Minsoo Rhu

Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations

Feb 23, 2023
Yujeong Choi, John Kim, Minsoo Rhu

Figure 2 for Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations

Figure 3 for Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations

Figure 4 for Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations

GPU-based Private Information Retrieval for On-Device Machine Learning Inference

Jan 27, 2023
Maximilian Lam, Jeff Johnson, Wenjie Xiong, Kiwan Maeng, Udit Gupta, Minsoo Rhu, Hsien-Hsin S. Lee, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks, Edward Suh

Figure 2 for GPU-based Private Information Retrieval for On-Device Machine Learning Inference

Figure 3 for GPU-based Private Information Retrieval for On-Device Machine Learning Inference

Figure 4 for GPU-based Private Information Retrieval for On-Device Machine Learning Inference

Access Paper or Ask Questions

DiVa: An Accelerator for Differentially Private Machine Learning

Aug 26, 2022
Beomsik Park, Ranggi Hwang, Dongho Yoon, Yoonhyuk Choi, Minsoo Rhu

Figure 2 for DiVa: An Accelerator for Differentially Private Machine Learning

Figure 3 for DiVa: An Accelerator for Differentially Private Machine Learning

Figure 4 for DiVa: An Accelerator for Differentially Private Machine Learning

* Accepted for publication at the 55th IEEE/ACM International Symposium on Microarchitecture (MICRO-55), 2022

Access Paper or Ask Questions

SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures

May 10, 2022
Yunjae Lee, Jinha Chung, Minsoo Rhu

Figure 2 for SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures

Figure 3 for SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures

Figure 4 for SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures

* Accepted for publication at the 49th IEEE/ACM International Symposium on Computer Architecture (ISCA-49), 2022

Access Paper or Ask Questions

Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards

May 10, 2022
Youngeun Kwon, Minsoo Rhu

Figure 2 for Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards

Figure 3 for Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards

Figure 4 for Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards

* Accepted for publication at the 49th IEEE/ACM International Symposium on Computer Architecture (ISCA-49), 2022

Access Paper or Ask Questions

GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks

Mar 02, 2022
Minhoo Kang, Ranggi Hwang, Jiwon Lee, Dongyun Kam, Youngjoo Lee, Minsoo Rhu

Figure 2 for GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks

Figure 3 for GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks

Figure 4 for GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks

Access Paper or Ask Questions

PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers

Feb 27, 2022
Yunseong Kim, Yujeong Choi, Minsoo Rhu

Figure 2 for PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers

Figure 3 for PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers

Figure 4 for PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers

* This is an extended version of our work, which is accepted for publication at the 59th ACM/ESDA/IEEE Design Automation Conference (DAC), 2022

Access Paper or Ask Questions

LazyBatching: An SLA-aware Batching System for Cloud Machine Learning Inference

Oct 25, 2020
Yujeong Choi, Yunseong Kim, Minsoo Rhu

Figure 2 for LazyBatching: An SLA-aware Batching System for Cloud Machine Learning Inference

Figure 3 for LazyBatching: An SLA-aware Batching System for Cloud Machine Learning Inference

Figure 4 for LazyBatching: An SLA-aware Batching System for Cloud Machine Learning Inference

Access Paper or Ask Questions

Tensor Casting: Co-Designing Algorithm-Architecture for Personalized Recommendation Training

Oct 25, 2020
Youngeun Kwon, Yunjae Lee, Minsoo Rhu

Figure 2 for Tensor Casting: Co-Designing Algorithm-Architecture for Personalized Recommendation Training

Figure 3 for Tensor Casting: Co-Designing Algorithm-Architecture for Personalized Recommendation Training

Figure 4 for Tensor Casting: Co-Designing Algorithm-Architecture for Personalized Recommendation Training

Access Paper or Ask Questions

1

2

>>