PUMPS 2011: Programming and Tuning Massively Parallel Systems Summer School. (Part 6: Algorithm Optimization Patterns Part I)

07/19/2011 10:45
Campus Nord, UPC
Wen-mei W. Hwu
Wen-mei W. Hwu


The PUMPS 2011 Summer School, “Programming and tUning Massively Parallel Systems (PUMPS),” was offered in July 18-22, 2011 at the Universitat Politecnica de Catalunya (UPC) campus. The event was co-sponsored by the Barcelona Supercomputing Center, UPC, the University of Illinois, HiPEAC NOE and NVIDIA, with distinguished faculty members Dr. David B. Kirk of NVIDIA and Prof. Wen-mei Hwu of the University of Illinois. PUMPS hosted 100 attendees from throughout the EU and beyond, from beginners to advanced programmers.
The content was based on CUDA, OpenCL, OpenMP, and StarSs programming languages and numerical methods including FFT, Graph, Tiling, Grid, Montecarlo, DTD, Sparse matrices, etc. The school featured lectures on cutting-edge new techniques and hands-on laboratory experience in developing applications for many-core processors with massively parallel computing resources such as the GPU accelerators, highlighting the new Fermi architecture. Applications case studies focused on Molecular Dynamics, MRI Reconstruction, RTM Stencil, and Dense Linear Systems.

More info on the summer school's website

Part 6:

This lecture covers some algorithm optimization patterns such as parallelism scalability transformation


Wen-mei W. Hwu is the Walter J. ("Jerry") Sanders III-Advanced Micro Devices Endowed Chair in Electrical and Computer Engineering in the Coordinated Science Laboratory of the University of Illinois at Urbana-Champaign. Dr. Hwu received his Ph.D. degree in Computer Science from the University of California, Berkeley, 1987

University of Illinois
Event Type: 
HiPEAC, BSC, Microsoft Research, NVIDIA
Contact Organizer: 
Nacho Navarro
E-Mail Contact:
pumps2011_lecture5.avi414.51 MB
pumps_2011_barcelona_lecture5_parallelism_scalability.pdf343.66 KB