-
Notifications
You must be signed in to change notification settings - Fork 31
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
Update Frontier installation #1208
Conversation
Are you using clang directly or hipcc? Looking at rocThrust, compiler.h and device_system.h, if |
@esseivaju This was happening through the The change is only to provide Thrust more information when going into |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
On the rocmThrust readme they recommend using hipcc
to compile cc files but I guess this work around works as long as we include device_runtime_api.h
before any Thrust headers.
OLCF recommends using their wacky Cray compiler wrappers... and those guys forward to llvm directly apparently |
* Fix thrust build with rocm 5.7.1 * Fix non-agnostic test name * Update frontier environment * Load miniforge for python * Ignore pr workflow for unrelated scripts * Fix loaded data and cmake flags * Use more cores * Use conda path * Unload darshan
* Fix thrust build with rocm 5.7.1 * Fix non-agnostic test name * Update frontier environment * Load miniforge for python * Ignore pr workflow for unrelated scripts * Fix loaded data and cmake flags * Use more cores * Use conda path * Unload darshan
This updates the build on Frontier to use the new
hep143
allocation and installation with ROCm 5.7.1.The only weird thing was that somehow thrust now assumes that it's building CUDA when we build from clang (and include it via
device_runtime_api.h
):