When FEX hits the optimal case that the destination isn't one of the
incoming sources (other than the incomingDest source) then we can
optimize out two moves per 128-bit lane.
Cuts 256-bit non-SVE gather loads from 50 instructions down to 46.
We can avoid a LOT of pointless work with some dedicated IR ops for specifically
overriding the round mode.
Small behaviour change here: we no longer reset FTZ. I think this is a bug fix?
But if it's not it's not hard to fix.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
This does a gather load three ways, SVE256, SVE128, and ASIMD.
This operation is a bit special since it it can't quite handle all
gather loadstores in the 256-bit case and requires the frontend to
decompose the operation in the case that the striding hits a mode that
SVE doesn't support!
The 128-bit case is a lot simpler since both support all the cases where
stride doesn't match. I find this to be a nice compromise while there
aren't any SVE256 products on the market.
In the 128-bit case there is an SVE path which is utilized if the passed
in stride supports what SVE understands, otherwise it falls back to an
ASIMD implementation which manually emulates everything that is
necessary.
This instruction is very explicitly doing basically exactly what AVX
gather instructions want, because it's complex enough that we don't want
to try and make this a generic solution.
to be consistent with the scalar _Andn opcode, which is specifically named _Andn
and not _Bic.
noticed while reviewing AVX patches
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Needed something inbetween the `InlineJITBlockHeader` and `avx_high` in
order to match alignment requirements of 16-byte for avx_high. Chose the
`DeferredSignalRefCount` because we hit it quite frequently and it is
basically the only 64-bit variable that we end up touching
significantly.
In the future the CPUState object is going to need to change its view of
the object depending on if the device supports SVE256 or not, but we
don't need to frontload the work right now. It'll become significantly
easier to support that path once the RCLSE pass gets deleted.
In quite a few locations we are mixing the case that SVE256 == AVX or
that AVX means the guest register size is 256-bit.
While this is true today, this is entanglement is going to change very
quickly and cause confusion in follow-up PRs.
Now we have SVE128, SVE256, and SVE2 HostFeatures to disambiguate the
different features which mean different things.
This PR keeps the alias that `SupportsAVX` = `SupportsSVE256 && SupportsSVE2`
but that alias is going to very quickly change its definition.
This currently doesn't do much but soon this will be very important to
ensure the data prefetcher of Cortex keeps the cachelines following this
variable in L1.
No instcountci changes yet, since nothing currently spills in instcountci. This
mitigates spilling later seen with #3703, and should help for certain
pathological blocks even without those changes (maybe we should try to get some
of those blocks in instcountci?).
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
slightly worse for compile time, slightly better output, honestly I'll take the
win because this is easier to reason about.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
I don't get the point, it should be handled by a combination of existing
passes/techniques just fine. no instcountci changes.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
No reason to have a separate pass for this, merging should be a bit faster since
it eliminates an IR walk.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
find-and-replace across the tree, excluding IR.h itself.
also excluded IRValidation because its treatment of blocks blows up and will be
reformed in the new IR anyway.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
deduplicate all the things.
functional change:
hit by sse4_1-pmaxuw.c.gcc-target-test-64.jit.gcc-target-64
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
This was causing us to generate invalid code in Darwinia, resulting in a
crash. With assertions enabled this would be picked up in the emitter.
Only implement AddShift optimizations for now because I don't want to do
the remaining optimizations in a bug fix PR.
Fixes Darwinia.
Accidentally we were swapping which sources were the base and which was
the one getting shifted. This wasn't super common so it usually didn't
matter.
Fixes one crash in Darwinia.
use a vec. block indices will be dense in the new IR. This is memory intensive
but seems faster in practice.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Flag DCE needs to do general DCE anyway to converge in one pass. So we can move
the special syscall/atomic logic over to flag DCE and then drop the second DCE
pass altogether. Now local dead code of both is eliminated in a single pass.
Flag DCE is carefully written to converge in a single iteration which makes this
scheme work.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
If both the destination and the flags are dead for an AddWithFlags, we need to
eliminate it in one pass. If we only replace without elimiating, we would need a
second DCE pass to eliminate. We want DCE to finish in one pass, so fix this.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Ryan Houdek