Repeated inserts into AliasSetTracker have quadratic behavior - inserting a
pointer into AST is linear, since it requires walking over all "may" alias
sets and running an alias check vs. every pointer in the set.
We can avoid this by tracking the total number of pointers in "may" sets,
and when that number exceeds a threshold, declare the tracker "saturated".
This lumps all pointers into a single "may" set that aliases every other
pointer.
(This is a stop-gap solution until we migrate to MemorySSA)
This fixes PR28832.
Differential Revision: https://reviews.llvm.org/D23432
llvm-svn: 279274
The patch is to fix the bug in PR28705. It was caused by setting wrong return
value for SCEVExpander::findExistingExpansion. The return values of findExistingExpansion
have different meanings when the function is used in different ways so it is easy to make
mistake. The fix creates two new interfaces to replace SCEVExpander::findExistingExpansion,
and specifies where each interface is expected to be used.
Differential Revision: https://reviews.llvm.org/D22942
llvm-svn: 278161
The fix for PR28705 will be committed consecutively.
In D12090, the ExprValueMap was added to reuse existing value during SCEV expansion.
However, const folding and sext/zext distribution can make the reuse still difficult.
A simplified case is: suppose we know S1 expands to V1 in ExprValueMap, and
S1 = S2 + C_a
S3 = S2 + C_b
where C_a and C_b are different SCEVConstants. Then we'd like to expand S3 as
V1 - C_a + C_b instead of expanding S2 literally. It is helpful when S2 is a
complex SCEV expr and S2 has no entry in ExprValueMap, which is usually caused
by the fact that S3 is generated from S1 after const folding.
In order to do that, we represent ExprValueMap as a mapping from SCEV to
ValueOffsetPair. We will save both S1->{V1, 0} and S2->{V1, C_a} into the
ExprValueMap when we create SCEV for V1. When S3 is expanded, it will first
expand S2 to V1 - C_a because of S2->{V1, C_a} in the map, then expand S3 to
V1 - C_a + C_b.
Differential Revision: https://reviews.llvm.org/D21313
llvm-svn: 278160
Shifts with a uniform but non-constant count were considered very expensive to
vectorize, because the splat of the uniform count and the shift would tend to
appear in different blocks. That made the splat invisible to ISel, and we'd
scalarize the shift at codegen time.
Since r201655, CodeGenPrepare sinks those splats to be next to their use, and we
are able to select the appropriate vector shifts. This updates the cost model to
to take this into account by making shifts by a uniform cheap again.
Differential Revision: https://reviews.llvm.org/D23049
llvm-svn: 277782
As it turns out, modref queries are broken with CFLAA. Specifically,
the data source we were using for determining modref behaviors
explicitly ignores operations on non-pointer values. So, it wouldn't
note e.g. storing an i32 to an i32* (or loading an i64 from an i64*).
It also ignores external function calls, rather than acting
conservatively for them.
(N.B. These operations, where necessary, *are* tracked by CFLAA; we just
use a different mechanism to do so. Said mechanism is relatively
imprecise, so it's unlikely that we can provide reasonably good modref
answers with it as implemented.)
Patch by Jia Chen.
Differential Revision: https://reviews.llvm.org/D22978
llvm-svn: 277366
Summary:
The motivation is the same as in D22141: In order to add the hotness
attribute to optimization remarks we need BFI to be available in all
passes that emit optimization remarks. BFI depends on BPI so unless we
make this lazy as well we would still compute BPI unconditionally.
The solution is to use the new LazyBPI pass in LazyBFI and only compute
BPI when computation of BFI is requested by the client.
I extended the laziness test using a LoopDistribute test to also cover
BPI.
Reviewers: hfinkel, davidxl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D22835
llvm-svn: 277083
This patch lets CFLAnders respond to mod-ref queries. It also includes
a small bugfix to CFLSteens.
Patch by Jia Chen.
Differential Revision: https://reviews.llvm.org/D22823
llvm-svn: 276939
This change lets us prove things like
"{X,+,10} s< 5000" implies "{X+7,+,10} does not sign overflow"
It does this by replacing replacing getConstantDifference by
computeConstantDifference (which is smarter) in
isImpliedCondOperandsViaRanges.
llvm-svn: 276505
In D12090, the ExprValueMap was added to reuse existing value during SCEV expansion.
However, const folding and sext/zext distribution can make the reuse still difficult.
A simplified case is: suppose we know S1 expands to V1 in ExprValueMap, and
S1 = S2 + C_a
S3 = S2 + C_b
where C_a and C_b are different SCEVConstants. Then we'd like to expand S3 as
V1 - C_a + C_b instead of expanding S2 literally. It is helpful when S2 is a
complex SCEV expr and S2 has no entry in ExprValueMap, which is usually caused
by the fact that S3 is generated from S1 after const folding.
In order to do that, we represent ExprValueMap as a mapping from SCEV to
ValueOffsetPair. We will save both S1->{V1, 0} and S2->{V1, C_a} into the
ExprValueMap when we create SCEV for V1. When S3 is expanded, it will first
expand S2 to V1 - C_a because of S2->{V1, C_a} in the map, then expand S3 to
V1 - C_a + C_b.
Differential Revision: https://reviews.llvm.org/D21313
llvm-svn: 276136
This patch adds costs for the vectorized implementations of CTPOP, the default values were seriously underestimating the cost of these and was encouraging vectorization on targets where serialized use of POPCNT would be much better.
Differential Revision: https://reviews.llvm.org/D22456
llvm-svn: 276104
This patch adds function summary support to CFLAnders. It also comes
with a lot of tests! Woohoo!
Patch by Jia Chen.
Differential Revision: https://reviews.llvm.org/D22450
llvm-svn: 276026
This patch adds proper handling of stratified attributes into our
anders-style CFLAA implementation. It also comes bundled with more
CFLAnders tests. :)
Patch by Jia Chen.
Differential Revision: https://reviews.llvm.org/D22325
llvm-svn: 275604
This adds an incomplete anders-style implementation for CFLAA. It's
incomplete in that it's missing interprocedural analysis, attrs
handling, etc. and that it needs more tests. More tests and features
will be added in future commits.
Patch by Jia Chen.
Differential Revision: https://reviews.llvm.org/D22291
llvm-svn: 275602
Summary:
In preparation for changing GlobalsAA to stop assuming that intrinsics
can't read arbitrary globals, we need to make sure GlobalsAA is querying
function attributes rather than relying on this assumption.
This patch was inspired by: http://reviews.llvm.org/D20206
Reviewers: jmolloy, hfinkel
Subscribers: eli.friedman, llvm-commits
Differential Revision: https://reviews.llvm.org/D21318
llvm-svn: 275433
Summary:
This is necessary for D21771. In order to add the hotness attribute to
optimization remarks we need BFI to be available in all passes that emit
optimization remarks.
However we don't want to pay for computing BFI unless the hotness
attribute is requested.
This is achieved by making BFI lazy at the very high-level through a new
analysis pass -- BFI is not calculated unless requested.
I am adding a test to check the laziness under D21771 where the first
user of the analysis is added.
Reviewers: hfinkel, dexonsmith, davidxl
Subscribers: davidxl, dexonsmith, llvm-commits
Differential Revision: http://reviews.llvm.org/D22141
llvm-svn: 275250
Make some AVX and AVX512 cast costs more precise.
Based on part of a patch by Elena Demikhovsky (D15604).
Differential Revision: http://reviews.llvm.org/D22064
llvm-svn: 275106
For functions which are known to return their argument,
isDereferenceableAndAlignedPointer can examine the argument value.
Differential Revision: http://reviews.llvm.org/D9384
llvm-svn: 275038
When building SCEVs, if a function is known to return its argument, then we can
build the SCEV using the corresponding argument value.
Differential Revision: http://reviews.llvm.org/D9381
llvm-svn: 275037
Motivated by the work on the llvm.noalias intrinsic, teach BasicAA to look
through returned-argument functions when answering queries. This is essential
so that we don't loose all other AA information when supplementing with
llvm.noalias.
Differential Revision: http://reviews.llvm.org/D9383
llvm-svn: 275035
This is a follow-on to r274452.
The LAA with the new PM is a loop pass so we go from inner to outer loops.
Also using a CHECK-NOT didn't make much sense because we print something
in either case; whether an invariant is 'found' or 'not found'.
llvm-svn: 274935
- Rename the ptx.read.* intrinsics to nvvm.read.ptx.sreg.* - some but
not all of these registers were already accessible via the nvvm
name.
- Rename ptx.bar.sync nvvm.bar.sync, to match nvvm.bar0.
There's a fair amount of code motion here, but it's all very
mechanical.
llvm-svn: 274769
This is "cvtdq2ps" which does not appear to be particularly slow on any CPU
according to Agner's tables. Choosing "5" as a cost here as suggested in:
https://llvm.org/bugs/show_bug.cgi?id=21356
...but it seems very conservative given that the instruction is fully pipelined,
and I think these costs are supposed to model throughput.
Note that related costs are also most likely too high, but this fixes PR21356
and partly fixes PR28434.
llvm-svn: 274658
The cost model should not assume vector casts get completely scalarized, since
on targets that have vector support, the common case is a partial split up to
the legal vector size. So, when a vector cast gets split, the resulting casts
end up legal and cheap.
Instead of pessimistically assuming scalarization, base TTI can use the costs
the concrete TTI provides for the split vector, plus a fudge factor to account
for the cost of the split itself. This fudge factor is currently 1 by default,
except on AMDGPU where inserts and extracts are considered free.
Differential Revision: http://reviews.llvm.org/D21251
llvm-svn: 274642
StratifiedSets (as implemented) is very fast, but its accuracy is also
limited. If we take a more aggressive andersens-like approach, we can be
way more accurate, but we'll also end up being slower.
So, we've decided to split CFLAA into CFLSteensAA and CFLAndersAA.
Long-term, we want to end up in a place where CFLSteens is queried
first; if it can provide an answer, great (since queries are basically
map lookups). Otherwise, we'll fall back to CFLAnders, BasicAA, etc.
This patch splits everything out so we can try to do something like
that when we get a reasonable CFLAnders implementation.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21910
llvm-svn: 274589
This patch corresponds to review:
http://reviews.llvm.org/D20443
It changes the legalization strategy for illegal vector types from integer
promotion to widening. This only applies for vectors with elements of width
that is a multiple of a byte since we have hardware support for vectors with
1, 2, 3, 8 and 16 byte elements.
Integer promotion for vectors is quite expensive on PPC due to the sequence
of breaking apart the vector, extending the elements and reconstituting the
vector. Two of these operations are expensive.
This patch causes between minor and major improvements in performance on most
benchmarks. There are very few benchmarks whose performance regresses. These
regressions can be handled in a subsequent patch with a DAG combine (similar
to how this patch handles int -> fp conversions of illegal vector types).
llvm-svn: 274535
Summary:
This complements the earlier addition of IntrWriteMem and IntrWriteArgMem
LLVM intrinsic properties, see D18291.
Also start using the attribute for memset, memcpy, and memmove intrinsics,
and remove their special-casing in BasicAliasAnalysis.
Reviewers: reames, joker.eph
Subscribers: joker.eph, llvm-commits
Differential Revision: http://reviews.llvm.org/D18714
llvm-svn: 274485
This patch makes CFLAA answer some ModRef queries. Because we don't
distinguish between reading/writing when making StratifiedSets, we're
unable to offer any of the readonly-related answers.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21858
llvm-svn: 274197
This is a resubmittion of 263158 change after fixing the existing problem with intrinsics mangling (see LTO and intrinsics mangling llvm-dev thread for details).
This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.
The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.
Reviewed By: reames
Differential Revision: http://reviews.llvm.org/D17270
llvm-svn: 274043
This is a resubmittion of 263158 change after fixing the existing problem with intrinsics mangling (see LTO and intrinsics mangling llvm-dev thread for details).
This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.
The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.
Reviewed By: reames
Differential Revision: http://reviews.llvm.org/D17270
llvm-svn: 273892
This patch also has a refactor that kills StratifiedAttr, and leaves us
with StratifiedAttrs, because having both was mildly redundant.
This patch makes us correctly handle stratified attributes when doing
interprocedural analysis. It also adds another attribute, AttrCaller,
which acts like AttrUnknown. We can filter out AttrCaller values when
during interprocedural analysis, since the caller should have
information about what arguments it's passing to its callee.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21645
llvm-svn: 273636
Previously, we just unified any arguments that seemed to be related to
each other. With this patch, we now respect dereference levels, etc.
which should make us substantially more accurate. Proper handling of
StratifiedAttrs will be done in a later patch.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21536
llvm-svn: 273596
This patch makes us perform interprocedural analysis on functions that
don't have internal linkage. It also removes a test that should've been
deleted in an earlier commit (since other tests now cover everything
that the newly-removed test covers).
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21513
llvm-svn: 273229
This patch adds function summaries, so that we don't need to recompute
various properties about function parameters/return values at each
callsite of a function. It also adds many interprocedural tests for
CFLAA.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21475#inline-182390
llvm-svn: 273219
The BSWAP of vector types is quite efficiently implemented using vector shuffles on SSE/AVX targets, we should reflect the typical cost of this to encourage vectorization.
Differential Revision: http://reviews.llvm.org/D21521
llvm-svn: 273217
The way we elide max expressions when computing trip counts is incorrect
-- it breaks cases like this:
```
static int wrapping_add(int a, int b) {
return (int)((unsigned)a + (unsigned)b);
}
void test() {
volatile int end_buf = 2147483548; // INT_MIN - 100
int end = end_buf;
unsigned counter = 0;
for (int start = wrapping_add(end, 200); start < end; start++)
counter++;
print(counter);
}
```
Note: the `NoWrap` variable that was being tested has little to do with
the values flowing into the max expression; it is a property of the
induction variable.
test/Transforms/LoopUnroll/nsw-tripcount.ll was added to solely test
functionality I'm reverting in this change, so I've deleted the test
fully.
llvm-svn: 273079
This patch also includes some refactoring.
Prior to this patch, we tagged all CFLAA attributes as unknown. This is
suboptimal, since it meant that any Value used as an argument would be
considered to alias any other Value that existed.
Now that we have the machinery to tag sets below the set for an
arbitrary value with attributes, it's okay to be less conservative with
arguments. (Specifically, we still tag the set under an argument with
unknown).
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21262
llvm-svn: 272690
The costs are somewhat hand-wavy, but should be much closer to the truth
than what we get from BasicTTI.
Differential Revision: http://reviews.llvm.org/D21156
llvm-svn: 272406
Prior to this patch, we used argument/global stratified attributes in
order to note that a value could have come from either dereferencing a
global/arg, or from the assignment from a global/arg.
Now, AttrUnknown is placed on sets when we see a dereference, instead of
the global/arg attributes. This allows us to be more aggressive in the
future when we see global/arg attributes without AttrUnknown.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21110
llvm-svn: 272335
We can safely rely on a NoWrap add recurrence causing UB down the road
only if we know the loop does not have a exit expressed in a way that is
opaque to ScalarEvolution (e.g. by a function call that conditionally
calls exit(0)).
I believe with this change PR28012 is fixed.
Note: I had to change some llvm-lit tests in LoopReroll, since it looks
like they were depending on this incorrect behavior.
llvm-svn: 272237
Absence of may-unwind calls is not enough to guarantee that a
UB-generating use of an add-rec poison in the loop latch will actually
cause UB. We also need to guard against calls that terminate the thread
or infinite loop themselves.
This partially addresses PR28012.
llvm-svn: 272181
The worklist algorithm introduced in rL271151 didn't check to see if the
direct users of the post-inc add recurrence propagates poison. This
change fixes the problem and makes the code structure more obvious.
Note for release managers: correctness wise, this bug wasn't a
regression introduced by rL271151 -- the behavior of SCEV around
post-inc add recurrences was strictly improved (in terms of correctness)
in rL271151.
llvm-svn: 272179
This patch does a few things:
- Unifies AttrAll and AttrUnknown (since they were used for more or less
the same purpose anyway).
- Introduces AttrEscaped, an attribute that notes that a value escapes
our analysis for a given set, but not that an unknown value flows into
said set.
- Removes functions that take bit indices, since we also had functions
that took bitsets, and the use of both (with similar names) was
unclear and bug-prone.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D21000
llvm-svn: 272040
This patch extends CFLAA to recognize allocation functions such as
malloc, free, etc, so we can treat them more aggressively.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D20776
llvm-svn: 271421
Patch by Taewook Oh
Summary: Patch for Bug 27478. Make BasicAliasAnalysis claims NoAlias if two GEPs index different fields of the same structure.
Reviewers: hfinkel, dberlin
Subscribers: dberlin, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D20665
llvm-svn: 271415
Summary:
Change some of the internal interfaces in Loads.cpp to keep track of the
number of bytes we're trying to prove dereferenceable using an explicit
`Size` parameter.
Before this, the `Size` parameter was implicitly inferred from the
pointee type of the pointer whose dereferenceability we were trying to
prove, causing us to be conservative around bitcasts. This was
unfortunate since bitcast instructions are no-ops and should never
break optimizations. With an explicit `Size` parameter, we're more
precise (as shown in the test cases), and the code is simpler.
We should eventually move towards a `DerefQuery` struct that groups
together a base pointer, an offset, a size and an alignment; but this
patch is a first step.
Reviewers: apilipenko, dblaikie, hfinkel, reames
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D20764
llvm-svn: 271406
Code like the following is considered broken, and doesn't need to be
supported by our AA magicks:
void getFoo(int *P) {
int *PAlias = (int *)((char *)NULL + (uintptr_t)P);
}
This patch makes CFLAA drop support for code like this.
Patch by Jia Chen.
Differential Revision: http://reviews.llvm.org/D20775
llvm-svn: 271322
Summary:
This change teaches SCEV to see reduce `(extractvalue
0 (op.with.overflow X Y))` into `op X Y` (with a no-wrap tag if
possible).
This was first checked in at r265912 but reverted in r265950 because it
exposed some issues around how SCEV handled post-inc add recurrences.
Those issues have now been fixed.
Reviewers: atrick, regehr
Subscribers: mcrosier, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D18684
llvm-svn: 271152
Fixes PR27315.
The post-inc version of an add recurrence needs to "follow the same
rules" as a normal add or subtract expression. Otherwise we miscompile
programs like
```
int main() {
int a = 0;
unsigned a_u = 0;
volatile long last_value;
do {
a_u += 3;
last_value = (long) ((int) a_u);
if (will_add_overflow(a, 3)) {
// Leave, and don't actually do the increment, so no UB.
printf("last_value = %ld\n", last_value);
exit(0);
}
a += 3;
} while (a != 46);
return 0;
}
```
This patch changes SCEV to put no-wrap flags on post-inc add recurrences
only when the poison from a potential overflow will go ahead to cause
undefined behavior.
To avoid regressing performance too much, I've assumed infinite loops
without side effects is undefined behavior to prove poison<->UB
equivalence in more cases. This isn't ideal, but is not new to LLVM as
a whole, and far better than the situation I'm trying to fix.
llvm-svn: 271151
r270777 improved the precision of alloca vs. inbounbds GEP alias queries: if
we have (a) an inbounds GEP and (b) a pointer based on an alloca, and the
beginning of the object the GEP points to would have a negative offset with
respect to the alloca, then the GEP can not alias pointer (b).
This makes the same logic fire when (b) is based on a GlobalVariable instead
of an alloca.
Differential Revision: http://reviews.llvm.org/D20652
llvm-svn: 270893
If a we have (a) a GEP and (b) a pointer based on an alloca, and the
beginning of the object the GEP points would have a negative offset with
repsect to the alloca, then the GEP can not alias pointer (b).
For example, consider code like:
struct { int f0, int f1, ...} foo;
...
foo alloca;
foo *random = bar(alloca);
int *f0 = &alloca.f0
int *f1 = &random->f1;
Which is lowered, approximately, to:
%alloca = alloca %struct.foo
%random = call %struct.foo* @random(%struct.foo* %alloca)
%f0 = getelementptr inbounds %struct, %struct.foo* %alloca, i32 0, i32 0
%f1 = getelementptr inbounds %struct, %struct.foo* %random, i32 0, i32 1
Assume %f1 and %f0 alias. Then %f1 would point into the object allocated
by %alloca. Since the %f1 GEP is inbounds, that means %random must also
point into the same object. But since %f0 points to the beginning of %alloca,
the highest %f1 can be is (%alloca + 3). This means %random can not be higher
than (%alloca - 1), and so is not inbounds, a contradiction.
Differential Revision: http://reviews.llvm.org/D20495
llvm-svn: 270777
Summary:
**Description**
This makes `WidenIV::widenIVUse` (IndVarSimplify.cpp) fail to widen narrow IV uses in some cases. The latter affects IndVarSimplify which may not eliminate narrow IV's when there actually exists such a possibility, thereby producing ineffective code.
When `WidenIV::widenIVUse` gets a NarrowUse such as `{(-2 + %inc.lcssa),+,1}<nsw><%for.body3>`, it first tries to get a wide recurrence for it via the `getWideRecurrence` call.
`getWideRecurrence` returns recurrence like this: `{(sext i32 (-2 + %inc.lcssa) to i64),+,1}<nsw><%for.body3>`.
Then a wide use operation is generated by `cloneIVUser`. The generated wide use is evaluated to `{(-2 + (sext i32 %inc.lcssa to i64))<nsw>,+,1}<nsw><%for.body3>`, which is different from the `getWideRecurrence` result. `cloneIVUser` sees the difference and returns nullptr.
This patch also fixes the broken LLVM tests by adding missing <nsw> entries introduced by the correction.
**Minimal reproducer:**
```
int foo(int a, int b, int c);
int baz();
void bar()
{
int arr[20];
int i = 0;
for (i = 0; i < 4; ++i)
arr[i] = baz();
for (; i < 20; ++i)
arr[i] = foo(arr[i - 4], arr[i - 3], arr[i - 2]);
}
```
**Clang command line:**
```
clang++ -mllvm -debug -S -emit-llvm -O3 --target=aarch64-linux-elf test.cpp -o test.ir
```
**Expected result:**
The ` -mllvm -debug` log shows that all the IV's for the second `for` loop have been eliminated.
Reviewers: sanjoy
Subscribers: atrick, asl, aemerson, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D20058
llvm-svn: 270695
This patch changes the order in which we attempt to prove the independence of
strided accesses. We previously did this after we knew the dependence distance
was positive. With this change, we check for independence before handling the
negative distance case. The patch prevents LAA from reporting forward
dependences for independent strided accesses.
This change was requested in the review of D19984.
llvm-svn: 270072
... for AddRec's in loops for which SCEV is unable to compute a max
tripcount. This is the NUW variant of r269211 and fixes PR27691.
(Note: PR27691 is not a correct or stability bug, it was created to
track a pending task).
llvm-svn: 269790
SCEVExpander::replaceCongruentIVs assumes the backedge value of an
SCEV-analysable PHI to always be an instruction, when this is not
necessarily true. For now address this by bailing out of the
optimization if the backedge value of the PHI is a non-Instruction.
llvm-svn: 269213
`SCEVExpander::replaceCongruentIVs` bypasses `hoistIVInc` if both the
original and the isomorphic increments are PHI nodes. Doing this can
break SSA if the isomorphic increment is not dominated by the original
increment. Get rid of the bypass, and let `hoistIVInc` do the right
thing.
Fixes PR27232 (compile time crash/hang).
llvm-svn: 269212
... for AddRec's in loops for which SCEV is unable to compute a max
tripcount. This is not a problem for "normal" loops[0] that don't have
guards or assumes, but helps in cases where we have guards or assumes in
the loop that can be used to constrain incoming values over the backedge.
This partially fixes PR27691 (we still don't handle the NUW case).
[0]: for "normal" loops, in the cases where we'd be able to prove
no-wrap via isKnownPredicate, we'd also be able to compute a max
tripcount.
llvm-svn: 269211
Equivalent GEP indices with different types are treated as different
indices altogether, leading to an incorrect AA result. Fix the issue
by comparing indices based on their values.
Thanks to Mikael Holmén for reporting the issue!
Differential Revision: http://reviews.llvm.org/D19935
llvm-svn: 269197
Summary:
The idea is very close to what we do for assume intrinsics: we mark the
guard intrinsics as writing to arbitrary memory to maintain control
dependence, but under the covers we teach AA that they do not mod any
particular memory location.
Reviewers: chandlerc, hfinkel, gbiv, reames
Subscribers: george.burgess.iv, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D19575
llvm-svn: 269007
We can use calls to @llvm.experimental.guard to prove predicates,
relying on the fact that in all locations domianted by a call to
@llvm.experimental.guard the predicate it is guarding is known to be
true.
llvm-svn: 268997
As discussed on PR24888, until SSE42 we don't have access to PCMPGTQ for v2i64 comparisons, but the cost models don't reflect this, resulting in over-optimistic vectorizaton.
This patch adds SSE2 'base level' costs that match what a typical target is capable of and only reduces the v2i64 costs at SSE42.
Technically SSE41 provides a PCMPEQQ v2i64 equality test, but as getCmpSelInstrCost doesn't give us a way to discriminate between comparison test types we can't easily make use of this, otherwise we could split the cost of integer equality and greater-than tests to give better costings of each.
Differential Revision: http://reviews.llvm.org/D20057
llvm-svn: 268972
In the "LoopDispositions:" section:
- Instead of printing out a list, print out a "dictionary" to make it
obvious by inspection which disposition is for which loop. This is
just a cosmetic change.
- Print dispositions for parent _and_ sibling loops. I will use this
to write a test case.
llvm-svn: 268405
Summary:
This intrinsic is used to get flat-shaded fragment shader inputs. Those are
uniform across a primitive, but a fragment shader wave may process pixels from
multiple primitives (as indicated by the prim_mask), and so that's where
divergence can arise.
Reviewers: arsenm, tstellarAMD
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D19747
llvm-svn: 268259
There are currently some bugs in tree around SCEV caching an incorrect
loop disposition. Printing out loop dispositions will let us write
whitebox tests as those are fixed.
The dispositions are printed as a list in "inside out" order,
i.e. innermost loop first.
llvm-svn: 268177
Teach Value::getPointerAlignment that allocas with no explicit alignment are aligned to preferred alignment of the allocated type.
Reviewed By: hfinkel
Differential Revision: http://reviews.llvm.org/D17569
llvm-svn: 267689
Summary:
This implements a new method of run-time checking the NoWrap
SCEV predicates, which should be easier to optimize and nicer
for targets that don't correctly handle multiplication/addition
of large integer types (like i128).
If the AddRec is {a,+,b} and the backedge taken count is c,
the idea is to check that |b| * c doesn't have unsigned overflow,
and depending on the sign of b, that:
a + |b| * c >= a (b >= 0) or
a - |b| * c <= a (b <= 0)
where the comparisons above are signed or unsigned, depending on
the flag that we're checking.
The advantage of doing this is that we avoid extending to a larger
type and we avoid the multiplication of large types (multiplying
i128 can be expensive).
Reviewers: sanjoy
Subscribers: llvm-commits, mzolotukhin
Differential Revision: http://reviews.llvm.org/D19266
llvm-svn: 267389
Summary:
(... while still not using a PostDomTree)
The way we use isKnownNotFullPoison from SCEV today, the new CFG walking
logic will not trigger for any realistic cases -- it will kick in only
for situations where we could have merged the contiguous basic blocks
anyway[0], since the poison generating instruction dominates all of its
non-PHI uses (which are the only uses we consider right now).
However, having this change in place will allow a later bugfix to break
fewer llvm-lit tests.
[0]: i.e. cases where block A branches to block B and B is A's only
successor and A is B's only predecessor.
Reviewers: broune, bjarke.roune
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D19212
llvm-svn: 267175
Summary:
rL256194 transforms truncations between vectors of integers into PACKUS/PACKSS
operations during DAG combine. This generates better code for truncate, so cost
of truncate needs to be changed but looks like it got changed only in SSE2 table
Whereas this change is also applicable for SSE4.1, so the cost of truncate needs
to be changed for that as well. Cost of “TRUNCATE v16i32 to v16i8” & “TRUNCATE
v16i16 to v16i8” should be same in SSE4.1 & SSE2 table. Removing their cost from
SSE4.1, so it will fall back to SSE2.
Reviewers: Simon Pilgrim
llvm-svn: 267123
Summary:
Calls to @llvm.experimental.deoptimize are expected to "never execute",
so optimize them as such.
Reviewers: chandlerc
Subscribers: junbuml, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D19095
llvm-svn: 266654
Summary:
If a PHI has an incoming undef, we can pretend that it is equal to one
non-undef, non-self incoming value.
This is particularly relevant in combination with the StructurizeCFG
pass, which introduces PHI nodes with undefs. Previously, this lead to
branch conditions that were uniform before StructurizeCFG to become
non-uniform afterwards, which confused the SIAnnotateControlFlow
pass.
This fixes a crash when Mesa radeonsi compiles a shader from
dEQP-GLES3.functional.shaders.switch.switch_in_for_loop_dynamic_vertex
Reviewers: arsenm, tstellarAMD, jingyue
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D19013
llvm-svn: 266347
Summary:
Add a print method to Predicated Scalar Evolution which prints all interesting
transformations done by PSE.
Loop Access Analysis will now print this as part of the analysis output.
We now use this to check the exact expression transformations that were done
by PSE in LAA.
The additional checking also acts as white-box testing for the getAsAddRec method.
Reviewers: anemet, sanjoy
Subscribers: sanjoy, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D18792
llvm-svn: 266334
This is a resubmittion of 263158 change.
This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.
The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.
Reviewed By: reames
Differential Revision: http://reviews.llvm.org/D17270
llvm-svn: 266086
Summary:
This change teaches SCEV to see reduce `(extractvalue
0 (op.with.overflow X Y))` into `op X Y` (with a no-wrap tag if
possible).
Reviewers: atrick, regehr
Subscribers: mcrosier, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D18684
llvm-svn: 265912
This re-commits r265535 which was reverted in r265541 because it
broke the windows bots. The problem was that we had a PointerIntPair
which took a pointer to a struct allocated with new. The problem
was that new doesn't provide sufficient alignment guarantees.
This pattern was already present before r265535 and it just happened
to work. To fix this, we now separate the PointerToIntPair from the
ExitNotTakenInfo struct into a pointer and a bool.
Original commit message:
Summary:
When the backedge taken codition is computed from an icmp, SCEV can
deduce the backedge taken count only if one of the sides of the icmp
is an AddRecExpr. However, due to sign/zero extensions, we sometimes
end up with something that is not an AddRecExpr.
However, we can use SCEV predicates to produce a 'guarded' expression.
This change adds a method to SCEV to get this expression, and the
SCEV predicate associated with it.
In HowManyGreaterThans and HowManyLessThans we will now add a SCEV
predicate associated with the guarded backedge taken count when the
analyzed SCEV expression is not an AddRecExpr. Note that we only do
this as an alternative to returning a 'CouldNotCompute'.
We use new feature in Loop Access Analysis and LoopVectorize to analyze
and transform more loops.
Reviewers: anemet, mzolotukhin, hfinkel, sanjoy
Subscribers: flyingforyou, mcrosier, atrick, mssimpso, sanjoy, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D17201
llvm-svn: 265786
Summary:
Fixes PR26774.
If you're aware of the issue, feel free to skip the "Motivation"
section and jump directly to "This patch".
Motivation:
I define "refinement" as discarding behaviors from a program that the
optimizer has license to discard. So transforming:
```
void f(unsigned x) {
unsigned t = 5 / x;
(void)t;
}
```
to
```
void f(unsigned x) { }
```
is refinement, since the behavior went from "if x == 0 then undefined
else nothing" to "nothing" (the optimizer has license to discard
undefined behavior).
Refinement is a fundamental aspect of many mid-level optimizations done
by LLVM. For instance, transforming `x == (x + 1)` to `false` also
involves refinement since the expression's value went from "if x is
`undef` then { `true` or `false` } else { `false` }" to "`false`" (by
definition, the optimizer has license to fold `undef` to any non-`undef`
value).
Unfortunately, refinement implies that the optimizer cannot assume
that the implementation of a function it can see has all of the
behavior an unoptimized or a differently optimized version of the same
function can have. This is a problem for functions with comdat
linkage, where a function can be replaced by an unoptimized or a
differently optimized version of the same source level function.
For instance, FunctionAttrs cannot assume a comdat function is
actually `readnone` even if it does not have any loads or stores in
it; since there may have been loads and stores in the "original
function" that were refined out in the currently visible variant, and
at the link step the linker may in fact choose an implementation with
a load or a store. As an example, consider a function that does two
atomic loads from the same memory location, and writes to memory only
if the two values are not equal. The optimizer is allowed to refine
this function by first CSE'ing the two loads, and the folding the
comparision to always report that the two values are equal. Such a
refined variant will look like it is `readonly`. However, the
unoptimized version of the function can still write to memory (since
the two loads //can// result in different values), and selecting the
unoptimized version at link time will retroactively invalidate
transforms we may have done under the assumption that the function
does not write to memory.
Note: this is not just a problem with atomics or with linking
differently optimized object files. See PR26774 for more realistic
examples that involved neither.
This patch:
This change introduces a new set of linkage types, predicated as
`GlobalValue::mayBeDerefined` that returns true if the linkage type
allows a function to be replaced by a differently optimized variant at
link time. It then changes a set of IPO passes to bail out if they see
such a function.
Reviewers: chandlerc, hfinkel, dexonsmith, joker.eph, rnk
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D18634
llvm-svn: 265762
This makes it possible to distinguish between mesa shaders
and other kernels even in the presence of compute shaders.
Patch By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Differential Revision: http://reviews.llvm.org/D18559
llvm-svn: 265589
Summary:
When the backedge taken codition is computed from an icmp, SCEV can
deduce the backedge taken count only if one of the sides of the icmp
is an AddRecExpr. However, due to sign/zero extensions, we sometimes
end up with something that is not an AddRecExpr.
However, we can use SCEV predicates to produce a 'guarded' expression.
This change adds a method to SCEV to get this expression, and the
SCEV predicate associated with it.
In HowManyGreaterThans and HowManyLessThans we will now add a SCEV
predicate associated with the guarded backedge taken count when the
analyzed SCEV expression is not an AddRecExpr. Note that we only do
this as an alternative to returning a 'CouldNotCompute'.
We use new feature in Loop Access Analysis and LoopVectorize to analyze
and transform more loops.
Reviewers: anemet, mzolotukhin, hfinkel, sanjoy
Subscribers: flyingforyou, mcrosier, atrick, mssimpso, sanjoy, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D17201
llvm-svn: 265535
Prior to this patch, CFLAA wouldn't tag arguments/globals properly if
it didn't find any "interesting" edges on them. This means that, if all
you do is store constants to a global or argument, we would never
actually treat it as a global/argument.
Test case:
define void @foo(i32* %A, i32* %B) #0 {
entry:
store i32 0, i32* %A, align 4
store i32 0, i32* %B, align 4
ret void
}
CFLAA would say that %A can't alias %B, because neither pointer was
used in an interesting way. This patch makes us note whether something
is an argument, global, ... regardless of how interesting CFLAA thinks
its uses are.
(For the record, using a value in an interesting way means loading
from it, using it in a GEP, ...)
llvm-svn: 265474
A seg-fault occurs due to a reference of a null pointer, which is
the value returned by getConstantPart. This function returns
null if the constant part is not found. The code that calls this
function needs to check for the null return value.
Differential Revision: http://reviews.llvm.org/D18718
llvm-svn: 265319
PPC has a vector popcount, this lets the vectorizer use the correct cost
for it. Tweak X86 test to use an intrinsic that's actually scalarized (we
have a somewhat efficient lowering for vector popcount using SSE, the
cost model finds that now).
llvm-svn: 265005
We used to only allow SCEVAddRecExpr for pointer expressions in order to
be able to compute the bounds. However this is also trivially possible
for loop-invariant addresses (scUnknown) since then the bounds are the
address itself.
Interestingly, we used allow this for the special case when the
loop-invariant address happens to also be an SCEVAddRecExpr (in an outer
loop).
There are a couple more loops that are vectorized in SPEC after this.
My guess is that the main reason we don't see more because for example a
loop-invariant load is vectorized into a splat vector with several
vector-inserts. This is likely to make the vectorization unprofitable.
I.e. we don't notice that a later LICM will move all of this out of the
loop so the cost estimate should really be 0.
llvm-svn: 264243
Summary:
These intrinsics expose the BUFFER_ATOMIC_* instructions and will be used
by Mesa to implement atomics with buffer semantics. The intrinsic interface
matches that of buffer.load.format and buffer.store.format, except that the
GLC bit is not exposed (it is automatically deduced based on whether the
return value is used).
The change of hasSideEffects is required for TableGen to accept the pattern
that matches the intrinsic.
Reviewers: tstellarAMD, arsenm
Subscribers: arsenm, rivanvx, llvm-commits
Differential Revision: http://reviews.llvm.org/D18151
llvm-svn: 263791
Summary:
As explained by the comment, threads will typically see different values
returned by atomic instructions even if the arguments are equal.
Reviewers: arsenm, tstellarAMD
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D18156
llvm-svn: 263719
Summary:
When multiple threads perform an atomic op with the same arguments, they
will usually see different return values.
Reviewers: arsenm, tstellarAMD
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D18101
llvm-svn: 263440
This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.
The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.
Reviewed By: reames
Differential Revision: http://reviews.llvm.org/D17270
llvm-svn: 263158
actually finish wiring up the old call graph.
There were bugs in the old call graph that hadn't been caught because it
wasn't being tested. It wasn't being tested because it wasn't in the
pipeline system and we didn't have a printing pass to run in tests. This
fixes all of that.
As for why I'm still keeping the old call graph alive its so that I can
port GlobalsAA to the new pass manager with out forking it to work with
the lazy call graph. That's clearly the right eventual design, but it
seems pragmatic to defer that until its necessary. The old call graph
works just fine for GlobalsAA.
llvm-svn: 263104
As part of r251146 InstCombine was extended to call computeKnownBits on
every value in the function to determine whether it happens to be
constant. This increases typical compiletime by 1-3% (5% in irgen+opt
time) in my measurements. On the other hand this case did not trigger
once in the whole llvm-testsuite.
This patch introduces the notion of ExpensiveCombines which are only
enabled for OptLevel > 2. I removed the check in InstructionSimplify as
that is called from various places where the OptLevel is not known but
given the rarity of the situation I think a check in InstCombine is
enough.
Differential Revision: http://reviews.llvm.org/D16835
llvm-svn: 263047
Building on the previous change, this generalizes
ScalarEvolution::getRangeViaFactoring to work with
{Ext(C?A:B)+k0,+,Ext(C?A:B)+k1} where Ext can be a zero extend, sign
extend or truncate operation, and k0 and k1 are constants.
llvm-svn: 262979
This change generalizes ScalarEvolution::getRangeViaFactoring to work
with {Ext(C?A:B),+,Ext(C?A:B)} where Ext can be a zero extend, sign
extend or truncate operation.
llvm-svn: 262978
Summary:
This testcase had me confused. It made me believe that you can use
alias scopes and alias scopes list interchangeably with alias.scope and
noalias. Both langref and the other testcase use scope lists so I went
looking.
Turns out using scope directly only happens to work by chance. When
ScopedNoAliasAAResult::mayAliasInScopes traverses this as a scope list:
!1 = !{!1, !0, !"some scope"}
, the first entry is in fact a scope but only because the scope is
happened to be defined self-referentially to make it unique globally.
The remaining elements in the tuple (!0, !"some scope") are considered
as scopes but AliasScopeNode::getDomain will just bail on those without
any error.
This change avoids this ambiguity in the test but I've also been
wondering if we should issue some sort of a diagnostics.
Reviewers: dexonsmith, hfinkel
Subscribers: mssimpso, llvm-commits
Differential Revision: http://reviews.llvm.org/D16670
llvm-svn: 262841
This experiment was originally about trying to use facts implied dominating conditions to infer more precise known bits. While the compile time was found to be acceptable on several large code bases, we never found sufficiently profitable examples to justify turning on the code by default. Given this, it's time to abandon the experiment.
Several folks have commented that they've found this useful for experimentation, but nothing has come of those experiments. Given how easy the patch is to apply, there's no reason to leave the code in tree.
For anyone interested in further investigation in this area, I recommend finding the summary email I sent on one of the original review threads. In particular, I now believe the use-list based approach is strictly worse than the dom-tree-walking approach.
llvm-svn: 262646
After r262438 we can have provably positive NSW SCEV expressions whose
zero extensions cannot be simplified (since r262438 makes SCEV better at
computing constant ranges). This means demoting sexts of positive add
recurrences eagerly can result in an unsimplified zero extension where
we could have had a simplified sign extension. This change fixes the
issue by teaching SCEV to demote sext of a positive SCEV expression to a
zext only if the sext could not be simplified.
llvm-svn: 262638
Have ScalarEvolution::getRange re-consider cases like "{C?A:B,+,C?P:Q}"
by factoring out "C" and computing RangeOf{A,+,P} union RangeOf({B,+,Q})
instead.
The latter can be easier to compute precisely in cases like
"{C?0:N,+,C?1:-1}" N is the backedge taken count of the loop; since in
such cases the latter form simplifies to [0,N+1) union [0,N+1).
llvm-svn: 262438
it to actually test the new pass manager AA wiring.
This patch was extracted from the (somewhat too large) D12357 and
rebosed on top of the slightly different design of the new pass manager
AA wiring that I just landed. With this we can start testing the AA in
a thorough way with the new pass manager.
Some minor cleanups to the code in the pass was necessitated here, but
otherwise it is a very minimal change.
Differential Revision: http://reviews.llvm.org/D17372
llvm-svn: 261403
reference-edge SCCs.
This essentially builds a more normal call graph as a subgraph of the
"reference graph" that was the old model. This allows both to exist and
the different use cases to use the aspect which addresses their needs.
Specifically, the pass manager and other *ordering* constrained logic
can use the reference graph to achieve conservative order of visit,
while analyses reasoning about attributes and other properties derived
from reachability can reason about the direct call graph.
Note that this isn't necessarily complete: it doesn't model edges to
declarations or indirect calls. Those can be found by scanning the
instructions of the function if desirable, and in fact every user
currently does this in order to handle things like calls to instrinsics.
If useful, we could consider caching this information in the call graph
to save the instruction scans, but currently that doesn't seem to be
important.
An important realization for why the representation chosen here works is
that the call graph is a formal subset of the reference graph and thus
both can live within the same data structure. All SCCs of the call graph
are necessarily contained within an SCC of the reference graph, etc.
The design is to build 'RefSCC's to model SCCs of the reference graph,
and then within them more literal SCCs for the call graph.
The formation of actual call edge SCCs is not done lazily, unlike
reference edge 'RefSCC's. Instead, once a reference SCC is formed, it
directly builds the call SCCs within it and stores them in a post-order
sequence. This is used to provide a consistent platform for mutation and
update of the graph. The post-order also allows for very efficient
updates in common cases by bounding the number of nodes (and thus edges)
considered.
There is considerable common code that I'm still looking for the best
way to factor out between the various DFS implementations here. So far,
my attempts have made the code harder to read and understand despite
reducing the duplication, which seems a poor tradeoff. I've not given up
on figuring out the right way to do this, but I wanted to wait until
I at least had the system working and tested to continue attempting to
factor it differently.
This also requires introducing several new algorithms in order to handle
all of the incremental update scenarios for the more complex structure
involving two edge colorings. I've tried to comment the algorithms
sufficiently to make it clear how this is expected to work, but they may
still need more extensive documentation.
I know that there are some changes which are not strictly necessarily
coupled here. The process of developing this started out with a very
focused set of changes for the new structure of the graph and
algorithms, but subsequent changes to bring the APIs and code into
consistent and understandable patterns also ended up touching on other
aspects. There was no good way to separate these out without causing
*massive* merge conflicts. Ultimately, to a large degree this is
a rewrite of most of the core algorithms in the LCG class and so I don't
think it really matters much.
Many thanks to the careful review by Sanjoy Das!
Differential Revision: http://reviews.llvm.org/D16802
llvm-svn: 261040
than the SCC object, and have it scan the instruction stream directly
rather than relying on call records.
This makes the behavior of this routine consistent between libc routines
and LLVM intrinsics for libc routines. We can go and start teaching it
about those being norecurse, but we should behave the same for the
intrinsic and the libc routine rather than differently. I chatted with
James Molloy and the inconsistency doesn't seem intentional and likely
is due to intrinsic calls not being modelled in the call graph analyses.
This also fixes a bug where we would deduce norecurse on optnone
functions, when generally we try to handle optnone functions as-if they
were replaceable and thus unanalyzable.
llvm-svn: 260813
Summary:
Passes that call `getAnalysisIfAvailable<T>` also need to call
`addUsedIfAvailable<T>` in `getAnalysisUsage` to indicate to the
legacy pass manager that it uses `T`. This contract was being
violated by passes that used `createLegacyPMAAResults`. This change
fixes this by exposing a helper in AliasAnalysis.h,
`addUsedAAAnalyses`, that is complementary to createLegacyPMAAResults
and does the right thing when called from `getAnalysisUsage`.
Reviewers: chandlerc
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D17010
llvm-svn: 260183
IndVarSimplify assumes scAddRecExpr to be expanded in literal form instead of
canonical form by calling disableCanonicalMode after it creates SCEVExpander.
When CanonicalMode is disabled, SCEVExpander::expand should always return PHI
node for scAddRecExpr. r259736 broke the assumption.
The fix is to let SCEVExpander::expand skip the reuse Value logic if
CanonicalMode is false.
In addition, Besides IndVarSimplify, LSR pass also calls disableCanonicalMode
before doing rewrite. We can remove the original check of LSRMode in reuse
Value logic and use CanonicalMode instead.
llvm-svn: 260174
sanitizer issue. The PredicatedScalarEvolution's copy constructor
wasn't copying the Generation value, and was leaving it un-initialized.
Original commit message:
[SCEV][LAA] Add no wrap SCEV predicates and use use them to improve strided pointer detection
Summary:
This change adds no wrap SCEV predicates with:
- support for runtime checking
- support for expression rewriting:
(sext ({x,+,y}) -> {sext(x),+,sext(y)}
(zext ({x,+,y}) -> {zext(x),+,sext(y)}
Note that we are sign extending the increment of the SCEV, even for
the zext case. This is needed to cover the fairly common case where y would
be a (small) negative integer. In order to do this, this change adds two new
flags: nusw and nssw that are applicable to AddRecExprs and permit the
transformations above.
We also change isStridedPtr in LAA to be able to make use of
these predicates. With this feature we should now always be able to
work around overflow issues in the dependence analysis.
Reviewers: mzolotukhin, sanjoy, anemet
Subscribers: mzolotukhin, sanjoy, llvm-commits, rengolin, jmolloy, hfinkel
Differential Revision: http://reviews.llvm.org/D15412
llvm-svn: 260112
We shouldn't assert when there are no memchecks, since we
can have SCEV checks. There is already an assert covering
the case where there are no SCEV checks or memchecks.
This also changes the LAA pointer wrapping versioning test
to use the loop versioning pass (this was how I managed to
trigger the assert in the loop versioning pass).
llvm-svn: 260086
Summary:
This change adds no wrap SCEV predicates with:
- support for runtime checking
- support for expression rewriting:
(sext ({x,+,y}) -> {sext(x),+,sext(y)}
(zext ({x,+,y}) -> {zext(x),+,sext(y)}
Note that we are sign extending the increment of the SCEV, even for
the zext case. This is needed to cover the fairly common case where y would
be a (small) negative integer. In order to do this, this change adds two new
flags: nusw and nssw that are applicable to AddRecExprs and permit the
transformations above.
We also change isStridedPtr in LAA to be able to make use of
these predicates. With this feature we should now always be able to
work around overflow issues in the dependence analysis.
Reviewers: mzolotukhin, sanjoy, anemet
Subscribers: mzolotukhin, sanjoy, llvm-commits, rengolin, jmolloy, hfinkel
Differential Revision: http://reviews.llvm.org/D15412
llvm-svn: 260085
Current SCEV expansion will expand SCEV as a sequence of operations
and doesn't utilize the value already existed. This will introduce
redundent computation which may not be cleaned up throughly by
following optimizations.
This patch introduces an ExprValueMap which is a map from SCEV to the
set of equal values with the same SCEV. When a SCEV is expanded, the
set of values is checked and reused whenever possible before generating
a sequence of operations.
The original commit triggered regressions in Polly tests. The regressions
exposed two problems which have been fixed in current version.
1. Polly will generate a new function based on the old one. To generate an
instruction for the new function, it builds SCEV for the old instruction,
applies some tranformation on the SCEV generated, then expands the transformed
SCEV and insert the expanded value into new function. Because SCEV expansion
may reuse value cached in ExprValueMap, the value in old function may be
inserted into new function, which is wrong.
In SCEVExpander::expand, there is a logic to check the cached value to
be used should dominate the insertion point. However, for the above
case, the check always passes. That is because the insertion point is
in a new function, which is unreachable from the old function. However
for unreachable node, DominatorTreeBase::dominates thinks it will be
dominated by any other node.
The fix is to simply add a check that the cached value to be used in
expansion should be in the same function as the insertion point instruction.
2. When the SCEV is of scConstant type, expanding it directly is cheaper than
reusing a normal value cached. Although in the cached value set in ExprValueMap,
there is a Constant type value, but it is not easy to find it out -- the cached
Value set is not sorted according to the potential cost. Existing reuse logic
in SCEVExpander::expand simply chooses the first legal element from the cached
value set.
The fix is that when the SCEV is of scConstant type, don't try the reuse
logic. simply expand it.
Differential Revision: http://reviews.llvm.org/D12090
llvm-svn: 259736
Current SCEV expansion will expand SCEV as a sequence of operations
and doesn't utilize the value already existed. This will introduce
redundent computation which may not be cleaned up throughly by
following optimizations.
This patch introduces an ExprValueMap which is a map from SCEV to the
set of equal values with the same SCEV. When a SCEV is expanded, the
set of values is checked and reused whenever possible before generating
a sequence of operations.
Differential Revision: http://reviews.llvm.org/D12090
llvm-svn: 259662
This regresses a test in LoopVectorize, so I'll need to go away and think about how to solve this in a way that isn't broken.
From the writeup in PR26071:
What's happening is that ComputeKnownZeroes is telling us that all bits except the LSB are zero. We're then deciding that only the LSB needs to be demanded from the icmp's inputs.
This is where we're wrong - we're assuming that after simplification the bits that were known zero will continue to be known zero. But they're not - during trivialization the upper bits get changed (because an XOR isn't shrunk), so the icmp fails.
The fault is in demandedbits - its contract does clearly state that a non-demanded bit may either be zero or one.
llvm-svn: 259649
differentiate between indirect references to functions an direct calls.
This doesn't do a whole lot yet other than change the print out produced
by the analysis, but it lays the groundwork for a very major change I'm
working on next: teaching the call graph to actually be a call graph,
modeling *both* the indirect reference graph and the call graph
simultaneously. More details on that in the next patch though.
The rest of this is essentially a bunch of over-engineering that won't
be interesting until the next patch. But this also isolates essentially
all of the churn necessary to introduce the edge abstraction from the
very important behavior change necessary in order to separately model
the two graphs. So it should make review of the subsequent patch a bit
easier at the cost of making this patch seem poorly motivated. ;]
Differential Revision: http://reviews.llvm.org/D16038
llvm-svn: 259463
The computation of ICmp demanded bits is independent of the individual operand being evaluated. We simply return a mask consisting of the minimum leading zeroes of both operands.
We were incorrectly passing "I" to ComputeKnownBits - this should be "UserI->getOperand(0)". In cases where we were evaluating the 1th operand, we were taking the minimum leading zeroes of it and itself.
This should fix PR26266.
llvm-svn: 258690
Some patterns of select+compare allow us to know exactly the value of the uppermost bits in the select result. For example:
%b = icmp ugt i32 %a, 5
%c = select i1 %b, i32 2, i32 %a
Here we know that %c is bounded by 5, and therefore KnownZero = ~APInt(5).getActiveBits() = ~7.
There are several such patterns, and this patch attempts to understand a reasonable subset of them - namely when the base values are the same (as above), and when they are related by a simple (add nsw), for example (add nsw %a, 4) and %a.
llvm-svn: 257769
Summary:
Since globals may escape as function arguments (even when they have been
found to be non-escaping, because of optimizations such as memcpyoptimizer
that replaces stores with memcpy), all arguments to a function are checked
during query to make sure they are identifiable. At that time, also ensure
we return a conservative result only if the arguments don't alias to our global.
Reviewers: hfinkel, jmolloy
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D16140
llvm-svn: 257750
The early return seems to be missed. This causes a radical and wrong loop
optimization on powerpc. It isn't reproducible on x86_64, because
"UseInterleaved" is false.
Patch by Tim Shen.
llvm-svn: 257134
See PR25822 for a more full summary, but we were conflating the concepts of "capture" and "escape". We were proving nocapture and using that proof to infer noescape, which is not true. Escaped-ness is a function-local property - as soon as a value is used in a call argument it escapes. Capturedness is a related but distinct property. It implies a *temporally limited* escape. Consider:
static int a;
int b;
int g(int * nocapture arg);
int f() {
a = 2; // Even though a escapes to g, it is not captured so can be treated as non-escaping here.
g(&a); // But here it must be treated as escaping.
g(&b); // Now that g(&a) has returned we know it was not captured so we can treat it as non-escaping again.
}
The original commit did not sufficiently understand this nuance and so caused PR25822 and PR26046.
r248576 included both a performance improvement (which has been backed out) and a related conformance fix (which has been kept along with its testcase).
llvm-svn: 257058
Summary:
This reverts commit 5a9e526f29cf8510ab5c3d566fbdcf47ac24e1e9.
As per discussion in D15665
This also add a test case so that regression introduced by that diff are not reintroduced.
Reviewers: vaivaswatha, jmolloy, hfinkel, reames
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D15919
llvm-svn: 256932
Most of the properties of memset_pattern16 can be now covered by the generic attributes and inferred by InferFunctionAttrs. The only exceptions are:
- We don't yet have a writeonly attribute for the first argument.
- We don't have an attribute for modeling the access size facts encoded in MemoryLocation.cpp.
Differential Revision: http://reviews.llvm.org/D15879
llvm-svn: 256911
The cost is calculated for all X86 targets. When gather/scatter instruction
is not supported we calculate the cost of scalar sequence.
Differential revision: http://reviews.llvm.org/D15677
llvm-svn: 256519
Summary: This patch changes gc.statepoint intrinsic's return type to token type instead of i32 type. Using token types could prevent LLVM to merge different gc.statepoint nodes into PHI nodes and cause further problems with gc relocations. The patch also changes the way on how gc.relocate and gc.result look for their corresponding gc.statepoint on unwind path. The current implementation uses the selector value extracted from a { i8*, i32 } landingpad as a hook to find the gc.statepoint, while the patch directly uses a token type landingpad (http://reviews.llvm.org/D15405) to find the gc.statepoint.
Reviewers: sanjoy, JosephTremoulet, pgavlin, igor-laevsky, mjacob
Subscribers: reames, mjacob, sanjoy, llvm-commits
Differential Revision: http://reviews.llvm.org/D15662
llvm-svn: 256443
This patch removes all weight-related interfaces from BPI and replace
them by probability versions. With this patch, we won't use edge weight
anymore in either IR or MC passes. Edge probabilitiy is a better
representation in terms of CFG update and validation.
Differential revision: http://reviews.llvm.org/D15519
llvm-svn: 256263
This is recommit of r256028 with minor fixes in unittests:
CodeGen/Mips/eh.ll
CodeGen/Mips/insn-zero-size-bb.ll
Original commit message:
When identifying blocks post-dominated by an unreachable-terminated block
in BranchProbabilityInfo, consider only the edge to the normal destination
block if the terminator is InvokeInst and let calcInvokeHeuristics() decide
edge weights for the InvokeInst.
llvm-svn: 256202
This patch transforms truncation between vectors of integers into
X86ISD::PACKUS/PACKSS operations during DAG combine. We don't do it in
lowering phase because after type legalization, the original truncation
will be turned into a BUILD_VECTOR with each element that is extracted
from a vector and then truncated, and from them it is difficult to do
this optimization. This greatly improves the performance of truncations
on some specific types.
Cost table is updated accordingly.
Differential revision: http://reviews.llvm.org/D14588
llvm-svn: 256194
Summary:
The analysis of shader inputs was completely wrong. We were passing the
wrong index to AttributeSet::hasAttribute() and the logic for which
inputs where in SGPRs was wrong too.
Reviewers: arsenm
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D15608
llvm-svn: 256082
This patch removes all getEdgeWeight() interfaces from CodeGen directory. As
getEdgeProbability() is a little more expensive than getEdgeWeight(), I will
compose a patch soon in which BPI only stores probabilities instead of edge
weights so that getEdgeProbability() will have O(1) time.
Differential revision: http://reviews.llvm.org/D15489
llvm-svn: 256039
When identifying blocks post-dominated by an unreachable-terminated block
in BranchProbabilityInfo, consider only the edge to the normal destination
block if the terminator is InvokeInst and let calcInvokeHeuristics() decide
edge weights for the InvokeInst.
llvm-svn: 256028
Summary:
1. Modify AnalyzeCallGraph() to retain function info for external functions
if the function has [InaccessibleMemOr]ArgMemOnly flags.
2. When analyzing the use of a global is function parameter at a call site,
mark the callee also as modifying the global appropriately.
3. Add additional test cases.
Depends on D15499
Reviewers: hfinkel, jmolloy
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D15605
llvm-svn: 255994
Previously in the conversion cost table there are no entries for integer-integer
conversions on SSE2. This will result in imprecise costs for certain vectorized
operations. This patch adds those entries for SSE2 and SSE4.1. The cost numbers
are counted from the result of running llc on the new test case in this patch.
Differential revision: http://reviews.llvm.org/D15132
llvm-svn: 255315
Currently in LLVM's cost model, a vectorized arithmetic instruction will have
high cost if its type is split into multiple registers. However, this
punishment is too heavy and unnecessary. The overhead of the split should not
be on arithmetic instructions but instructions that implement the split. Note
that during vectorization we have calculated the register pressure, and we
only choose proper interleaving factor (and also vectorization factor) so
that we don't use more registers than the maximum number.
Here is a very simple example: if a vadd has the cost 1, and if we double VF
so that we need two registers to perform it, then its cost will become 4 with
the current implementation, which will prevent us to use larger VF.
Differential revision: http://reviews.llvm.org/D15159
llvm-svn: 254671
I checked and updated the cost of AVX-512 conversion operations. Added cost of conversion operations in DQ mode.
Conversion of illegal types that requires vector split is not calculated right now (like for other X86 targets).
Differential Revision: http://reviews.llvm.org/D15074
llvm-svn: 254494
The cost for scalarized operations is computed as N * (scalar operation
cost + 1 extractelement + 1 insertelement). This partially fixes
inflating the cost of scalarized operations since every operation is
scalarized and free. I don't think we want any cost asociated with
scalarization, but for now insertelement is still counted. I'm not sure
if we should pretend that insertelement is also free, or add a way
to compute a custom scalarization cost.
llvm-svn: 254438
Cost calculation for vector GEP failed with due to invalid cast to GEP index operand.
The bug is fixed, added a test.
http://reviews.llvm.org/D14976
llvm-svn: 254408
Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
These intrinsics currently have an explicit alignment argument which is
required to be a constant integer. It represents the alignment of the
source and dest, and so must be the minimum of those.
This change allows source and dest to each have their own alignments
by using the alignment attribute on their arguments. The alignment
argument itself is removed.
There are a few places in the code for which the code needs to be
checked by an expert as to whether using only src/dest alignment is
safe. For those places, they currently take the minimum of src/dest
alignments which matches the current behaviour.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
will now read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)
For out of tree owners, I was able to strip alignment from calls using sed by replacing:
(call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\)
with:
$1i1 false)
and similarly for memmove and memcpy.
I then added back in alignment to test cases which needed it.
A similar commit will be made to clang which actually has many differences in alignment as now
IRBuilder can generate different source/dest alignments on calls.
In IRBuilder itself, a new argument was added. Instead of calling:
CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false)
you now call
CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false)
There is a temporary class (IntegerAlignment) which takes the source alignment and rejects
implicit conversion from bool. This is to prevent isVolatile here from passing its default
parameter to the source alignment.
Note, changes in future can now be made to codegen. I didn't change anything here, but this
change should enable better memcpy code sequences.
Reviewed by Hal Finkel.
llvm-svn: 253511
The underlying issues surrounding codegen for 32-bit vselects have been resolved. The pessimistic costs for 64-bit vselects remain due to the bad
scalarization that is still happening there.
I tested this on A57 in T32, A32 and A64 modes. I saw no regressions, and some improvements.
From my benchmarks, I saw these improvements in A57 (T32)
spec.cpu2000.ref.177_mesa 5.95%
lnt.SingleSource/Benchmarks/Shootout/strcat 12.93%
lnt.MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32 11.89%
I also measured A57 A32, A53 T32 and A9 T32 and found no performance regressions. I see much bigger wins in third-party benchmarks with this change
Differential Revision: http://reviews.llvm.org/D14743
llvm-svn: 253349
A function can be marked as norecurse if:
* The SCC to which it belongs has cardinality 1; and either
a) It does not call any non-norecurse function. This includes self-recursion; or
b) It only has one callsite and the function that callsite is within is marked norecurse.
a) is best propagated bottom-up and b) is best propagated top-down.
We build up the norecurse attributes bottom-up using the existing SCC pass, and mark functions with no obvious recursion (but not provably norecurse) to sweep later, top-down.
llvm-svn: 252862
This is fix for PR24059.
When we are hoisting instruction above some condition it may turn out
that metadata on this instruction was control dependant on the condition.
This metadata becomes invalid and we need to drop it.
This patch should cover most obvious places of speculative execution (which
I have found by greping isSafeToSpeculativelyExecute). I think there are more
cases but at least this change covers the severe ones.
Differential Revision: http://reviews.llvm.org/D14398
llvm-svn: 252604
Summary:
GetUnderlyingObjects() can return "null" among its list of objects,
we don't want to deduce that two pointers can point to the same
memory in this case, so filter it out.
Reviewers: anemet
Subscribers: dexonsmith, llvm-commits
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 252149
Summary:
We now collect all types of dependences including lexically forward
deps not just "interesting" ones.
Reviewers: hfinkel
Subscribers: rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D13256
llvm-svn: 251985
Summary:
When the dependence distance in zero then we have a loop-independent
dependence from the earlier to the later access.
No current client of LAA uses forward dependences so other than
potentially hitting the MaxDependences threshold earlier, this change
shouldn't affect anything right now.
This and the previous patch were tested together for compile-time
regression. None found in LNT/SPEC.
Reviewers: hfinkel
Subscribers: rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D13255
llvm-svn: 251973
Summary:
Before this change, we didn't use to collect forward dependences since
none of the current clients (LV, LDist) required them.
The motivation to also collect forward dependences is a new pass
LoopLoadElimination (LLE) which discovers store-to-load forwarding
opportunities across the loop's backedge. The pass uses both lexically
forward or backward loop-carried dependences to detect these
opportunities.
The new pass also analyzes loop-independent (forward) dependences since
they can conflict with the loop-carried dependences in terms of how the
data flows through memory.
The newly added test only covers loop-carried forward dependences
because loop-independent ones are currently categorized as NoDep. The
next patch will fix this.
The two patches were tested together for compile-time regression. None
found in LNT/SPEC.
Note that with this change LAA provides all dependences rather than just
"interesting" ones. A subsequent NFC patch will remove the now trivial
isInterestingDependence and rename the APIs.
Reviewers: hfinkel
Subscribers: jmolloy, rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D13254
llvm-svn: 251972
Have `getConstantEvolutionLoopExitValue` work correctly with multiple
entry loops.
As far as I can tell, `getConstantEvolutionLoopExitValue` never did the
right thing for multiple entry loops; and before r249712 it would
silently return an incorrect answer. r249712 changed SCEV to fail an
assert on a multiple entry loop, and this change fixes the underlying
issue.
llvm-svn: 251770
Prevent `createNodeFromSelectLikePHI` from creating SCEV expressions
that break LCSSA.
A better fix for the same issue is to teach SCEVExpander to not break
LCSSA by inserting PHI nodes at appropriate places. That's planned for
the future.
Fixes PR25360.
llvm-svn: 251756
Summary:
When forming expressions for phi nodes having an incoming value from
outside the loop A and a value coming from the previous iteration B
we were forming an AddRec if:
- B was an AddRec
- the value A was equal to the value for B at iteration -1 (or equal
to the value of B shifted by one iteration, at iteration 0)
In this case, we were computing the expression to be the expression of
B, shifted by one iteration.
This changes generalizes the logic above by removing the restriction that
B needs to be an AddRec. For this we introduce two expression rewriters
that allow us to
- shift an expression by one iteration
- get the value of an expression at iteration 0
This allows us to get SCEV expressions for PHI nodes when these expressions
are not AddRecExprs.
Reviewers: sanjoy
Subscribers: llvm-commits, sanjoy
Differential Revision: http://reviews.llvm.org/D14175
llvm-svn: 251700
This teaches SCEV to compute //max// backedge taken counts for loops
like
for (int i = k; i != 0; i >>>= 1)
whatever();
SCEV yet cannot represent the exact backedge count for these loops, and
this patch does not change that. This is really geared towards teaching
SCEV that loops like the above are *not* infinite.
llvm-svn: 251558
In getArgModRefInfo we consider all arguments as having MRI_ModRef.
However for arguments marked with readonly attribute we can return
more precise answer - MRI_Ref.
Differential Revision: http://reviews.llvm.org/D13992
llvm-svn: 251525
When checking if an indirect global (a global with pointer type) is only assigned by allocation functions, first check if the global is itself initialized. If it is, it's not only assigned by allocation functions.
This fixes PR25309. Thanks to David Majnemer for reducing the test case!
llvm-svn: 251508
Even though we may not know the value of the shifter operand, it's possible we know the shifter operand is non-zero. This can allow us to infer more known bits - for example:
%1 = load %p !range {1, 5}
%2 = shl %q, %1
We don't know %1, but we do know that it is nonzero so %2[0] is known zero, and importantly %2 is known non-zero.
Calling isKnownNonZero is nontrivially expensive so use an Optional to run it lazily and cache its result.
llvm-svn: 251294
If the loaded type sizes don't match the element type of the sequential type, all bets are off and the addresses may, indeed, overlap.
Surprisingly, this just got caught in one test, on one builder, out of the 30+ builders testing this change. Congratulations go to http://lab.llvm.org:8011/builders/clang-aarch64-lnt/builds/5205.
llvm-svn: 251112
Summary:
This uses `ScalarEvolution::getRange` and not potentially control
dependent `nsw` and `nuw` bits on the arithmetic instruction.
Reviewers: atrick, hfinkel, nlewycky
Subscribers: llvm-commits, sanjoy
Differential Revision: http://reviews.llvm.org/D13613
llvm-svn: 251048
Instead of bailing out when we see loads, analyze them. If we can prove that the loaded-from address must escape, then we can conclude that a load from that address must escape too and therefore cannot alias a non-addr-taken global.
When checking if a Value can alias a non-addr-taken global, if the Value is a LoadInst of a non-global, recurse instead of bailing.
If we can follow a trail of loads up to some base that is captured, we know by inference that all the loads we followed are also captured.
llvm-svn: 251017
If the final indices of two GEPs can be proven to not be equal, and
the GEP is of a SequentialType (not a StructType), then the two GEPs
do not alias.
llvm-svn: 251016
isKnownNonEqual(A, B) returns true if it can be determined that A != B.
At the moment it only knows two facts, that a non-wrapping add of nonzero to a value cannot be that value:
A + B != A [where B != 0, addition is nsw or nuw]
and that contradictory known bits imply two values are not equal.
This patch also hooks this up to InstSimplify; InstSimplify had a peephole for the first fact but not the second so this teaches InstSimplify a new trick too (alas no measured performance impact!)
llvm-svn: 251012
Weak linkage and friends allow a symbol to be overriden outside the
code generator's model, so GlobalsAA shouldn't assume that anything it
can compute about such a symbol is valid.
llvm-svn: 250156
This patch also allows the -delinearize pass to delinearize expressions that do
not have an outermost SCEVAddRec expression. The SCEV::delinearize
infrastructure allowed this since r240952, but the -delinearize pass was not
updated yet.
llvm-svn: 250018
The new implementation works at least as well as the old implementation
did.
Also delete the associated preparation tests. They don't exercise
interesting corner cases of the new implementation. All the codegen
tests of the EH tables have already been ported.
llvm-svn: 249918
Instead of bailing out when we see an icmp, we can instead at least
say that if the upper bits of both operands are known zero, they are
not demanded. This doesn't help with signed comparisons, but it's at
least better than bailing out.
llvm-svn: 249687
Like adds and subtracts, muls ripple only to the left so we can use
the same logic.
While we're here, add a print method to DemandedBits so it can be used
with -analyze, which we'll use in the testcase.
llvm-svn: 249686
This reverts commit r249528 and reapply r249431. The fix for the
fallout has been commited in r249575.
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 249581
With this patch, clang -O3 optimizes correctly providing > 1000x speedup on this artificial benchmark):
for (a=0; a<n; a++)
for (b=0; b<n; b++)
for (c=0; c<n; c++)
for (d=0; d<n; d++)
for (e=0; e<n; e++)
for (f=0; f<n; f++)
x++;
From test-suite/SingleSource/Benchmarks/Shootout/nestedloop.c
Reviewers: sanjoyd
Differential Revision: http://reviews.llvm.org/D13390
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 249431
This commit changes the interface of the vld[1234], vld[234]lane, and vst[1234],
vst[234]lane ARM neon intrinsics and associates an address space with the
pointer that these intrinsics take. This changes, e.g.,
<2 x i32> @llvm.arm.neon.vld1.v2i32(i8*, i32)
to
<2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8*, i32)
This change ensures that address spaces are fully taken into account in the ARM
target during lowering of interleaved loads and stores.
Differential Revision: http://reviews.llvm.org/D12985
llvm-svn: 248887
The XOP shifts just have logical/arithmetic versions and the left/right shifts are controlled by whether the value is positive/negative. Because of this I've added new X86ISD nodes instead of trying to force them to use the existing shift nodes.
Additionally Excavator cores (bdver4) support XOP and AVX2 - meaning that it should use the AVX2 shifts when it can and fall back to XOP in other cases.
Differential Revision: http://reviews.llvm.org/D8690
llvm-svn: 248878
If a PHI starts at a non-negative constant, monotonically increases
(only adds of a constant are supported at the moment) and that add
does not wrap, then the PHI is known never to be zero.
llvm-svn: 248796
Summary:
If the trip count of a specific backedge is `N`, then we know that
backedge is effectively guarded by the condition `{0,+,1} u< N`. This
change teaches SCEV to use this condition to prove things in
`isLoopBackedgeGuardedByCond`.
Depends on D12948
Depends on D12949
The original checkin, r248608 had to be backed out due to an issue with
a ObjCXX unit test. That issue is now fixed, so re-landing.
Reviewers: atrick, reames, majnemer, hfinkel
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D12950
llvm-svn: 248638
BranchProbability now is represented by its numerator and denominator in uint32_t type. This patch changes this representation into a fixed point that is represented by the numerator in uint32_t type and a constant denominator 1<<31. This is quite similar to the representation of BlockMass in BlockFrequencyInfoImpl.h. There are several pros and cons of this change:
Pros:
1. It uses only a half space of the current one.
2. Some operations are much faster like plus, subtraction, comparison, and scaling by an integer.
Cons:
1. Constructing a probability using arbitrary numerator and denominator needs additional calculations.
2. It is a little less precise than before as we use a fixed denominator. For example, 1 - 1/3 may not be exactly identical to 1 / 3 (this will lead to many BranchProbability unit test failures). This should not matter when we only use it for branch probability. If we use it like a rational value for some precise calculations we may need another construct like ValueRatio.
One important reason for this change is that we propose to store branch probabilities instead of edge weights in MachineBasicBlock. We also want clients to use probability instead of weight when adding successors to a MBB. The current BranchProbability has more space which may be a concern.
Differential revision: http://reviews.llvm.org/D12603
llvm-svn: 248633
Summary:
If the trip count of a specific backedge is `N`, then we know that
backedge is effectively guarded by the condition `{0,+,1} u< N`. This
change teaches SCEV to use this condition to prove things in
`isLoopBackedgeGuardedByCond`.
Depends on D12948
Depends on D12949
Reviewers: atrick, reames, majnemer, hfinkel
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D12950
llvm-svn: 248608
Arguments to function calls marked "nocapture" can be marked as
non-escaping. However, nocapture is defined in terms of the lifetime
of the callee, and if the callee can directly or indirectly recurse to
the caller, the semantics of nocapture are invalid.
Therefore, we eagerly discover which SCC each function belongs to,
and later can check if callee and caller of a callsite belong to
the same SCC, in which case there could be recursion.
This means that we can't be so optimistic in
getModRefInfo(ImmutableCallsite) - previously we assumed all call
arguments never aliased with an escaping global. Now we need to check,
because a global could now be passed as an argument but still not
escape.
This also solves a related conformance problem: MemCpyOptimizer can
turn non-escaping stores of globals into calls to intrinsics like
llvm.memcpy/llvm/memset. This confuses GlobalsAA, which knows the
global can't escape and so returns NoModRef when queried, when
obviously a memcpy/memset call does indeed reference and modify its
arguments.
This fixes PR24800, PR24801, and PR24802.
llvm-svn: 248576
If the shifter operand is a constant, and all of the bits shifted out
are known to be zero, then if X is known non-zero at least one
non-zero bit must remain.
llvm-svn: 248508
Turns out that not every basic block is guaranteed to have a node within the DominatorTree. This is really hard to trigger, but the test case from the PR managed to do so. There's active discussion continuing about what documentation and/or invariants needed cleaned up.
llvm-svn: 248216
This patch addresses the issue of SCEV division asserting on some
input expressions (e.g., non-affine expressions) and quietly giving
up on others. When giving up, we set the quotient to be equal to
zero and the remainder to be equal to the numerator. With this
patch, we always quietly give up when we cannot perform the
division.
This patch also adds a test case for DependenceAnalysis that
previously caused an assertion.
Differential Revision: http://reviews.llvm.org/D11725
llvm-svn: 247314
Summary:
PR24757 was caused by some incorect math in
`ScalarEvolution::HowFarToZero` -- the smallest unsigned solution for X
in
2^N * A = 2^N * X
is not necessarily A.
Reviewers: atrick, majnemer, meheff
Subscribers: llvm-commits, sanjoy
Differential Revision: http://reviews.llvm.org/D12721
llvm-svn: 247242
with the new pass manager, and no longer relying on analysis groups.
This builds essentially a ground-up new AA infrastructure stack for
LLVM. The core ideas are the same that are used throughout the new pass
manager: type erased polymorphism and direct composition. The design is
as follows:
- FunctionAAResults is a type-erasing alias analysis results aggregation
interface to walk a single query across a range of results from
different alias analyses. Currently this is function-specific as we
always assume that aliasing queries are *within* a function.
- AAResultBase is a CRTP utility providing stub implementations of
various parts of the alias analysis result concept, notably in several
cases in terms of other more general parts of the interface. This can
be used to implement only a narrow part of the interface rather than
the entire interface. This isn't really ideal, this logic should be
hoisted into FunctionAAResults as currently it will cause
a significant amount of redundant work, but it faithfully models the
behavior of the prior infrastructure.
- All the alias analysis passes are ported to be wrapper passes for the
legacy PM and new-style analysis passes for the new PM with a shared
result object. In some cases (most notably CFL), this is an extremely
naive approach that we should revisit when we can specialize for the
new pass manager.
- BasicAA has been restructured to reflect that it is much more
fundamentally a function analysis because it uses dominator trees and
loop info that need to be constructed for each function.
All of the references to getting alias analysis results have been
updated to use the new aggregation interface. All the preservation and
other pass management code has been updated accordingly.
The way the FunctionAAResultsWrapperPass works is to detect the
available alias analyses when run, and add them to the results object.
This means that we should be able to continue to respect when various
passes are added to the pipeline, for example adding CFL or adding TBAA
passes should just cause their results to be available and to get folded
into this. The exception to this rule is BasicAA which really needs to
be a function pass due to using dominator trees and loop info. As
a consequence, the FunctionAAResultsWrapperPass directly depends on
BasicAA and always includes it in the aggregation.
This has significant implications for preserving analyses. Generally,
most passes shouldn't bother preserving FunctionAAResultsWrapperPass
because rebuilding the results just updates the set of known AA passes.
The exception to this rule are LoopPass instances which need to preserve
all the function analyses that the loop pass manager will end up
needing. This means preserving both BasicAAWrapperPass and the
aggregating FunctionAAResultsWrapperPass.
Now, when preserving an alias analysis, you do so by directly preserving
that analysis. This is only necessary for non-immutable-pass-provided
alias analyses though, and there are only three of interest: BasicAA,
GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is
preserved when needed because it (like DominatorTree and LoopInfo) is
marked as a CFG-only pass. I've expanded GlobalsAA into the preserved
set everywhere we previously were preserving all of AliasAnalysis, and
I've added SCEVAA in the intersection of that with where we preserve
SCEV itself.
One significant challenge to all of this is that the CGSCC passes were
actually using the alias analysis implementations by taking advantage of
a pretty amazing set of loop holes in the old pass manager's analysis
management code which allowed analysis groups to slide through in many
cases. Moving away from analysis groups makes this problem much more
obvious. To fix it, I've leveraged the flexibility the design of the new
PM components provides to just directly construct the relevant alias
analyses for the relevant functions in the IPO passes that need them.
This is a bit hacky, but should go away with the new pass manager, and
is already in many ways cleaner than the prior state.
Another significant challenge is that various facilities of the old
alias analysis infrastructure just don't fit any more. The most
significant of these is the alias analysis 'counter' pass. That pass
relied on the ability to snoop on AA queries at different points in the
analysis group chain. Instead, I'm planning to build printing
functionality directly into the aggregation layer. I've not included
that in this patch merely to keep it smaller.
Note that all of this needs a nearly complete rewrite of the AA
documentation. I'm planning to do that, but I'd like to make sure the
new design settles, and to flesh out a bit more of what it looks like in
the new pass manager first.
Differential Revision: http://reviews.llvm.org/D12080
llvm-svn: 247167
Summary:
We are not scalarizing the wide selects in codegen for i16 and i32 and
therefore we can remove the amortization factor. We still have issues
with i64 vectors in codegen though.
Reviewers: mcrosier
Subscribers: mcrosier, aemerson, llvm-commits, rengolin
Differential Revision: http://reviews.llvm.org/D12724
llvm-svn: 247156
This corner case happens when we have an irreducible SCC that is
deeply nested. As we work down the tree, the backedge masses start
getting smaller and smaller until we reach one that is down to 0.
Since we distribute the incoming mass using the backedge masses as
weight, the distributor does not allow zero weights. So, we simply
ignore them (which will just use the weights of the non-zero nodes).
llvm-svn: 247050
Pre-P8, when we generate code for unaligned vector loads (for Altivec and QPX
types), even when accounting for the combining that takes place for multiple
consecutive such loads, there is at least one load instructions and one
permutation for each load. Make sure the cost reported reflects the cost of the
permutes as well.
llvm-svn: 246807
I'm adding a regression test to better cover code generation for unaligned
vector loads and stores, but there's no functional change to the code
generation here. There is an improvement to the cost model for unaligned vector
loads and stores, mostly for QPX (for which we were not previously accounting
for the permutation-based loads), and the cost model implementation is cleaner.
llvm-svn: 246712
Hopefully this will end the GEPs saga!
This commit reverts r245394, i.e., it reapplies r221876 while incorporating the
fixes from D11847.
r221876 was not reapplied alone because it was not safe and D11847 was not
applied alone because it needs r221876 to produce correct results.
This should fix PR24596.
Original commit message for r221876:
Let's try this again...
This reverts r219432, plus a bug fix.
Description of the bug in r219432 (by Nick):
The bug was using AllPositive to break out of the loop; if the loop break
condition i != e is changed to i != e && AllPositive then the
test_modulo_analysis_with_global test I've added will fail as the Modulo will
be calculated incorrectly (as the last loop iteration is skipped, so Modulo
isn't updated with its Scale).
Nick also adds this comment:
ComputeSignBit is safe to use in loops as it takes into account phi nodes, and
the == EK_ZeroEx check is safe in loops as, no matter how the variable changes
between iterations, zero-extensions will always guarantee a zero sign bit. The
isValueEqualInPotentialCycles check is therefore definitely not needed as all
the variable analysis holds no matter how the variables change between loop
iterations.
And this patch also adds another enhancement to GetLinearExpression - basically
to convert ConstantInts to Offsets (see test_const_eval and
test_const_eval_scaled for the situations this improves).
Original commit message:
This reverts r218944, which reverted r218714, plus a bug fix.
Description of the bug in r218714 (by Nick):
The original patch forgot to check if the Scale in VariableGEPIndex flipped the
sign of the variable. The BasicAA pass iterates over the instructions in the
order they appear in the function, and so BasicAliasAnalysis::aliasGEP is
called with the variable it first comes across as parameter GEP1. Adding a
%reorder label puts the definition of %a after %b so aliasGEP is called with %b
as the first parameter and %a as the second. aliasGEP later calculates that %a
== %b + 1 - %idxprom where %idxprom >= 0 (if %a was passed as the first
parameter it would calculate %b == %a - 1 + %idxprom where %idxprom >= 0) -
ignoring that %idxprom is scaled by -1 here lead the patch to incorrectly
conclude that %a > %b.
Revised patch by Nick White, thanks! Thanks to Lang to isolating the bug.
Slightly modified by me to add an early exit from the loop and avoid
unnecessary, but expensive, function calls.
Original commit message:
Two related things:
1. Fixes a bug when calculating the offset in GetLinearExpression. The code
previously used zext to extend the offset, so negative offsets were converted
to large positive ones.
2. Enhance aliasGEP to deduce that, if the difference between two GEP
allocations is positive and all the variables that govern the offset are also
positive (i.e. the offset is strictly after the higher base pointer), then
locations that fit in the gap between the two base pointers are NoAlias.
Patch by Nick White!
Message from D11847:
Un-revert of r241981 and fix for PR23626. The 'Or' case of GetLinearExpression
delegates to 'Add' if possible, and if not it returns an Opaque value.
Unfortunately the Scale and Offsets weren't being set (and so defaulted to 0) -
and a scale of zero effectively removes the variable from the GEP instruction.
This meant that BasicAA would return MustAliases when it should have been
returning PartialAliases (and PR23626 was an example of the GVN pass using an
incorrect MustAlias to merge loads from what should have been different
pointers).
Differential Revision: http://reviews.llvm.org/D11847
Patch by Nick White <n.j.white@gmail.com>!
llvm-svn: 246502
Prior to this patch, we hadn't been marking StratifiedSets with the
appropriate StratifiedAttrs when handling the result of no-args call
instructions. This caused us to report NoAlias when handed, for
example, an escaped alloca and a result from an opaque function. Now we
properly mark the return value of said functions.
Thanks again to Chandler, Richard, and Nick for pinging me about this.
Differential review: http://reviews.llvm.org/D12408
llvm-svn: 246240
Fix how DependenceAnalysis calls delinearization, mirroring what is done in
Delinearization.cpp (mostly by making sure to call getSCEVAtScope before
delinearizing, and by removing the unnecessary 'Pairs == 1' check).
Patch by Vaivaswatha Nagaraj!
llvm-svn: 245408
Summary:
This change limits the minimum cost of an insert/extract
element operation to 2 in cases where this would result
in mixing of NEON and VFP code.
Reviewers: rengolin
Subscribers: mssimpso, aemerson, llvm-commits, rengolin
Differential Revision: http://reviews.llvm.org/D12030
llvm-svn: 245225
This change makes ScalarEvolution a stand-alone object and just produces
one from a pass as needed. Making this work well requires making the
object movable, using references instead of overwritten pointers in
a number of places, and other refactorings.
I've also wired it up to the new pass manager and added a RUN line to
a test to exercise it under the new pass manager. This includes basic
printing support much like with other analyses.
But there is a big and somewhat scary change here. Prior to this patch
ScalarEvolution was never *actually* invalidated!!! Re-running the pass
just re-wired up the various other analyses and didn't remove any of the
existing entries in the SCEV caches or clear out anything at all. This
might seem OK as everything in SCEV that can uses ValueHandles to track
updates to the values that serve as SCEV keys. However, this still means
that as we ran SCEV over each function in the module, we kept
accumulating more and more SCEVs into the cache. At the end, we would
have a SCEV cache with every value that we ever needed a SCEV for in the
entire module!!! Yowzers. The releaseMemory routine would dump all of
this, but that isn't realy called during normal runs of the pipeline as
far as I can see.
To make matters worse, there *is* actually a key that we don't update
with value handles -- there is a map keyed off of Loop*s. Because
LoopInfo *does* release its memory from run to run, it is entirely
possible to run SCEV over one function, then over another function, and
then lookup a Loop* from the second function but find an entry inserted
for the first function! Ouch.
To make matters still worse, there are plenty of updates that *don't*
trip a value handle. It seems incredibly unlikely that today GVN or
another pass that invalidates SCEV can update values in *just* such
a way that a subsequent run of SCEV will incorrectly find lookups in
a cache, but it is theoretically possible and would be a nightmare to
debug.
With this refactoring, I've fixed all this by actually destroying and
recreating the ScalarEvolution object from run to run. Technically, this
could increase the amount of malloc traffic we see, but then again it is
also technically correct. ;] I don't actually think we're suffering from
tons of malloc traffic from SCEV because if we were, the fact that we
never clear the memory would seem more likely to have come up as an
actual problem before now. So, I've made the simple fix here. If in fact
there are serious issues with too much allocation and deallocation,
I can work on a clever fix that preserves the allocations (while
clearing the data) between each run, but I'd prefer to do that kind of
optimization with a test case / benchmark that shows why we need such
cleverness (and that can test that we actually make it faster). It's
possible that this will make some things faster by making the SCEV
caches have higher locality (due to being significantly smaller) so
until there is a clear benchmark, I think the simple change is best.
Differential Revision: http://reviews.llvm.org/D12063
llvm-svn: 245193
Summary:
http://reviews.llvm.org/D11212 made Scalar Evolution able to propagate NSW and NUW flags from instructions to SCEVs for add instructions. This patch expands that to sub, mul and shl instructions.
This change makes LSR able to generate pointer induction variables for loops like these, where the index is 32 bit and the pointer is 64 bit:
for (int i = 0; i < numIterations; ++i)
sum += ptr[i - offset];
for (int i = 0; i < numIterations; ++i)
sum += ptr[i * stride];
for (int i = 0; i < numIterations; ++i)
sum += ptr[3 * (i << 7)];
Reviewers: atrick, sanjoy
Subscribers: sanjoy, majnemer, hfinkel, llvm-commits, meheff, jingyue, eliben
Differential Revision: http://reviews.llvm.org/D11860
llvm-svn: 245118
I looked into adding a warning / error for this to FileCheck, but there doesn't
seem to be a good way to avoid it triggering on the instances of it in RUN lines.
llvm-svn: 244481
In PR24288 it was pointed out that the easy case of a non-escaping
global and something that *obviously* required an escape sometimes is
hidden behind PHIs (or selects in theory). Because we have this binary
test, we can easily just check that all possible input values satisfy
the requirement. This is done with a (very small) recursion through PHIs
and selects. With this, the specific example from the PR is correctly
folded by GVN.
Differential Revision: http://reviews.llvm.org/D11707
llvm-svn: 244078
This patch vectorizes the v2i64/v4i64 ASHR shift operations - the last remaining integer vector shifts that are still being transferred to/from the scalar unit to be completed.
Differential Revision: http://reviews.llvm.org/D11439
llvm-svn: 243569
Simon Pilgrim