-
Notifications
You must be signed in to change notification settings - Fork 47
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
od: use -O3 #114
base: opendingux
Are you sure you want to change the base?
od: use -O3 #114
Conversation
Here are the results of my test. PS: Dingoonity was closed recently, where else can I get more information about OpenDingux? |
So I guess we should go with #112, which has both |
I'm guessing you're on the Discord already but in case you're not: https://discord.gg/t7GeHScr |
Rebased, so now the build in this PR has both |
@pcercuei Let's merge this? |
Actually, shall we enable this for all systems, not just the rs90? |
Improves performance in emulators, e.g. Gambatte on the RS90. Signed-off-by: Gleb Mazovetskiy <[email protected]>
Now enabled on all systems, similar to #115 |
Can we have more tests with various games / apps, and emulators that don't use dynarecs (e.g. PocketSNES)? |
This doesn't change the compilation flags for emulators nor the kernel, just the buildroot packages. The improvement likely comes from SDL. So I'm guessing SDL blitting functions get more optimized or something like that. I don't have 2 devices to run side-by-side, if someone does please do test! 🙏 |
I haven't been able to measure any meaningful difference between just -fipa-pta and -fipa-pta + -O3, neither on the rs90 nor a rg350m It's possible the difference seen was unrelated to -O3, it's after all rather doubtful that it would introduce a dramatic improvement at blitting, that's not generally how things work (it barely does anything, or even worsens emulators perfs, so I doubt OS itself would have a clear benefit personnally) |
No description provided.