Iran
  • Colony of NPUs: Scaling the Efficiency of Neural Accelerators
    Babak Zamirai, Daya S Khudia, Mehrzad Samadi, and Scott Mahlke
    The 2015 Workshop on Approximate Computing Across the Stack (WAX 2015)

  • Approximating with Input Level Granularity
    Parker Hill, Michael Laurenzano, Mehrzad Samadi, Scott Mahlke, Jason Mars, and Lingjia Tang
    The 2015 Workshop on Approximate Computing Across the Stack (WAX 2015)

  • Rumba: An Online Quality Management System for Approximate Computing
    Daya S Khudia, Babak Zamirai, Mehrzad Samadi and Scott Mahlke
    Forty second International Symposium on Computer Architecture (ISCA 2015)

  • Scaling Performance Via Self-Tuning Approximation for Graphics Engines
    Mehrzad Samadi, Janghaeng Lee, D. Anoushe Jamshidi, Amir Hormati, and Scott Mahlke
    ACM Transactions Journal on Computer Systems (TOCS 2014)
    Paper: pdf
  • D2MA: Accelerating Coarse-Grained Data Transfer for GPUs
    D. Anoushe Jamshidi, Mehrzad Samadi, and Scott Mahlke
    Twenty third International Conference on Parallel Architectures and Compilation Techniques (PACT 2014)
    Paper: pdf Slides: pptx
  • VAST: The Illusion of a Large Memory Space for GPUs
    Janghaeng Lee, Mehrzad Samadi, and Scott Mahlke
    Twenty third International Conference on Parallel Architectures and Compilation Techniques (PACT 2014)
    Paper: pdf Slides: pptx
  • Paraprox: Pattern-Based Approximation for Data Parallel Applications
    Mehrzad Samadi, D. Anoushe Jamshidi, Janghaeng Lee, and Scott Mahlke
    Nineteenth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2014)
    Paper: pdf Slides: pptx
  • Leveraging GPUs Using Cooperative Loop Speculation
    Mehrzad Samadi, Amir Hormati, Janghaeng Lee, and Scott Mahlke
    ACM Transactions Journal on Architecture and Code Optimization (TACO 2014)
    Paper: pdf
  • SAGE: Self-Tuning Approximation on Graphics Engines
    Mehrzad Samadi, Janghaeng Lee, D. Anoushe Jamshidi, Amir Hormati, and Scott Mahlke
    Forty sixth International Symposium on Microarchitecture (MICRO 2013)
    Best Paper Award
    Paper: pdf Slides: pptx
  • Transparent CPU-GPU Collaboration for Data-Parallel Kernels on Heterogeneous Systems
    Janghaeng Lee, Mehrzad Samadi, Yongjun Park, and Scott Mahlke
    Twenty second International Conference on Parallel Architectures and Compilation Techniques (PACT 2013)
    Paper: pdf Slides: pptx
  • APOGEE: Adaptive Prefetching on GPU for Energy Efficiency
    Ankit Sethia, Ganesh Dasika, Mehrzad Samadi, and Scott Mahlke
    Twenty second International Conference on Parallel Architectures and Compilation Techniques (PACT 2013)
    Paper: pdf Slides: pptx
  • Adaptive Input-aware Compilation for Graphics Engines
    Mehrzad Samadi, Amir Hormati, Mojtaba Mehrara, Janghaeng Lee, and Scott Mahlke
    Thirty third conference on Programming Language Design and Implementation (PLDI 2012)
    Paper: pdf Slides: pptx
  • Paragon: Collaborative Speculative Loop Execution on GPU and CPU
    Mehrzad Samadi, Amir Hormati, Janghaeng Lee, and Scott Mahlke
    Fifth Workshop on General-Purpose Computation on Graphics Processing Units (GPGPU 2012)
    Paper: pdf Slides: pptx
  • Sponge: Portable Stream Programming on Graphics Engines
    Amir Hormati, Mehrzad Samadi, Mark Woh, Trevor Mudge, and Scott Mahlke
    Sixteenth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2011)
    Paper: pdf Slides: pptx
  • Dynamic Parallelization of JavaScript Applications Using an Ultra-lightweight Speculation Mechanism
    Mojtaba Mehrara, Po-Chun Hsu, Mehrzad Samadi, and Scott Mahlke
    Seventeenth IEEE International Symposium on High Performance Computer Architecture (HPCA 2011)
    Paper: pdf Slides: pptx
  • Dynamic Voltage and Frequency Scheduling for Embedded Processors under Power and Deadline Constraints
    Mostafa Salehi, Mehrzad Samadi, Mehrdad Najibi, Ali Afzali-Kusha, Massoud Pedram, and Sied Mehdi Fakhraie
    IEEE Transaction on VLSI Systems, 2010
    Paper: pdf
  • Dynamic Power Management with Fuzzy Decision Support System
    Mehrzad Samadi and Ali Afzali-Kusha
    IEICE Electronics Express Journal, Vol 5, No. 19, pp.789-795,2008
  • Power Management with Fuzzy Decision Support System
    Mehrzad Samadi and Ali Afzali-Kusha
    Seventh International conference on ASIC (ASICON 2007)
  • Power Management by Brain Emotional Learning Algorithm
    Mehrzad Samadi, Ali Afzali-Kusha, and Caro Lucas
    Seventh International conference on ASIC (ASICON 2007)
My photo

Mehrzad Samadi

mehrzads at umich dot edu


University of Michigan

Dept. of EECS

Advanced computer Arch. Lab.

2260 Hayward Street Ann Arbor, MI, 48109
Office: 4861 CSE
Phone: 734-239-4249