OpenMP is an easy way to play with multi-core C ++ programming. The wikipedia example doesn't actually make the processor more intensive, but you can replace 'cout' with some independent, long-lasting function.
Openmp
As for 64-bit, most of your productivity growth will come from several places.
Increased throughput, since all data elements are wider, the processor can process more data at any given clock cycle. Take a look at some of the Microsoft benchmarks for Exchange Server, they have now switched to 64-bit support only because the increase in throughput is incredible.
More registers, since the 64-bit architecture has a large number of registers for most function parameters, and the return value can be passed using registers.
In x86 ABI, with some calling conventions, one or two parameters can be passed through registers, and the rest must be pushed onto the stack. When using a generic calling convention such as cdecl, no parameter or return value is placed in the register. Since the stack is in main memory, this can be a great success.
joshperry
source share