FPGA

SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (🔥📣New Paper & Project🔥📣! )
Cite PDF Code
CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
Dense matrix multiply (MM) serves as one of the most heavily used kernels in deep learning applications. To cope with the high …
Cite PDF Code Slides Video
CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
MOCHA: Multinode Cost Optimization in Heterogeneous Clouds with Accelerators
FPGAs have been widely deployed in public clouds, e.g., Amazon Web Services (AWS) and Huawei Cloud. However, simply offloading …
Cite PDF Slides Video
MOCHA: Multinode Cost Optimization in Heterogeneous Clouds with Accelerators
ARAPrototyper: Enabling Rapid Prototyping and Evaluation for Accelerator-Rich Architecture
Compared to conventional general-purpose processors, accelerator-rich architectures (ARAs) can provide orders-of-magnitude performance …
Cite PDF Poster