Fixes about `test_sparse_sum_op.py`

[lawrence910426]

PR Category

Operator Mechanism

PR Types

Bug fixes

Description

1. sum_kernel.cu The size of out_cols_data is only x_dim0 * x_dim1. It is illegal to access memory after x_dim0 * x_dim1. To prevent such illegal access, the loop in SumCsr3DGradCudaKernel is splitted into two loops.

2. sum_grad_kernel.cu The length of x_crows_data is only x_dim0 * (x_dim1 + 1). Access to x_crows_data[x_dim0 * (x_dim1 + 1)] is in fact illegal. However, x_crows_data[x_dim0 * (x_dim1 + 1)] would be 0 to the alignment mechanism of StreamSafeAllocator.

Moreover, dx_values_data would never be filled when index = x_dim0 * (x_dim1 + 1) - 1. Therefore, the last iteration of the loop could be ignored.

[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]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
6 out of 7 committers have signed the CLA.

:white_check_mark: zlsh80826
:white_check_mark: jeng1220
:white_check_mark: Tom-Zheng
:white_check_mark: Wong4j
:white_check_mark: lawrence910426
:white_check_mark: eee4017
:x: Frank Lin (Engrg-Hardware 1)

---

Frank Lin (Engrg-Hardware 1) seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}