mapa

• PTX ISA: mapa

This instruction can currently not be implemented by libcu++. The instruction can be accessed through the cooperative groups cluster_group API:

Usage:

#include <cooperative_groups.h>

__cluster_dims__(2)
__global__ void kernel() {
    __shared__ int x;
    x = 1;
    namespace cg = cooperative_groups;
    cg::cluster_group cluster = cg::this_cluster();

    cluster.sync();

    // Get address of remote shared memory value:
    unsigned int other_block_rank = cluster.block_rank() ^ 1;
    int * remote_x = cluster.map_shared_rank(&bar, other_block_rank);

    // Write to remote value:
    *remote_x = 2;
}