Function std::webgpu_sum_f32
int webgpu_sum_f32([]const float a, []float out)out[0] = sum(a[0..n)): a reduction per workgroup, added atomically.
int webgpu_sum_f32([]const float a, []float out)out[0] = sum(a[0..n)): a reduction per workgroup, added atomically.