MARCA: Mamba Accelerator with ReConfigurable Architecture
Jinhao Li, Shan Huang, Jiaming Xu, Jun Liu, Li Ding, Ningyi Xu, Guohao, Dai

TL;DR
MARCA introduces a reconfigurable accelerator architecture with novel reduction, nonlinear function, and buffer strategies, significantly enhancing speed and energy efficiency for deep learning workloads.
Contribution
The paper presents a novel reconfigurable architecture for the Mamba accelerator, including new reduction methods, nonlinear function units, and buffer management strategies.
Findings
Achieves up to 463.22× speedup over CPU.
Achieves up to 9761.42× energy efficiency over GPU.
Demonstrates effective reconfigurable nonlinear function execution.
Abstract
We propose a Mamba accelerator with reconfigurable architecture, MARCA.We propose three novel approaches in this paper. (1) Reduction alternative PE array architecture for both linear and element-wise operations. For linear operations, the reduction tree connected to PE arrays is enabled and executes the reduction operation. For element-wise operations, the reduction tree is disabled and the output bypasses. (2) Reusable nonlinear function unit based on the reconfigurable PE. We decompose the exponential function into element-wise operations and a shift operation by a fast biased exponential algorithm, and the activation function (SiLU) into a range detection and element-wise operations by a piecewise approximation algorithm. Thus, the reconfigurable PEs are reused to execute nonlinear functions with negligible accuracy loss.(3) Intra-operation and inter-operation buffer management…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParticle Detector Development and Performance · Particle accelerators and beam dynamics · Embedded Systems Design Techniques
MethodsMamba: Linear-Time Sequence Modeling with Selective State Spaces
