llvm dev - Jan 2019 - Reducing the number of ptrtoint/inttoptrs that are generated by LLVM

On Mon, Jan 14, 2019 at 9:36 AM Chandler Carruth via llvm-dev <
llvm-dev at lists.llvm.org> wrote:
> While I'm very interested in the end result here, I have some questions
> that don't seem well answered yet around pointer subtraction...
>
> First and foremost - how do you address correctness issues here? Because
> the subtraction `A - B` can escape/capture more things. Specifically, if
> one of `A` or `B` is escaped/captured, the subtraction can be used to
> escape or capture the other pointer.
>
Isn't escaping supposed to work at the "address ranges" level and
not at
the pointer value?
I mean that if `A` or `B` is escaped/captured, then any pointer that is
associated to the same memory range should be considered as "escaped",
and
thus the subtraction does not seem to leak anything more to me.

-- 
Mehdi



> So *some* of the conservative treatment is necessary. What is the plan to
> update all the analyses to remain correct? What correctness testing have
> you done?
>
> Second - an intrinsic seems a poor fit here given the significance of this
> operation. We have an instruction that covers most pointer arithmetic
> (`getelementptr`), and I can imagine growing pointer subtraction, but it
> seems like it should be an instruction if we're going to have it. Based
on
> the above, we will need to use it very often in analysis.
>
>
> Regarding the instcombine, it should be very easy to keep loads and stores
> of pointers as pointer typed in instcombine. Likely just a missing case in
> the code I added/touched there.
>
> On Mon, Jan 14, 2019 at 3:23 AM Juneyoung Lee via llvm-dev <
> llvm-dev at lists.llvm.org> wrote:
>
>> Hello all,
>>
>> This is a proposal for reducing # of ptrtoint/inttoptr casts which are
not
>> written by programmers but rather generated by LLVM passes.
>> Currently the majority of ptrtoint/inttoptr casts are generated by
LLVM;
>> when compiling SPEC 2017 with LLVM r348082 (Dec 2 2018) with -O3,
>> the output IR contains 22,771 inttoptr instructions. However, when
>> compiling it with -O0, there are only 1048 inttoptrs, meaning that
95.4%
>> of them are generated by LLVM passes.
>>
>> This trend is similar in ptrtoint instruction as well. When compiling
>> SPEC 2017
>> with -O0, there are 23,208 ptrtoint instructions, but among them 22,016
>> (94.8%)
>> are generated by Clang frontend to represent pointer subtraction.
>> They aren't effectively optimized out because there are even more
>> ptrtoints (31,721) after -O3.
>> This is bad for performance because existence of ptrtoint makes
analysis
>> return conservative
>> result as a pointer can be escaped through the cast.
>> Memory accesses to a pointer came from inttoptr is assumed
>> to possibly access anywhere, therefore it may block
>> store-to-load forwarding, merging two same loads, etc.
>>
>> I believe this can be addressed by applying two patches - first one is
>> representing pointer subtraction with a dedicated intrinsic function,
>> llvm.psub, and second one is disabling InstCombine transformation
>>
>>     %q = load i8*, i8** %p1
>>     store i8* %q, i8** %p2
>> =>
>>   %1 = bitcast i8** %p1 to i64*
>>   %q1 = load i64, i64* %1, align 8
>>   %2 = bitcast i8** %p2 to i64*
>>   store i64 %q1, i64* %2, align 8
>>
>> This transformation can introduce inttoptrs later if loads are followed
(
>> https://godbolt.org/z/wsZ3II ). Both are discussed in
>> https://bugs.llvm.org/show_bug.cgi?id=39846 as well.
>> After llvm.psub is used & this transformation is disabled, # of
inttoptrs
>> decreases from 22,771 to 1,565 (6.9%), and # of ptrtoints decreases
from
>> 31,721 to 7,772 (24.5%).
>>
>> I'll introduce llvm.psub patch first.
>>
>>
>> --- Adding llvm.psub ---
>>
>> By defining pointer subtraction intrinsic, we can get performance gain
>> because it gives more undefined behavior than just subtracting two
>> ptrtoints.
>>
>> Patch https://reviews.llvm.org/D56598 adds llvm.psub(p1,p2) intrinsic
>> function, which subtracts two pointers and returns the difference. Its
>> semantic is as follows.
>> If p1 and p2 point to different objects, and neither of them is based
on
>> a pointer casted from an integer, `llvm.psub(p1, p2)` returns poison.
For
>> example,
>>
>> %p = alloca
>> %q = alloca
>> %i = llvm.psub(p, q) ; %i is poison
>>
>> This allows aggressive escape analysis on pointers. Given i >>
llvm.psub(p1, p2), if neither of p1 and p2 is based on a pointer casted
>> from an integer, the llvm.psub call does not make p1 or p2 escape. (
>> https://reviews.llvm.org/D56601 )
>>
>> If either p1 or p2 is based on a pointer casted from integer, or p1 and
>> p2 point to a same object, it returns the result of subtraction (in
bytes);
>> for example,
>>
>> %p = alloca
>> %q = inttoptr %x
>> %i = llvm.psub(p, q) ; %i is equivalent to (ptrtoint %p) - %x
>>
>> `null` is regarded as a pointer casted from an integer because
>> it is equivalent to `inttoptr 0`.
>>
>> Adding llvm.psub allows LLVM to utilize significant portion of
ptrtoints
>> & reduce a portion of inttoptrs. After llvm.psub is used, when
SPECrate
>> 2017 is compiled with -O3, # of inttoptr decreases to ~13,500 (59%) and
#
>> of ptrtoint decreases to ~14,300 (45%).
>>
>> To see the performance change, I ran SPECrate 2017 (thread # = 1) with
>> three versions of LLVM, which are r313797 (Sep 21, 2017), LLVM 6.0
>> official, and r348082 (Dec 2, 2018).
>> Running r313797 shows that 505.mcf_r has consistent 2.0% speedup over 3
>> different machines (which are i3-6100, i5-6600, i7-7700). For LLVM 6.0
and
>> r348082, there's neither consistent speedup nor slowdown, but the
average
>> speedup is near 0. I believe there's still a room of improvement
because
>> there are passes which are not aware of llvm.psub.
>>
>> Thank you for reading this, and any comment is welcome.
>>
>> Best Regards,
>> Juneyoung Lee
>> _______________________________________________
>> LLVM Developers mailing list
>> llvm-dev at lists.llvm.org
>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>
> _______________________________________________
> LLVM Developers mailing list
> llvm-dev at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20190114/6eb4f82b/attachment.html>

On Mon, Jan 14, 2019, 15:59 Mehdi AMINI <joker.eph at gmail.com wrote:
>
>
> On Mon, Jan 14, 2019 at 9:36 AM Chandler Carruth via llvm-dev <
> llvm-dev at lists.llvm.org> wrote:
>
>> While I'm very interested in the end result here, I have some
questions
>> that don't seem well answered yet around pointer subtraction...
>>
>> First and foremost - how do you address correctness issues here?
Because
>> the subtraction `A - B` can escape/capture more things. Specifically,
if
>> one of `A` or `B` is escaped/captured, the subtraction can be used to
>> escape or capture the other pointer.
>>
>
> Isn't escaping supposed to work at the "address ranges" level
and not at
> the pointer value?
> I mean that if `A` or `B` is escaped/captured, then any pointer that is
> associated to the same memory range should be considered as
"escaped", and
> thus the subtraction does not seem to leak anything more to me.
>
I believe this is true for subtracting "inbounds" (to borrow the gep
terminology), but just as we support non inbounds GEP, we support non
imbounds subtracting. There it seems like this does escape the other
global. I know that in the past I've discussed this exact case with
nlewycky and he believed that to be the case, so I suspect quite a bit of
LLVM is written under this model. No idea what would be the impact of
changing it beyond the ability to represent code like the example I gave
earlier on the thread.
>
> --
> Mehdi
>
>
>
>
>> So *some* of the conservative treatment is necessary. What is the plan
to
>> update all the analyses to remain correct? What correctness testing
have
>> you done?
>>
>> Second - an intrinsic seems a poor fit here given the significance of
>> this operation. We have an instruction that covers most pointer
arithmetic
>> (`getelementptr`), and I can imagine growing pointer subtraction, but
it
>> seems like it should be an instruction if we're going to have it.
Based on
>> the above, we will need to use it very often in analysis.
>>
>>
>> Regarding the instcombine, it should be very easy to keep loads and
>> stores of pointers as pointer typed in instcombine. Likely just a
missing
>> case in the code I added/touched there.
>>
>> On Mon, Jan 14, 2019 at 3:23 AM Juneyoung Lee via llvm-dev <
>> llvm-dev at lists.llvm.org> wrote:
>>
>>> Hello all,
>>>
>>> This is a proposal for reducing # of ptrtoint/inttoptr casts which
are
>>> not
>>> written by programmers but rather generated by LLVM passes.
>>> Currently the majority of ptrtoint/inttoptr casts are generated by
LLVM;
>>> when compiling SPEC 2017 with LLVM r348082 (Dec 2 2018) with -O3,
>>> the output IR contains 22,771 inttoptr instructions. However, when
>>> compiling it with -O0, there are only 1048 inttoptrs, meaning that
95.4%
>>> of them are generated by LLVM passes.
>>>
>>> This trend is similar in ptrtoint instruction as well. When
compiling
>>> SPEC 2017
>>> with -O0, there are 23,208 ptrtoint instructions, but among them
22,016
>>> (94.8%)
>>> are generated by Clang frontend to represent pointer subtraction.
>>> They aren't effectively optimized out because there are even
more
>>> ptrtoints (31,721) after -O3.
>>> This is bad for performance because existence of ptrtoint makes
analysis
>>> return conservative
>>> result as a pointer can be escaped through the cast.
>>> Memory accesses to a pointer came from inttoptr is assumed
>>> to possibly access anywhere, therefore it may block
>>> store-to-load forwarding, merging two same loads, etc.
>>>
>>> I believe this can be addressed by applying two patches - first one
is
>>> representing pointer subtraction with a dedicated intrinsic
function,
>>> llvm.psub, and second one is disabling InstCombine transformation
>>>
>>>     %q = load i8*, i8** %p1
>>>     store i8* %q, i8** %p2
>>> =>
>>>   %1 = bitcast i8** %p1 to i64*
>>>   %q1 = load i64, i64* %1, align 8
>>>   %2 = bitcast i8** %p2 to i64*
>>>   store i64 %q1, i64* %2, align 8
>>>
>>> This transformation can introduce inttoptrs later if loads are
followed (
>>> https://godbolt.org/z/wsZ3II ). Both are discussed in
>>> https://bugs.llvm.org/show_bug.cgi?id=39846 as well.
>>> After llvm.psub is used & this transformation is disabled, # of
>>> inttoptrs decreases from 22,771 to 1,565 (6.9%), and # of ptrtoints
>>> decreases from 31,721 to 7,772 (24.5%).
>>>
>>> I'll introduce llvm.psub patch first.
>>>
>>>
>>> --- Adding llvm.psub ---
>>>
>>> By defining pointer subtraction intrinsic, we can get performance
gain
>>> because it gives more undefined behavior than just subtracting two
>>> ptrtoints.
>>>
>>> Patch https://reviews.llvm.org/D56598 adds llvm.psub(p1,p2)
intrinsic
>>> function, which subtracts two pointers and returns the difference.
Its
>>> semantic is as follows.
>>> If p1 and p2 point to different objects, and neither of them is
based on
>>> a pointer casted from an integer, `llvm.psub(p1, p2)` returns
poison. For
>>> example,
>>>
>>> %p = alloca
>>> %q = alloca
>>> %i = llvm.psub(p, q) ; %i is poison
>>>
>>> This allows aggressive escape analysis on pointers. Given i
>>> llvm.psub(p1, p2), if neither of p1 and p2 is based on a pointer
casted
>>> from an integer, the llvm.psub call does not make p1 or p2 escape.
(
>>> https://reviews.llvm.org/D56601 )
>>>
>>> If either p1 or p2 is based on a pointer casted from integer, or p1
and
>>> p2 point to a same object, it returns the result of subtraction (in
bytes);
>>> for example,
>>>
>>> %p = alloca
>>> %q = inttoptr %x
>>> %i = llvm.psub(p, q) ; %i is equivalent to (ptrtoint %p) - %x
>>>
>>> `null` is regarded as a pointer casted from an integer because
>>> it is equivalent to `inttoptr 0`.
>>>
>>> Adding llvm.psub allows LLVM to utilize significant portion of
ptrtoints
>>> & reduce a portion of inttoptrs. After llvm.psub is used, when
SPECrate
>>> 2017 is compiled with -O3, # of inttoptr decreases to ~13,500 (59%)
and #
>>> of ptrtoint decreases to ~14,300 (45%).
>>>
>>> To see the performance change, I ran SPECrate 2017 (thread # = 1)
with
>>> three versions of LLVM, which are r313797 (Sep 21, 2017), LLVM 6.0
>>> official, and r348082 (Dec 2, 2018).
>>> Running r313797 shows that 505.mcf_r has consistent 2.0% speedup
over 3
>>> different machines (which are i3-6100, i5-6600, i7-7700). For LLVM
6.0 and
>>> r348082, there's neither consistent speedup nor slowdown, but
the average
>>> speedup is near 0. I believe there's still a room of
improvement because
>>> there are passes which are not aware of llvm.psub.
>>>
>>> Thank you for reading this, and any comment is welcome.
>>>
>>> Best Regards,
>>> Juneyoung Lee
>>> _______________________________________________
>>> LLVM Developers mailing list
>>> llvm-dev at lists.llvm.org
>>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>>
>> _______________________________________________
>> LLVM Developers mailing list
>> llvm-dev at lists.llvm.org
>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20190114/9db5a6c4/attachment.html>

On Mon, Jan 14, 2019 at 4:51 PM Chandler Carruth <chandlerc at gmail.com>
wrote:
>
> On Mon, Jan 14, 2019, 15:59 Mehdi AMINI <joker.eph at gmail.com wrote:
>
>>
>>
>> On Mon, Jan 14, 2019 at 9:36 AM Chandler Carruth via llvm-dev <
>> llvm-dev at lists.llvm.org> wrote:
>>
>>> While I'm very interested in the end result here, I have some
questions
>>> that don't seem well answered yet around pointer subtraction...
>>>
>>> First and foremost - how do you address correctness issues here?
Because
>>> the subtraction `A - B` can escape/capture more things.
Specifically, if
>>> one of `A` or `B` is escaped/captured, the subtraction can be used
to
>>> escape or capture the other pointer.
>>>
>>
>> Isn't escaping supposed to work at the "address ranges"
level and not at
>> the pointer value?
>> I mean that if `A` or `B` is escaped/captured, then any pointer that is
>> associated to the same memory range should be considered as
"escaped", and
>> thus the subtraction does not seem to leak anything more to me.
>>
>
> I believe this is true for subtracting "inbounds" (to borrow the
gep
> terminology), but just as we support non inbounds GEP, we support non
> imbounds subtracting. There it seems like this does escape the other
> global. I know that in the past I've discussed this exact case with
> nlewycky and he believed that to be the case, so I suspect quite a bit of
> LLVM is written under this model. No idea what would be the impact of
> changing it beyond the ability to represent code like the example I gave
> earlier on the thread.
>
That does not match my current reading of LangRef (admittedly
shallow/imperfect): not having inbounds allows you to form pointers that
are outside of the memory range, however the "result value may not
necessarily be used to access memory though, even if it happens to point
into allocated storage".
Also the "pointer aliasing rules" section mentions: "Any memory
access must
be done through a pointer value associated with an address range of the
memory access, otherwise the behavior is undefined".


>
>>
>>
>>> So *some* of the conservative treatment is necessary. What is the
plan
>>> to update all the analyses to remain correct? What correctness
testing have
>>> you done?
>>>
>>> Second - an intrinsic seems a poor fit here given the significance
of
>>> this operation. We have an instruction that covers most pointer
arithmetic
>>> (`getelementptr`), and I can imagine growing pointer subtraction,
but it
>>> seems like it should be an instruction if we're going to have
it. Based on
>>> the above, we will need to use it very often in analysis.
>>>
>>>
>>> Regarding the instcombine, it should be very easy to keep loads and
>>> stores of pointers as pointer typed in instcombine. Likely just a
missing
>>> case in the code I added/touched there.
>>>
>>> On Mon, Jan 14, 2019 at 3:23 AM Juneyoung Lee via llvm-dev <
>>> llvm-dev at lists.llvm.org> wrote:
>>>
>>>> Hello all,
>>>>
>>>> This is a proposal for reducing # of ptrtoint/inttoptr casts
which are
>>>> not
>>>> written by programmers but rather generated by LLVM passes.
>>>> Currently the majority of ptrtoint/inttoptr casts are generated
by LLVM;
>>>> when compiling SPEC 2017 with LLVM r348082 (Dec 2 2018) with
-O3,
>>>> the output IR contains 22,771 inttoptr instructions. However,
when
>>>> compiling it with -O0, there are only 1048 inttoptrs, meaning
that 95.4%
>>>> of them are generated by LLVM passes.
>>>>
>>>> This trend is similar in ptrtoint instruction as well. When
compiling
>>>> SPEC 2017
>>>> with -O0, there are 23,208 ptrtoint instructions, but among
them 22,016
>>>> (94.8%)
>>>> are generated by Clang frontend to represent pointer
subtraction.
>>>> They aren't effectively optimized out because there are
even more
>>>> ptrtoints (31,721) after -O3.
>>>> This is bad for performance because existence of ptrtoint makes
>>>> analysis return conservative
>>>> result as a pointer can be escaped through the cast.
>>>> Memory accesses to a pointer came from inttoptr is assumed
>>>> to possibly access anywhere, therefore it may block
>>>> store-to-load forwarding, merging two same loads, etc.
>>>>
>>>> I believe this can be addressed by applying two patches - first
one is
>>>> representing pointer subtraction with a dedicated intrinsic
function,
>>>> llvm.psub, and second one is disabling InstCombine
transformation
>>>>
>>>>     %q = load i8*, i8** %p1
>>>>     store i8* %q, i8** %p2
>>>> =>
>>>>   %1 = bitcast i8** %p1 to i64*
>>>>   %q1 = load i64, i64* %1, align 8
>>>>   %2 = bitcast i8** %p2 to i64*
>>>>   store i64 %q1, i64* %2, align 8
>>>>
>>>> This transformation can introduce inttoptrs later if loads are
followed
>>>> (https://godbolt.org/z/wsZ3II ). Both are discussed in
>>>> https://bugs.llvm.org/show_bug.cgi?id=39846 as well.
>>>> After llvm.psub is used & this transformation is disabled,
# of
>>>> inttoptrs decreases from 22,771 to 1,565 (6.9%), and # of
ptrtoints
>>>> decreases from 31,721 to 7,772 (24.5%).
>>>>
>>>> I'll introduce llvm.psub patch first.
>>>>
>>>>
>>>> --- Adding llvm.psub ---
>>>>
>>>> By defining pointer subtraction intrinsic, we can get
performance gain
>>>> because it gives more undefined behavior than just subtracting
two
>>>> ptrtoints.
>>>>
>>>> Patch https://reviews.llvm.org/D56598 adds llvm.psub(p1,p2)
intrinsic
>>>> function, which subtracts two pointers and returns the
difference. Its
>>>> semantic is as follows.
>>>> If p1 and p2 point to different objects, and neither of them is
based
>>>> on a pointer casted from an integer, `llvm.psub(p1, p2)`
returns poison.
>>>> For example,
>>>>
>>>> %p = alloca
>>>> %q = alloca
>>>> %i = llvm.psub(p, q) ; %i is poison
>>>>
>>>> This allows aggressive escape analysis on pointers. Given i
>>>> llvm.psub(p1, p2), if neither of p1 and p2 is based on a
pointer casted
>>>> from an integer, the llvm.psub call does not make p1 or p2
escape. (
>>>> https://reviews.llvm.org/D56601 )
>>>>
>>>> If either p1 or p2 is based on a pointer casted from integer,
or p1 and
>>>> p2 point to a same object, it returns the result of subtraction
(in bytes);
>>>> for example,
>>>>
>>>> %p = alloca
>>>> %q = inttoptr %x
>>>> %i = llvm.psub(p, q) ; %i is equivalent to (ptrtoint %p) - %x
>>>>
>>>> `null` is regarded as a pointer casted from an integer because
>>>> it is equivalent to `inttoptr 0`.
>>>>
>>>> Adding llvm.psub allows LLVM to utilize significant portion of
>>>> ptrtoints & reduce a portion of inttoptrs. After llvm.psub
is used, when
>>>> SPECrate 2017 is compiled with -O3, # of inttoptr decreases to
~13,500
>>>> (59%) and # of ptrtoint decreases to ~14,300 (45%).
>>>>
>>>> To see the performance change, I ran SPECrate 2017 (thread # =
1) with
>>>> three versions of LLVM, which are r313797 (Sep 21, 2017), LLVM
6.0
>>>> official, and r348082 (Dec 2, 2018).
>>>> Running r313797 shows that 505.mcf_r has consistent 2.0%
speedup over 3
>>>> different machines (which are i3-6100, i5-6600, i7-7700). For
LLVM 6.0 and
>>>> r348082, there's neither consistent speedup nor slowdown,
but the average
>>>> speedup is near 0. I believe there's still a room of
improvement because
>>>> there are passes which are not aware of llvm.psub.
>>>>
>>>> Thank you for reading this, and any comment is welcome.
>>>>
>>>> Best Regards,
>>>> Juneyoung Lee
>>>> _______________________________________________
>>>> LLVM Developers mailing list
>>>> llvm-dev at lists.llvm.org
>>>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>>>
>>> _______________________________________________
>>> LLVM Developers mailing list
>>> llvm-dev at lists.llvm.org
>>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20190114/80c22cc3/attachment.html>