D6.4: Report on approaches to Petascaling
- 1. BSC
- 2. CINECA
- 3. EPCC
- 4. GRNET
Description
This deliverable reports on approaches to petascaling and evaluates promising petascaling techniques and optimizations. The approach taken to achieve this goal was to port and optimize several important and highly used applications to different HPC prototypes, so as to achieve as much scalability as possible in the given time of WP6. The best practices and lessons learned by scaling each application have been documented in this deliverable. The idea is that others can draw from these experiences when scaling their own applications.
The above applications are from the scientific community and were chosen in tasks 6.1 and 6.2 so as to cover a broad range of scientific areas, and are considered to be representative of the European HPC usage. Furthermore each application has been ported and optimized to several different architectures to get a better understanding of the suitability of the applications on different architectures and vice versa.
The work done in task 6.4 will together with task 6.5 be used in task 6.3 to create a benchmark set. Task 6.3 in return, will be used by task 5.4 for evaluating and comparing potential future petaflop/s systems.
Files
PP-D6.4.pdf
Files
(2.2 MB)
Name | Size | Download all |
---|---|---|
md5:4b993fd343a2ee659b1e89eb73451e64
|
2.2 MB | Preview Download |