This replaces the select chain for edge-padding with an scf.if that
performs the memory operation when the index is in bounds and uses the
pad value when it's not. For transfer_write the same mechanism is used,
skipping the store when the index is out of bounds.
The integration test has a bunch of cases of how I believe this should
work.
Differential Revision: https://reviews.llvm.org/D87241
In this commit a new way of convolution ops lowering is introduced.
The conv op vectorization pass lowers linalg convolution ops
into vector contractions. This lowering is possible when conv op
is first tiled by 1 along specific dimensions which transforms
it into dot product between input and kernel subview memory buffers.
This pass converts such conv op into vector contraction and does
all necessary vector transfers that make it work.
Differential Revision: https://reviews.llvm.org/D86619
This patch is cherry-picked from 04b0a4e22e3b4549f9d241f8a9f37eebecb62a31, and
amended to prevent an undefined reference to `llvm::EnableABIBreakingChecks'
MSVC's cl.exe has a few command line arguments which start with -M such
as "-MD", "-MDd", "-MT", "-MTd", "-MP".
These arguments are not dependency file generation related, and these
arguments were being removed by getClangStripDependencyFileAdjuster()
which was wrong.
Differential revision: https://reviews.llvm.org/D86999
Commit 3c0b3250 introduced memory cluster under pwr10 target, but a
check for operands was unexpectedly removed. This adds it back to avoid
regression.
Implement AArch64 variant of shouldCoalesce() to detect a known failing case
and prevent the coalescing of a 32-bit copy into a 64-bit sign-extending load.
Do not coalesce in the following case:
COPY where source is bottom 32 bits of a 64-register,
and destination is a 32-bit subregister of a 64-bit register,
ie it causes the rest of the register to be implicitly set to zero.
A mir test has been added.
In the test case, the 32-bit copy implements a 32 to 64 bit zero extension
and relies on the upper 32 bits being zeroed.
Coalescing to the result of the 64-bit load meant overwriting
the upper 32 bits incorrectly when the loaded byte was negative.
Reviewed By: john.brawn
Differential Revision: https://reviews.llvm.org/D85956
Without gcc 7.4 warns with
../lib/Target/PowerPC/PPCInstrInfo.cpp:2284:25: warning: suggest parentheses around '&&' within '||' [-Wparentheses]
BaseOp1.isFI() &&
~~~~~~~~~~~~~~~^~
"Only base registers and frame indices are supported.");
~
In GenerateConstantOffsetsImpl, we may generate non canonical Formula
if BaseRegs of that Formula is updated and includes a recurrent expr reg
related with current loop while its ScaledReg is not.
Patched by: mdchen
Reviewed By: qcolombet
Differential Revision: https://reviews.llvm.org/D86939
The CloneFunctionInto has implicit requirements with regards to the
linkage and visibility of the function. We now update these after we did
the CloneFunctionInto on the copy with the same linkage and visibility
as the original.
One run line was different and probably introduced for the manually
added function attribute & name checks. We can do this with the script
and a check prefix used for the other run lines as well.
Deleting or replacing anything is certainly a modification. This caused
a later assertion in IPSCCP when compiling 400.perlbench with the new PM.
I'm not sure how to test this.
On Power10, it's profitable to schedule some stores with adjacent target
address together. This patch implements this feature.
Reviewed By: steven.zhang
Differential Revision: https://reviews.llvm.org/D86754
In this diff the tests which verify version printing functionality are refactored.
Since they are not specific to a particular format we move them into tool-version.test
and slightly unify (similarly to tool-name.test and tool-help-message.test).
Test plan: make check-all
Differential revision: https://reviews.llvm.org/D87211
No point in making __parityti2 go through 2 calls to get to
__paritysi2.
Reviewed By: MaskRay, efriedma
Differential Revision: https://reviews.llvm.org/D87218
LLD supports -Ttext but with the option there is still a PT_LOAD at address zero
and thus the Linux kernel will map it to a different address and the test will fail.
Use --image-base instead.
This was reverted in 503deec218
because it caused gigantic increase (3x) in branch mispredictions
in certain benchmarks on certain CPU's,
see https://reviews.llvm.org/D84108#2227365.
It has since been investigated and here are the results:
https://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20200907/827578.html
> It's an amazingly severe regression, but it's also all due to branch
> mispredicts (about 3x without this). The code layout looks ok so there's
> probably something else to deal with. I'm not sure there's anything we can
> reasonably do so we'll just have to take the hit for now and wait for
> another code reorganization to make the branch predictor a bit more happy :)
>
> Thanks for giving us some time to investigate and feel free to recommit
> whenever you'd like.
>
> -eric
So let's just reland this.
Original commit message:
I've been looking at missed vectorizations in one codebase.
One particular thing that stands out is that some of the loops
reach vectorizer in a rather mangled form, with weird PHI's,
and some of the loops aren't even in a rotated form.
After taking a more detailed look, that happened because
the loop's headers were too big by then. It is evident that
SimplifyCFG's common code hoisting transform is at fault there,
because the pattern it handles is precisely the unrotated
loop basic block structure.
Surprizingly, `SimplifyCFGOpt::HoistThenElseCodeToIf()` is enabled
by default, and is always run, unlike it's friend, common code sinking
transform, `SinkCommonCodeFromPredecessors()`, which is not enabled
by default and is only run once very late in the pipeline.
I'm proposing to harmonize this, and disable common code hoisting
until //late// in pipeline. Definition of //late// may vary,
here currently i've picked the same one as for code sinking,
but i suppose we could enable it as soon as right after
loop rotation happens.
Experimentation shows that this does indeed unsurprizingly help,
more loops got rotated, although other issues remain elsewhere.
Now, this undoubtedly seriously shakes phase ordering.
This will undoubtedly be a mixed bag in terms of both compile- and
run- time performance, codesize. Since we no longer aggressively
hoist+deduplicate common code, we don't pay the price of said hoisting
(which wasn't big). That may allow more loops to be rotated,
so we pay that price. That, in turn, that may enable all the transforms
that require canonical (rotated) loop form, including but not limited to
vectorization, so we pay that too. And in general, no deduplication means
more [duplicate] instructions going through the optimizations. But there's still
late hoisting, some of them will be caught late.
As per benchmarks i've run {F12360204}, this is mostly within the noise,
there are some small improvements, some small regressions.
One big regression i saw i fixed in rG8d487668d09fb0e4e54f36207f07c1480ffabbfd, but i'm sure
this will expose many more pre-existing missed optimizations, as usual :S
llvm-compile-time-tracker.com thoughts on this:
http://llvm-compile-time-tracker.com/compare.php?from=e40315d2b4ed1e38962a8f33ff151693ed4ada63&to=c8289c0ecbf235da9fb0e3bc052e3c0d6bff5cf9&stat=instructions
* this does regress compile-time by +0.5% geomean (unsurprizingly)
* size impact varies; for ThinLTO it's actually an improvement
The largest fallout appears to be in GVN's load partial redundancy
elimination, it spends *much* more time in
`MemoryDependenceResults::getNonLocalPointerDependency()`.
Non-local `MemoryDependenceResults` is widely-known to be, uh, costly.
There does not appear to be a proper solution to this issue,
other than silencing the compile-time performance regression
by tuning cut-off thresholds in `MemoryDependenceResults`,
at the cost of potentially regressing run-time performance.
D84609 attempts to move in that direction, but the path is unclear
and is going to take some time.
If we look at stats before/after diffs, some excerpts:
* RawSpeed (the target) {F12360200}
* -14 (-73.68%) loops not rotated due to the header size (yay)
* -272 (-0.67%) `"Number of live out of a loop variables"` - good for vectorizer
* -3937 (-64.19%) common instructions hoisted
* +561 (+0.06%) x86 asm instructions
* -2 basic blocks
* +2418 (+0.11%) IR instructions
* vanilla test-suite + RawSpeed + darktable {F12360201}
* -36396 (-65.29%) common instructions hoisted
* +1676 (+0.02%) x86 asm instructions
* +662 (+0.06%) basic blocks
* +4395 (+0.04%) IR instructions
It is likely to be sub-optimal for when optimizing for code size,
so one might want to change tune pipeline by enabling sinking/hoisting
when optimizing for size.
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D84108
This reverts commit 503deec218.
For intrinsics supported by ConstantRange, compute the result range
based on the argument ranges. We do this independently of whether
some or all of the input ranges are full, as we can often still
constrain the result in some way.
Differential Revision: https://reviews.llvm.org/D87183
Rather than using SELECT instructions, use SRA, UADDO/ADDCARRY and
XORs to expand ABS. This is the multi-part version of the sequence
we use in LegalizeDAG.
It's also the same as the Custom sequence uses for i64 on 32-bit
and i128 on 64-bit. So we can remove the X86 customization.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D87215
This was supposed to be an NFC cleanup, but there's
a real logic difference (did not drop 'nsw') visible
in some tests in addition to an efficiency improvement.
This is because in the case where we have 2 GEPs,
the code was *always* swapping the operands and
negating the result. But if we have 2 GEPs, we
should *never* need swapping/negation AFAICT.
This is part of improving flags propagation noticed
with PR47430.
This is a follow-up suggested in D86420 - if we have a pair of stores
in inverted order for the target endian, we can rotate the source
bits into place.
The "be_i64_to_i16_order" test shows a limitation of the current
function (which might be avoided if we integrate this function with
the other cases in mergeConsecutiveStores). In the earlier
"be_i64_to_i16" test, we skip the first 2 stores because we do not
match the full set as consecutive or rotate-able, but then we reach
the last 2 stores and see that they are an inverted pair of 16-bit
stores. The "be_i64_to_i16_order" test alters the program order of
the stores, so we miss matching the sub-pattern.
Differential Revision: https://reviews.llvm.org/D87112
MASM allows variables defined by equate statements to be used in expressions.
Reviewed By: thakis
Differential Revision: https://reviews.llvm.org/D86946
MASM aligns fields to the _minimum_ of the STRUCT alignment value and the size of the next field.
Reviewed By: thakis
Differential Revision: https://reviews.llvm.org/D86945
Qiu Chaofan