I've just installed 2 GTX 1080ti on Threadripper 1950x. And hope these two cards can communicate with unified memory. However, if I run the P2P benchmarks provided by Nvidia's sample (such as simpleP2P, p2pBandwidthLatencyTest), they crash. The cause should be caused by the following function call:
cudaMemcpy(g1, g0, buf_size, cudaMemcpyDefault)
where g0 and g1 are defined as:
float *g0; checkCudaErrors(cudaMalloc(&g0, buf_size)); float *g1; checkCudaErrors(cudaMalloc(&g1, buf_size));
I've also enabled AMD-V and IOMMU in UEFI options. But it still does not work.
Hope to get your help. Thanks a lot.