3 papers
cs.AR2026
MINISA: Minimal Instruction Set Architecture for Next-gen Reconfigurable Inference Accelerator
Jianming Tong, Devansh Jain, Yujie Li +2
Modern reconfigurable AI accelerators rely on rich mapping and data-layout flexibility to sustain high utilization across matrix multiplication, convolution, and emerging applicati…
cs.PL2025
TensorRight: Automated Verification of Tensor Graph Rewrites
Jai Arora, Sirui Lu, Devansh Jain +9
Tensor compilers, essential for generating efficient code for deep learning models across various applications, employ tensor graph rewrites as one of the key optimizations. These…
cs.PL2025
Automatically Generating ML Compiler Backends from Tensor Accelerator ISA Descriptions
Devansh Jain, Akash Pardeshi, Marco Frigo +5
Machine learning (ML) compilers play a key role in enabling high-performance implementations of ML workloads. These compilers use existing CPU and GPU backends to generate device-s…