Bugfix/unique consecutive

[LCStayingdullCircuit]

trafficstars

PR Category

Operator Mechanism

PR Types

Bug fixes

Description

修复了 paddle.unique_consecutive 大 Tensor 下的报错问题。

• 算子简介 paddle.unique_consecutive 主要功能是去除张量中的连续重复元素，同时可以根据传入的 flag 值返回不同的元组。

• 修改点 问题定位在 unique_consecutive_functor.h 中的以下代码段。怀疑是 auto 自动判定类型导致溢出，修改为 int64_t 后可以成功编译：

  for (auto i = 0; i < outer_nums; i++) {
    auto input_start_offset = i * input_width;
    auto output_start_offset = i * output_width;
  
    for (auto j = 0; j < index_size; j++) {
      IndexT index_value = index_vec[j];
      if (index_value < 0) {
        index_value += input_dim[dim];
      }
      for (auto k = 0; k < slice_size; k++) {
        out_vec[output_start_offset + j * slice_size + k] =
            input_vec[input_start_offset + index_value * slice_size + k];
      }
    }
  }
  

• 性能变化 性能下降了 2% 左右。

[paddle-bot[bot]]

你的PR提交成功，感谢你对开源项目的贡献! 请关注后续CI自动化测试结果，详情请参考Paddle-CI手册。 Your PR has been submitted. Thanks for your contribution! Please wait for the result of CI firstly. See Paddle CI Manual for details.

[CLAassistant]

All committers have signed the CLA.

[LCStayingdullCircuit]

/re-run all-failed

[paddle-ci-bot[bot]]

Sorry to inform you that a7504f8's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.