List of Open Source Software which can be built on Fugaku

Spack logo
Spack will be used to manage open source software packages on Fugaku. Fugaku users can easily use pre-installed packages and built packages based on Spack recipes. The following list shows the results of building/compiling packages for aarch64 according to the Spack recipes. Note that the results in this list do not guarantee that each package will work properly. On the other hand, Fujitsu will provide the following packages compiled with Fujitsu compiler on Fugaku as "external" packages, of which Spack can be aware.
  • OpenJDK 11
  • Ruby 2.6.5 or later
  • Python2 2.7.15
  • Python3 3.6.8
  • Numpy 1.14.3
  • SciPy 1.0.0
  • Eclipse IDE 2019-09 R Packages
Please contact us from email:

starpu

Package

starpu

Description

StarPU runtime system StarPU is a runtime support for scheduling
applications written as task graphs on heterogeneous multi-core
architectures. Tasks may define several implementations, for different
architectures (e.g one implementation for CPUs, and one implementation
for CUDA). StarPU takes care of scheduling and executing those tasks as
efficiently as possible over the entire machine. It also provides a
high-level data management library which enforces memory coherency over
the differents processing units of the machine, and over a cluster when
using distributed computing. Various data structures are supported
mainline (vectors, dense matrices, CSR/BCSR/COO sparse matrices, ...),
but application-specific data structures can also be supported.

Note


<= Back to list