Summary:
vectorizer-maximize-bandwidth is generally useful in terms of performance. I've tested the impact of changing this to default on speccpu benchmarks on sandybridge machines. The result shows non-negative impact:
spec/2006/fp/C++/444.namd 26.84 -0.31%
spec/2006/fp/C++/447.dealII 46.19 +0.89%
spec/2006/fp/C++/450.soplex 42.92 -0.44%
spec/2006/fp/C++/453.povray 38.57 -2.25%
spec/2006/fp/C/433.milc 24.54 -0.76%
spec/2006/fp/C/470.lbm 41.08 +0.26%
spec/2006/fp/C/482.sphinx3 47.58 -0.99%
spec/2006/int/C++/471.omnetpp 22.06 +1.87%
spec/2006/int/C++/473.astar 22.65 -0.12%
spec/2006/int/C++/483.xalancbmk 33.69 +4.97%
spec/2006/int/C/400.perlbench 33.43 +1.70%
spec/2006/int/C/401.bzip2 23.02 -0.19%
spec/2006/int/C/403.gcc 32.57 -0.43%
spec/2006/int/C/429.mcf 40.35 +0.27%
spec/2006/int/C/445.gobmk 26.96 +0.06%
spec/2006/int/C/456.hmmer 24.4 +0.19%
spec/2006/int/C/458.sjeng 27.91 -0.08%
spec/2006/int/C/462.libquantum 57.47 -0.20%
spec/2006/int/C/464.h264ref 46.52 +1.35%
geometric mean +0.29%
The regression on 453.povray seems real, but is due to secondary effects as all hot functions are bit-identical with and without the flag.
I started this patch to consult upstream opinions on this. It will be greatly appreciated if the community can help test the performance impact of this change on other architectures so that we can decided if this should be target-dependent.
Reviewers: hfinkel, mkuper, davidxl, chandlerc
Reviewed By: chandlerc
Subscribers: rengolin, sanjoy, javed.absar, bjope, dorit, magabari, RKSimon, llvm-commits, mzolotukhin
Differential Revision: https://reviews.llvm.org/D33341
llvm-svn: 306336
Fixes bug 33597.
Use of substituteRegister in the tied operand case messes
up the register use iterator, causing some uses to be left
unprocessed.
llvm-svn: 306333
Instead of providing access to the internal MapStorage holding all Values
associated with a given Key, used for setting or resetting them all together,
ValueMap keeps its MapStorage internal; its new interface allows getting,
setting or resetting a single Value, per part or per part-and-lane.
Follows the discussion in https://reviews.llvm.org/D32871.
Differential Revision: https://reviews.llvm.org/D34473
llvm-svn: 306331
When we forward a stored value to a load and eliminate it entirely we need to
make sure the liveness of the register is maintained all the way to its use.
Previously we only cleared liveness on the store doing the forwarding, but
there could be other killing uses in between.
We already do the right thing when the load has to be converted into something
else, it was just this one path that skipped it.
llvm-svn: 306318
Some forms have sizes that depend on the DWARF version, DWARF format
(32/64-bit), or the size of an address. Collect these into a struct
to simplify passing them around. Require callers to provide one when
they query a form's size.
Differential Revision: http://reviews.llvm.org/D34570
llvm-svn: 306315
The recommit fixes three bugs: The first one is to use CurrentBlock instead of
PREInstr's Parent as param of performScalarPREInsertion because the Parent
of a clone instruction may be uninitialized. The second one is stop PRE when
CurrentBlock to its predecessor is a backedge and an operand of CurInst is
defined inside of CurrentBlock. The same value defined inside of loop in last
iteration can not be regarded as available. The third one is an out-of-bound
array access in a flipped if guard.
Right now scalarpre doesn't have phi-translate support, so it will miss some
simple pre opportunities. Like the following testcase, current scalarpre cannot
recognize the last "a * b" is fully redundent because a and b used by the last
"a * b" expr are both defined by phis.
long a[100], b[100], g1, g2, g3;
__attribute__((pure)) long goo();
void foo(long a, long b, long c, long d) {
g1 = a * b;
if (__builtin_expect(g2 > 3, 0)) {
a = c;
b = d;
g2 = a * b;
}
g3 = a * b; // fully redundant.
}
The patch adds phi-translate support in scalarpre. This is only a temporary
solution before the newpre based on newgvn is available.
llvm-svn: 306313
This patch removes the dependency on the external rc.exe tool by writing
a simple .res file using our own library. In this patch I also added an
explicit definition for the .res file magic. Furthermore, I added a
unittest for embeded manifests and fixed a bug exposed by the test.
llvm-svn: 306311
Summary: Minor changes that allow opt-stats.py to support both Python 2 and 3.
Reviewers: anemet, davidxl
Reviewed By: anemet
Subscribers: llvm-commits, fhahn
Differential Revision: https://reviews.llvm.org/D34564
llvm-svn: 306306
We sometimes need emergency spill slots for the register scavenger.
This may be the case when code needs to access a stack slot that
has an offset of 4096 or more relative to the stack pointer.
To make that determination, processFunctionBeforeFrameFinalized
currently simply checks the total stack frame size of the current
function. But this is not enough, since code may need to access
stack slots in the caller's stack frame as well, in particular
incoming arguments stored on the stack.
This commit fixes the problem by taking argument slots into account.
llvm-svn: 306305
The non-AVX-512 behavior was changed in r248266 to match N1778
(C bindings for IEEE-754 (2008)), which defined the four functions
to not raise the inexact exception ("rint" is still defined as raising
it).
Update the AVX-512 lowering of these functions to match that: it should
not be different.
llvm-svn: 306299
Convert vector increment or decrement to sub/add with an all-ones constant:
add X, <1, 1...> --> sub X, <-1, -1...>
sub X, <1, 1...> --> add X, <-1, -1...>
The all-ones vector constant can be materialized using a pcmpeq instruction that is
commonly recognized as an idiom (has no register dependency), so that's better than
loading a splat 1 constant.
AVX512 uses 'vpternlogd' for 512-bit vectors because there is apparently no better
way to produce 512 one-bits.
The general advantages of this lowering are:
1. pcmpeq has lower latency than a memop on every uarch I looked at in Agner's tables,
so in theory, this could be better for perf, but...
2. That seems unlikely to affect any OOO implementation, and I can't measure any real
perf difference from this transform on Haswell or Jaguar, but...
3. It doesn't look like it from the diffs, but this is an overall size win because we
eliminate 16 - 64 constant bytes in the case of a vector load. If we're broadcasting
a scalar load (which might itself be a bug), then we're replacing a scalar constant
load + broadcast with a single cheap op, so that should always be smaller/better too.
4. This makes the DAG/isel output more consistent - we use pcmpeq already for padd x, -1
and psub x, -1, so we should use that form for +1 too because we can. If there's some
reason to favor a constant load on some CPU, let's make the reverse transform for all
of these cases (either here in the DAG or in a later machine pass).
This should fix:
https://bugs.llvm.org/show_bug.cgi?id=33483
Differential Revision: https://reviews.llvm.org/D34336
llvm-svn: 306289
Csmith discovered that this function can be called with a zero argument,
in which case an assert for this triggered.
This patch also adds a guard before the other call to this function since
it was missing, although the test only covers the case where it was
discovered.
Reduced test case attached as CodeGen/SystemZ/int-cmp-54.ll.
Review: Ulrich Weigand
llvm-svn: 306287
As noted on PR32585, the change in D29780/rL295325 resulted in calls to Rand32() (values 0 -> 0xFFFFFFFF) but the min()/max() operators indicated it would be (0 -> 0x7FFFF).
This patch changes the random operator to call Rand() instead which does respect the 0 -> 0x7FFFF range and asserts that the value is in range as well.
Differential Revision: https://reviews.llvm.org/D34089
llvm-svn: 306281
This method doesn't do any initializing. It just contains asserts. So renaming to AssertOK makes it consistent with similar instructions in other Instruction classes.
llvm-svn: 306277
We added the initilization of disassembler passes in r306208 with the goal to
bring bugpoint in line with 'opt'. However, 'opt' does itself not initialize
dissassembler passes. As our goal was consistency, we drop the initialization
of dissassembler passes again from bugpoint.
Thanks to Chandler for pointing this out!
llvm-svn: 306275
This is a last fix for the corner case of PR32214. Actually this is not really corner case in general.
We should not do a loop rotation if we create an additional branch due to it.
Consider the case where we have a loop chain H, M, B, C , where
H is header with viable fallthrough from pre-header and exit from the loop
M - some middle block
B - backedge to Header but with exit from the loop also.
C - some cold block of the loop.
Let's H is determined as a best exit. If we do a loop rotation M, B, C, H we can introduce the extra branch.
Let's compute the change in number of branches:
+1 branch from pre-header to header
-1 branch from header to exit
+1 branch from header to middle block if there is such
-1 branch from cold bock to header if there is one
So if C is not a predecessor of H then we introduce extra branch.
This change actually prohibits rotation of the loop if both true
1) Best Exit has next element in chain as successor.
2) Last element in chain is not a predecessor of first element of chain.
Reviewers: iteratee, xur
Reviewed By: iteratee
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34271
llvm-svn: 306272
metadata out of InstCombine and into helpers.
NFC, this just exposes the logic used by InstCombine when propagating
metadata from one load instruction to another. The plan is to use this
in SROA to address PR32902.
If anyone has better ideas about how to factor this or name variables,
I'm all ears, but this seemed like a pretty good start and lets us make
progress on the PR.
This is based on a patch by Ariel Ben-Yehuda (D34285).
llvm-svn: 306267
This should not be treated as a different version of
private_segment_buffer. These are distinct things with
different uses and register classes, and requires the
function argument info to have more context about the
function's type and environment.
Also add missing test coverage for the intrinsic, and
emit an error for HSA. This also encovers that the intrinsic
is broken unless there happen to be stack objects.
llvm-svn: 306264
This was reverted in r306252, but I already had the bug fixed and was
just trying to form a test case.
The original commit factored the logic for forming dedicated exits
inside of LoopSimplify into a helper that could be used elsewhere and
with an approach that required fewer intermediate data structures. See
that commit for full details including the change to the statistic, etc.
The code looked fine to me and my reviewers, but in fact didn't handle
indirectbr correctly -- it left the 'InLoopPredecessors' vector dirty.
If you have code that looks *just* right, you can end up leaking these
predecessors into a subsequent rewrite, and crash deep down when trying
to update PHI nodes for predecessors that don't exist.
I've added an assert that makes the bug much more obvious, and then
changed the code to reliably clear the vector so we don't get this bug
again in some other form as the code changes.
I've also added a test case that *does* manage to catch this while also
giving some nice positive coverage in the face of indirectbr.
The real code that found this came out of what I think is CPython's
interpreter loop, but any code with really "creative" interpreter loops
mixing indirectbr and other exit paths could manage to tickle the bug.
I was hard to reduce the original test case because in addition to
having a particular pattern of IR, the whole thing depends on the order
of the predecessors which is in turn depends on use list order. The test
case added here was designed so that in multiple different predecessor
orderings it should always end up going down the same path and tripping
the same bug. I hope. At least, it tripped it for me without
manipulating the use list order which is better than anything bugpoint
could do...
llvm-svn: 306257
I did some basic testing while looking for a bug in my recent change to
loop simplify and even though it didn't find the bug it seems like
a useful improvement anyways.
llvm-svn: 306256
Recommit NFC patch (rL306157) where I missed incrementing the basic block iterator,
which caused loop deletion tests to hang due to infinite loop.
Had reverted it in rL306162.
rL306157 commit message:
Currently, the implementation of delete dead loops has a special case
when the loop being deleted is never executed. This special case
(updating of exit block's incoming values for phis) can be
run as a prepass for non-executable loops before performing
the actual deletion.
llvm-svn: 306254
Summary:
This patch does a few things that should remove some copies around PatternsToMatch. These were noticed while reviewing code for D34341.
Change constructor to take Dstregs by value and move it into the class. Change one of the callers to add std::move to the argument so that it gets moved.
Make AddPatternToMatch take PatternToMatch by rvalue reference so we can move it into the PatternsToMatch vector. I believe we should have a implicit default move constructor available on PatternToMatch. I chose rvalue reference because both callers call it with temporaries already.
Reviewers: RKSimon, aymanmus, spatel
Reviewed By: aymanmus
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34411
llvm-svn: 306251
Vedant Kumar