Anshuman Goswami

Can a pool memory resource be used to avoid cudaMalloc on each async call?

4

In my test, I have two calls to `thrust::async::sort` as below - ``` auto e1 = thrust::async::sort(exec_policy(stream)->on(stream), keys.begin(), keys.end()); auto e2 = thrust::async::sort(exec_policy(stream)->on(stream), keys.begin(), keys.end()); ``` I am using a...

Is --expt-extended-lambda and --expt-relaxed-constexpr not supported?

5

From the [nvrtc docs](https://docs.nvidia.com/cuda/nvrtc/index.html#group__options), it seems that the above options are *not* supported. Can you please confirm? @maddyscientist

Compilation error with histogram test program

7

I am trying to compile the following CUB test program - ``` #include int main() { uint32_t* d_samples; uint8_t* d_histogram; uint8_t* d_levels; size_t temp_storage_bytes; int num_levels; size_t num_samples; cub::DeviceHistogram::HistogramRange(nullptr, temp_storage_bytes,...

mallocMC managing two or more contexts

7

@slizzered @ax3l Thank you for developing this library and providing the sources :+1: I was thinking of using it to run two or more applications that allocate memory on the...