#pragma once

// CUDA translation of stage 01: one work item is one seed, its positions are serial.
__global__ void seedKernel(DeviceArgs a, show::Hit* hits, unsigned long long* count) {
    const uint64_t stride=uint64_t(gridDim.x)*blockDim.x;
    for(uint64_t s=uint64_t(blockIdx.x)*blockDim.x+threadIdx.x;s<a.seeds;s+=stride) {
        for(uint64_t xi=0;xi<a.width;++xi) for(uint64_t zi=0;zi<a.height;++zi) {
            const int32_t x=int32_t(int64_t(a.x0)+int64_t(xi));
            const int32_t z=int32_t(int64_t(a.z0)+int64_t(zi));
            if(show::solid<2>(a.seed+s,x,z,a.n)) emit(a,hits,count,a.seed+s,x,z);
        }
    }
}