Handle this in DAGCombiner::visitEXTRACT_VECTOR_ELT the same as we already do in SelectionDAG::getNode and use APInt instead of getZExtValue.
This should also fix oss-fuzz #4910
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321767 91177308-0d34-0410-b5e6-96231b3b80d8
Our internal testing has revealed has discovered bugs in PPC builds.
I have forward reproduction instructions to the original author (Nirav).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321649 91177308-0d34-0410-b5e6-96231b3b80d8
For example, float operations may fail to constant fold under certain circumstances (inf/nan/denormal creation etc.)
Reduced from oss-fuzz #4802 test case
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321488 91177308-0d34-0410-b5e6-96231b3b80d8
This moves the combine for turning ANDs into shuffle with zero out of SimplifyVBinOps and places it only in visitAND below the reassociate handling. This fixes the specific case I noticed where we failed to combine two ands with constants.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321417 91177308-0d34-0410-b5e6-96231b3b80d8
getOperand returns an SDValue that contains the node and the result number. There is no guarantee that the result number if 0. By using the -> operator we are calling SDNode::getValueType rather than SDValue::getValueType. This requires supplying a result number and we shouldn't assume it was 0.
I don't have a test case. Just noticed while cleaning up some other code and saw that it occurred in other places.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321397 91177308-0d34-0410-b5e6-96231b3b80d8
BaseIndexOffset supercedes findBaseOffset analysis save only Constant
Pool addresses. Migrate analysis to BaseIndexOffset.
Relanding after correcting base address matching check.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321389 91177308-0d34-0410-b5e6-96231b3b80d8
which was causing miscompilations in for some test-suite components.
This reverts commit 3e9de9ff0f3162920a2a3cba51c7dc14b54b4d16.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321380 91177308-0d34-0410-b5e6-96231b3b80d8
BaseIndexOffset supercedes findBaseOffset analysis save only Constant
Pool addresses. Migrate analysis to BaseIndexOffset.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321364 91177308-0d34-0410-b5e6-96231b3b80d8
More general cases are already handled by constant canonicalization and then the ReassociateOps call at line 5327
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321280 91177308-0d34-0410-b5e6-96231b3b80d8
The knownbits_mask_or_shuffle_uitofp change is interesting - shuffle combines manage to kick in, removing the AND constant mask load. For targets with fast-variable-shuffle this should reduce further to VPOR+VPSHUFB+VCVTDQ2PS.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321279 91177308-0d34-0410-b5e6-96231b3b80d8
If the SRL node is only used by an AND, we may be able to set the
ExtVT to the width of the mask, making the AND redundant. To support
this, another check has been added in isLegalNarrowLoad which queries
whether the load is valid.
Differential Revision: https://reviews.llvm.org/D41350
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321259 91177308-0d34-0410-b5e6-96231b3b80d8
Prevent overlapping store elision when overlapping store is
pre-inc/dec as analysis is wrong in these cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321204 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Extend overlapping store elision to handle overwrites of stores by
larger stores.
Nontemporal tests have been modified to add memory dependencies to
prevent store elision.
Reviewers: craig.topper, rnk, t.p.northover
Subscribers: javed.absar, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D40969
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321089 91177308-0d34-0410-b5e6-96231b3b80d8
Search from AND nodes to find whether they can be propagated back to
loads, so that the AND and load can be combined into a narrow load.
We search through OR, XOR and other AND nodes and all bar one of the
leaves are required to be loads or constants. The exception node then
needs to be masked off meaning that the 'and' isn't removed, but the
loads(s) are narrowed still.
Differential Revision: https://reviews.llvm.org/D41177
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320962 91177308-0d34-0410-b5e6-96231b3b80d8
Recommitting rL319773, which was reverted due to a recursive issue
causing timeouts. This happened because I failed to check whether
the discovered loads could be narrowed further. In the case of a tree
with one or more narrow loads, that could not be further narrowed, as
well as a node that would need masking, an AND could be introduced
which could then be visited and recombined again with the same load.
This could again create the masking load, with would be combined
again... We now check that the load can be narrowed so that this
process stops.
Original commit message:
Search from AND nodes to find whether they can be propagated back to
loads, so that the AND and load can be combined into a narrow load.
We search through OR, XOR and other AND nodes and all bar one of the
leaves are required to be loads or constants. The exception node then
needs to be masked off meaning that the 'and' isn't removed, but the
loads(s) are narrowed still.
Differential Revision: https://reviews.llvm.org/D41177
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320679 91177308-0d34-0410-b5e6-96231b3b80d8
At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap())
to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some
element types, but...it's difficult.
Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG
combine and preserve all of the existing behavior AFAICT otherwise.
Some tests that will probably fail if someone does try to restrict this in a more targeted way
for x86-only may be found in:
test/CodeGen/X86/combine-mul.ll
test/CodeGen/X86/vector-mul.ll
test/CodeGen/X86/widen_arith-5.ll
This should prevent the infinite looping seen with:
https://bugs.llvm.org/show_bug.cgi?id=35579
Differential Revision: https://reviews.llvm.org/D41040
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320374 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is the first part of https://reviews.llvm.org/D40348.
In order to allow target combines to be performed on newly combined
indexed loads, add them back to the worklist. The remainder of the
above patch will be committed in subsequent revisions and will use
this. Test cases will be included with those follow-up commits.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320365 91177308-0d34-0410-b5e6-96231b3b80d8
This is a preparatory step for D34515.
This change:
- makes nodes ISD::ADDCARRY and ISD::SUBCARRY legal for i32
- lowering is done by first converting the boolean value into the carry flag
using (_, C) ← (ARMISD::ADDC R, -1) and converted back to an integer value
using (R, _) ← (ARMISD::ADDE 0, 0, C). An ARMISD::ADDE between the two
operations does the actual addition.
- for subtraction, given that ISD::SUBCARRY second result is actually a
borrow, we need to invert the value of the second operand and result before
and after using ARMISD::SUBE. We need to invert the carry result of
ARMISD::SUBE to preserve the semantics.
- given that the generic combiner may lower ISD::ADDCARRY and
ISD::SUBCARRYinto ISD::UADDO and ISD::USUBO we need to update their lowering
as well otherwise i64 operations now would require branches. This implies
updating the corresponding test for unsigned.
- add new combiner to remove the redundant conversions from/to carry flags
to/from boolean values (ARMISD::ADDC (ARMISD::ADDE 0, 0, C), -1) → C
- fixes PR34045
- fixes PR34564
- fixes PR35103
Differential Revision: https://reviews.llvm.org/D35192
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320355 91177308-0d34-0410-b5e6-96231b3b80d8
I noticed this pattern in D38316 / D38388. We failed to combine a shuffle that is either
repeating a scalar insertion at the same position in a vector or translated to a different
element index.
Like the earlier patch, this could be an instcombine too, but since we opted to make this
a DAG transform earlier, I've made this one a DAG patch too.
We do not need any legality checking because the new insert is identical to the existing
insert except that it may have a different constant insertion operand.
The constant insertion test in test/CodeGen/X86/vector-shuffle-combining.ll was the
motivation for D38756.
Differential Revision: https://reviews.llvm.org/D40209
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320050 91177308-0d34-0410-b5e6-96231b3b80d8
Search from AND nodes to find whether they can be propagated back to
loads, so that the AND and load can be combined into a narrow load.
We search through OR, XOR and other AND nodes and all bar one of the
leaves are required to be loads or constants. The exception node then
needs to be masked off meaning that the 'and' isn't removed, but the
loads(s) are narrowed still.
Differential Revision: https://reviews.llvm.org/D39604
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319773 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Found out, at code inspection, that there was a fault in
DAGCombiner::CombineConsecutiveLoads for big-endian targets.
A BUILD_PAIR is always having the least significant bits of
the composite value in element 0. So when we are doing the checks
for consecutive loads, for big endian targets, we should check
if the load to elt 1 is at the lower address and the load
to elt 0 is at the higher address.
Normally this bug only resulted in missed oppurtunities for
doing the load combine. I guess that in some rare situation it
could lead to faulty combines, but I've not seen that happen.
Note that this patch actually will trigger load combine for
some big endian regression tests.
One example is test/CodeGen/PowerPC/anon_aggr.ll where we now get
t76: i64,ch = load<LD8[FixedStack-9]
instead of
t37: i32,ch = load<LD4[FixedStack-10]>
t35: i32,ch = load<LD4[FixedStack-9]>
t41: i64 = build_pair t37, t35
before legalization. Then the legalization will split the LD8
into two loads, so the end result is the same. That should
verify that the transfomation is correct now.
Reviewers: niravd, hfinkel
Reviewed By: niravd
Subscribers: nemanjai, llvm-commits
Differential Revision: https://reviews.llvm.org/D40444
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319771 91177308-0d34-0410-b5e6-96231b3b80d8
MatchRotate assumes the types of the types of LHS and RHS are equal,
which is always the case then they come from an OR node, but here
we're getting them from two different TRUNC nodes, so we have to check
the types.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319695 91177308-0d34-0410-b5e6-96231b3b80d8
visitAND attempts to narrow the width of extending loads that are
then masked off. ReduceLoadWidth already exists for a similar purpose
and handles shifts, so I've moved the code to handle AND nodes there.
Differential Revision: https://reviews.llvm.org/D39595
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319421 91177308-0d34-0410-b5e6-96231b3b80d8
This is needed for cases when the memory access is not as big as the width of
the data type. For instance, storing i1 (1 bit) would be done in a byte (8
bits).
Using 'BitSize >> 3' (or '/ 8') would e.g. give the memory access of an i1 a
size of 0, which for instance makes alias analysis return NoAlias even when
it shouldn't.
There are no tests as this was done as a follow-up to the bugfix for the case
where this was discovered (r318824). This handles more similar cases.
Review: Björn Petterson
https://reviews.llvm.org/D40339
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319173 91177308-0d34-0410-b5e6-96231b3b80d8
Unoptimized IR can have linear sequences of stores to an array, where the
initial GEP for the first store is formed from the pointer to the array, and the
GEP for each store after the first is formed from the previous GEP with some
offset in an inductive fashion.
The (large) resulting DAG when analyzed by DAGCombine undergoes an excessive
number of combines as each store node is examined every time its' offset node
is combined with any child of the offset. One of the transformations is
findBetterNeighborChains which assists MergeConsecutiveStores. The former
relies on repeated chain walking to do its' work, however MergeConsecutiveStores
is disabled at O0 which makes the transformation redundant.
Any optimization level other than O0 would invoke InstCombine which would
resolve the chain of GEPs into flat base + offset GEP for each store which
does not exhibit the repeated examination of each store to the array.
Disabling this optimization fixes an excessive compile time issue (30~ minutes
for the test case provided) at O0.
Reviewers: niravd, craig.topper, t.p.northover
Differential Revision: https://reviews.llvm.org/D40193
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319142 91177308-0d34-0410-b5e6-96231b3b80d8
With AVX512 vXi1 types are legal so we shouldn't be extending them.
This change is similar to existing code in the zext(setcc) combine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319120 91177308-0d34-0410-b5e6-96231b3b80d8
Since i1 is a legal type, this:
NumBytes = Op1->getMemoryVT().getSizeInBits() >> 3;
is wrong and should be instead
NumBytes = Op0->getMemoryVT().getStoreSize();
There seems to be more places where this should be fixed outside DAGCombiner.
Review: Hal Finkel
https://bugs.llvm.org/show_bug.cgi?id=35366
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@318824 91177308-0d34-0410-b5e6-96231b3b80d8
All these headers already depend on CodeGen headers so moving them into
CodeGen fixes the layering (since CodeGen depends on Target, not the
other way around).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@318490 91177308-0d34-0410-b5e6-96231b3b80d8
Sam Parker