You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
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-Core:
SST-Elements:
–with-cuda=[DIR]
switch can be used during configure to specify the root directory for a CUDA installation–with-gpgpusim=[DIR]
switch can be used during configure to specify the root directory for a GPGPU-Sim installationSST-Macro:
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
The text was updated successfully, but these errors were encountered: