37 citations · 52 across the 6 of their papers we have counts for
8 papers
AttnFuse: A Composable DSL for Compiling Attentions to Fused GPU Kernels
Varun Kumar Dasoju, Tian Zhao
Modern AI systems are built on the Transformer architecture, whose core operation, attention, accounts for the majority of computation and memory cost. Researchers continually prop…
Hybrid JIT-CUDA Graph Optimization for Low-Latency Large Language Model Inference
Divakar Kumar Yadav, Tian Zhao
Large Language Models (LLMs) have achieved strong performance across natural language and multimodal tasks, yet their practical deployment remains constrained by inference latency…
Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs
Divakar Kumar Yadav, Tian Zhao, Deepak Kumar
NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor…
Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture
Olivia Hsu, Alexander Rucker, Tian Zhao +2
We introduce Stardust, a compiler that compiles sparse tensor algebra to reconfigurable dataflow architectures (RDAs). Stardust introduces new user-provided data representation and…
Efficient Memory Partitioning in Software Defined Hardware
Matthew Feldman, Tian Zhao, Kunle Olukotun
As programmers turn to software-defined hardware (SDH) to maintain a high level of productivity while programming hardware to run complex algorithms, heavy-lifting must be done by…
Capstan: A Vector RDA for Sparsity
Alexander Rucker, Matthew Vilim, Tian Zhao +3
This paper proposes Capstan: a scalable, parallel-patterns-based, reconfigurable dataflow accelerator (RDA) for sparse and dense tensor applications. Instead of designing for one a…
Serving Recurrent Neural Networks Efficiently with a Spatial Accelerator
Tian Zhao, Yaqi Zhang, Kunle Olukotun
Recurrent Neural Network (RNN) applications form a major class of AI-powered, low-latency data center workloads. Most execution models for RNN acceleration break computation graphs…
Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
Cody Coleman, Daniel Kang, Deepak Narayanan +7
Researchers have proposed hardware, software, and algorithmic optimizations to improve the computational performance of deep learning. While some of these optimizations perform the…