warpAggregatedAtomicsCG --std=c++11 cudaMemset cudaFree cudaDeviceGetAttribute cudaMalloc cudaMemcpy ./ ../ ../../../Common Cooperative Groups Atomic Intrinsics GPGPU Cooperative Groups Atomic CPP11 true warpAggregatedAtomicsCG.cu 1:CUDA Advanced Topics sm35 sm37 sm50 sm52 sm53 sm60 sm61 sm70 sm72 sm75 sm80 sm86 sm87 x86_64 linux ppc64le linux x86_64 macosx windows7 arm aarch64 sbsa 3.5 Warp Aggregated Atomics using Cooperative Groups