• Publications
  • Influence
What scientific applications can benefit from hardware transactional memory?
TLDR
Achieving efficient and correct synchronization of multiple threads is a difficult and error-prone task at small scale and, as we march towards extreme scale computing, will be even more challenging when the resulting application is supposed to utilize millions of cores efficiently. Expand
  • 30
  • 5
  • PDF
Towards Transactional Memory Support for GCC
TLDR
This paper describes the design of a transactional memory extension for GCC, and highlights research challenges and perspectives enabled by this design. Expand
  • 25
  • PDF
Efficient Synchronization Techniques in a Decentralized Memory Management System Enabling Shared Memory
TLDR
The rising integration level enables combining more logic on a single chip. Expand
  • 4
  • PDF
Thread Creation for Self-aware Parallel Systems
TLDR
The goal of this work is to establish a POSIX-like thread model in a distributed system, to enable a smooth upgrade path for legacy software. Expand
  • 4
Multi-parallel prefiltering on the convey HC-1 for supporting homology detection
TLDR
We use the Convey HC-1 with four FPGAs and high memory bandwidth of up to 76.8 GB/s to accelerate an application for searching homologous sequences. Expand
  • 2
Capturing Transactional Memory Application's Behavior - The Prerequisite for Performance Analysis
TLDR
This paper presents a methodology and an implementation to capture event logs representing the behavior of a transactional memory application and study the impact of the trace generation on the throughput of the STM system. Expand
  • 2
Evaluation of Two Formulations of the Conjugate Gradients Method with Transactional Memory
TLDR
This paper evaluates TM implementations of two algorithmic variations of the wide-spread conjugate gradients method (CG) regarding their performance on multi-core CPUs employing TM. Expand
  • 1
Compiler-Directed Performance Model Construction for Parallel Programs
TLDR
In this paper, we introduce our framework and demonstrate its applicability to benchmarks as well as real world numerical workloads. Expand
  • 1
Software Transactional Memory, OpenMP and Pthread Implementations of the Conjugate Gradients Method - A Preliminary Evaluation
TLDR
This paper shows the runtime and cache-efficiency of parallel implementations of the Conjugate Gradients Method based on the three paradigms Software Transactional Memory (STM), OpenMP and Pthreads. Expand
  • 7
Performance Optimization Strategies for Transactional Memory Applications
TLDR
Transactional Memory (TM) has been proposed as an architectural extension to enable lock-free data structures. Expand