Xuhao Chen comments

Results 7 comments of


                                            Xuhao Chen

BlockRadixSort needs overloads that take the problem size and correctly sets the padding value for unused inputs

> If that suits your needs, we could expose this algorithm as a block-scope facility (something like `cub::BlockSort`). this will be very much appreciated. Currently the agent implementation is a...

BlockRadixSort needs overloads that take the problem size and correctly sets the padding value for unused inputs

> @chenxuhao, I've attached a fixed version of your routine [here](https://github.com/NVIDIA/cub/issues/327#issuecomment-1250816657). Currently, we are not ready to expose it though. thanks a lot!

BlockRadixSort needs overloads that take the problem size and correctly sets the padding value for unused inputs

> @chenxuhao, I've attached a fixed version of your routine [here](https://github.com/NVIDIA/cub/issues/327#issuecomment-1250816657). Currently, we are not ready to expose it though. Also, I wonder if it is possible to create a...

BlockRadixSort needs overloads that take the problem size and correctly sets the padding value for unused inputs

> Hello, @chenxuhao! Does `cub::WarpMergeSort` work for you? I don't think you need and agent for that. Agent's are used to share implementation of device-scope algorithms in CUB. > Thanks...

Issue with GPU code

Have you set this flag for your GPU? CUDA_ARCH := -gencode arch=compute_70,code=sm_70

Issue with GPU code

> Yes, I set this flag for my GPU but I still have the same problem. which GPU do you use? I don't see this problem with a V100.

undefined reference to `BCSolver(Graph&, int, float*)'

> Could you please update the implementations when you can reproduce the following error ? Thanks. > > ``` > make bc_ocl_base > g++ -Wall -fopenmp -O3 -std=c++11 -I../../include -I...