lupesko commented on a change in pull request #11780: fix flaky test
test_operator_gpu.test_countsketch
URL: https://github.com/apache/incubator-mxnet/pull/11780#discussion_r203254416
##########
File path: src/operator/contrib/count_sketch.cu
##########
@@ -129,8 +129,8 @@ inline void CountSketchForward(const Tensor<gpu, 2, DType>
&out,
nthreads, out_ptr+bstart*out_dim, h_ptr,
s_ptr, in_ptr+bstart*in_dim, batchlen,
in_dim, out_dim);
- MSHADOW_CUDA_POST_KERNEL_CHECK(sketch_forward_kernel);
- // cudaThreadSynchronize();
+ cudaError_t err = cudaDeviceSynchronize();
+ CHECK_EQ(err, cudaSuccess) << "Error occured! CUDA: " <<
cudaGetErrorString(err);
Review comment:
@haojin2 can you note this here now that github is up, so others can see the
answer to the question?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
