Paper-Conference

cuPTW: Leveraging Idle Compute Units for Massively Parallel GPU Page Table Walks featured image
GPU Archiecture

cuPTW: Leveraging Idle Compute Units for Massively Parallel GPU Page Table Walks

Virtual memory has become a cornerstone of modern GPUs, enabling unified address spaces and advanced memory management techniques. However, the performance of address translation …

avatar
Zihang Chen
•
Read more
VESTA: A Secure and Efficient FHE-based Three-Party Vectorized Evaluation System for Tree Aggregation Models featured image
Security

VESTA: A Secure and Efficient FHE-based Three-Party Vectorized Evaluation System for Tree Aggregation Models

Machine Learning as a Service (MLaaS) platforms simplify the development of machine learning applications across multiple parties. However, the model owner, compute server, and …

haosong-zhao
•
Read more