Hardware Sharing between function calls on Intel FPGA OpenCL SDK
I am trying to compile a single work item kernel so that each function call within a scope uses the same hardware. Only information about this I could find was on Programming Guide, in chapter about limitations of RTL modules: "Every function call that corresponds to RTL module instantiation is completely independent of other instantiations. There is no hardware sharing." This implies that other (non RTL module) functions would have hardware sharing. When I check the area usage report generated by aoc I can see that not each step of a function call increases resource usage. So I guess there is already hardware sharing to some extent. But what I want to do is to keep extra hardware generation for each function call at zero.