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
Interpreter: optimize NaN checks #2586
Conversation
LGTM |
double t = a * c; | ||
if (t != t) | ||
{ | ||
if (a != a) return a; | ||
if (b != b) return b; |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
Now that I understand this, LGTM :) 👍 |
NaNs always propagate, so we can get away with only checking for NaN inputs in the rare case that the result is NaN (as already done in Jit64::HandleNaNs()).
LGTM |
Interpreter: optimize NaN checks
FifoCI detected that this change impacts graphical rendering. Here are the behavior differences detected by the system:
automated-fifoci-reporter |
What is the performance difference? |
To not check all inputs for being NaNs within the interpreter. For general gameplay: none |
@Icekhaos Thanks for the praise, but please use this forum thread for that instead. In general, please remember that many contributors get a notification email for every single comment you post on GitHub. |
NaNs always propagate, so we can get away with only checking for NaN inputs in the rare case that the result is NaN (as already done in Jit64::HandleNaNs()).