Merge branch 'branch-24.04' into reuse-indexing

rapidsai · Feb 29, 2024 · 5095760 · 5095760
2 parents fbcfa3c + a356ec6
commit 5095760
Show file tree

Hide file tree

Showing 355 changed files with 1,648 additions and 1,204 deletions.
diff --git a/BUILD.md b/BUILD.md
@@ -18,7 +18,7 @@ To install cuML from source, ensure the following dependencies are met:
 It is recommended to use conda for environment/package management. If doing so, development environment .yaml files are located in `conda/environments/all_*.yaml`. These files contains most of the dependencies mentioned above (notable exceptions are `gcc` and `zlib`). To create a development environment named `cuml_dev`, you can use the follow commands:
 
 ```bash
-conda create -n cuml_dev python=3.10
+conda create -n cuml_dev python=3.11
 conda env update -n cuml_dev --file=conda/environments/all_cuda-118_arch-x86_64.yaml
 conda activate cuml_dev
 ```

diff --git a/conda/environments/all_cuda-118_arch-x86_64.yaml b/conda/environments/all_cuda-118_arch-x86_64.yaml
@@ -58,7 +58,7 @@ dependencies:
 - pytest-cov
 - pytest-xdist
 - pytest==7.*
-- python>=3.9,<3.11
+- python>=3.9,<3.12
 - raft-dask==24.4.*
 - rapids-dask-dependency==24.4.*
 - recommonmark

diff --git a/conda/environments/all_cuda-122_arch-x86_64.yaml b/conda/environments/all_cuda-122_arch-x86_64.yaml
@@ -54,7 +54,7 @@ dependencies:
 - pytest-cov
 - pytest-xdist
 - pytest==7.*
-- python>=3.9,<3.11
+- python>=3.9,<3.12
 - raft-dask==24.4.*
 - rapids-dask-dependency==24.4.*
 - recommonmark

diff --git a/conda/recipes/cuml-cpu/meta.yaml b/conda/recipes/cuml-cpu/meta.yaml
@@ -31,7 +31,7 @@ requirements:
     - cython>=3.0.0
   run:
     - python x.x
-    - numpy
+    - numpy>=1.23
     - pandas
     - scikit-learn=1.2
     - hdbscan<=0.8.30

diff --git a/cpp/.clang-format b/cpp/.clang-format
@@ -15,7 +15,7 @@ AlignTrailingComments: true
 AllowAllArgumentsOnNextLine: true
 AllowAllConstructorInitializersOnNextLine: true
 AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortBlocksOnASingleLine: true 
+AllowShortBlocksOnASingleLine: true
 AllowShortCaseLabelsOnASingleLine: true
 AllowShortEnumsOnASingleLine: true
 AllowShortFunctionsOnASingleLine: All
@@ -27,7 +27,7 @@ AlwaysBreakAfterDefinitionReturnType: None
 AlwaysBreakAfterReturnType: None
 AlwaysBreakBeforeMultilineStrings: true
 AlwaysBreakTemplateDeclarations: Yes
-BinPackArguments:  false       
+BinPackArguments:  false
 BinPackParameters: false
 BraceWrapping:
   AfterClass:            false
@@ -71,8 +71,26 @@ ForEachMacros:
   - foreach
   - Q_FOREACH
   - BOOST_FOREACH
-IncludeBlocks: Preserve
-IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeBlocks: Regroup
+IncludeCategories:
+  - Regex:           '^"' # quoted includes
+    Priority:        1
+  - Regex:           '^<(common|benchmarks|tests)/' # benchmark/test includes
+    Priority:        2
+  - Regex:           '^<cuml/' # cuML includes
+    Priority:        3
+  - Regex:           '^<(cudf|raft|kvikio|cumlprims)' # Other RAPIDS includes
+    Priority:        4
+  - Regex:           '^<rmm/' # RMM includes
+    Priority:        5
+  - Regex:           '^<(thrust|cub|cuda)/' # CCCL includes
+    Priority:        6
+  - Regex:           '^<(cooperative_groups|cuco|cuda|device_types|driver_types|math_constants|nvtx3)' # CUDA includes
+    Priority:        6
+  - Regex:           '^<.*\..*' # other system includes (e.g. with a '.')
+    Priority:        7
+  - Regex:           '^<[^.]+' # STL includes (no '.')
+    Priority:        8
 IndentCaseLabels: true
 IndentPPDirectives: None
 IndentWidth:     2

diff --git a/cpp/bench/common/ml_benchmark.hpp b/cpp/bench/common/ml_benchmark.hpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -16,13 +16,18 @@
 
 #pragma once
 
-#include <benchmark/benchmark.h>
-#include <cuda_runtime.h>
 #include <cuml/common/logger.hpp>
 #include <cuml/common/utils.hpp>
-#include <memory>
+
 #include <raft/util/cudart_utils.hpp>
+
 #include <rmm/mr/device/per_device_resource.hpp>
+
+#include <cuda_runtime.h>
+
+#include <benchmark/benchmark.h>
+
+#include <memory>
 #include <sstream>
 #include <string>
 #include <vector>

diff --git a/cpp/bench/sg/arima_loglikelihood.cu b/cpp/bench/sg/arima_loglikelihood.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -14,18 +14,20 @@
  * limitations under the License.
  */
 
-#include <thrust/execution_policy.h>
-#include <thrust/for_each.h>
-#include <thrust/iterator/counting_iterator.h>
+#include "benchmark.cuh"
 
 #include <cuml/tsa/arima_common.h>
 #include <cuml/tsa/batched_arima.hpp>
+
 #include <raft/core/handle.hpp>
 #include <raft/random/rng.cuh>
+#include <raft/util/cudart_utils.hpp>
+
 #include <rmm/device_uvector.hpp>
 
-#include "benchmark.cuh"
-#include <raft/util/cudart_utils.hpp>
+#include <thrust/execution_policy.h>
+#include <thrust/for_each.h>
+#include <thrust/iterator/counting_iterator.h>
 
 namespace ML {
 namespace Bench {

diff --git a/cpp/bench/sg/benchmark.cuh b/cpp/bench/sg/benchmark.cuh
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -19,12 +19,16 @@
 #include "../common/ml_benchmark.hpp"
 #include "dataset.cuh"
 #include "dataset_ts.cuh"
-#include <benchmark/benchmark.h>
-#include <cuda_runtime.h>
+
 #include <cuml/common/logger.hpp>
+
 #include <raft/core/handle.hpp>
 #include <raft/util/cudart_utils.hpp>
 
+#include <cuda_runtime.h>
+
+#include <benchmark/benchmark.h>
+
 namespace ML {
 namespace Bench {
 

diff --git a/cpp/bench/sg/dataset.cuh b/cpp/bench/sg/dataset.cuh
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -17,14 +17,16 @@
 #pragma once
 
 #include <cuml/datasets/make_blobs.hpp>
-#include <fstream>
-#include <iostream>
+
 #include <raft/core/handle.hpp>
 #include <raft/linalg/transpose.cuh>
 #include <raft/linalg/unary_op.cuh>
 #include <raft/random/make_regression.cuh>
 #include <raft/util/cuda_utils.cuh>
 #include <raft/util/cudart_utils.hpp>
+
+#include <fstream>
+#include <iostream>
 #include <sstream>
 #include <string>
 #include <vector>

diff --git a/cpp/bench/sg/dbscan.cu b/cpp/bench/sg/dbscan.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -14,9 +14,10 @@
  * limitations under the License.
  */
 
+#include "benchmark.cuh"
+
 #include <cuml/cluster/dbscan.hpp>
 
-#include "benchmark.cuh"
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/fil.cu b/cpp/bench/sg/fil.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -14,14 +14,16 @@
  * limitations under the License.
  */
 
-#include <cuml/fil/fil.h>
-
 #include "benchmark.cuh"
+
 #include <cuml/common/logger.hpp>
 #include <cuml/ensemble/randomforest.hpp>
+#include <cuml/fil/fil.h>
 #include <cuml/tree/algo_helper.h>
+
 #include <treelite/c_api.h>
 #include <treelite/tree.h>
+
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/filex.cu b/cpp/bench/sg/filex.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023, NVIDIA CORPORATION.
+ * Copyright (c) 2023-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -14,20 +14,22 @@
  * limitations under the License.
  */
 
+#include "benchmark.cuh"
+
+#include <cuml/common/logger.hpp>
+#include <cuml/ensemble/randomforest.hpp>
 #include <cuml/experimental/fil/detail/raft_proto/device_type.hpp>
 #include <cuml/experimental/fil/infer_kind.hpp>
 #include <cuml/experimental/fil/tree_layout.hpp>
 #include <cuml/experimental/fil/treelite_importer.hpp>
 #include <cuml/fil/fil.h>
-
-#include "benchmark.cuh"
-#include <chrono>
-#include <cstdint>
-#include <cuml/common/logger.hpp>
-#include <cuml/ensemble/randomforest.hpp>
 #include <cuml/tree/algo_helper.h>
+
 #include <treelite/c_api.h>
 #include <treelite/tree.h>
+
+#include <chrono>
+#include <cstdint>
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/kmeans.cu b/cpp/bench/sg/kmeans.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,10 +15,13 @@
  */
 
 #include "benchmark.cuh"
+
 #include <cuml/cluster/kmeans.hpp>
 #include <cuml/common/logger.hpp>
+
 #include <raft/distance/distance_types.hpp>
 #include <raft/random/rng_state.hpp>
+
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/linkage.cu b/cpp/bench/sg/linkage.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,10 +15,13 @@
  */
 
 #include "benchmark.cuh"
+
 #include <cuml/cluster/linkage.hpp>
 #include <cuml/common/logger.hpp>
+
 #include <raft/distance/distance_types.hpp>
 #include <raft/sparse/hierarchy/common.h>
+
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/rf_classifier.cu b/cpp/bench/sg/rf_classifier.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,8 +15,10 @@
  */
 
 #include "benchmark.cuh"
-#include <cmath>
+
 #include <cuml/ensemble/randomforest.hpp>
+
+#include <cmath>
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/rf_regressor.cu b/cpp/bench/sg/rf_regressor.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,8 +15,10 @@
  */
 
 #include "benchmark.cuh"
-#include <cmath>
+
 #include <cuml/ensemble/randomforest.hpp>
+
+#include <cmath>
 #include <utility>
 
 namespace ML {

diff --git a/cpp/bench/sg/svc.cu b/cpp/bench/sg/svc.cu
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,11 +15,14 @@
  */
 
 #include "benchmark.cuh"
-#include <cmath>
+
 #include <cuml/svm/svc.hpp>
 #include <cuml/svm/svm_model.h>
 #include <cuml/svm/svm_parameter.h>
+
 #include <raft/distance/kernels.cuh>
+
+#include <cmath>
 #include <sstream>
 #include <utility>