Skip to main content
NVIDIA Homepage
Research

Search form

  • Publications
  • Research Areas
  • People
  • About
  • Collaborations 
    • Academic
    • AI Research Residency
    • Government
    • Graduate Fellowships
  • Careers 
    • Internships
    • Research Scientists
People
 

Mark Stephenson

Mark Stephenson joined NVIDIA in February 2014.  He is primarily interested in program analysis, code generation, and architecture.  Before joining NVIDIA, Mark spent time at IBM Research, and the Massachusetts Institute of Technology, where he earned his PhD in 2006.

See Mark's external page for additional information.

Research Area(s): 
Computer Architecture
Computer Graphics
Programming Languages, Systems and Tools
Main Field of Interest: 
Computer Architecture
Google Scholar: 
https://scholar.google.com/citations

Publications

Zeroploit: Exploiting Zero Valued Operands in Interactive Gaming Applications
Estimating Silent Data Corruption Rates Using a Two-Level Model
Speculative Reconvergence for Improved SIMT Efficiency
NVBit: A Dynamic Binary Instrumentation Framework for NVIDIA GPUs
Exposing Memory Access Patterns to Improve Instruction and Memory Efficiency in GPUs
Software-Directed Techniques for Improved GPU Register File Utilization
SASSIFI: An Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation
Automatically Exploiting Implicit Pipeline Parallelism from Multiple Dependent Kernels for GPUs
Flexible Software Profiling of GPU Architectures
Page Placement Strategies for GPUs within Heterogeneous Memory Systems
Exploring the Design Space of SPMD Divergence Management on Data-Parallel Architectures
Copyright © 2021 NVIDIA Corporation |  Login |  Legal Information |  Privacy Policy