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.

Sign up for GitHub

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

BLAS::BLAS CMake target duplicate with CMake >= 3.18 #10

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

BLAS::BLAS CMake target duplicate with CMake >= 3.18 #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6fae49b
BLAS::BLAS CMake target duplicate with CMake >= 3.18
etiennemlb Mar 4, 2024
5341c69
Typos
etiennemlb Mar 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@ HPL.out output file name (if any)
8 memory alignment in double (> 0)
```

The `mpirun_rochpl` wraps a second script, `run_rochpl`, wherein some CPU core bindings are determined autmotically based on the node-local MPI grid. Users wishing to launch rocHPL via a workload manager such as slurm may directly use this run script. For example,
The `mpirun_rochpl` wraps a second script, `run_rochpl`, wherein some CPU core bindings are determined automatically based on the node-local MPI grid. Users wishing to launch rocHPL via a workload manager such as slurm may directly use this run script. For example,
```
srun -N 2 -n 16 run_rochpl -P 4 -Q 4 -N 128000 --NB 512
```
Expand All @@ -107,7 +107,7 @@ or
```
srun -N 2 -n 16 run_rochpl -P 4 -Q 4 -p 4 -q 2 -N 128000 --NB 512
```
This helps to control where/how much inter-node communication is occuring.
This helps to control where/how much inter-node communication is occurring.

## Performance evaluation
rocHPL is typically weak scaled so that the global matrix fills all available VRAM on all GPUs. The matrix size N is usually selected to be a multiple of the blocksize NB. Some sample runs on 32GB MI100 GPUs include:
Expand All @@ -123,7 +123,7 @@ See [the Wiki](../../wiki/Common-rocHPL-run-configurations) for some common run
## Testing rocHPL
At the end of each benchmark run, residual error checking is computed, and PASS or FAIL is printed to output.

The simplest suite of tests should run configurations from 1 to 4 GPUs to exercise different communcation code paths. For example the tests:
The simplest suite of tests should run configurations from 1 to 4 GPUs to exercise different communication code paths. For example the tests:
```
mpirun_rochpl -P 1 -Q 1 -N 45312
mpirun_rochpl -P 1 -Q 2 -N 45312
Expand Down
8 changes: 6 additions & 2 deletions cmake/Dependencies.cmake
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,8 +63,12 @@ else()
# If we still havent found a blas library, maybe cmake will?
find_package(BLAS REQUIRED)
endif()
add_library(BLAS::BLAS IMPORTED INTERFACE)
set_property(TARGET BLAS::BLAS PROPERTY INTERFACE_LINK_LIBRARIES "${BLAS_LP64_LIBRARIES};${BLAS_SEQ_LIBRARIES};${BLAS_LIBRARIES}")

if(NOT TARGET BLAS::BLAS)
# Prior to 3.18, CMake did not define this target.
add_library(BLAS::BLAS IMPORTED INTERFACE)
set_property(TARGET BLAS::BLAS PROPERTY INTERFACE_LINK_LIBRARIES "${BLAS_LP64_LIBRARIES};${BLAS_SEQ_LIBRARIES};${BLAS_LIBRARIES}")
endif()

# Find OpenMP package
find_package(OpenMP)
Expand Down