Merge branch 'master' into 2779_split_element_order

.github/workflows/compilation.yml

@@ -51,13 +51,13 @@ on:
   push
 
 env:
-  CUDA_VERSION: 12.6.2
+  CUDA_VERSION: 12.6.3
   GFORTRAN_VERSION: 14.2.0
   HDF5_VERSION: 1.14.5
   NETCDF_C_VERSION: 4.9.2
   NETCDF_FORTRAN_VERSION: 4.6.1
-  NVFORTRAN_VERSION: 24.9
-  OPENMPI_VERSION: 5.0.5
+  NVFORTRAN_VERSION: 24.11
+  OPENMPI_VERSION: 5.0.6
   PYTHON_VERSION: 3.13.0
 
 jobs:

.github/workflows/nemo_tests.yml

@@ -202,20 +202,19 @@ jobs:
         export COMPILER_ARCH=linux_intel
         export ADD_KEYS="IEEE_IS_NAN=ieee_is_nan key_nosignedzero"
         export DEL_KEYS="key_iomput"
-        export MODEL_DIR=/archive/ssiso/ecmwf_eORCA1_GO8/
-        export NAMELISTS_DIR=${NEMO_DIR}/testscripts_V40/output/openmp_outer_V40_eORCA1_GO8_Z75_20170906_cray_dp_1x1/
+        export INPUT_DIR=/archive/NEMO_INPUTS/NEMOv4/ECMWF/eORCA1_GO8/
         export MPI_INC_DIR=${I_MPI_ROOT}/include
         cd $PSYCLONE_NEMO_DIR
         make -j 4 openmp_cpu
         make -j 4 compile-openmp_cpu
         export OMP_NUM_THREADS=4
         make run-openmp_cpu |& tee output.txt
-        # Check the output is as expected for the first 6 digits
+        # Check the output is as expected (TODO #2787: improve numerical reproducibility)
         tail -n 1 output.txt | grep -q " it :      10" || (echo "Error: 'it :      10' not found!" & false)
-        tail -n 1 output.txt | grep -q "|ssh|_max:  0.199714" || (echo "Error: '|ssh|_max:  0.199714' not found!" & false)
-        tail -n 1 output.txt | grep -q "|U|_max:  0.148409" || (echo "Error: '|U|_max:  0.148409' not found!" & false)
-        tail -n 1 output.txt | grep -q "S_min:  0.108530" || (echo "Error: 'S_min:  0.108530' not found!" & false)
-        tail -n 1 output.txt | grep -q "S_max:  0.404045" || (echo "Error: 'S_max:  0.404045' not found!" & false)
+        tail -n 1 output.txt | grep -q "|ssh|_max:  0.199" || (echo "Error: '|ssh|_max:  0.199' not found!" & false)
+        tail -n 1 output.txt | grep -q "|U|_max:  0.148" || (echo "Error: '|U|_max:  0.148' not found!" & false)
+        tail -n 1 output.txt | grep -q "S_min:  0.10" || (echo "Error: 'S_min:  0.10' not found!" & false)
+        tail -n 1 output.txt | grep -q "S_max:  0.404" || (echo "Error: 'S_max:  0.404' not found!" & false)
         export VAR_TIME=$(grep -A 1 "Elapsed Time" output.txt | head -n 2 | tail -n 1 | awk '{print $1}')
         echo  $GITHUB_REF_NAME $GITHUB_SHA $VAR_TIME >> ${HOME}/store_results/performance_history_openmp_cpu
         ${HOME}/mongosh-2.1.1-linux-x64/bin/mongosh \

.github/workflows/nemo_v5_tests.yml

@@ -80,26 +80,25 @@ jobs:
         export PSYCLONE_NEMO_DIR=${GITHUB_WORKSPACE}/examples/nemo/scripts
         export PSYCLONE_HOME=${PWD}/.runner_venv
         export NEMO_DIR=${HOME}/NEMOv5
+        export TEST_DIR=BENCH_PASSTHROUGH_GCC
 
         # Set up FCM: PATHs are loaded from SPACK, we only need to set the FCFLAGS
         cd $NEMO_DIR
         cp $PSYCLONE_NEMO_DIR/KGOs/arch-linux_spack.fcm arch/arch-linux_spack.fcm
         export FCFLAGS="-fdefault-real-8 -O2 -fcray-pointer -ffree-line-length-none -g"
 
         # Clean up and compile
-        ./makenemo -r BENCH -m linux_spack -n BENCH_PASSTHROUGH_GCC clean -y
-        ./makenemo -r BENCH -m linux_spack -n BENCH_PASSTHROUGH_GCC -p ${PSYCLONE_NEMO_DIR}/passthrough.py \
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} clean -y
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} -p ${PSYCLONE_NEMO_DIR}/passthrough.py \
             add_key "key_nosignedzero" -j 4 -v 1
 
         # Run test
-        cd $NEMO_DIR/tests/BENCH_PASSTHROUGH_GCC/EXP00
+        cd $NEMO_DIR/tests/${TEST_DIR}/EXP00
         cp $PSYCLONE_NEMO_DIR/KGOs/namelist_cfg_bench_small namelist_cfg
         mpirun -np 4 ./nemo
         tail run.stat
         # This was produced with gfortran, so we can do an exact diff
-        diff $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.small.100steps run.stat
-        export VAR_TIME=$(awk '/ step /{print $3}' timing.output | head -n 1 | sed -e 's/s//')
-        echo "Time-stepping duration = " $VAR_TIME
+        diff $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.gfortran.small.100steps run.stat
 
     - name: NEMO 5.0 nvidia passthrough
       run: |
@@ -110,24 +109,25 @@ jobs:
         export PSYCLONE_NEMO_DIR=${GITHUB_WORKSPACE}/examples/nemo/scripts
         export PSYCLONE_HOME=${PWD}/.runner_venv
         export NEMO_DIR=${HOME}/NEMOv5
+        export TEST_DIR=BENCH_PASSTHROUGH_NVHPC
         
         # Set up FCM: PATHs are loaded from SPACK, we only need to set the FCFLAGS
         cd $NEMO_DIR
         cp $PSYCLONE_NEMO_DIR/KGOs/arch-linux_spack.fcm arch/arch-linux_spack.fcm
-        export FCFLAGS="-i4 -Mr8 -O2 -Minline -Mcray=pointer -Mpre -g"
+        export FCFLAGS="-i4 -Mr8 -O1 -Kieee -nofma -Mnovect"
         
         # Clean up and compile
         # Without key_mpi_off it fails to compile (even without psyclone)
-        ./makenemo -r BENCH -m linux_spack -n BENCH_PASSTHROUGH_NVHPC clean -y
-        ./makenemo -r BENCH -m linux_spack -n BENCH_PASSTHROUGH_NVHPC -p ${PSYCLONE_NEMO_DIR}/passthrough.py \
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} clean -y
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} -p ${PSYCLONE_NEMO_DIR}/passthrough.py \
           add_key "key_mpi_off key_nosignedzero" -j 4 -v 1
 
         # Run test
-        cd $NEMO_DIR/tests/BENCH_PASSTHROUGH_NVHPC/EXP00
+        cd $NEMO_DIR/tests/${TEST_DIR}/EXP00
         cp $PSYCLONE_NEMO_DIR/KGOs/namelist_cfg_bench_small namelist_cfg
         ./nemo
-        python $PSYCLONE_NEMO_DIR/compare_ouput.py $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.small.100steps run.stat
         tail run.stat
+        diff $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.nvhpc.small.100steps run.stat
         export VAR_TIME=$(awk '/ step /{print $3}' timing.output | head -n 1 | sed -e 's/s//')
         echo "Time-stepping duration = " $VAR_TIME
 
@@ -140,25 +140,24 @@ jobs:
         export PSYCLONE_NEMO_DIR=${GITHUB_WORKSPACE}/examples/nemo/scripts
         export PSYCLONE_HOME=${PWD}/.runner_venv
         export NEMO_DIR=${HOME}/NEMOv5
+        export TEST_DIR=BENCH_PASSTHROUGH_ONEAPI
         
         # Set up FCM: PATHs are loaded from SPACK, we only need to set the FCFLAGS
         cd $NEMO_DIR
         cp $PSYCLONE_NEMO_DIR/KGOs/arch-linux_spack.fcm arch/arch-linux_spack.fcm
         export FCFLAGS="-i4 -r8 -O2 -fp-model precise -fno-alias -g"
         
         # Clean up and compile
-        ./makenemo -r BENCH -m linux_spack -n BENCH_PASSTHROUGH_ONEAPI clean -y
-        ./makenemo -r BENCH -m linux_spack -n BENCH_PASSTHROUGH_ONEAPI -p ${PSYCLONE_NEMO_DIR}/passthrough.py \
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} clean -y
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} -p ${PSYCLONE_NEMO_DIR}/passthrough.py \
           add_key "key_nosignedzero" -j 4 -v 1
 
         # Run test
-        cd $NEMO_DIR/tests/BENCH_PASSTHROUGH_ONEAPI/EXP00
+        cd $NEMO_DIR/tests/${TEST_DIR}/EXP00
         cp $PSYCLONE_NEMO_DIR/KGOs/namelist_cfg_bench_small namelist_cfg
         mpirun -np 6 ./nemo
         tail run.stat
-        python $PSYCLONE_NEMO_DIR/compare_ouput.py $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.small.100steps run.stat
-        export VAR_TIME=$(awk '/ step /{print $3}' timing.output | head -n 1 | sed -e 's/s//')
-        echo "Time-stepping duration = " $VAR_TIME
+        diff $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.oneapi.small.100steps run.stat
         
     - name: NEMO 5.0 gfortran OpenMP for CPUs
       run: |
@@ -169,25 +168,34 @@ jobs:
         export PSYCLONE_NEMO_DIR=${GITHUB_WORKSPACE}/examples/nemo/scripts
         export PSYCLONE_HOME=${PWD}/.runner_venv
         export NEMO_DIR=${HOME}/NEMOv5
+        export TEST_DIR=BENCH_OMP_THREADING_GCC
         
         # Set up FCM: PATHs are loaded from SPACK, we only need to set the FCFLAGS
         cd $NEMO_DIR
         cp $PSYCLONE_NEMO_DIR/KGOs/arch-linux_spack.fcm arch/arch-linux_spack.fcm
         export FCFLAGS="-fdefault-real-8 -O2 -fcray-pointer -ffree-line-length-none -g -fopenmp"
         
         # Clean up and compile
-        ./makenemo -r BENCH -m linux_spack -n BENCH_OMP_THREADING_GCC clean -y
-        ./makenemo -r BENCH -m linux_spack -n BENCH_OMP_THREADING_GCC -p ${PSYCLONE_NEMO_DIR}/omp_cpu_trans.py \
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} clean -y
+        export NEMOV5=1  # Enables specific NEMOV5 optimisations in the PSyclone transformation script
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} -p ${PSYCLONE_NEMO_DIR}/omp_cpu_trans.py \
           add_key "key_nosignedzero" -j 4 -v 1
 
         # Run test
-        cd $NEMO_DIR/tests/BENCH_OMP_THREADING_GCC/EXP00
+        cd $NEMO_DIR/tests/${TEST_DIR}/EXP00
         cp $PSYCLONE_NEMO_DIR/KGOs/namelist_cfg_bench_small namelist_cfg
         OMP_NUM_THREADS=4 mpirun -np 1 ./nemo
         tail run.stat
-        python $PSYCLONE_NEMO_DIR/compare_ouput.py $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.small.100steps run.stat
-        export VAR_TIME=$(awk '/ step /{print $3}' timing.output | head -n 1 | sed -e 's/s//')
-        echo "Time-stepping duration = " $VAR_TIME
+        diff $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.gfortran.small.100steps run.stat
+        export TIME_sec=$(grep "local proces" timing.output | head -n 1 | awk '{print $4}' | tr -d s)
+        ${HOME}/mongosh-2.1.1-linux-x64/bin/mongosh \
+          "mongodb+srv://cluster0.x8ncpxi.mongodb.net/PerformanceMonitoring" \
+          --quiet --apiVersion 1 --username ${{ secrets.MONGODB_USERNAME }} \
+          --password ${{ secrets.MONGODB_PASSWORD }} \
+          --eval 'db.GitHub_CI.insertOne({branch_name: "'"$GITHUB_REF_NAME"'", commit: "'"$GITHUB_SHA"'",
+          github_job: "'"$GITHUB_RUN_ID"'"-"'"$GITHUB_RUN_ATTEMPT"'",
+          ci_test: "NEMOv5 OpenMP for CPU", nemo_version: "NEMOv5", system: "GlaDos",
+          compiler:"gfortran-14" , date: new Date(), elapsed_time: '"${TIME_sec}"'})'
         
     - name: NEMO 5.0 nvidia OpenMP for GPUs (managed memory)
       run: |
@@ -198,24 +206,32 @@ jobs:
         export PSYCLONE_NEMO_DIR=${GITHUB_WORKSPACE}/examples/nemo/scripts
         export PSYCLONE_HOME=${PWD}/.runner_venv
         export NEMO_DIR=${HOME}/NEMOv5
+        export TEST_DIR=BENCH_OMP_OFFLOAD_NVHPC
         
         # Set up FCM: PATHs are loaded from SPACK, we only need to set the FCFLAGS
         # We compile at -O1 to permit comparison of the results.
         cd $NEMO_DIR
         cp $PSYCLONE_NEMO_DIR/KGOs/arch-linux_spack.fcm arch/arch-linux_spack.fcm
-        export FCFLAGS="-i4 -Mr8 -O3 -Minline -Mcray=pointer -Mpre -g -mp=gpu -gpu=managed"
+        export FCFLAGS="-i4 -Mr8 -O1 -Kieee -nofma -Mnovect -g -mp=gpu -gpu=managed"
         
         # Clean up and compile
         # Without key_mpi_off it fails to compile (even without psyclone)
-        ./makenemo -r BENCH -m linux_spack -n BENCH_OMP_OFFLOAD_NVHPC clean -y
-        ./makenemo -r BENCH -m linux_spack -n BENCH_OMP_OFFLOAD_NVHPC -p ${PSYCLONE_NEMO_DIR}/omp_gpu_trans.py \
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} clean -y
+        ./makenemo -r BENCH -m linux_spack -n ${TEST_DIR} -p ${PSYCLONE_NEMO_DIR}/omp_gpu_trans.py \
           add_key "key_mpi_off key_nosignedzero" -j 4 -v 1
 
-        # Run test
-        cd $NEMO_DIR/tests/BENCH_OMP_OFFLOAD_NVHPC/EXP00
-        cp $PSYCLONE_NEMO_DIR/KGOs/namelist_cfg_bench_small namelist_cfg
-        ./nemo
-        tail run.stat
-        python $PSYCLONE_NEMO_DIR/compare_ouput.py $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.small.100steps run.stat
-        export VAR_TIME=$(awk '/ step /{print $3}' timing.output | head -n 1 | sed -e 's/s//')
-        echo "Time-stepping duration = " $VAR_TIME
+        # Run test (disabled because it is currently too slow)
+        # cd $NEMO_DIR/tests/${TEST_DIR}/EXP00
+        # cp $PSYCLONE_NEMO_DIR/KGOs/namelist_cfg_bench_small namelist_cfg
+        # ./nemo
+        # tail run.stat
+        # diff $PSYCLONE_NEMO_DIR/KGOs/run.stat.bench.nvhpc.small.100steps run.stat
+        # export TIME_sec=$(grep "local proces" timing.output | head -n 1 | awk '{print $4}' | tr -d s)
+        # ${HOME}/mongosh-2.1.1-linux-x64/bin/mongosh \
+        #   "mongodb+srv://cluster0.x8ncpxi.mongodb.net/PerformanceMonitoring" \
+        #   --quiet --apiVersion 1 --username ${{ secrets.MONGODB_USERNAME }} \
+        #   --password ${{ secrets.MONGODB_PASSWORD }} \
+        #   --eval 'db.GitHub_CI.insertOne({branch_name: "'"$GITHUB_REF_NAME"'", commit: "'"$GITHUB_SHA"'",
+        #   github_job: "'"$GITHUB_RUN_ID"'"-"'"$GITHUB_RUN_ATTEMPT"'",
+        #   ci_test: "NEMOv5 OpenMP for GPU", nemo_version: "NEMOv5", system: "GlaDos",
+        #   compiler:"nvhpc-24.5" , date: new Date(), elapsed_time: '"${TIME_sec}"'})'

.gitignore

@@ -2,11 +2,13 @@
 *~
 *.a
 *.o
+*.psycache
 gnu_opt_report.txt
 *.mod
 *.MOD
 .cache
 .coverage
+*.swp
 doc/*/_build
 doc/*/*/_build
 doc/reference_guide/source/autogenerated/
@@ -25,3 +27,5 @@ src/*.egg-info
 .idea
 .rtx.toml
 .venv
+cov.xml
+.coverage.*

README.md

@@ -2,7 +2,7 @@
   <img width="460" src="doc/logo/psyclone_v1.0.png">
 </p>
 
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11190458.svg)](https://doi.org/10.5281/zenodo.11190458)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11190457.svg)](https://doi.org/10.5281/zenodo.11190457)
 ![Build Status](https://github.com/stfc/PSyclone/workflows/PSyclone%20tests%20and%20examples/badge.svg)
 [![codecov](https://codecov.io/gh/stfc/PSyclone/branch/master/graph/badge.svg)](https://codecov.io/gh/stfc/PSyclone)
 
@@ -50,6 +50,10 @@ cloning this repository and using:
 
     $ pip install .
 
+or in developer (editable) mode using
+
+    $ pip install -e .
+
 For more information about the installation process see
 [this section of the User Guide](https://psyclone.readthedocs.io/en/latest/system_specific_setup.html).
 

changelog

@@ -1,3 +1,20 @@
+	1) PR #2827. Update Zenodo with release 3.0.0 and update link in
+	README.md.
+
+	2) PR #2759 for #2758. Fixes failure seen in compilation tests if
+	a previous build of infrastructure existed.
+
+	3) PR #2807 for #2806. Adds a new 'RESOLVE_IMPORTS' global variable
+	to transformation scripts which allows the user to instruct the
+	frontend to chase down some (or all) module imports when constructing
+	the PSyIR for existing code.
+
+	4) PR #2821 for #1247. Adds support for parsing comments from the fparser2
+	AST tree. There are two new FortranReader arguments to select the behaviour
+	for comments and directives (by default they are not parsed).
+
+release 3.0.0 6th of December 2024
+
 	1) PR #2477 for #2463. Add support for Fortran Namelist statements.
 
 	2) PR #2367 for #2296. Extends ModuleInfo so that it can be queried
@@ -225,8 +242,8 @@
 
 	77) PR #2708 for #2663. Add LFRic OpenACC in the integration tests.
 
-	78) PR #2678 for #2636. Alter LFRic PSy-layer to lookup nlevels for
-	each kernel
+	78) PR #2678 for #2636. Alter LFRic PSy-layer to lookup nlayers for
+	each kernel.
 
 	79) PR #2687 for #2684. Add support for WHERE constructs that contain
 	references without range-notation (and prevent some incorrect cases).
@@ -247,7 +264,7 @@
 	Python used in the CI.
 
 	85) PR #2748. Revert Python used on RTD to 3.12 as 3.13 unsupported.
-	
+
 	86) PR #2707 for #257. Fixes bugs in the loop-fusion transformation.
 
 	87) PR #2752 towards #2717. Adds Assignment.is_literal_assignment property.
@@ -298,6 +315,43 @@
 	113) PR #2769 for #2768. Generalises Sign2CodeTrans and Abs2CodeTrans
 	to allow non-floating point scalar literals.
 
+	114) PR #2461 for #2460. Renames DynamoPSy class to LFRicPSy and moves
+	into a new module lfric_psy.py in domain/lfric.
+
+	115) PR #2697 towards #2671. Fixes various issues relating to incorrect
+	parallelisation of loops in NEMO. Also adds support for array-
+	privatisation option.
+
+	116) PR #2804 towards #2737. Update PSyclone to use fparser 0.2.0 release.
+
+	117) PR #2803 for #2796. Fixes bug where PSyData nodes inserted within
+	LFRic loops did not have the associated variable declared.
+
+	118) PR #2792 for # 2766. Updates to all the examples and test
+	infrastructure now that the index ordering for operators in LFRic
+	has been changed.
+
+	119) PR #2775. Adds Call.get_callee() which matches the arguments of
+	a Call against the signature of potential callees.
+
+	120) PR #2628 for #2624. Improves debug_string output for Schedules.
+
+	121) PR #2800. Updates integration test dependencies and documentation
+	about compiling for GPUs.
+
+	122) PR #2811. Adds sphinx-autodoc-typehints package to 'doc'
+	dependencies so that Sphinx markup is able to make use of the
+	typehints that we are starting to add to the code base.
+
+	123) PR #2809 for #2737. Updates documentation on OpenMP to point to
+	examples of tranformations for CPU and GPU.
+
+	124) PR #2815 for #2636. Get nlayers from first field or operator
+	argument to each kernel in LFRic.
+
+	125) PR #2817 for #2816. Fix index type in initialisation of arrays
+	of fields in PSyAD test harness construction.
+
 release 2.5.0 14th of February 2024
 
 	1) PR #2199 for #2189. Fix bugs with missing maps in enter data

doc/developer_guide/conf.py

@@ -43,6 +43,7 @@
 extensions = ['sphinx.ext.autodoc', 'sphinx.ext.doctest',
               'sphinx.ext.intersphinx', 'sphinx.ext.coverage',
               'sphinx.ext.imgmath', 'sphinx.ext.viewcode',
+              'sphinx_autodoc_typehints',
               'sphinxcontrib.bibtex', 'apilinks']
 bibtex_bibfiles = ['../bibliography/references.bib']
 

doc/developer_guide/psyir.rst

@@ -898,7 +898,7 @@ class, for example:
 
 .. code-block:: python
 
-    from psyclone.psyir.nodes.commentable_mixin import CommentableMixin
+    from psyclone.psyir.commentable_mixin import CommentableMixin
 
     class MyNode(Node, CommentableMixin):
         ''' Example node '''

doc/developer_guide/system_specific_setup.rst

@@ -64,11 +64,11 @@ Installing Documentation Tools
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 Install Sphinx along with bibtex support for creating PSyclone documentation::
 
-   > sudo pip install sphinx sphinxcontrib.bibtex
+   > pip install .[doc]
 
-You can now build html documentation::
+You can now build html documentation. E.g., for the developer documentation::
 
-   > cd doc
+   > cd doc/developer_guide/
    > make html
 
 The latex package is required to create the pdf documentation