# Open SourceMolecular Dynamics

### Sidebar

#### For Developers

howto:libcusmm

This is an old revision of the document!

# Howto Optimize Cuda Kernels for Libcusmm

#### Step 1: Go to the directory ''$CP2K_ROOT/src/dbcsr/cuda/libcusmm'' #### Step 2: Run the script tune.py The script takes as arguments the blocksizes you want to add to libcusmm. For example if your system contains the blocks of size 5 and 8 type: $ ./tune.py 5 8
Found 23 parameter sets for 5x5x5
Found 31 parameter sets for 5x5x8
Found 107 parameter sets for 5x8x5
Found 171 parameter sets for 5x8x8
Found 75 parameter sets for 8x5x5
Found 107 parameter sets for 8x5x8
Found 248 parameter sets for 8x8x5
Found 424 parameter sets for 8x8x8

The script will create a directory for each combination of the blocksizes:

$ls -d tune_* tune_5x5x5 tune_5x5x8 tune_5x8x5 tune_5x8x8 tune_8x5x5 tune_8x5x8 tune_8x8x5 tune_8x8x8 Each directory contains a number of files: $ ls -1 tune_8x8x8/
Makefile
tune_8x8x8_exe0_main.cu
tune_8x8x8_exe0_part0.cu
tune_8x8x8_exe0_part1.cu
tune_8x8x8_exe0_part2.cu
tune_8x8x8_exe0_part3.cu
tune_8x8x8_exe0_part4.cu
tune_8x8x8.job

For each possible parameter set a launcher is generated. A launcher is a small snipped of C code, which launches the kernel using the cuda specifica «< »>-notation . It also instantiates the C++ template which contains the actual kernel code.

In order to parallelize the compilation and the benchmarking the launchers are distributed over several files. Currently, up to 10000 launchers are compiled into one executable. Each executable is linked together from several parts and a tune_*_main.o . Each parts contains up to 100 launchers and is compiled into a separate object file tune_*_part???.o.

#### Step 3: Submit Jobs

Each tune-directory contains a job file. Since, there might be many tune-directories the convince script submit.py can be used. It will go through all the tune_*-directories and check if it has already been submited or run. For this the script calls squeue in the background and it searches for slurm-*.out files.

When submit.py is called without arguments it will just list the jobs that could be submitted:

$./submit.py tune_5x5x5: Would submit, run with "doit!" tune_5x5x8: Would submit, run with "doit!" tune_5x8x5: Would submit, run with "doit!" tune_5x8x8: Would submit, run with "doit!" tune_8x5x5: Would submit, run with "doit!" tune_8x5x8: Would submit, run with "doit!" tune_8x8x5: Would submit, run with "doit!" tune_8x8x8: Would submit, run with "doit!" Number of jobs submitted: 8 Only when submit.py is called with doit! as its first argument it will actually submit job: $ ./submit.py doit!
tune_5x5x5: Submitting
Submitted batch job 277987
tune_5x5x8: Submitting
Submitted batch job 277988
tune_5x8x5: Submitting
Submitted batch job 277989
tune_5x8x8: Submitting
Submitted batch job 277990
tune_8x5x5: Submitting
Submitted batch job 277991
tune_8x5x8: Submitting
Submitted batch job 277992
tune_8x8x5: Submitting
Submitted batch job 277993
tune_8x8x8: Submitting
Submitted batch job 277994
Number of jobs submitted: 8

#### Step 4: Collect Results

Run collect.py to parse all log files and to determine the best kernel for each blocksize:

\$ ./collect.py
Kernel_dnt_tiny(m=8, n=8, k=8, split_thread=32, threads=128, grouping=16, minblocks=1) , # 90.7763 GFlops