Ethan comments

Results 3 comments of


                                            Ethan

reduce failed to synchronize: cudaErrorIllegalAddress: an illegal memory access was encountered

target:204761[pts] source:59051[pts] --- ndt_cuda (P2D) --- terminate called after throwing an instance of 'thrust::system::system_error' what(): reduce failed to synchronize: cudaErrorIllegalAddress: an illegal memory access was encountered Aborted (core dumped) Is...

Cuda filter demo, cuda-pcl is worse than pcl if MemCpyTime(4.6285ms) is considered.

> 大家好， > > 我添加了时间跨度计算来测量输入和输出内存分配所消耗的时间。 > > 在每个 cuda 函数调用之前都需要这种内存分配。 > > 代码如下。 > > ```c++ > t1 = std::chrono::steady_clock::now(); > cudaMallocManaged(&input, sizeof(float) * 4 * nCount, cudaMemAttachHost); > cudaStreamAttachMemAsync...

Cuda filter demo, cuda-pcl is worse than pcl if MemCpyTime(4.6285ms) is considered.

> > 请问你的测试机器是？ > > x86 pc with > > * qudro-p4000 gpu > * 3.2GHz 12 core cpu 我使用该代码在jetson xavier nx(emmc-16G)上运行cuNDT，最大功耗下，使用的test_P.pcd和test_Q.pcd，跑了100次，平均耗时在110.5ms左右，jetson xavier AGX的FP32浮点性能是jetson xavier nx的1.6倍，但是耗时不是，请问性能对吗？您那边有计划发布其他机器的jetson性能比较吗？期待您的回复，谢谢。