[Feature] Add MLU support for Sparse Convolution op (open-mmlab#2589)

* [Feature] Add sparse convolution MLU API * [Feature] update cpp code style * end-of-file * delete libext.a * code style * update ops.md --------- Co-authored-by: budefei <budefei@cambricon.com>
fwenguang · Oct 24, 2023 · ba7e8f1 · ba7e8f1
1 parent 770fc8c
commit ba7e8f1
Show file tree

Hide file tree

Showing 7 changed files with 508 additions and 24 deletions.
diff --git a/docs/en/understand_mmcv/ops.md b/docs/en/understand_mmcv/ops.md
@@ -52,7 +52,7 @@ We implement common ops used in detection, segmentation, etc.
 | SigmoidFocalLoss             |     | √    | √   |     | √      |
 | SoftmaxFocalLoss             |     | √    |     |     | √      |
 | SoftNMS                      |     | √    |     |     |        |
-| Sparse Convolution           |     | √    |     |     |        |
+| Sparse Convolution           |     | √    | √   |     |        |
 | Synchronized BatchNorm       |     | √    |     |     |        |
 | ThreeInterpolate             |     | √    |     |     |        |
 | ThreeNN                      |     | √    | √   |     |        |

diff --git a/docs/zh_cn/understand_mmcv/ops.md b/docs/zh_cn/understand_mmcv/ops.md
@@ -52,7 +52,7 @@ MMCV 提供了检测、分割等任务中常用的算子
 | SigmoidFocalLoss             |     | √    | √   |     | √      |
 | SoftmaxFocalLoss             |     | √    |     |     | √      |
 | SoftNMS                      |     | √    |     |     |        |
-| Sparse Convolution           |     | √    |     |     |        |
+| Sparse Convolution           |     | √    | √   |     |        |
 | Synchronized BatchNorm       |     | √    |     |     |        |
 | ThreeInterpolate             |     | √    |     |     |        |
 | ThreeNN                      |     | √    | √   |     |        |

diff --git a/mmcv/ops/csrc/pytorch/mlu/mlu_common_helper.h b/mmcv/ops/csrc/pytorch/mlu/mlu_common_helper.h
@@ -18,8 +18,8 @@
 #include "pytorch_device_registry.hpp"
 
 #define MLUOP_MAJOR 0
-#define MLUOP_MINOR 4
-#define MLUOP_PATCHLEVEL 1
+#define MLUOP_MINOR 5
+#define MLUOP_PATCHLEVEL 302
 
 mluOpDataType_t getMluOpDataType(const caffe2::TypeMeta& data_type);
 mluOpTensorLayout_t getMluOpSuggestLayout(const at::Tensor& input);