Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SST 9.1.0 Has been released #9

Open
allevin opened this issue Nov 6, 2019 · 0 comments
Open

SST 9.1.0 Has been released #9

allevin opened this issue Nov 6, 2019 · 0 comments

Comments

@allevin
Copy link
Contributor

allevin commented Nov 6, 2019

SST 9.1.0 Released

SST v9.1.0 is now available and can be downloaded here

The SST v9.1.0 release follows the standard release process of having our point releases provide improved performance and stability.

A selection of the improvement highlights are:

General:

  • SST v9.1.0 includes a small number of fixes to elements and core to address compiler warnings and small improvements to simulation performance and robustness.
  • SST now contains support for modeling GPUs via the Balar component. This component only works with Cuda-based applications and requires the Ariel component to drive the host portion of the simulation. It is expected that this will undergo substantive changes before the next release.

SST-Core:

  • Update ELI and Subcomponent interfaces
  • Fixes known issues with automatic Python config generator
  • Fixes known issues with graph (dot) representation of configurations
  • Support for custom discrete event sorting in the SST core

SST-Elements:

  • Improved multi-thread support for IBM’s memory controller module (CramSim)
  • Ariel memory management support now isolated into sub-component interface for improved customizability
  • Reduced simulation time in large-scale SHMEM simulations through data structure optimization
  • Added the Balar GPU model, derived from GPGPU-Sim
  • The –with-cuda=[DIR] switch can be used during configure to specify the root directory for a CUDA installation
  • The –with-gpgpusim=[DIR] switch can be used during configure to specify the root directory for a GPGPU-Sim installation

SST-Macro:

  • Improved documentation
  • Bug fixes and stability improvements
  • Added new network models supporting QoS
  • Added new network statistics and performance counters
  • Compiler wrapper improvements for auto-skeletonization

Current release information can be found here

We look forward to hearing your successes with the latest release!


SST Research and Product Teams and all of our SST Collaborators!
Sandia National Laboratories, USA

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant