We weren't checking if the post-index variants of these instructions
were using the correct post-offset. These support /only/ the correctly
sized post-index. The no-offset version is an entirely different set of
functions.
If ProfileStats aren't enabled then `Initialize` early returns, but some
of these values weren't being zero initialized which could result in
crashes.
Ensure all the values in StatAlloc are zero initialized so this doesn't
occur.
The argument loader was loading configuration from the arguments twice.
The use of the argument loader needs to preload the arguments before
being handed off to the config system. This way we can pull remaining
arguments that get passed to the guest application.
Due to this, `Load` was getting called twice, once in the constructor
and once in the Config system. This was causing the backend to allocate
twice as much memory since the second load appends the arguments to a
fextl::list internally.
Not really any functional change but it was causing some heartburn with
some changes I was working on.
3DNow Reciprocal estimations did not have enough accuracy. Tests were enabled
to check for accurate values of reciprocals.
* where needed, reciprocal accuracy was increased.
* 3DNow sqrt reciprocal fixed for negative values.
* New helper VFCopySign IR op added.
Fixes#4319.
If AFP.AH is supported then fmin/fmax behaves like the x86 min/max
instruction so we don't need to jump through any additional hoops.
Support this use case to save a few instructions when AFP is supported.
We already have this mask generated, and because sha instructions
typically don't exist in a vacuum it is actually beneficial to cache the
mask and use a single tbl instruction per shuffle.
OpenSSL has 12 sha1 instructions in their hot loop as an example, so
this would be a fairly good reduction in that loop. Sadly we don't have
it in instcountci, instead having their sha256 hotloop instead (Which
currently doesn't have sha256rnds2 optimized).
Even in a vacuum this is technically 1 instruction savings for each
instruction which is nice.
```diff
"sha1rnds4 xmm0, xmm1, 10b": {
- "ExpectedInstructionCount": 55,
+ "ExpectedInstructionCount": 10,
```
So I spent a few hours glaring at this instruction. Then spent a few
more glaring in to the sunset and then found the optimization.
Saw these while scanning around. Funnily it makes it look like libnss is
worse off because there are multiple instructions using the same table
lookup to swizzle. So one instruction turns in to two.
We don't have a way to choose one path or the other, so it's usually
better to go the route that the instruction in a vacuum is improved, so
on average it is also improved.
Only saves a handful of instructions, but still an improvement.
```
"sha1msg2 xmm0, xmm1": {
- "ExpectedInstructionCount": 11,
+ "ExpectedInstructionCount": 7,
```
I kept finding I needed `./fex_shm_stats_read `FEXpidof Celeste.exe``
but FEXpidof wasn't ever wired up to find FEX in the face of emulating
wine and arm64 wine.
This adds two new features basically:
- If x86 wine is being emulated, then walk the argument list just like
our config options to see what the program executable name is.
- If it is arm64 wine using FEX, then we need to detect that, and walk
the arguments in a similar fashion
The detection is the main thing here in that the only way to detect FEX
for arm64 wine is checking the applications mapped files and seeing if
it is mapping arm64ecfex.dll or wow64fex.dll.
x86 Wine is easy since that's just skipping the wine{64,}{-preloader,}
arguments to get to the executable name.
Ryan Houdek