this gets deleted by an upcoming opt pass, but we shouldn't be depending on
the opt pass for it!
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Instead of keeping the vlaue as a string array in the MetaLayer, convert
the value to its final type once.
Improves performance in some hotpaths that were doing config based
string conversion in a relatively high frequency.
ZF needs to be preserved.
the new code is the same instr count on flagm although probably an extra uop.
the inst count regression is on flagm, but we can't tolerate broken behaviour.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Turn this into stp to save a move in a /ton/ of AVX-128 code. It's pretty
annoying to optimize this at the dispatcher level because of the SRA cache, so
doing it in the ConstProp is a nice compromise solution.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
This is embarassing. We were throwing away performance by failing to
use the softfloat library's inline helpers.
Turns out we needed to define `INLINE` to something in order for them to
work.
Feels bad.
Somehow I had completely missed this and recent reciprocal tests have
exposed it as a problem. When AFP is supported but not RPRES then we
were hitting this code path.
We were failing to insert in to the destination correctly, which because
the reciprocal is calculated using fdiv using a synthesized constant,
this would just zero the remaining portion of the register.
When the shift size is exactly 16bytes, then it turns in to a move.
If the shift size is above 16-bytes then synthesize the zero register in
the OpcodeDispatcher, so the backend doesn't synthesize and not cache.
This was only wired up for 256-bit SVE and wasn't ever hit for 128-bit
SVE. Ensure it works with 128-bit SVE, so mulvl needs to know when
128-bit is used. Then wire it up for vmaskmovps/pd. This saves one
instruction per operation.
Fixes#3791.
With the previous fixes in place, we can now stop burning a fextl::list
in every single config option. This list is only required for strarray
options so reserve it for those entirely.
We also don't need to save the config option enum for each, so these
actually go from ~32 bytes per object down to their base type for most
everything.
Paulo Matos