MegaDrive performance tuning #8
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Significant performance boost gained by: 1. copying m68k core into md module, preventing virtual function call overhead 2. simplifying/optimizing conditional branches 3. disabling sega/mega cd support 4. helping the compiler to inline small functions with hints & moving some functions to header files
inline z80 core into the md apu class to avoid virtual function overhead
- Agressive optimisation/caching of vdp fields to reduce per-line or per-pixel calculations - Use const where possible to better allow the compiler to optimize calls
- apu and cpu only check for interrupts per-block, rather than per-instruction - cartridge is hard-coded to linear type, this will break Super Street Fighter II, but all other games should still work - m68k cpu clock speed can be customised (see higan/md/cpu/cpu.cpp) fix an issue preventing most common Sonic & Knuckles roms from working out-of-the-box
- Use templates within VDP to reduce per-pixel calculations/branches - Simplify APU interrupt handling, since MD only uses specific functionality here
- simplified apu interrupt handler (md doesn't use NMI or mode 2) - more agressive inlining
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is my preliminary work on performance tuning for the Megadrive core
On an iPhone 7, this brings the performance of Columns from 30-40fps (approx 19-20 ms per frame) to 59-61fps (approx 11-16ms).
On a desktop computer, with the frame limiter disabled, I have been able to hit 90-100fps.
Work has been submitted as several individual commits within this pull-request, each detailing the work that was done within the commit message. I highly recommend throughly reading those commit messages, but I will point to “part 4” specifically, as it contains a compile-time configurable option that can be used to fine tune emulated cpu clock speed.