<div dir="ltr">FYI, a commit is up for the inline asm change: <a href="https://reviews.llvm.org/D114335">https://reviews.llvm.org/D114335</a>.</div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sun, Nov 14, 2021 at 11:16 PM Nicolas Vasilache <<a href="mailto:ntv@google.com">ntv@google.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr">Not yet, the InlineAsmOp in MLIR is still generally unused.<div>It has been used a bit in the IREE project though (<a href="https://github.com/google/iree/blob/49a81c60329437e64791ee1abd09d47fe1cde205/iree/compiler/Codegen/LLVMCPU/VectorContractToAArch64InlineAsmOp.cpp#L103" target="_blank">https://github.com/google/iree/blob/49a81c60329437e64791ee1abd09d47fe1cde205/iree/compiler/Codegen/LLVMCPU/VectorContractToAArch64InlineAsmOp.cpp#L103</a>).</div><div><br></div><div>I should be be indeed able to intersperse my lowering (<a href="https://github.com/llvm/llvm-project/blob/main/mlir/lib/Dialect/X86Vector/Transforms/AVXTranspose.cpp#L124" target="_blank">https://github.com/llvm/llvm-project/blob/main/mlir/lib/Dialect/X86Vector/Transforms/AVXTranspose.cpp#L124</a>) with some InlineAsmOp uses.</div><div>I'll report back when I have something.</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sun, Nov 14, 2021 at 4:53 PM Simon Pilgrim <<a href="mailto:llvm-dev@redking.me.uk" target="_blank">llvm-dev@redking.me.uk</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div>
<p>Nicolas - have you investigated just using inline asm instead?<br>
</p>
<div>On 11/11/2021 08:34, Wang, Pengfei via
llvm-dev wrote:<br>
</div>
<blockquote type="cite">
<div>
<p class="MsoNormal">>As I am very new to this part of LLVM,
I am not sure what is feasible or not. Would it be
envisionnable to either:<u></u><u></u></p>
<p class="MsoNormal">>1. have a way to inject some numeric
cost to influence the value of some resulting combinations?<u></u><u></u></p>
<p class="MsoNormal">>2. revive some form of intrinsic and
guarantee that the instruction would be generated?<u></u><u></u></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)">I think a
feasible way is to add a new tuningXXX feature for given
targets and do something different with the flag in the
combine.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)">1) seems
overengineering and 2) seems overkilled for potential
opportunities by the combine.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)">Thanks<u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)">Phoebe<u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:rgb(31,73,125)"><u></u> <u></u></span></p>
<div style="border-right:none;border-bottom:none;border-left:none;border-top:1pt solid rgb(225,225,225);padding:3pt 0in 0in">
<p class="MsoNormal"><b>From:</b> llvm-dev
<a href="mailto:llvm-dev-bounces@lists.llvm.org" target="_blank"><llvm-dev-bounces@lists.llvm.org></a> <b>On Behalf Of
</b>Nicolas Vasilache via llvm-dev<br>
<b>Sent:</b> Wednesday, November 10, 2021 5:46 PM<br>
<b>To:</b> Diego Caballero <a href="mailto:diegocaballero@google.com" target="_blank"><diegocaballero@google.com></a><br>
<b>Cc:</b> <a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br>
<b>Subject:</b> Re: [llvm-dev] Understanding and controlling
some of the AVX shuffle emission paths<u></u><u></u></p>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<div>
<p class="MsoNormal">On Wed, Nov 10, 2021 at 10:30 AM
Diego Caballero <<a href="mailto:diegocaballero@google.com" target="_blank">diegocaballero@google.com</a>>
wrote:<u></u><u></u></p>
</div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<div>
<p class="MsoNormal"><a href="mailto:ntv@google.com" target="_blank">+Nicolas
Vasilache</a> :)<u></u><u></u></p>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Thanks Diego, email is hard, I could
not find ways to inject myself into my own discussion...<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<div>
<p class="MsoNormal">On Tue, Nov 9, 2021 at 10:32 PM
Simon Pilgrim via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>>
wrote:<u></u><u></u></p>
</div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal">On 09/11/2021 20:44, Simon
Pilgrim wrote:<br>
<br>
> On 09/11/2021 08:57, Nicolas Vasilache via
llvm-dev wrote:<br>
>> Hi everyone,<br>
>><br>
>> I am experimenting with LLVM lowering,
intrinsics and shufflevector <br>
>> in general.<br>
>><br>
>> Here is an IR that I produce with the
objective of emitting some <br>
>> vblendps instructions: <br>
>> <a href="https://gist.github.com/nicolasvasilache/0fe30c83cbfe5b4776ec9f0ee465611a" target="_blank">
https://gist.github.com/nicolasvasilache/0fe30c83cbfe5b4776ec9f0ee465611a</a>.
<br>
>><br>
> From what I can see, the original IR code was
(effectively):<br>
><br>
> 8 x UNPCKLPS/UNPCKHPS<br>
> 4 x SHUFPS<br>
> 8 x BLENDPS<br>
> 4 x INSERTF128<br>
> 4 x PERM2F128<br>
><br>
>> I compile this further with<br>
>><br>
>> clang -x ir -emit-llvm -S -mcpu=haswell -O3
-o - | llc -O3 <br>
>> -mcpu=haswell - -o -<br>
>><br>
>> to obtain:<br>
>><br>
>> <a href="https://gist.github.com/nicolasvasilache/2c773b86fcda01cc28711828a0a9ce0a" target="_blank">
https://gist.github.com/nicolasvasilache/2c773b86fcda01cc28711828a0a9ce0a</a>
<br>
>><br>
><br>
> and after the x86 shuffle combines:<br>
><br>
> 8 x UNPCKLPS/UNPCKHPS<br>
> 8 x UNPCKLPD/UNPCKHPD<br>
> 4 x INSERTF128<br>
> 4 x PERM2F128<br>
><br>
> Starting from each BLENDPS, they've combined
with the SHUFPS to create <br>
> the UNPCK*PD nodes. We nearly always benefit
from folding shuffle <br>
> chains to reduce total instruction counts, even
if some inner nodes <br>
> have multiple uses (like the SHUFPS), and I'd
hate to lose that.<br>
><br>
>> At this point, I would expect to see some
vblendps instructions <br>
>> generated for the pieces of IR that produce
%48/%49 %51/%52 %54/%55 <br>
>> and %57/%58 to reduce pressure on port 5
(vblendps can also go on <br>
>> ports 0 and 1). However the expected
instruction does not get <br>
>> generated and llvm-mca continues to show me
high port 5 contention.<br>
>><br>
>> Could people suggest some steps / commands
to help better understand <br>
>> why my expectation is not met and whether I
can do something to make <br>
>> the compiler generate what I want? Thanks
in advance!<br>
> So on Haswell, we've gained 4 extra Port5-only
shuffles but removed <br>
> the 8 Port015 blends.<br>
><br>
> We have very little arch-specific shuffle
combines, just the <br>
> fast-variable-shuffle tuning flags to avoid
unnecessary shuffle mask <br>
> loads, the shuffle combines just aims for the
reduction in simple <br>
> target shuffle nodes. And tbh I'm reluctant to
add to this as shuffle <br>
> combining is complex already.<br>
><br>
> We should be preferring to lower/combine to
BLENDPS in more <br>
> circumstances (its commutable and never slower
than any other target <br>
> shuffle, although demanded elts can do less
with 'undef' elements), <br>
> but that won't help us here.<br>
><br>
> So far I've failed to find a BLEND-based 8x8
transpose pattern that <br>
> the shuffle combiner doesn't manage to combine
back to the <br>
> 8xUNPCK/SHUFPS ops :(<u></u><u></u></p>
</blockquote>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">If you are referring to this specific
code, yes same for me.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">If you are thinking about the general
8x8 transpose problem, I have a version with
vector<4xf32> loads that ends up using blends; as
expected, the port 5 pressure reduction helps and both
llvm-mca and runtime agree that this is 20-30% faster.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal"><br>
The only thing I can think of is you might want to
see if you can <br>
reorder the INSERTF128/PERM2F128 shuffles in between
the UNPACK*PS and <br>
the SHUFPS/BLENDPS:<br>
<br>
8 x UNPCKLPS/UNPCKHPS<br>
4 x INSERTF128<br>
4 x PERM2F128<br>
4 x SHUFPS<br>
8 x BLENDPS<br>
<br>
Splitting the per-lane shuffles with the
subvector-shuffles could help <br>
stop the shuffle combiner.<u></u><u></u></p>
</blockquote>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Right, I tried different variations
here but invariably getting the same result.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">The vector<4xf32> based version
is something that I also want to target for a bunch of
orthogonal reasons.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">I'll note that my use case is MLIR
codegen with explicit vectors and intrinsics -> LLVM
so I have quite some flexibility.<u></u><u></u></p>
</div>
<p class="MsoNormal">But it feels unnatural in the compiler
flow to have to branch off at a significant higher-level
of abstraction to sidestep concerns related to X86
microarchitecture details.<u></u><u></u></p>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">As I am very new to this part of
LLVM, I am not sure what is feasible or not. Would it be
envisionnable to either:<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">1. have a way to inject some numeric
cost to influence the value of some resulting
combinations?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">2. revive some form of intrinsic and
guarantee that the instruction would be generated?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">I realize point 2. is contrary to the
evolution of LLVM as these intrinsics were removed ca.
2015 in favor of the combiner-based approach.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">Still it seems that `we have very
little arch-specific shuffle combines` could be the
signal that such intrinsics are needed?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<div>
<blockquote style="border-top:none;border-right:none;border-bottom:none;border-left:1pt solid rgb(204,204,204);padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal"><br>
>> I have verified independently that in
isolation, a single such <br>
>> shuffle creates a vblendps. I see them
being recombined in the <br>
>> produced assembly and I am looking for
experimenting with avoiding <br>
>> that vshufps + vblendps + vblendps get
recombined into vunpckxxx + <br>
>> vunpckxxx instructions.<br>
>><br>
>> -- <br>
_______________________________________________<br>
LLVM Developers mailing list<br>
<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br>
<a href="https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" target="_blank">https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a><u></u><u></u></p>
</blockquote>
</div>
</blockquote>
</div>
<p class="MsoNormal"><br clear="all">
<u></u><u></u></p>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<p class="MsoNormal">-- <u></u><u></u></p>
<div>
<div>
<p class="MsoNormal">N<u></u><u></u></p>
</div>
</div>
</div>
</div>
<br>
<fieldset></fieldset>
<pre>_______________________________________________
LLVM Developers mailing list
<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>
<a href="https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" target="_blank">https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a>
</pre>
</blockquote>
</div>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr"><div dir="ltr">N</div></div>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail_signature"><div dir="ltr">N</div></div>