This patch swaps A and B in the interleaved access analysis and clarifies
related comments. The algorithm is more intuitive if we let access A precede
access B in program order rather than the reverse. This change was requested in
the review of D19984.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275567 91177308-0d34-0410-b5e6-96231b3b80d8
We now collect all accesses with a constant stride, not just the ones with a
stride greater than one. This change was requested in the review of D19984.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275473 91177308-0d34-0410-b5e6-96231b3b80d8
This patch prevents increases in the number of instructions, pre-instcombine,
due to induction variable scalarization. An increase in instructions can lead
to an increase in the compile-time required to simplify the induction
variables. We now maintain a new map for scalarized induction variables to
prevent us from converting between the scalar and vector forms.
This patch should resolve compile-time regressions seen after r274627.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275419 91177308-0d34-0410-b5e6-96231b3b80d8
The LCSSA pass itself will not generate several redundant PHI nodes in a single
exit block. However, such redundant PHI nodes don't violate LCSSA form, and may
be introduced by passes that preserve LCSSA, and/or preserved by the LCSSA pass
itself. So, assuming a single PHI node per exit block is not safe.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275217 91177308-0d34-0410-b5e6-96231b3b80d8
Use range-based for loops instead of doing everything manually.
Use auto when appropriate.
No functional change is intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275205 91177308-0d34-0410-b5e6-96231b3b80d8
We currently always vectorize induction variables. However, if an induction
variable is only used for counting loop iterations or computing addresses with
getelementptr instructions, we don't need to do this. Vectorizing these trivial
induction variables can create vector code that is difficult to simplify later
on. This is especially true when the unroll factor is greater than one, and we
create vector arithmetic when computing step vectors. With this patch, we check
if an induction variable is only used for counting iterations or computing
addresses, and if so, scalarize the arithmetic when computing step vectors
instead. This allows for greater simplification.
This patch addresses the suboptimal pointer arithmetic sequence seen in
PR27881.
Reference: https://llvm.org/bugs/show_bug.cgi?id=27881
Differential Revision: http://reviews.llvm.org/D21620
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274627 91177308-0d34-0410-b5e6-96231b3b80d8
This will be re-used by the LoadStoreVectorizer.
Fix handling of range metadata and testcase by Justin Lebar.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274281 91177308-0d34-0410-b5e6-96231b3b80d8
Except the seed uniform instructions (conditional branch and consecutive ptr
instructions), dependencies to be added into uniform set should only be used
by existing uniform instructions or intructions outside of current loop.
Differential Revision: http://reviews.llvm.org/D21755
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274262 91177308-0d34-0410-b5e6-96231b3b80d8
For the new hotness attribute, the API will take the pass rather than
the pass name so we can no longer play the trick of AlwaysPrint being a
special pass name. This adds a getter to help the transition.
There is also a corresponding clang patch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274100 91177308-0d34-0410-b5e6-96231b3b80d8
It did not handle correctly cases without GEP.
The following loop wasn't vectorized:
for (int i=0; i<len; i++)
*to++ = *from++;
I use getPtrStride() to find Stride for memory access and return 0 is the Stride is not 1 or -1.
Re-commit rL273257 - revision: http://reviews.llvm.org/D20789
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@273864 91177308-0d34-0410-b5e6-96231b3b80d8
The interleaved access analysis currently assumes that the inserted run-time
pointer aliasing checks ensure the absence of dependences that would prevent
its instruction reordering. However, this is not the case.
Issues can arise from how code generation is performed for interleaved groups.
For a load group, all loads in the group are essentially moved to the location
of the first load in program order, and for a store group, all stores in the
group are moved to the location of the last store. For groups having members
involved in a dependence relation with any other instruction in the loop, this
reordering can violate the dependence.
This patch teaches the interleaved access analysis how to avoid breaking such
dependences, and should fix PR27626.
An assumption of the original analysis was that the accesses had been collected
in "program order". The analysis was then simplified by visiting the accesses
bottom-up. However, this ordering was never guaranteed for anything other than
single basic block loops. Thus, this patch also enforces the desired ordering.
Reference: https://llvm.org/bugs/show_bug.cgi?id=27626
Differential Revision: http://reviews.llvm.org/D19984
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@273687 91177308-0d34-0410-b5e6-96231b3b80d8
It did not handle correctly cases without GEP.
The following loop wasn't vectorized:
for (int i=0; i<len; i++)
*to++ = *from++;
I use getPtrStride() to find Stride for memory access and return 0 is the Stride is not 1 or -1.
Differential revision: http://reviews.llvm.org/D20789
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@273257 91177308-0d34-0410-b5e6-96231b3b80d8
This is a functional change for LLE and LDist. The other clients (LV,
LVerLICM) already had this explicitly enabled.
The temporary boolean parameter to LAA is removed that allowed turning
off speculation of symbolic strides. This makes LAA's caching interface
LAA::getInfo only take the loop as the parameter. This makes the
interface more friendly to the new Pass Manager.
The flag -enable-mem-access-versioning is moved from LV to a LAA which
now allows turning off speculation globally.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@273064 91177308-0d34-0410-b5e6-96231b3b80d8
This is still NFCI, so the list of clients that allow symbolic stride
speculation does not change (yes: LV and LoopVersioningLICM, no: LLE,
LDist). However since the symbolic strides are now managed by LAA
rather than passed by client a new bool parameter is used to enable
symbolic stride speculation.
The existing test Transforms/LoopVectorize/version-mem-access.ll checks
that stride speculation is performed for LV.
The previously added test Transforms/LoopLoadElim/symbolic-stride.ll
ensures that no speculation is performed for LLE.
The next patch will change the functionality and turn on symbolic stride
speculation in all of LAA's clients and remove the bool parameter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272970 91177308-0d34-0410-b5e6-96231b3b80d8
Turns out SymbolicStrides is actually used in canVectorizeWithIfConvert
before it gets set up in canVectorizeMemory.
This works fine as long as SymbolicStrides resides in LV since we just
have an empty map. Based on this the conclusion is made that there are
no symbolic strides which is conservatively correct.
However once SymbolicStrides becomes part of LAI, LAI is nullptr at this
point so we need to differentiate the uninitialized state by returning a
nullptr for SymbolicStrides.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272966 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorizationLegality holds a constant reference to LAI, so this
will have to be const as well.
Also added missed function comment.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272851 91177308-0d34-0410-b5e6-96231b3b80d8
r272715 broke libcxx because it did not correctly handle cases where the
last iteration of one IV is the second-to-last iteration of another.
Original commit message:
Vectorizing loops with "escaping" IVs has been disabled since r190790, due to
PR17179. This re-enables it, with support for external use of both
"post-increment" (last iteration) and "pre-increment" (second-to-last iteration)
IVs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272742 91177308-0d34-0410-b5e6-96231b3b80d8
Vectorizing loops with "escaping" IVs has been disabled since r190790, due to
PR17179. This re-enables it, with support for external use of both
"post-increment" (last iteration) and "pre-increment" (second-to-last iteration)
IVs.
Differential Revision: http://reviews.llvm.org/D21048
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272715 91177308-0d34-0410-b5e6-96231b3b80d8
Previously, we materialized secondary vector IVs from the primary scalar IV,
by offseting the primary to match the correct start value, and then broadcasting
it - inside the loop body. Instead, we can use a real vector IV, like we do for
the primary.
This enables using vector IVs for secondary integer IVs whose type matches the
type of the primary.
Differential Revision: http://reviews.llvm.org/D20932
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272283 91177308-0d34-0410-b5e6-96231b3b80d8
Previously, whenever we needed a vector IV, we would create it on the fly,
by splatting the scalar IV and adding a step vector. Instead, we can create a
real vector IV. This tends to save a couple of instructions per iteration.
This only changes the behavior for the most basic case - integer primary
IVs with a constant step.
Differential Revision: http://reviews.llvm.org/D20315
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@271410 91177308-0d34-0410-b5e6-96231b3b80d8
In truncateToMinimalBitwidths() we were RAUW'ing an instruction then erasing it. However, that intruction could be cached in the map we're iterating over. The first check is "I->use_empty()" which in most cases would return true, as the (deleted) object was RAUW'd first so would have zero use count. However in some cases the object could have been polluted or written over and this wouldn't be the case. Also it makes valgrind, asan and traditionalists who don't like their compiler to crash sad.
No testcase as there are no externally visible symptoms apart from a crash if the stars align.
Fixes PR26509.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269908 91177308-0d34-0410-b5e6-96231b3b80d8
The selection of the vectorization factor currently doesn't consider
interleaved accesses. The vectorization factor is based on the maximum safe
dependence distance computed by LAA. However, for loops with interleaved
groups, we should instead base the vectorization factor on the maximum safe
dependence distance divided by the maximum interleave factor of all the
interleaved groups. Interleaved accesses not in a group will be scalarized.
Differential Revision: http://reviews.llvm.org/D20241
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269659 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorBody was changed from a single pointer to a SmallVector when
store predication was introduced in r200270. Since r247139, store predication
no longer splits the vector loop body in-place, so we can go back to having
a single LoopVectorBody block.
This reverts the no-longer-needed changes from r200270.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269321 91177308-0d34-0410-b5e6-96231b3b80d8
Allow vectorization when the step is a loop-invariant variable.
This is the loop example that is getting vectorized after the patch:
int int_inc;
int bar(int init, int *restrict A, int N) {
int x = init;
for (int i=0;i<N;i++){
A[i] = x;
x += int_inc;
}
return x;
}
"x" is an induction variable with *loop-invariant* step.
But it is not a primary induction. Primary induction variable with non-constant step is not handled yet.
Differential Revision: http://reviews.llvm.org/D19258
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269023 91177308-0d34-0410-b5e6-96231b3b80d8
