News

The Liberty Computer Architecture Research Group exploits unique opportunities exposed by considering the interaction of compilers and architectures to increase performance, to improve reliability, to reduce cost, to lower power, and to shorten the time to market of microprocessor systems. This objective is accomplished by providing critical computer architecture and compiler research, expertise, and prototypes to the community.

Current Members (all members...)

Faculty

David I. August
[Publications]

Graduate Students

Ziyang Xu
[Publications]
Bhargav Reddy Godala
[Publications]
Susan Tan
[Publications]
Ishita Chaturvedi
[Publications]
Yebin Chon
[Publications]
Yucan Wu
[Publications]

Selected Publications (full list...)

  • NOELLE Offers Empowering LLVM Extensions (CGO 2022)
  • SCAF: A Speculation-Aware Collaborative Dependence Analysis Framework (PLDI 2020)
  • AsmDB: Understanding and Mitigating Front-End Stalls in Warehouse-Scale Computers (IEEE Micro’s "Top Picks" 2020, original work at ISCA 2019)
  • Perspective: A Sensible Approach to Speculative Automatic Parallelization (ASPLOS 2020)
  • Architectural Support for Containment-based Security (ASPLOS 2019)
  • Hardware Multithreaded Transactions (ASPLOS 2018)
  • Parcae: A System for Flexible Parallel Execution (PLDI 2012, related work at PLDI 2011)
  • Speculative Separation for Privatization and Reductions (PLDI 2012)
  • A Survey of the Practice of Computational Science (SC 2011)
  • Automatic CPU-GPU Communication Management and Optimization (PLDI 2011, related work at CGO 2012)
  • Commutative Set: A Language Extension for Implicit Parallel Programming (PLDI 2011)
  • Scalable Speculative Parallelization on Commodity Clusters (MICRO 2010, related work at CGO 2012)
  • DAFT: Decoupled Acyclic Fault Tolerance (PACT 2010, selected for IJPP 2012)
  • Speculative Parallelization Using Software Multi-threaded Transactions (ASPLOS 2010)
  • Revisiting the Sequential Programming Model for Multi-Core (IEEE Micro’s "Top Picks" 2008, original work at MICRO 2007)
  • Automatic Instruction-Level Software-Only Recovery Methods (IEEE Micro’s "Top Picks" 2007, original work at DSN 2006)
  • Recent News (more news...)