Summary:
Currently, InstCombine is already able to fold expressions of the form `logic(cast(A), cast(B))` to the simpler form `cast(logic(A, B))`, where logic designates one of `and`/`or`/`xor`. This transformation is implemented in `foldCastedBitwiseLogic()` in InstCombineAndOrXor.cpp. However, this optimization will not be performed if both `A` and `B` are `icmp` instructions. The decision to preclude casts of `icmp` instructions originates in r48715 in combination with r261707, and can be best understood by the title of the former one:
> Transform (zext (or (icmp), (icmp))) to (or (zext (cimp), (zext icmp))) if at least one of the (zext icmp) can be transformed to eliminate an icmp.
Apparently, it introduced a transformation that is a reverse of the transformation that is done in `foldCastedBitwiseLogic()`. Its purpose is to expose pairs of `zext icmp` that would subsequently be optimized by `transformZExtICmp()` in InstCombineCasts.cpp. Therefore, in order to avoid an endless loop of switching back and forth between these two transformations, the one in `foldCastedBitwiseLogic()` has been restricted to exclude `icmp` instructions which is mirrored in the responsible check:
`if ((!isa<ICmpInst>(Cast0Src) || !isa<ICmpInst>(Cast1Src)) && ...`
This check seems to sort out more cases than necessary because:
- the reverse transformation is obviously done for `or` instructions only
- and also not every `zext icmp` pair is necessarily the result of this reverse transformation
Therefore we now remove this check and replace it by a more finegrained one in `shouldOptimizeCast()` that now rejects only those `logic(zext(icmp), zext(icmp))` that would be able to be optimized by `transformZExtICmp()`, which also avoids the mentioned endless loop. That means we are now able to also simplify expressions of the form `logic(cast(icmp), cast(icmp))` to `cast(logic(icmp, icmp))` (`cast` being an arbitrary `CastInst`).
As an example, consider the following IR snippet
```
%1 = icmp sgt i64 %a, %b
%2 = zext i1 %1 to i8
%3 = icmp slt i64 %a, %c
%4 = zext i1 %3 to i8
%5 = and i8 %2, %4
```
which would now be transformed to
```
%1 = icmp sgt i64 %a, %b
%2 = icmp slt i64 %a, %c
%3 = and i1 %1, %2
%4 = zext i1 %3 to i8
```
This issue became apparent when experimenting with the programming language Julia, which makes use of LLVM. Currently, Julia lowers its `Bool` datatype to LLVM's `i8` (also see https://github.com/JuliaLang/julia/pull/17225). In fact, the above IR example is the lowered form of the Julia snippet `(a > b) & (a < c)`. Like shown above, this may introduce `zext` operations, casting between `i1` and `i8`, which could for example hinder ScalarEvolution and Polly on certain code.
Reviewers: grosser, vtjnash, majnemer
Subscribers: majnemer, llvm-commits
Differential Revision: https://reviews.llvm.org/D22511
Contributed-by: Matthias Reisinger
llvm-svn: 275989
Only if the value is negative or positive is what matters,
so use a constant that doesn't require an instruction to
materialize.
These should really just emit the write exec directly,
but for stick with the kill pseudo-terminator.
llvm-svn: 275988
D20859 and D20860 attempted to replace the SSE (V)CVTTPS2DQ and VCVTTPD2DQ truncating conversions with generic IR instead.
It turns out that the behaviour of these intrinsics is different enough from generic IR that this will cause problems, INF/NAN/out of range values are guaranteed to result in a 0x80000000 value - which plays havoc with constant folding which converts them to either zero or UNDEF. This is also an issue with the scalar implementations (which were already generic IR and what I was trying to match).
This patch changes both scalar and packed versions back to using x86-specific builtins.
It also deals with the other scalar conversion cases that are runtime rounding mode dependent and can have similar issues with constant folding.
A companion clang patch is at D22105
Differential Revision: https://reviews.llvm.org/D22106
llvm-svn: 275981
Recommitting after r274347 was reverted. This patch introduces some
classes to refactor the 3 and 4 register Thumb2 multiplication
instruction descriptions, plus improved tests for some of those
instructions.
Differential Revision: https://reviews.llvm.org/D21929
llvm-svn: 275979
The standard local dynamic model for TLS on ARM systems needs two
relocations:
- R_ARM_TLS_LDM32 (module idx)
- R_ARM_TLS_LDO32 (offset of object from origin of module TLS block)
In GNU style assembler we use symbol(tlsldm) and symbol(tlsldo) to
produce these relocations.
llvm-mc for ARM supports symbol(tlsldo) but does not support symbol(tlsldm).
This patch wires up the existing symbol(tlsldm) to R_ARM_TLS_LDM32.
TLS for ARM is defined in Addenda to, and Errata in, the ABI for the
ARM Architecture
Differential Revision: https://reviews.llvm.org/D22461
llvm-svn: 275977
As discussed on PR27654, this patch fixes the triples of a lot of aarch64 tests and enables lit tests on windows
This will hopefully help stop cases where windows developers break the aarch64 target
Differential Revision: https://reviews.llvm.org/D22191
llvm-svn: 275973
Summary:
N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own
($).
This fixes the majority of object differences between -fintegrated-as and
-fno-integrated-as.
Reviewers: sdardis
Subscribers: dsanders, sdardis, llvm-commits
Differential Revision: https://reviews.llvm.org/D22412
llvm-svn: 275967
Summary:
The triple used for this distribution is mips64el-linux-gnuabi64.
Reviewers: sdardis
Subscribers: sdardis, llvm-commits
Differential Revision: https://reviews.llvm.org/D22406
llvm-svn: 275966
Summary:
This patch cleans up parts of InstCombine to raise its compliance with the LLVM coding standards and to increase its readability. The changes and according rationale are summarized in the following:
- Rename `ShouldOptimizeCast()` to `shouldOptimizeCast()` since functions should start with a lower case letter.
- Move `shouldOptimizeCast()` from InstCombineCasts.cpp to InstCombineAndOrXor.cpp since it's only used there.
- Simplify interface of `shouldOptimizeCast()`.
- Minor code style adaptions in `shouldOptimizeCast()`.
- Remove the documentation on the function definition of `shouldOptimizeCast()` since it just repeats the documentation on its declaration. Also enhance the documentation on its declaration with more information describing its intended use and make it doxygen-compliant.
- Change a comment in `foldCastedBitwiseLogic()` from `fold (logic (cast A), (cast B)) -> (cast (logic A, B))` to `fold logic(cast(A), cast(B)) -> cast(logic(A, B))` since the surrounding comments use this format.
- Remove comment `Only do this if the casts both really cause code to be generated.` in `foldCastedBitwiseLogic()` since it just repeats parts of the documentation of `shouldOptimizeCast()` and does not help to improve readability.
- Simplify the interface of `isEliminableCastPair()`.
- Removed the documentation on the function definition of `isEliminableCastPair()` which only contained obvious statements about its implementation. Instead added more general doxygen-compliant documentation to its declaration.
- Renamed parameter `DoXform` of `transformZExtIcmp()` to `DoTransform` to make its intention clearer.
- Moved documentation of `transformZExtIcmp()` from its definition to its declaration and made it doxygen-compliant.
Reviewers: vtjnash, grosser
Subscribers: majnemer, llvm-commits
Differential Revision: https://reviews.llvm.org/D22449
Contributed-by: Matthias Reisinger
llvm-svn: 275964
The following condition expression ( a >> n) & 1 is converted to "bt a, n" instruction. It works on all intel targets.
But on AVX-512 it was broken because the expression is modified to (truncate (a >>n) to i1).
I added the new sequence (truncate (a >>n) to i1) to the BT pattern.
Differential Revision: https://reviews.llvm.org/D22354
llvm-svn: 275950
This patch updates MemorySSA's use-optimizing walker to be more
accurate and, in some cases, faster.
Essentially, this changed our core walking algorithm from a
cache-as-you-go DFS to an iteratively expanded DFS, with all of the
caching happening at the end. Said expansion happens when we hit a Phi,
P; we'll try to do the smallest amount of work possible to see if
optimizing above that Phi is legal in the first place. If so, we'll
expand the search to see if we can optimize to the next phi, etc.
An iteratively expanded DFS lets us potentially quit earlier (because we
don't assume that we can optimize above all phis) than our old walker.
Additionally, because we don't cache as we go, we can now optimize above
loops.
As an added bonus, this patch adds a ton of verification (if
EXPENSIVE_CHECKS are enabled), so finding bugs is easier.
Differential Revision: https://reviews.llvm.org/D21777
llvm-svn: 275940
Add a "-j" option to llvm-profdata to control the number of threads used.
Auto-detect NumThreads when it isn't specified, and avoid spawning threads when
they wouldn't be beneficial.
I tested this patch using a raw profile produced by clang (147MB). Here is the
time taken to merge 4 copies together on my laptop:
No thread pool: 112.87s user 5.92s system 97% cpu 2:01.08 total
With 2 threads: 134.99s user 26.54s system 164% cpu 1:33.31 total
Changes since the initial commit:
- When handling odd-length inputs, call ThreadPool::wait() before merging the
last profile. Should fix a race/off-by-one (see r275937).
Differential Revision: https://reviews.llvm.org/D22438
llvm-svn: 275938
For instructions in uniform set, they will not have vector versions so
add them to VecValuesToIgnore.
For induction vars, those only used in uniform instructions or consecutive
ptrs instructions have already been added to VecValuesToIgnore above. For
those induction vars which are only used in uniform instructions or
non-consecutive/non-gather scatter ptr instructions, the related phi and
update will also be added into VecValuesToIgnore set.
The change will make the vector RegUsages estimation less conservative.
Differential Revision: https://reviews.llvm.org/D20474
The recommit fixed the testcase global_alias.ll.
llvm-svn: 275936
This is to help moveSILowerControlFlow to before regalloc.
There are a couple of tradeoffs with this. The complete CFG
is visible to more passes, the loop body avoids an extra copy of m0,
vcc isn't required, and immediate offsets can be shrunk into s_movk_i32.
The disadvantage is the register allocator doesn't understand that
the single lane's vector is dead within the loop body, so an extra
register is used to outlive the loop block when expanding the
VGPR -> m0 loop. This also now results in worse waitcnt insertion
before the loop instead of after for pending operations at the point
of the indexing, but that should be fixed by future improvements to
cross block waitcnt insertion.
v_movreld_b32's operands are now modeled more correctly since vdst
is not a true output. This is kind of a hack to treat vdst as a
use operand. Extra checking is required in the verifier since
I can't seem to get tablegen to emit an implicit operand for a
virtual register.
llvm-svn: 275934
Add an overview of stubs and compile callbacks before the discussion of the
source changes.
-- This line, and those below, will be ignored--
M docs/tutorial/BuildingAJIT3.rst
llvm-svn: 275933
This is for a situation where the encoding for a register may be
different depending on the specific operand. For some instructions,
we want to apply additional restrictions beyond the encoding's
constraints.
In AMDGPU some operands are VSrc_32, using the VS_32 pseudo register
class which accept VGPRs, SGPRs, or immediates in the encoding.
Some specific instructions with the same encoding operand do not want
to allow immediates or SGPRs, but the encoding format is different
in this case than a regular VGPR_32 operand.
This allows specifying the encoding should be treated the same
without introducing yet another dummy register class.
llvm-svn: 275929
Instead of extracting raw coverage mappings into an artifact directory,
actually generate useful html reports for a given list of binaries with
symbol demangling turned on.
No tests, but this is actively being used to drive the (still nascent)
coverage bot.
llvm-svn: 275927
Add a "-j" option to llvm-profdata to control the number of threads
used. Auto-detect NumThreads when it isn't specified, and avoid spawning
threads when they wouldn't be beneficial.
I tested this patch using a raw profile produced by clang (147MB). Here is the
time taken to merge 4 copies together on my laptop:
No thread pool: 112.87s user 5.92s system 97% cpu 2:01.08 total
With 2 threads: 134.99s user 26.54s system 164% cpu 1:33.31 total
Differential Revision: https://reviews.llvm.org/D22438
llvm-svn: 275921
For instructions in uniform set, they will not have vector versions so
add them to VecValuesToIgnore.
For induction vars, those only used in uniform instructions or consecutive
ptrs instructions have already been added to VecValuesToIgnore above. For
those induction vars which are only used in uniform instructions or
non-consecutive/non-gather scatter ptr instructions, the related phi and
update will also be added into VecValuesToIgnore set.
The change will make the vector RegUsages estimation less conservative.
Differential Revision: https://reviews.llvm.org/D20474
llvm-svn: 275912
Summary:
Per D22441, MSVC warns on our old implementation of isUInt<64>. It sees
uint64_t(1) << 64 and doesn't realize that it's not going to be
executed. Writing as a template specialization is ugly, but prevents
the warning.
Reviewers: RKSimon
Subscribers: majnemer, llvm-commits
Differential Revision: https://reviews.llvm.org/D22472
llvm-svn: 275909
This doesn't seem to work with Bash:
$ /work/llvm/utils/release/merge.sh --proj llvm --rev r275870
/work/llvm/utils/release/merge.sh: line 34: ${$1#r}: bad substitution
I get the same error with and without a leading 'r'.
llvm-svn: 275898
Taking address of a byval variable in PTX is legal, but currently runs
into miscompilation by ptxas on sm_50+ (NVIDIA issue 1789042).
Work around the issue by enforcing minimum alignment on byval arguments
of device functions.
The change is a no-op on SASS level for sm_3x where ptxas already aligns
local copy by at least 4.
Differential Revision: https://reviews.llvm.org/D22428
llvm-svn: 275893
Summary:
Usually LCSSA survives this transformation, but in some cases (see
attached test) it doesn't: values from the original loop after
separating might be used from the outer loop. Before the transformation
it was the same loop, so LCSSA phis were not required.
This fixes PR28272.
Reviewers: sanjoy, hfinkel, chandlerc
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D21665
llvm-svn: 275891
