numpy · charris · Aug 12, 2023 · Aug 11, 2023
diff --git a/.github/meson_actions/action.yml b/.github/meson_actions/action.yml
@@ -0,0 +1,29 @@
+name: MesonBuildTest
+description: "checkout repo, build, and test numpy"
+runs:
+  using: composite
+  steps:
+  - name: Install dependencies
+    shell: bash
+    run: pip install -r build_requirements.txt
+  - name: Build
+    shell: 'script -q -e -c "bash --noprofile --norc -eo pipefail {0}"'
+    env:
+      TERM: xterm-256color
+    run:
+      spin build -- ${MESON_ARGS[@]}
+  - name: Check build-internal dependencies
+    shell: bash
+    run:
+      ninja -C build -t missingdeps
+  - name: Check installed test and stub files
+    shell: bash
+    run:
+      python tools/check_installed_files.py $(find ./build-install -path '*/site-packages/numpy')
+  - name: Test
+    shell: 'script -q -e -c "bash --noprofile --norc -eo pipefail {0}"'
+    env:
+      TERM: xterm-256color
+    run: |
+      pip install pytest pytest-xdist hypothesis typing_extensions
+      spin test -j auto
diff --git a/.github/workflows/build_test.yml b/.github/workflows/build_test.yml
@@ -49,7 +49,7 @@ jobs:
     if: "github.repository == 'numpy/numpy'"
     runs-on: ubuntu-latest
     env:
-      WITHOUT_SIMD: 1
+      MESON_ARGS: "-Dallow-noblas=true -Dcpu-baseline=none -Dcpu-dispatch=none"
     steps:
     - uses: actions/checkout@c85c95e3d7251135ab7dc9ce3241c5835cc595a9 # v3.5.3
       with:
@@ -58,7 +58,7 @@ jobs:
     - uses: actions/setup-python@61a6322f88396a6271a6ee3565807d608ecaddd1 # v4.7.0
       with:
         python-version: ${{ env.PYTHON_VERSION }}
-    - uses: ./.github/actions
+    - uses: ./.github/meson_actions
 
   basic:
     needs: [smoke_test]
@@ -122,7 +122,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.event_name != 'push'
     env:
-      WITHOUT_OPTIMIZATIONS: 1
+      MESON_ARGS: "-Dallow-noblas=true -Ddisable-optimization=true"
     steps:
     - uses: actions/checkout@c85c95e3d7251135ab7dc9ce3241c5835cc595a9 # v3.5.3
       with:
@@ -131,14 +131,14 @@ jobs:
     - uses: actions/setup-python@61a6322f88396a6271a6ee3565807d608ecaddd1 # v4.7.0
       with:
         python-version: ${{ env.PYTHON_VERSION }}
-    - uses: ./.github/actions
+    - uses: ./.github/meson_actions
 
   with_baseline_only:
     needs: [smoke_test]
     runs-on: ubuntu-latest
     if: github.event_name != 'push'
     env:
-      CPU_DISPATCH: "none"
+      MESON_ARGS: "-Dallow-noblas=true -Dcpu-dispatch=none"
     steps:
     - uses: actions/checkout@c85c95e3d7251135ab7dc9ce3241c5835cc595a9 # v3.5.3
       with:
@@ -147,14 +147,14 @@ jobs:
     - uses: actions/setup-python@61a6322f88396a6271a6ee3565807d608ecaddd1 # v4.7.0
       with:
         python-version: ${{ env.PYTHON_VERSION }}
-    - uses: ./.github/actions
+    - uses: ./.github/meson_actions
 
   without_avx512:
     needs: [smoke_test]
     runs-on: ubuntu-latest
     if: github.event_name != 'push'
     env:
-      CPU_DISPATCH: "max -xop -fma4 -avx512f -avx512cd -avx512_knl -avx512_knm -avx512_skx -avx512_clx -avx512_cnl -avx512_icl"
+      MESON_ARGS: "-Dallow-noblas=true -Dcpu-dispatch=SSSE3,SSE41,POPCNT,SSE42,AVX,F16C,AVX2,FMA3"
     steps:
     - uses: actions/checkout@c85c95e3d7251135ab7dc9ce3241c5835cc595a9 # v3.5.3
       with:
@@ -163,14 +163,14 @@ jobs:
     - uses: actions/setup-python@61a6322f88396a6271a6ee3565807d608ecaddd1 # v4.7.0
       with:
         python-version: ${{ env.PYTHON_VERSION }}
-    - uses: ./.github/actions
+    - uses: ./.github/meson_actions
 
   without_avx512_avx2_fma3:
     needs: [smoke_test]
     runs-on: ubuntu-latest
     if: github.event_name != 'push'
     env:
-      CPU_DISPATCH: "SSSE3 SSE41 POPCNT SSE42 AVX F16C"
+      MESON_ARGS: "-Dallow-noblas=true -Dcpu-dispatch=SSSE3,SSE41,POPCNT,SSE42,AVX,F16C"
     steps:
     - uses: actions/checkout@c85c95e3d7251135ab7dc9ce3241c5835cc595a9 # v3.5.3
       with:
@@ -179,7 +179,7 @@ jobs:
     - uses: actions/setup-python@61a6322f88396a6271a6ee3565807d608ecaddd1 # v4.7.0
       with:
         python-version: ${{ env.PYTHON_VERSION }}
-    - uses: ./.github/actions
+    - uses: ./.github/meson_actions
 
   debug:
     needs: [smoke_test]

diff --git a/MANIFEST.in b/MANIFEST.in
@@ -21,6 +21,8 @@ recursive-include numpy/random *.pyx *.pxd *.pyx.in *.pxd.in
 include numpy/py.typed
 include numpy/random/include/*
 include numpy/*.pxd
+# Meson CPU Dispatcher
+recursive-include meson_cpu *.build *.in
 # Add build support that should go in sdist, but not go in bdist/be installed
 # Note that sub-directories that don't have __init__ are apparently not
 # included by 'recursive-include', so list those separately

diff --git a/build_requirements.txt b/build_requirements.txt
@@ -1,5 +1,5 @@
-meson-python>=0.10.0
-Cython
+meson-python>=0.13.1
+Cython>=3.0
 wheel==0.38.1
 ninja
 spin==0.4
diff --git a/doc/source/user/quickstart.rst b/doc/source/user/quickstart.rst
@@ -517,7 +517,7 @@ and other Python sequences.
     >>> for i in a:
     ...     print(i**(1 / 3.))
     ...
-    9.999999999999998
+    9.999999999999998  # may vary
     1.0
     9.999999999999998
     3.0

diff --git a/meson.build b/meson.build
@@ -6,7 +6,7 @@ project(
   # See `numpy/__init__.py`
   version: '1.26.0.dev0',
   license: 'BSD-3',
-  meson_version: '>= 1.1.0',
+  meson_version: '>=1.2.99',  # version in vendored-meson is 1.2.99
   default_options: [
     'buildtype=debugoptimized',
     'b_ndebug=if-release',
@@ -80,4 +80,5 @@ else
     meson.add_dist_script(py, versioneer, '-o', '_version_meson.py')
 endif
 
+subdir('meson_cpu')
 subdir('numpy')
diff --git a/meson_cpu/arm/meson.build b/meson_cpu/arm/meson.build
@@ -0,0 +1,58 @@
+source_root = meson.project_source_root()
+mod_features = import('features')
+NEON = mod_features.new(
+  'NEON', 1,
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_neon.c')[0]
+)
+NEON_FP16 = mod_features.new(
+  'NEON_FP16', 2, implies: NEON,
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_neon_fp16.c')[0]
+)
+# FMA
+NEON_VFPV4 = mod_features.new(
+  'NEON_VFPV4', 3, implies: NEON_FP16,
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_neon_vfpv4.c')[0]
+)
+# Advanced SIMD
+ASIMD = mod_features.new(
+  'ASIMD', 4, implies: NEON_VFPV4, detect: {'val': 'ASIMD', 'match': 'NEON.*'},
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_asimd.c')[0]
+)
+cpu_family = host_machine.cpu_family()
+if cpu_family == 'aarch64'
+  # hardware baseline
+  NEON.update(implies: [NEON_FP16, NEON_VFPV4, ASIMD])
+  NEON_FP16.update(implies: [NEON, NEON_VFPV4, ASIMD])
+  NEON_VFPV4.update(implies: [NEON, NEON_FP16, ASIMD])
+elif cpu_family == 'arm'
+  NEON.update(args: '-mfpu=neon')
+  NEON_FP16.update(args: ['-mfp16-format=ieee', {'val': '-mfpu=neon-fp16', 'match': '-mfpu=.*'}])
+  NEON_VFPV4.update(args: [{'val': '-mfpu=neon-vfpv4', 'match': '-mfpu=.*'}])
+  ASIMD.update(args: [
+    {'val': '-mfpu=neon-fp-armv8', 'match': '-mfpu=.*'},
+    '-march=armv8-a+simd'
+  ])
+endif
+# ARMv8.2 half-precision & vector arithm
+ASIMDHP = mod_features.new(
+  'ASIMDHP', 5, implies: ASIMD,
+  args: {'val': '-march=armv8.2-a+fp16', 'match': '-march=.*', 'mfilter': '\+.*'},
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_asimdhp.c')[0]
+)
+## ARMv8.2 dot product
+ASIMDDP = mod_features.new(
+  'ASIMDDP', 6, implies: ASIMD,
+  args: {'val': '-march=armv8.2-a+dotprod', 'match': '-march=.*', 'mfilter': '\+.*'},
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_asimddp.c')[0]
+)
+## ARMv8.2 Single & half-precision Multiply
+ASIMDFHM = mod_features.new(
+  'ASIMDFHM', 7, implies: ASIMDHP,
+  args: {'val': '-march=armv8.2-a+fp16fml', 'match': '-march=.*', 'mfilter': '\+.*'},
+  test_code: files(source_root + '/numpy/distutils/checks/cpu_asimdfhm.c')[0]
+)
+# TODO: Add support for MSVC
+ARM_FEATURES = {
+  'NEON': NEON, 'NEON_FP16': NEON_FP16, 'NEON_VFPV4': NEON_VFPV4,
+  'ASIMD': ASIMD, 'ASIMDHP': ASIMDHP, 'ASIMDFHM': ASIMDFHM
+}