• Publications
  • Influence
Invyswell: A hybrid transactional memory for Haswell's restricted transactional memory
TLDR
We present Invyswell, a novel HyTM that exploits the benefits and manages the limitations of Haswell's RTM, which is the first commodity-based hardware transactional memory to become publicly available. Expand
  • 55
  • 7
  • PDF
An efficient software transactional memory using commit-time invalidation
TLDR
We present an efficient implementation of commit-time invalidation, a strategy where transactions resolve their conflicts with in-flight (uncommitted) transactions before they commit, allowing the contention manager to make decisions that increase transaction throughput. Expand
  • 57
  • 7
  • PDF
DracoSTM: a practical C++ approach to software transactional memory
Transactional memory (TM) is a recent parallel programming concept which reduces challenges found in parallel programming. TM offers numerous advantages over other synchronization mechanisms, yetExpand
  • 37
  • 3
  • PDF
CoreRacer: A practical memory race recorder for multicore x86 TSO processors
TLDR
We describe CoreRacer, a chunk-based memory race recorder architecture for multicore x86 TSO processors that efficiently log an ordering of the shared memory interleavings between threads. Expand
  • 26
  • 2
  • PDF
Using Elimination and Delegation to Implement a Scalable NUMA-Friendly Stack
TLDR
We propose the first NUMA-friendly stack design that improves data locality and minimizes interconnect contention. Expand
  • 27
  • 2
  • PDF
AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms
TLDR
We present the first-of-its-kind machine learning (ML) system, called AI Programmer, that can automatically generate full software programs requiring only minimal human guidance. Expand
  • 17
  • 2
  • PDF
QuickRec: prototyping an intel architecture extension for record and replay of multithreaded programs
TLDR
This paper presents QuickRec, the first multicore Intel Architecture (IA) prototype of RnR for multithreaded programs. Expand
  • 28
  • 1
  • PDF
Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection
TLDR
This short paper describes our ongoing research on Greenhouse - a zero-positive machine learning system for time-series anomaly detection. Expand
  • 17
  • 1
  • PDF
Toward Scalable Verification for Safety-Critical Deep Networks
TLDR
The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Expand
  • 19
  • 1
  • PDF
Precision and Recall for Time Series
TLDR
We present a new mathematical model to evaluate the accuracy of time series classification algorithms for range-based anomalies. Expand
  • 17
  • 1
  • PDF