predecessors before returning. Otherwise, if multiple predecessor edges need
splitting, we only get one of them per iteration. This makes a small but
measurable compile time improvement with -enable-full-load-pre.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97521 91177308-0d34-0410-b5e6-96231b3b80d8
confusing the old MAT variable with the new GlobalType one. This caused
us to promote the @disp global pointer into:
@disp.body = internal global double*** undef
instead of:
@disp.body = internal global [3 x double**] undef
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97285 91177308-0d34-0410-b5e6-96231b3b80d8
which branch on undef to branch on a boolean constant for the edge
exiting the loop. This helps ScalarEvolution compute trip counts for
loops.
Teach ScalarEvolution to recognize single-value PHIs, when safe, and
ForgetSymbolicName to forget such single-value PHI nodes as apprpriate
in ForgetSymbolicName.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97126 91177308-0d34-0410-b5e6-96231b3b80d8
argument is non-null, pass it along to PHITranslateSubExpr so that it can
prefer using existing values that dominate the PredBB, instead of just
blindly picking the first equivalent value that it finds on a uselist.
Also when the DominatorTree is specified, have PHITranslateValue filter
out any result that does not dominate the PredBB. This is basically just
refactoring the check that used to be in GetAvailablePHITranslatedSubExpr
and also in GVN.
Despite my initial expectations, this change does not affect the results
of GVN for any testcases that I could find, but it should help compile time.
Before this change, if PHITranslateSubExpr picked a value that does not
dominate, PHITranslateWithInsertion would then insert a new value, which GVN
would later determine to be redundant and would replace. By picking a good
value to begin with, we save GVN the extra work of inserting and then
replacing a new value.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97010 91177308-0d34-0410-b5e6-96231b3b80d8
induction variable value and a loop-variant value, don't force the
insert position to be at the post-increment position, because it may
not be dominated by the loop-variant value. This fixes a
use-before-def problem noticed on PPC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96774 91177308-0d34-0410-b5e6-96231b3b80d8
strides in foreign loops. This helps locate reuse opportunities
with existing induction variables in foreign loops and reduces
the need for inserting new ones. This fixes rdar://7657764.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96629 91177308-0d34-0410-b5e6-96231b3b80d8
a loop exit value, so that if a loop gets deleted, ScalarEvolution
isn't stick holding on to dangling SCEVAddRecExprs for that loop. This
fixes PR6339.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96626 91177308-0d34-0410-b5e6-96231b3b80d8
and T->isPointerTy(). Convert most instances of the first form to the second form.
Requested by Chris.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96344 91177308-0d34-0410-b5e6-96231b3b80d8
as it also peeks at which registers are being used by other uses. This
makes LSR less sensitive to use-list order.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96308 91177308-0d34-0410-b5e6-96231b3b80d8
with multiplication by constants distributed through, occasionally
those subexpressions can include both x and -x. For now, if this
condition is discovered within LSR, just prune such cases away,
as they won't be profitable. This fixes a "zero allocated in a
base register" assertion failure.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96177 91177308-0d34-0410-b5e6-96231b3b80d8
odd offsets since the bitcasted pointer size and the offset pointer
size are going to be different types for the GEP vs base object.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96134 91177308-0d34-0410-b5e6-96231b3b80d8
and add a doxygen comment.
Cache the phi entry to avoid doing tons of
PHINode::getBasicBlockIndex calls in the common case.
On my insane testcase from re2c, this speeds up CGP from
617.4s to 7.9s (78x).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96083 91177308-0d34-0410-b5e6-96231b3b80d8
to a PHI, avoid it in the common case where the BB occurs
in the same index for multiple phis. This speeds up CGP on
an insane testcase from 8.35 to 3.58s.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96080 91177308-0d34-0410-b5e6-96231b3b80d8
Functions explicitly marked inline will get an inlining threshold slightly
more aggressive than the default for -O3. This means than -O3 builds are
mostly unaffected while -Os builds will be a bit bigger and faster.
The difference depends entirely on how many 'inline's are sprinkled on the
source.
In the CINT2006 suite, only these tests are significantly affected under -Os:
Size Time
471.omnetpp +1.63% -1.85%
473.astar +4.01% -6.02%
483.xalancbmk +4.60% 0.00%
Note that 483.xalancbmk runs too quickly to give useful timing results.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96066 91177308-0d34-0410-b5e6-96231b3b80d8
2. don't bother trying to merge globals in non-default sections,
doing so is quite dubious at best anyway.
3. fix a bug reported by Arnaud de Grandmaison where we'd try to
merge two globals in different address spaces.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95995 91177308-0d34-0410-b5e6-96231b3b80d8
bug fixes, and with improved heuristics for analyzing foreign-loop
addrecs.
This change also flattens IVUsers, eliminating the stride-oriented
groupings, which makes it easier to work with.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95975 91177308-0d34-0410-b5e6-96231b3b80d8
what it does. Enhance it to return false to optimizing vector
sign extensions from vector comparisions, which is the idiom used
to get a splatted vector for a vector comparison.
Doing this breaks vector-casts.ll, add some compensating
transformations to handle the important case they cover without
depending on this canonicalization.
This fixes rdar://7434900 a serious pessimization of vector compares.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95855 91177308-0d34-0410-b5e6-96231b3b80d8
block. Other blocks may have pointer cycles that will crash
basicaa and other alias analyses. In any case, there is no
point wasting cycles optimizing dead blocks. This fixes
rdar://7635088
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95852 91177308-0d34-0410-b5e6-96231b3b80d8
Initial skeleton and SCEVUnknown lowering implemented,
the rest should come relatively quickly. Move testcase
to new directory.
Move pass to right before SimplifyLibCalls - which is
moved down a bit so we can take advantage of a few opts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95628 91177308-0d34-0410-b5e6-96231b3b80d8
This time it's for real! I am going to hook this up in the frontends as well.
The inliner has some experimental heuristics for dealing with the inline hint.
When given a -respect-inlinehint option, functions marked with the inline
keyword are given a threshold just above the default for -O3.
We need some experiments to determine if that is the right thing to do.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95466 91177308-0d34-0410-b5e6-96231b3b80d8
xform it is checking to actually pass. There is no need to match
m_SelectCst<0, -1> since instcombine canonicalizes that into not(sext).
Add matches for sext(not(x)) in addition to not(sext(x)).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95420 91177308-0d34-0410-b5e6-96231b3b80d8
container data. This prevents it from holding onto dangling
pointers and potentially behaving unpredictably.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95409 91177308-0d34-0410-b5e6-96231b3b80d8
short-circuited conditions to AND/OR expressions, and those expressions
are often converted back to a short-circuited form in code gen. The
original source order may have been optimized to take advantage of the
expected values, and if we reassociate them, we change the order and
subvert that optimization. Radar 7497329.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95333 91177308-0d34-0410-b5e6-96231b3b80d8
This makes the inliner about as agressive as it was before my changes to the
inliner cost calculations. These levels give the same performance and slightly
smaller code than before.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95320 91177308-0d34-0410-b5e6-96231b3b80d8
Fix bugs where we would compute out of bounds as in bounds, and where
we couldn't know that the linker could override the size of an array.
Add a few new testcases, change existing testcase to use a private
global array instead of extern.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95283 91177308-0d34-0410-b5e6-96231b3b80d8
The SRThreshold value makes perfect sense for checking if an entire aggregate
should be promoted to a scalar integer, but it is not so good for splitting
an aggregate into its separate elements. A struct may contain a large embedded
array along with some scalar fields that would benefit from being split apart
by SROA. Even if the total aggregate size is large, it may still be good to
perform SROA. Thus, the most important piece of this patch is simply moving
the aggregate size comparison vs. SRThreshold so that it guards only the
aggregate promotion.
We have also been checking the number of elements to decide if an aggregate
should be split up. The limit of "SRThreshold/4" seemed rather arbitrary,
and I don't think it's very useful to derive this limit from SRThreshold
anyway. I've collected some data showing that the current default limit of
32 (since SRThreshold defaults to 128) is a reasonable cutoff for struct
types. One thing suggested by the data is that distinguishing between structs
and arrays might be useful. There are (obviously) a lot more large arrays
than large structs (as measured by the number of elements and not the total
size -- a large array inside a struct still counts as a single element given
the way we do SROA right now). Out of 8377 arrays where we successfully
performed SROA while compiling a large set of benchmarks, only 16 of them had
more than 8 elements. And, for those 16 arrays, it's not at all clear that
SROA was actually beneficial. So, to offset the compile time cost of
investigating more large structs for SROA, the patch lowers the limit on array
elements to 8.
This fixes Apple Radar 7563690.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95224 91177308-0d34-0410-b5e6-96231b3b80d8