[DCU] new features

[yuguo-Jack]

PR Category

Performance Optimization

PR Types

New features

Description

surpport multiclass_nms3 op for DCU（单测通过） surpport miopen bn for DCU when FLAGS_cudnn_batchnorm_spatial_persistent is 1（test_batch_norm_op/test_batch_norm_op_v2单测通过） surpport gemm fp16 compute type for DCU when FLAGS_gemm_use_half_precision_compute_type is 1

[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.

[paddle-ci-bot[bot]]

Sorry to inform you that 3d36c6f's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.

[paddle-ci-bot[bot]]

Sorry to inform you that 5326497's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.