PPU: Fix VMAXFP, VMINFP NaN handling #8659
Merged
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
elad335
force-pushed
the
fix-min-max-fp
branch
4 times, most recently
from
bb376ec to
4c5ace4
Compare
elad335
changed the title
|
I will add interpreters fix as well. |
elad335
force-pushed
the
fix-min-max-fp
branch
2 times, most recently
from
b2da0e8 to
130534e
Compare
|
Makes the testcase https://github.com/elad335/ps3autotests/blob/master/tests/cpu/ppu_vpu/ppu_vpu.expected match rpcs3 output for these instructions on interpreters. |
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Outdated suggestions cannot be applied.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.
Using ordered (and even unordered) floating comparison to determine MIN/MAX floating pointing value results in a bug where the VMAXFP/VMINFP instructions on realhw always select NaN operand as the result if either is a NaN (with the ordering of VA then VB) but on master only the "greater/lower" value is selected making NaN not always return as the result when either of the operands is a NaN.
The correct behaviour is the opposite as x86's instructions MAXPS, MINPS (as std::fmax, std::fmin). So use the opposite operand from the result of the opposite instruction.
Misc: Improve cpu_translator::fre() and cpu_translator::frsqe() to accept unevaluated expressions, evaluate them in-place.