Hello my name is Daniel Hanrahan. Do you think my games should have optional calls to assembly functions for certain CPUs and GPUs in order to reach maximum possible performance and use parts/functions of the CPUs and GPUs that are not standard, but it’s use for them would for tasks that is not perfect for the standard parts of CPUs and GPUs if possible, for example: instead of using the standard parts/functions of the z80 for the randomization you use the refresh register instead. Let me be clear my games have good performance.
Link to my games: https://daniel-hanrahan-tools-and-games.github.io/
Thank you, but are you sure because I know linux does something similar to make sure it is at maximum performance.
On modern CPUs it doesn’t matter that much. And any optimization would have to be updated for each CPU type (Zen/4, Alder lake, etc.) Modern CPUs have insane out of order execution that makes compiler generated code nearly as fast as the most optimized handwritten ones. On older CPUs you’d see more of a performance bump.
Thanks for the information.
99% of the time, memory is the bottleneck. It’s why DMA is so huge of a feature.