8 citations · 13 across the 9 of their papers we have counts for
9 papers
SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference
Aditya Anirudh Jonnalagadda, Agasthi Haputhanthri, Pranav Dangi +5
The key-value (KV) cache has become the dominant consumer of memory in large language model (LLM) serving systems as context lengths, concurrency, and request lifetimes grow. High-…
A Data-Driven Dynamic Execution Orchestration Architecture
Zhenyu Bai, Pranav Dangi, Rohan Juneja +4
Domain-specific accelerators deliver exceptional performance on their target workloads through fabrication-time orchestrated datapaths. However, such specialized architectures ofte…
TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators
Wei Li, Zhenyu Bai, Heru Wang +6
Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such…
Building an Open CGRA Ecosystem for Agile Innovation
Rohan Juneja, Pranav Dangi, Thilini Kaushalya Bandara +4
Modern computing workloads, particularly in AI and edge applications, demand hardware-software co-design to meet aggressive performance and energy targets. Such co-design benefits…
Data-aware Dynamic Execution of Irregular Workloads on Heterogeneous Systems
Zhenyu Bai, Dan Wu, Pranav Dangi +3
Current approaches to scheduling workloads on heterogeneous systems with specialized accelerators often rely on manual partitioning, offloading tasks with specific compute patterns…
Nexus Machine: An Active Message Inspired Reconfigurable Architecture for Irregular Workloads
Rohan Juneja, Pranav Dangi, Thilini Kaushalya Bandara +2
Modern reconfigurable architectures are increasingly favored for resource-constrained edge devices as they balance high performance, energy efficiency, and programmability well. Ho…
Enhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning
Zhaoying Li, Pranav Dangi, Chenyang Yin +5
Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse…
Sustainable Hardware Specialization
Pranav Dangi, Thilini Kaushalya Bandara, Saeideh Sheikhpour +2
Hardware specialization is commonly viewed as a way to scale performance in the dark silicon era with modern-day SoCs featuring multiple tens of dedicated accelerators. By only pow…
SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs
Zhenyu Bai, Pranav Dangi, Huize Li +1
Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding w…