Scalable Data Analysis](https://arxiv.org/pdf/2006.08975.pdf)

#### 5-3. In-storage Computing
1. 2020 IEEE, [Towards Scalable Analytics with Inference-Enabled Solid-State Drives](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8770061)
2. 2019 UCI, [Computational storage: an efficient and scalable platform for big data and HPC applications](https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0265-5.pdf)
3. 2019, [Cognitive SSD: A Deep Learning Engine for In-Storage Data Retrieval](https://www.usenix.org/system/files/atc19-liang.pdf)
4. 2020, [Accelerating Bandwidth-Bound Deep Learning Inference with Main-Memory Accelerators](https://arxiv.org/pdf/2012.00158.pdf)