We may be able to assert that no shl-shl or lshr-lshr pairs ever get here
because we should have already handled those in foldShiftedShift().
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292726 91177308-0d34-0410-b5e6-96231b3b80d8
This depended on libm's errno behavior (we constant fold iff libm's
sqrt(-2) does not set errno) and was breaking on mac.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292701 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Currently we return undef, but we're in the process of changing the
LangRef so that llvm.sqrt behaves like the other math intrinsics,
matching the return value of the standard libcall but not setting errno.
This change is legal even without the LangRef change because currently
calling llvm.sqrt(x) where x is negative is spec'ed to be UB. But in
practice it's also safe because we're simply constant-folding fewer
inputs: Inputs >= -0 get constant-folded as before, but inputs < -0 now
aren't constant-folded, because ConstantFoldFP aborts if the host math
function raises an fp exception.
Reviewers: hfinkel, efriedma, sanjoy
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28929
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292692 91177308-0d34-0410-b5e6-96231b3b80d8
Add missing fabs(fpext) optimzation that worked with the call,
and also fixes it creating a second fpext when there were multiple
uses.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292172 91177308-0d34-0410-b5e6-96231b3b80d8
cover domtree and alias analysis. These are the pretty clear analyses
that we would always want to survive this pass.
To make these survive, we also need to preserve the assumption cache.
Added a test that verifies the important bits of this preservation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292037 91177308-0d34-0410-b5e6-96231b3b80d8
Allows LLVM to optimize sequences like the following:
%add = add nuw i32 %x, 1
%cmp = icmp ugt i32 %add, %y
Into:
%cmp = icmp uge i32 %x, %y
Previously, only signed comparisons were being handled.
Decrements could also be handled, but 'sub nuw %x, 1' is currently canonicalized to
'add %x, -1' in InstCombineAddSub, losing the nuw flag. Removing that canonicalization
seems like it might have far-reaching ramifications so I kept this simple for now.
Patch by Matti Niemenmaa!
Differential Revision: https://reviews.llvm.org/D24700
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291975 91177308-0d34-0410-b5e6-96231b3b80d8
fabs(x * x) is not generally safe to assume x is positive if x is a NaN.
This is also less general than it could be, so this will be replaced
with a transformation on the intrinsic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291359 91177308-0d34-0410-b5e6-96231b3b80d8
We can perform the following:
(add (zext (add nuw X, C1)), C2) -> (zext (add nuw X, C1+C2))
This is only possible if C2 is negative and C2 is greater than or equal to negative C1.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290927 91177308-0d34-0410-b5e6-96231b3b80d8
The accidentally had trivially dead code. Also needed to adjust the rounding mode to not CUR_DIRECTION so the intrinsics don't get converted to native operations before going through SimplifyDemandedVectorElts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290702 91177308-0d34-0410-b5e6-96231b3b80d8
We currently ignore the `allocsize` attribute on functions calls with
the `nobuiltin` attribute when trying to lower `@llvm.objectsize`. We
shouldn't care about `nobuiltin` here: `allocsize` is explicitly added
by the user, not inferred based on a function's symbol.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290588 91177308-0d34-0410-b5e6-96231b3b80d8
PMULDQ/PMULUDQ vXi64 instructions only use the even numbered v2Xi32 input elements which SimplifyDemandedVectorElts should try and use.
This builds on r290554 which added supported for 128 and 256-bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290582 91177308-0d34-0410-b5e6-96231b3b80d8
An earlier commit added support for unmasked scalar operations. At that time isel wouldn't generate an optimal sequence for masked operations, but that has now been fixed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290566 91177308-0d34-0410-b5e6-96231b3b80d8
The CUR_DIRECTION case will be optimized in a future commit so this provides coverage for the other cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290565 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
I only do this for unmasked cases for now because isel is failing to fold the mask. I'll try to fix that soon.
I'll do the same thing for packed add/sub/mul/div in a future patch.
Reviewers: delena, RKSimon, zvi, craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D27879
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290535 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This patch adds support for converting the masked vpermv intrinsics into shufflevector instructions if the indices are constants.
We also need to wrap a select instruction around the shuffle to take care of the masking part. InstCombine will take care of optimizing the select if the mask is constant so I didn't bother checking for that.
Reviewers: zvi, delena, spatel, RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D27825
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290530 91177308-0d34-0410-b5e6-96231b3b80d8
Background/motivation - I was circling back around to:
https://llvm.org/bugs/show_bug.cgi?id=28296
I made a simple patch for that and noticed some regressions, so added test cases for
those with rL281055, and this is hopefully the minimal fix for just those cases.
But as you can see from the surrounding untouched folds, we are missing commuted patterns
all over the place, and of course there are no regression tests to cover any of those cases.
We could sprinkle "m_c_" dust all over this file and catch most of the missing folds, but
then we still wouldn't have test coverage, and we'd still miss some fraction of commuted
patterns because they require adjustments to the match order.
I'm aware of the concern about the potential compile-time performance impact of adding
matches like this (currently being discussed on llvm-dev), but I don't think there's any
evidence yet to suggest that handling commutative pattern matching more thoroughly is not
a worthwhile goal of InstCombine.
Differential Revision: https://reviews.llvm.org/D24419
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290067 91177308-0d34-0410-b5e6-96231b3b80d8
Min/max canonicalization (r287585) exposes the fact that we're missing combines for min/max patterns.
This patch won't solve the example that was attached to that thread, so something else still needs fixing.
The line between InstCombine and InstSimplify gets blurry here because sometimes the icmp instruction that
we want to fold to already exists, but sometimes it's the swapped form of what we want.
Corresponding changes for smax/umin/umax to follow.
Differential Revision: https://reviews.llvm.org/D27531
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289855 91177308-0d34-0410-b5e6-96231b3b80d8
A number of new patterns for simplifying and/xor of icmp:
(icmp ne %x, 0) ^ (icmp ne %y, 0) => icmp ne %x, %y if the following is true:
1- (%x = and %a, %mask) and (%y = and %b, %mask)
2- %mask is a power of 2.
(icmp eq %x, 0) & (icmp ne %y, 0) => icmp ult %x, %y if the following is true:
1- (%x = and %a, %mask1) and (%y = and %b, %mask2)
2- Let %t be the smallest power of 2 where %mask1 & %t != 0. Then for any
%s that is a power of 2 and %s & %mask2 != 0, we must have %s <= %t.
For example if %mask1 = 24 and %mask2 = 16, setting %s = 16 and %t = 8
violates condition (2) above. So this optimization cannot be applied.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289813 91177308-0d34-0410-b5e6-96231b3b80d8
There was an efficiency problem with how we processed @llvm.assume in
ValueTracking (and other places). The AssumptionCache tracked all of the
assumptions in a given function. In order to find assumptions relevant to
computing known bits, etc. we searched every assumption in the function. For
ValueTracking, that means that we did O(#assumes * #values) work in InstCombine
and other passes (with a constant factor that can be quite large because we'd
repeat this search at every level of recursion of the analysis).
Several of us discussed this situation at the last developers' meeting, and
this implements the discussed solution: Make the values that an assume might
affect operands of the assume itself. To avoid exposing this detail to
frontends and passes that need not worry about it, I've used the new
operand-bundle feature to add these extra call "operands" in a way that does
not affect the intrinsic's signature. I think this solution is relatively
clean. InstCombine adds these extra operands based on what ValueTracking, LVI,
etc. will need and then those passes need only search the users of the values
under consideration. This should fix the computational-complexity problem.
At this point, no passes depend on the AssumptionCache, and so I'll remove
that as a follow-up change.
Differential Revision: https://reviews.llvm.org/D27259
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289755 91177308-0d34-0410-b5e6-96231b3b80d8
Only the lower bits of the input element are used. And only the lower element can be undef since the upper bits are zeroed.
Have InstCombineCalls call SimplifyDemandedVectorElts for these intrinsics to reuse this support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289523 91177308-0d34-0410-b5e6-96231b3b80d8
We could truncate the condition and then try to fold the add into the
original condition value causing wrong case constants to be used.
Move the offset transform ahead of the truncate transform and return
after each transform, so there's no chance of getting confused values.
Fix for:
https://llvm.org/bugs/show_bug.cgi?id=31260
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289442 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This change adds some verification in the IR verifier around struct path
TBAA metadata.
Other than some basic sanity checks (e.g. we get constant integers where
we expect constant integers), this checks:
- That by the time an struct access tuple `(base-type, offset)` is
"reduced" to a scalar base type, the offset is `0`. For instance, in
C++ you can't start from, say `("struct-a", 16)`, and end up with
`("int", 4)` -- by the time the base type is `"int"`, the offset
better be zero. In particular, a variant of this invariant is needed
for `llvm::getMostGenericTBAA` to be correct.
- That there are no cycles in a struct path.
- That struct type nodes have their offsets listed in an ascending
order.
- That when generating the struct access path, you eventually reach the
access type listed in the tbaa tag node.
Reviewers: dexonsmith, chandlerc, reames, mehdi_amini, manmanren
Subscribers: mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D26438
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289402 91177308-0d34-0410-b5e6-96231b3b80d8
This teaches SimplifyDemandedElts that the FMA can be removed if the lower element isn't used. It also teaches it that if upper elements of the first operand aren't used then we can simplify them.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289377 91177308-0d34-0410-b5e6-96231b3b80d8
The tests that already work are folded in InstSimplify, so those
tests should be redundant and we can remove them if they don't
seem worthwhile for completeness.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288957 91177308-0d34-0410-b5e6-96231b3b80d8
Demonstrate missed opportunity for urem -> and combine for powerof2 or zero non-uniform constant dividers
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288510 91177308-0d34-0410-b5e6-96231b3b80d8
The instcombine code which folds loads and stores into their use types can trip up if the use is a bitcast to a type which we can't directly load or store in the IR. In principle, such types shouldn't exist, but in practice they do today. This is a workaround to avoid a bug while we work towards the long term goal.
Differential Revision: https://reviews.llvm.org/D24365
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288415 91177308-0d34-0410-b5e6-96231b3b80d8
We had a limited version of this for scalar 'and'; this expands
the transform to 'or' and 'xor' and allows vectors types too.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288273 91177308-0d34-0410-b5e6-96231b3b80d8
In PR27925:
https://llvm.org/bugs/show_bug.cgi?id=27925
...we proposed adding this fold to eliminate a bitcast. In D20774, there was
some concern about changing the type of a bitwise op as well as creating
bitcasts that might not be free for a target. However, if we're strictly
eliminating an instruction (by limiting this to one-use ops), then we should
be able to do this in InstCombine.
But we're cautiously restricting the transform for now to vector types to
avoid possible backend problems. A transform to make sure the logic op is
legal for the target should be added to reverse this transform and improve
codegen.
Differential Revision: https://reviews.llvm.org/D26641
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287707 91177308-0d34-0410-b5e6-96231b3b80d8
This is a first step towards canonicalization and improved folding/codegen
for integer min/max as discussed here:
http://lists.llvm.org/pipermail/llvm-dev/2016-November/106868.html
Here, we're just matching the simplest min/max patterns and adjusting the
icmp predicate while swapping the select operands.
I've included FIXME tests in test/Transforms/InstCombine/select_meta.ll
so it's easier to see how this might be extended (corresponds to the TODO
comment in the code). That's also why I'm using matchSelectPattern()
rather than a simpler check; once the backend is patched, we can just
remove some of the restrictions to allow the obfuscated min/max patterns
in the FIXME tests to be matched.
Differential Revision: https://reviews.llvm.org/D26525
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287585 91177308-0d34-0410-b5e6-96231b3b80d8
Currently LLVM assumes that a pointer addrspacecasted to a different addr space is equivalent to trunc or zext bitwise, which is not true. For example, in amdgcn target, when a null pointer is addrspacecasted from addr space 4 to 0, its value is changed from i64 0 to i32 -1.
This patch teaches LLVM not to assume known bits of addrspacecast instruction to its operand.
Differential Revision: https://reviews.llvm.org/D26803
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287545 91177308-0d34-0410-b5e6-96231b3b80d8
This is a straightforward extension of the existing support for 32/64-bit element types. Just needed to add the additional instrinsics to the switches.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287316 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: These intrinsics have been unused for clang for a while. This patch removes them. We auto upgrade them to extractelements, a scalar operation and then an insertelement. This matches the sequence used by clangs intrinsic file.
Reviewers: zvi, delena, RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D26660
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287083 91177308-0d34-0410-b5e6-96231b3b80d8
Note that the existing metadata checking was re-added by hand because the
script doesn't currently know how to generate checks for lines outside of
functions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286460 91177308-0d34-0410-b5e6-96231b3b80d8
Removing the limitation in visitInsertElementInst() causes several regressions
because we're not prepared to fold sequences of shuffles or inserts and extracts
separated by shuffles. Fixing that appears to be a difficult mission because we
are purposely trying to avoid creating shuffles with arbitrary shuffle masks
because some targets may choke on those.
https://llvm.org/bugs/show_bug.cgi?id=30923
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286423 91177308-0d34-0410-b5e6-96231b3b80d8
As the test change shows, we can increase the critical path by adding
a 'not' instruction, so make sure that we're actually removing an
instruction if we do this transform.
This transform could also cause us to miss folds of min/max pairs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286315 91177308-0d34-0410-b5e6-96231b3b80d8
This was reverted at r285866 because there was a crash handling a scalar
select of vectors. I added a check for that pattern and a test case based
on the example provided in the post-commit thread for r285732.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286113 91177308-0d34-0410-b5e6-96231b3b80d8
This reverts commit r285732.
This change introduced a new assertion failure in the following
testcase at -O2:
typedef short __v8hi __attribute__((__vector_size__(16)));
__v8hi foo(__v8hi &V1, __v8hi &V2, unsigned mask) {
__v8hi Result = V1;
if (mask & 0x80)
Result[0] = V2[0];
return Result;
}
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@285866 91177308-0d34-0410-b5e6-96231b3b80d8
I think the former 'test50' had a typo making it functionally equivalent
to the former 'test49'; changed the predicate to provide more coverage.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@285706 91177308-0d34-0410-b5e6-96231b3b80d8
This patch introduces the combine:
(C1 shift (A add C2)) -> ((C1 shift C2) shift A)
iff A and C2 are both positive
If both A and C2 are know to be positive then we can safely split into 2 shifts, permitting the folding of the Inner shift.
Fix for the spec benchmark case mentioned by @nadav on PR15141 (assuming we can prove that the inputs as positive).
Differential Revision: https://reviews.llvm.org/D26000
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@285696 91177308-0d34-0410-b5e6-96231b3b80d8
