From the 1 of 8 linked papers with an AI index.
8 papers
At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference
Bowen Wang, Chi Zhang, Diyou Shen +3
The paper introduces Ventaglio, a hardware extension and ISA support for vector processors that efficiently executes sparse tensor contractions in Transformer inference, achieving…
Accelerating Precise End-to-End Simulation: Latency-Sensitive Many-core System Modeling
Yinrong Li, Zexin Fu, Yichao Zhang +5
Modern large language model workloads put increasing demands on parallel compute capability and on-chip memory capacity, while also stressing fine-grained data movement and synchro…
FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Large Attention-Based Model Inference on Tile-Based Accelerators
Chi Zhang, Luca Colagrande, Renzo Andri +1
Attention accounts for an increasingly dominant fraction of total computation during inference for mixture-of-experts (MoE) models, making efficient acceleration critical. Emerging…
TeraPool: A Physical Design Aware, 1024 RISC-V Cores Shared-L1-Memory Scaled-up Cluster Design with High Bandwidth Main Memory Link
Yichao Zhang, Marco Bertuletti, Chi Zhang +5
Shared L1-memory clusters of streamlined instruction processors (processing elements - PEs) are commonly used as building blocks in modern, massively parallel computing architectur…
Design in Tiles: Automating GEMM Deployment on Tile-Based Many-PE Accelerators
Aofeng Shen, Chi Zhang, Yakup Budanaz +4
Tile-based many-Processing Element (PE) accelerators can achieve competitive performance on General Matrix Multiplication (GEMM), but they are extremely hard to program, as their o…
VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking
Kichang Yang, Seonjun Kim, Minjae Kim +3
Edge deployment of large Vision-Language Models (VLMs) increasingly relies on flash-based weight offloading, where activation sparsification is used to reduce I/O overhead. However…