Set up GPU CI testing (explosion#7293)

* Set up CI for tests with GPU agent * Update tests for enabled GPU * Fix steps filename * Add parallel build jobs as a setting * Fix test requirements * Fix install test requirements condition * Fix pipeline models test * Reset current ops in prefer/require testing * Fix more tests * Remove separate test_models test * Fix regression 5551 * fix StaticVectors for GPU use * fix vocab tests * Fix regression test 5082 * Move azure steps to .github and reenable default pool jobs * Consolidate/rename azure steps Co-authored-by: svlandeg <[email protected]>
paolodedios · Apr 22, 2021 · 36ecba2 · 36ecba2
1 parent bdb485c
commit 36ecba2
Show file tree

Hide file tree

Showing 16 changed files with 239 additions and 138 deletions.
diff --git a/.github/azure-steps.yml b/.github/azure-steps.yml
@@ -0,0 +1,57 @@
+parameters:
+  python_version: ''
+  architecture: ''
+  prefix: ''
+  gpu: false
+  num_build_jobs: 1
+
+steps:
+  - task: UsePythonVersion@0
+    inputs:
+      versionSpec: ${{ parameters.python_version }}
+      architecture: ${{ parameters.architecture }}
+
+  - script: |
+      ${{ parameters.prefix }} python -m pip install -U pip setuptools
+      ${{ parameters.prefix }} python -m pip install -U -r requirements.txt
+    displayName: "Install dependencies"
+
+  - script: |
+      ${{ parameters.prefix }} python setup.py build_ext --inplace -j ${{ parameters.num_build_jobs }}
+      ${{ parameters.prefix }} python setup.py sdist --formats=gztar
+    displayName: "Compile and build sdist"
+
+  - task: DeleteFiles@1
+    inputs:
+      contents: "spacy"
+    displayName: "Delete source directory"
+
+  - script: |
+      ${{ parameters.prefix }} python -m pip freeze --exclude torch --exclude cupy-cuda110 > installed.txt
+      ${{ parameters.prefix }} python -m pip uninstall -y -r installed.txt
+    displayName: "Uninstall all packages"
+
+  - bash: |
+      ${{ parameters.prefix }} SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
+      ${{ parameters.prefix }} python -m pip install dist/$SDIST
+    displayName: "Install from sdist"
+
+  - script: |
+      ${{ parameters.prefix }} python -m pip install -U -r requirements.txt
+    displayName: "Install test requirements"
+
+  - script: |
+      ${{ parameters.prefix }} python -m pip install -U cupy-cuda110
+      ${{ parameters.prefix }} python -m pip install "torch==1.7.1+cu110" -f https://download.pytorch.org/whl/torch_stable.html
+    displayName: "Install GPU requirements"
+    condition: eq(${{ parameters.gpu }}, true)
+
+  - script: |
+      ${{ parameters.prefix }} python -m pytest --pyargs spacy
+    displayName: "Run CPU tests"
+    condition: eq(${{ parameters.gpu }}, false)
+
+  - script: |
+      ${{ parameters.prefix }} python -m pytest --pyargs spacy -p spacy.tests.enable_gpu
+    displayName: "Run GPU tests"
+    condition: eq(${{ parameters.gpu }}, true)
diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -76,39 +76,24 @@ jobs:
       maxParallel: 4
     pool:
       vmImage: $(imageName)
-
     steps:
-      - task: UsePythonVersion@0
-        inputs:
-          versionSpec: "$(python.version)"
-          architecture: "x64"
-
-      - script: |
-          python -m pip install -U setuptools
-          pip install -r requirements.txt
-        displayName: "Install dependencies"
-
-      - script: |
-          python setup.py build_ext --inplace
-          python setup.py sdist --formats=gztar
-        displayName: "Compile and build sdist"
-
-      - task: DeleteFiles@1
-        inputs:
-          contents: "spacy"
-        displayName: "Delete source directory"
+      - template: .github/azure-steps.yml
+        parameters:
+          python_version: '$(python.version)'
+          architecture: 'x64'
 
-      - script: |
-          pip freeze > installed.txt
-          pip uninstall -y -r installed.txt
-        displayName: "Uninstall all packages"
-
-      - bash: |
-          SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
-          pip install dist/$SDIST
-        displayName: "Install from sdist"
-
-      - script: |
-          pip install -r requirements.txt
-          python -m pytest --pyargs spacy
-        displayName: "Run tests"
+  - job: "TestGPU"
+    dependsOn: "Validate"
+    strategy:
+      matrix:
+        Python38LinuxX64_GPU:
+          python.version: '3.8'
+    pool:
+      name: "LinuxX64_GPU"
+    steps:
+      - template: .github/azure-steps.yml
+        parameters:
+          python_version: '$(python.version)'
+          architecture: 'x64'
+          gpu: true
+          num_build_jobs: 24
diff --git a/spacy/ml/staticvectors.py b/spacy/ml/staticvectors.py
@@ -38,7 +38,7 @@ def forward(
         return _handle_empty(model.ops, model.get_dim("nO"))
     key_attr = model.attrs["key_attr"]
     W = cast(Floats2d, model.ops.as_contig(model.get_param("W")))
-    V = cast(Floats2d, docs[0].vocab.vectors.data)
+    V = cast(Floats2d, model.ops.asarray(docs[0].vocab.vectors.data))
     rows = model.ops.flatten(
         [doc.vocab.vectors.find(keys=doc.to_array(key_attr)) for doc in docs]
     )

diff --git a/spacy/tests/enable_gpu.py b/spacy/tests/enable_gpu.py
@@ -0,0 +1,3 @@
+from spacy import require_gpu
+
+require_gpu()
diff --git a/spacy/tests/pipeline/test_entity_ruler.py b/spacy/tests/pipeline/test_entity_ruler.py
@@ -5,6 +5,7 @@
 from spacy.language import Language
 from spacy.pipeline import EntityRuler
 from spacy.errors import MatchPatternError
+from thinc.api import NumpyOps, get_current_ops
 
 
 @pytest.fixture
@@ -201,13 +202,14 @@ def test_entity_ruler_overlapping_spans(nlp):
 
 @pytest.mark.parametrize("n_process", [1, 2])
 def test_entity_ruler_multiprocessing(nlp, n_process):
-    texts = ["I enjoy eating Pizza Hut pizza."]
+    if isinstance(get_current_ops, NumpyOps) or n_process < 2:
+        texts = ["I enjoy eating Pizza Hut pizza."]
 
-    patterns = [{"label": "FASTFOOD", "pattern": "Pizza Hut", "id": "1234"}]
+        patterns = [{"label": "FASTFOOD", "pattern": "Pizza Hut", "id": "1234"}]
 
-    ruler = nlp.add_pipe("entity_ruler")
-    ruler.add_patterns(patterns)
+        ruler = nlp.add_pipe("entity_ruler")
+        ruler.add_patterns(patterns)
 
-    for doc in nlp.pipe(texts, n_process=2):
-        for ent in doc.ents:
-            assert ent.ent_id_ == "1234"
+        for doc in nlp.pipe(texts, n_process=2):
+            for ent in doc.ents:
+                assert ent.ent_id_ == "1234"
diff --git a/spacy/tests/pipeline/test_models.py b/spacy/tests/pipeline/test_models.py
@@ -4,7 +4,7 @@
 import pytest
 from numpy.testing import assert_almost_equal
 from spacy.vocab import Vocab
-from thinc.api import NumpyOps, Model, data_validation
+from thinc.api import Model, data_validation, get_current_ops
 from thinc.types import Array2d, Ragged
 
 from spacy.lang.en import English
@@ -13,7 +13,7 @@
 from spacy.tokens import Doc
 
 
-OPS = NumpyOps()
+OPS = get_current_ops()
 
 texts = ["These are 4 words", "Here just three"]
 l0 = [[1, 2], [3, 4], [5, 6], [7, 8]]
@@ -82,7 +82,7 @@ def util_batch_unbatch_docs_list(
         Y_batched = model.predict(in_data)
         Y_not_batched = [model.predict([u])[0] for u in in_data]
         for i in range(len(Y_batched)):
-            assert_almost_equal(Y_batched[i], Y_not_batched[i], decimal=4)
+            assert_almost_equal(OPS.to_numpy(Y_batched[i]), OPS.to_numpy(Y_not_batched[i]), decimal=4)
 
 
 def util_batch_unbatch_docs_array(
@@ -91,7 +91,7 @@ def util_batch_unbatch_docs_array(
     with data_validation(True):
         model.initialize(in_data, out_data)
         Y_batched = model.predict(in_data).tolist()
-        Y_not_batched = [model.predict([u])[0] for u in in_data]
+        Y_not_batched = [model.predict([u])[0].tolist() for u in in_data]
         assert_almost_equal(Y_batched, Y_not_batched, decimal=4)
 
 
@@ -100,8 +100,8 @@ def util_batch_unbatch_docs_ragged(
 ):
     with data_validation(True):
         model.initialize(in_data, out_data)
-        Y_batched = model.predict(in_data)
+        Y_batched = model.predict(in_data).data.tolist()
         Y_not_batched = []
         for u in in_data:
             Y_not_batched.extend(model.predict([u]).data.tolist())
-        assert_almost_equal(Y_batched.data, Y_not_batched, decimal=4)
+        assert_almost_equal(Y_batched, Y_not_batched, decimal=4)
diff --git a/spacy/tests/pipeline/test_textcat.py b/spacy/tests/pipeline/test_textcat.py
@@ -1,7 +1,7 @@
 import pytest
 import random
 import numpy.random
-from numpy.testing import assert_equal
+from numpy.testing import assert_almost_equal
 from thinc.api import fix_random_seed
 from spacy import util
 from spacy.lang.en import English
@@ -222,8 +222,12 @@ def test_overfitting_IO():
     batch_cats_1 = [doc.cats for doc in nlp.pipe(texts)]
     batch_cats_2 = [doc.cats for doc in nlp.pipe(texts)]
     no_batch_cats = [doc.cats for doc in [nlp(text) for text in texts]]
-    assert_equal(batch_cats_1, batch_cats_2)
-    assert_equal(batch_cats_1, no_batch_cats)
+    for cats_1, cats_2 in zip(batch_cats_1, batch_cats_2):
+        for cat in cats_1:
+            assert_almost_equal(cats_1[cat], cats_2[cat], decimal=5)
+    for cats_1, cats_2 in zip(batch_cats_1, no_batch_cats):
+        for cat in cats_1:
+            assert_almost_equal(cats_1[cat], cats_2[cat], decimal=5)
 
 
 def test_overfitting_IO_multi():
@@ -270,8 +274,12 @@ def test_overfitting_IO_multi():
     batch_deps_1 = [doc.cats for doc in nlp.pipe(texts)]
     batch_deps_2 = [doc.cats for doc in nlp.pipe(texts)]
     no_batch_deps = [doc.cats for doc in [nlp(text) for text in texts]]
-    assert_equal(batch_deps_1, batch_deps_2)
-    assert_equal(batch_deps_1, no_batch_deps)
+    for cats_1, cats_2 in zip(batch_deps_1, batch_deps_2):
+        for cat in cats_1:
+            assert_almost_equal(cats_1[cat], cats_2[cat], decimal=5)
+    for cats_1, cats_2 in zip(batch_deps_1, no_batch_deps):
+        for cat in cats_1:
+            assert_almost_equal(cats_1[cat], cats_2[cat], decimal=5)
 
 
 # fmt: off

diff --git a/spacy/tests/pipeline/test_tok2vec.py b/spacy/tests/pipeline/test_tok2vec.py
@@ -8,8 +8,8 @@
 from spacy.training import Example
 from spacy import util
 from spacy.lang.en import English
-from thinc.api import Config
-from numpy.testing import assert_equal
+from thinc.api import Config, get_current_ops
+from numpy.testing import assert_array_equal
 
 from ..util import get_batch, make_tempdir
 
@@ -160,7 +160,8 @@ def test_tok2vec_listener():
 
     doc = nlp("Running the pipeline as a whole.")
     doc_tensor = tagger_tok2vec.predict([doc])[0]
-    assert_equal(doc.tensor, doc_tensor)
+    ops = get_current_ops()
+    assert_array_equal(ops.to_numpy(doc.tensor), ops.to_numpy(doc_tensor))
 
     # TODO: should this warn or error?
     nlp.select_pipes(disable="tok2vec")

diff --git a/spacy/tests/regression/test_issue4501-5000.py b/spacy/tests/regression/test_issue4501-5000.py
@@ -9,6 +9,7 @@
 from spacy.util import ensure_path, load_model_from_path
 import numpy
 import pickle
+from thinc.api import NumpyOps, get_current_ops
 
 from ..util import make_tempdir
 
@@ -169,21 +170,22 @@ def test_issue4725_1():
 
 
 def test_issue4725_2():
-    # ensures that this runs correctly and doesn't hang or crash because of the global vectors
-    # if it does crash, it's usually because of calling 'spawn' for multiprocessing (e.g. on Windows),
-    # or because of issues with pickling the NER (cf test_issue4725_1)
-    vocab = Vocab(vectors_name="test_vocab_add_vector")
-    data = numpy.ndarray((5, 3), dtype="f")
-    data[0] = 1.0
-    data[1] = 2.0
-    vocab.set_vector("cat", data[0])
-    vocab.set_vector("dog", data[1])
-    nlp = English(vocab=vocab)
-    nlp.add_pipe("ner")
-    nlp.initialize()
-    docs = ["Kurt is in London."] * 10
-    for _ in nlp.pipe(docs, batch_size=2, n_process=2):
-        pass
+    if isinstance(get_current_ops, NumpyOps):
+        # ensures that this runs correctly and doesn't hang or crash because of the global vectors
+        # if it does crash, it's usually because of calling 'spawn' for multiprocessing (e.g. on Windows),
+        # or because of issues with pickling the NER (cf test_issue4725_1)
+        vocab = Vocab(vectors_name="test_vocab_add_vector")
+        data = numpy.ndarray((5, 3), dtype="f")
+        data[0] = 1.0
+        data[1] = 2.0
+        vocab.set_vector("cat", data[0])
+        vocab.set_vector("dog", data[1])
+        nlp = English(vocab=vocab)
+        nlp.add_pipe("ner")
+        nlp.initialize()
+        docs = ["Kurt is in London."] * 10
+        for _ in nlp.pipe(docs, batch_size=2, n_process=2):
+            pass
 
 
 def test_issue4849():
@@ -204,10 +206,11 @@ def test_issue4849():
         count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
     assert count_ents == 2
     # USING 2 PROCESSES
-    count_ents = 0
-    for doc in nlp.pipe([text], n_process=2):
-        count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
-    assert count_ents == 2
+    if isinstance(get_current_ops, NumpyOps):
+        count_ents = 0
+        for doc in nlp.pipe([text], n_process=2):
+            count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
+        assert count_ents == 2
 
 
 @Language.factory("my_pipe")
@@ -239,10 +242,11 @@ def test_issue4903():
     nlp.add_pipe("sentencizer")
     nlp.add_pipe("my_pipe", after="sentencizer")
     text = ["I like bananas.", "Do you like them?", "No, I prefer wasabi."]
-    docs = list(nlp.pipe(text, n_process=2))
-    assert docs[0].text == "I like bananas."
-    assert docs[1].text == "Do you like them?"
-    assert docs[2].text == "No, I prefer wasabi."
+    if isinstance(get_current_ops(), NumpyOps):
+        docs = list(nlp.pipe(text, n_process=2))
+        assert docs[0].text == "I like bananas."
+        assert docs[1].text == "Do you like them?"
+        assert docs[2].text == "No, I prefer wasabi."
 
 
 def test_issue4924():

diff --git a/spacy/tests/regression/test_issue5001-5500.py b/spacy/tests/regression/test_issue5001-5500.py
@@ -6,6 +6,7 @@
 from spacy.lang.en.syntax_iterators import noun_chunks
 from spacy.vocab import Vocab
 import spacy
+from thinc.api import get_current_ops
 import pytest
 
 from ...util import make_tempdir
@@ -54,16 +55,17 @@ def test_issue5082():
     ruler.add_patterns(patterns)
     parsed_vectors_1 = [t.vector for t in nlp(text)]
     assert len(parsed_vectors_1) == 4
-    numpy.testing.assert_array_equal(parsed_vectors_1[0], array1)
-    numpy.testing.assert_array_equal(parsed_vectors_1[1], array2)
-    numpy.testing.assert_array_equal(parsed_vectors_1[2], array3)
-    numpy.testing.assert_array_equal(parsed_vectors_1[3], array4)
+    ops = get_current_ops()
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[0]), array1)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[1]), array2)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[2]), array3)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_1[3]), array4)
     nlp.add_pipe("merge_entities")
     parsed_vectors_2 = [t.vector for t in nlp(text)]
     assert len(parsed_vectors_2) == 3
-    numpy.testing.assert_array_equal(parsed_vectors_2[0], array1)
-    numpy.testing.assert_array_equal(parsed_vectors_2[1], array2)
-    numpy.testing.assert_array_equal(parsed_vectors_2[2], array34)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[0]), array1)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[1]), array2)
+    numpy.testing.assert_array_equal(ops.to_numpy(parsed_vectors_2[2]), array34)
 
 
 def test_issue5137():