Merge branch 'main' into additions

.github/workflows/fpga-ci.yml

@@ -2,18 +2,21 @@ name: FPGA Tests
 
 on:
   push:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   pull_request:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   merge_group:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
+
+env:
+  CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
 jobs:
   test-fpga:
     if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-ci') }}
     runs-on: [self-hosted, linux, intel-fpga, xilinx-fpga]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         submodules: 'recursive'
     - name: Install dependencies

.github/workflows/general-ci.yml

@@ -2,11 +2,11 @@ name: General Tests
 
 on:
   push:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   pull_request:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   merge_group:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
 
 jobs:
   test:
@@ -18,11 +18,11 @@ jobs:
         simplify: [0,1,autoopt]
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         submodules: 'recursive'
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -55,7 +55,7 @@ jobs:
         else
             export DACE_optimizer_automatic_simplification=${{ matrix.simplify }}
         fi
-        pytest -n auto --cov-report=xml --cov=dace --tb=short -m "not gpu and not verilator and not tensorflow and not mkl and not sve and not papi and not mlir and not lapack and not fpga and not mpi and not rtl_hardware and not scalapack and not datainstrument"
+        pytest -n auto --cov-report=xml --cov=dace --tb=short -m "not gpu and not verilator and not tensorflow and not mkl and not sve and not papi and not mlir and not lapack and not fpga and not mpi and not rtl_hardware and not scalapack and not datainstrument and not long"
         ./codecov
 
     - name: Test OpenBLAS LAPACK
@@ -85,4 +85,8 @@ jobs:
         ./tests/polybench_test.sh
         ./tests/xform_test.sh
         coverage combine .; coverage report; coverage xml
-        ./codecov
+
+    - uses: codecov/codecov-action@v4
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+        verbose: true

.github/workflows/gpu-ci.yml

@@ -2,23 +2,24 @@ name: GPU Tests
 
 on:
   push:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   pull_request:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   merge_group:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
 
 env:
   CUDACXX: /usr/local/cuda/bin/nvcc
   MKLROOT: /opt/intel/oneapi/mkl/latest/
+  CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
 
 jobs:
   test-gpu:
     if: "!contains(github.event.pull_request.labels.*.name, 'no-ci')"
     runs-on: [self-hosted, gpu]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         submodules: 'recursive'
     - name: Install dependencies

.github/workflows/hardware_test.yml

@@ -4,7 +4,7 @@ jobs:
   test-rtl:
     runs-on: [self-hosted, linux, xilinx-fpga]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         submodules: 'recursive'
     - name: Install dependencies

.github/workflows/heterogeneous-ci.yml

@@ -2,23 +2,24 @@ name: Heterogeneous Tests
 
 on:
   push:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   pull_request:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   merge_group:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
 
 env:
   CUDA_HOME: /usr/local/cuda
   CUDACXX: nvcc
   MKLROOT: /opt/intel/oneapi/mkl/latest/
+  CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
 jobs:
   test-heterogeneous:
     if: "!contains(github.event.pull_request.labels.*.name, 'no-ci')"
     runs-on: [self-hosted, linux]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
       with:
         submodules: 'recursive'
     - name: Install dependencies

.github/workflows/pyFV3-ci.yml

@@ -2,11 +2,11 @@ name: NASA/NOAA pyFV3 repository build test
 
 on:
   push:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   pull_request:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
   merge_group:
-    branches: [ master, ci-fix ]
+    branches: [ main, ci-fix ]
 
 defaults:
     run:
@@ -21,18 +21,18 @@ jobs:
               python-version: [3.11.7]
 
       steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
               repository: 'NOAA-GFDL/PyFV3'
               ref: 'ci/DaCe'
               submodules: 'recursive'
               path: 'pyFV3'
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with: 
             path: 'dace'
             submodules: 'recursive'
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
               python-version: ${{ matrix.python-version }}
       - name: Install library dependencies
@@ -53,11 +53,11 @@ jobs:
           cd pyFV3
           mkdir -p test_data
           cd test_data
-          wget https://portal.nccs.nasa.gov/datashare/astg/smt/pace-regression-data/8.1.3_c12_6ranks_standard.D_SW.tar.gz
+          wget --retry-connrefused https://portal.nccs.nasa.gov/datashare/astg/smt/pace-regression-data/8.1.3_c12_6ranks_standard.D_SW.tar.gz
           tar -xzvf 8.1.3_c12_6ranks_standard.D_SW.tar.gz
-          wget https://portal.nccs.nasa.gov/datashare/astg/smt/pace-regression-data/8.1.3_c12_6ranks_standard.RiemSolver3.tar.gz
+          wget --retry-connrefused https://portal.nccs.nasa.gov/datashare/astg/smt/pace-regression-data/8.1.3_c12_6ranks_standard.RiemSolver3.tar.gz
           tar -xzvf 8.1.3_c12_6ranks_standard.RiemSolver3.tar.gz
-          wget https://portal.nccs.nasa.gov/datashare/astg/smt/pace-regression-data/8.1.3_c12_6ranks_standard.Remapping.tar.gz
+          wget --retry-connrefused https://portal.nccs.nasa.gov/datashare/astg/smt/pace-regression-data/8.1.3_c12_6ranks_standard.Remapping.tar.gz
           tar -xzvf 8.1.3_c12_6ranks_standard.Remapping.tar.gz
           cd ../..
       # Clean up caches between run for stale un-expanded SDFG to trip the build system (NDSL side issue)

.github/workflows/verilator_compatibility.yml

@@ -17,14 +17,14 @@ jobs:
     steps:
       - name: trigger reason
         run: echo "Trigger Reason:" ${{ github.event.inputs.reason }}
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: checkout submodules
         run: git submodule update --init --recursive
       - name: install apt packages
         run: sudo apt-get update && sudo apt-get -y install git make autoconf g++ flex bison libfl2 libfl-dev
       - name: compile verilator
         run: git clone https://github.com/verilator/verilator.git && cd verilator && git fetch origin && if [ ! "${{ matrix.verilator_version }}" == "master" ]; then  git checkout v${{ matrix.verilator_version }}; fi && autoconf && ./configure && make -j2 && sudo make install
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.8'
           architecture: 'x64'

CONTRIBUTING.md

@@ -47,7 +47,7 @@ For automatic styling, we use the [yapf](https://github.com/google/yapf) file fo
 We use [pytest](https://www.pytest.org/) for our testing infrastructure. All tests under the `tests/` folder 
 (and any subfolders within) are automatically read and run. The files must be under the right subfolder
 based on the component being tested (e.g., `tests/sdfg/` for IR-related tests), and must have the right
-suffix: either `*_test.py` or `*_cudatest.py`. See [pytest.ini](https://github.com/spcl/dace/blob/master/pytest.ini)
+suffix: either `*_test.py` or `*_cudatest.py`. See [pytest.ini](https://github.com/spcl/dace/blob/main/pytest.ini)
 for more information, and for the markers we use to specify software/hardware requirements.
 
 The structure of the test file must follow `pytest` standards (i.e., free functions called `test_*`), and

README.md

@@ -3,15 +3,15 @@
 [![FPGA Tests](https://github.com/spcl/dace/actions/workflows/fpga-ci.yml/badge.svg)](https://github.com/spcl/dace/actions/workflows/fpga-ci.yml)
 [![Documentation Status](https://readthedocs.org/projects/spcldace/badge/?version=latest)](https://spcldace.readthedocs.io/en/latest/?badge=latest)
 [![PyPI version](https://badge.fury.io/py/dace.svg)](https://badge.fury.io/py/dace)
-[![codecov](https://codecov.io/gh/spcl/dace/branch/master/graph/badge.svg)](https://codecov.io/gh/spcl/dace)
+[![codecov](https://codecov.io/gh/spcl/dace/branch/main/graph/badge.svg)](https://codecov.io/gh/spcl/dace)
 
 
 ![D](dace.svg)aCe - Data-Centric Parallel Programming
 =====================================================
 
 _Decoupling domain science from performance optimization._
 
-DaCe is a [fast](https://nbviewer.org/github/spcl/dace/blob/master/tutorials/benchmarking.ipynb) parallel programming
+DaCe is a [fast](https://nbviewer.org/github/spcl/dace/blob/main/tutorials/benchmarking.ipynb) parallel programming
 framework that takes code in Python/NumPy and other programming languages, and maps it to high-performance 
 **CPU, GPU, and FPGA** programs, which can be optimized to achieve state-of-the-art. Internally, DaCe 
 uses the Stateful DataFlow multiGraph (SDFG) *data-centric intermediate 
@@ -61,13 +61,13 @@ be used in any C ABI compatible language (C/C++, FORTRAN, etc.).
 
 For more information on how to use DaCe, see the [samples](samples) or tutorials below:
 
-* [Getting Started](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/getting_started.ipynb)
-* [Benchmarks, Instrumentation, and Performance Comparison with Other Python Compilers](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/benchmarking.ipynb)
-* [Explicit Dataflow in Python](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/explicit.ipynb)
-* [NumPy API Reference](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/numpy_frontend.ipynb)
-* [SDFG API](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/sdfg_api.ipynb)
-* [Using and Creating Transformations](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/transformations.ipynb)
-* [Extending the Code Generator](https://nbviewer.jupyter.org/github/spcl/dace/blob/master/tutorials/codegen.ipynb)
+* [Getting Started](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/getting_started.ipynb)
+* [Benchmarks, Instrumentation, and Performance Comparison with Other Python Compilers](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/benchmarking.ipynb)
+* [Explicit Dataflow in Python](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/explicit.ipynb)
+* [NumPy API Reference](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/numpy_frontend.ipynb)
+* [SDFG API](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/sdfg_api.ipynb)
+* [Using and Creating Transformations](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/transformations.ipynb)
+* [Extending the Code Generator](https://nbviewer.jupyter.org/github/spcl/dace/blob/main/tutorials/codegen.ipynb)
 
 Publication
 -----------

dace/cli/dacelab.py

@@ -2,11 +2,6 @@
 # Copyright 2019-2021 ETH Zurich and the DaCe authors. All rights reserved.
 
 import argparse
-import numpy
-import pickle
-import json
-
-import dace
 from dace.frontend.octave import parse
 from dace.sdfg.nodes import AccessNode
 

dace/cli/sdfg_diff.py

@@ -7,9 +7,12 @@
 import os
 import platform
 import tempfile
-from typing import Dict, Literal, Set, Tuple, Union
+from typing import Dict, Set, Tuple, Union
+try:
+    from typing import Literal
+except ImportError:
+    from typing_extensions import Literal
 
-import jinja2
 import dace
 from dace import memlet as mlt
 from dace.sdfg import nodes as nd
@@ -179,6 +182,11 @@ def main():
     diff_sets = _sdfg_diff(sdfg_A, sdfg_B, eq_strategy)
 
     if args.graphical:
+        try:
+            import jinja2
+        except (ImportError, ModuleNotFoundError):
+            raise ImportError('Graphical SDFG diff requires jinja2, please install by running `pip install jinja2`')
+
         basepath = os.path.join(os.path.dirname(os.path.realpath(dace.__file__)), 'viewer')
         template_loader = jinja2.FileSystemLoader(searchpath=os.path.join(basepath, 'templates'))
         template_env = jinja2.Environment(loader=template_loader)

dace/cli/sdfgcc.py

@@ -48,7 +48,7 @@ def main():
         sdfg = SDFGOptimizer(sdfg).optimize()
 
     # Compile SDFG
-    sdfg.compile(outpath)
+    sdfg.compile(outpath, return_program_handle=False)
 
     # Copying header file to optional path
     if outpath is not None:

dace/cli/sdfv.py

@@ -13,7 +13,6 @@
 
 import dace
 import tempfile
-import jinja2
 
 
 def partialclass(cls, *args, **kwds):
@@ -44,10 +43,19 @@ def view(sdfg: dace.SDFG, filename: Optional[Union[str, int]] = None, verbose: b
         ):
             fd, filename = tempfile.mkstemp(suffix='.sdfg')
             sdfg.save(filename)
-            os.system(f'code {filename}')
+            if platform.system() == 'Darwin':
+                # Special case for MacOS
+                os.system(f'open {filename}')
+            else:
+                os.system(f'code {filename}')
             os.close(fd)
             return
 
+    try:
+        import jinja2
+    except (ImportError, ModuleNotFoundError):
+        raise ImportError('SDFG.view() requires jinja2, please install by running `pip install jinja2`')
+
     if type(sdfg) is dace.SDFG:
         sdfg = dace.serialize.dumps(sdfg.to_json())
 

dace/codegen/compiled_sdfg.py

@@ -518,6 +518,9 @@ def _construct_args(self, kwargs) -> Tuple[Tuple[Any], Tuple[Any]]:
                     # Otherwise, None values are passed as null pointers below
                 elif isinstance(arg, ctypes._Pointer):
                     pass
+                elif isinstance(arg, str):
+                    # Cast to bytes
+                    arglist[i] = ctypes.c_char_p(arg.encode('utf-8'))
                 else:
                     raise TypeError(f'Passing an object (type {type(arg).__name__}) to an array in argument "{a}"')
             elif is_array and not is_dtArray:
@@ -550,6 +553,8 @@ def _construct_args(self, kwargs) -> Tuple[Tuple[Any], Tuple[Any]]:
                     pass
                 elif isinstance(arg, float) and atype.dtype.type == np.float64:
                     pass
+                elif isinstance(arg, bool) and atype.dtype.type == np.bool_:
+                    pass
                 elif (isinstance(arg, str) or arg is None) and atype.dtype == dtypes.string:
                     if arg is None:
                         arglist[i] = ctypes.c_char_p(None)
@@ -575,7 +580,7 @@ def _construct_args(self, kwargs) -> Tuple[Tuple[Any], Tuple[Any]]:
         arg_ctypes = tuple(at.dtype.as_ctypes() for at in argtypes)
 
         constants = self.sdfg.constants
-        callparams = tuple((actype(arg.get()) if isinstance(arg, symbolic.symbol) else arg, actype, atype, aname)
+        callparams = tuple((arg, actype, atype, aname)
                            for arg, actype, atype, aname in zip(arglist, arg_ctypes, argtypes, argnames)
                            if not (symbolic.issymbolic(arg) and (hasattr(arg, 'name') and arg.name in constants)))