| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This also means we have to check if the latch is the exiting block now,
as `transform` expects the latches to be the exiting blocks too.
https://bugs.llvm.org/show_bug.cgi?id=36586
Reviewers: efriedma, davide, karthikthecool
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D45279
llvm-svn: 330806
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
modes.
This patch adds parsing support for 'vector + shift/extend' and
corresponding asm operand classes, needed for implementing SVE's
gather/scatter addressing modes.
The added combinations of vector (ZPR) and Shift/Extend are:
Unscaled:
ZPR64ExtLSL8: signed 64-bit offsets (z0.d)
ZPR32ExtUXTW8: unsigned 32-bit offsets (z0.s, uxtw)
ZPR32ExtSXTW8: signed 32-bit offsets (z0.s, sxtw)
Unpacked and unscaled:
ZPR64ExtUXTW8: unsigned 32-bit offsets (z0.d, uxtw)
ZPR64ExtSXTW8: signed 32-bit offsets (z0.d, sxtw)
Unpacked and scaled:
ZPR64ExtUXTW<scale>: unsigned 32-bit offsets (z0.d, uxtw #<shift>)
ZPR64ExtSXTW<scale>: signed 32-bit offsets (z0.d, sxtw #<shift>)
Scaled:
ZPR32ExtUXTW<scale>: unsigned 32-bit offsets (z0.s, uxtw #<shift>)
ZPR32ExtSXTW<scale>: signed 32-bit offsets (z0.s, sxtw #<shift>)
ZPR64ExtLSL<scale>: unsigned 64-bit offsets (z0.d, lsl #<shift>)
ZPR64ExtLSL<scale>: signed 64-bit offsets (z0.d, lsl #<shift>)
Patch [1/3] in series to add support for SVE's gather load instructions
that use scalar+vector addressing modes:
- Patch [1/3]: https://reviews.llvm.org/D45951
- Patch [2/3]: https://reviews.llvm.org/D46023
- Patch [3/3]: https://reviews.llvm.org/D45958
Reviewers: fhahn, rengolin, samparker, SjoerdMeijer, t.p.northover, echristo, evandro, javed.absar
Reviewed By: fhahn
Differential Revision: https://reviews.llvm.org/D45951
llvm-svn: 330805
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
When Reassociate is rewriting an expression tree it may
reuse old binary expression nodes, for new expressions.
Whenever an expression node is reused, but with a non-trivial
change in the result, we need to invalidate any debug info
that is associated with the node.
If for example rewriting
x = mul a, b
y = mul c, x
into
x = mul c, b
y = mul a, x
we still get the same result for 'y', but 'x' is a new expression.
All debug info referring to 'x' must be invalidated (marked as
optimized out) since we no longer calculate the expected value.
As a side-effect this patch avoid (at least some) problems where
reassociate could end up creating IR with debug-use before def.
Earlier the dbg.value nodes where left untouched in the IR, while
the reused binary nodes where sinked to just before the root node
of the rewritten expression tree. See PR27273 for more info about
such problems.
Reviewers: dblaikie, aprantl, dexonsmith
Reviewed By: aprantl
Subscribers: JDevlieghere, llvm-commits
Tags: #debug-info
Differential Revision: https://reviews.llvm.org/D45975
llvm-svn: 330804
|
| |
|
|
|
|
| |
------------------------------------------------------------------------
llvm-svn: 330799
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Use a MapVector instead of a DenseMap for RemMap since it is iteratated
over and the order of iteration can effect the order that new
instructions are created. This can in turn effect the use list order of
div/rem input values if multiple new instructions are created that share
any input values.
Reviewers: spatel
Subscribers: mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D45858
llvm-svn: 330792
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
update API for dominators rather than doing manual, hacky updates.
This is just the first step, but in some ways the most important as it
moves the non-trivial unswitching to update the domtree rather than
fully recalculating it each time.
Subsequent patches should remove the custom update logic used by the
trivial unswitch and replace it with uses of the update API.
This also fixes a number of bugs I was seeing when testing non-trivial
unswitch due to it querying the quasi-correct dominator tree. Now the
tree is 100% correct and safe to query. That said, there are still more
bugs I can see with non-trivial unswitch just running over the test
suite, so more bugfix patches are needed as well.
Thanks to both Sanjoy and Fedor for reviews and testing!
Differential Revision: https://reviews.llvm.org/D45943
llvm-svn: 330787
|
| |
|
|
|
|
|
|
|
|
| |
Before, the outliner would grab ADRPs that used LR/W30. This patch fixes
that by checking for explicit uses of those registers before the special-casing
for ADRPs.
This also adds a test that ensures that those sorts of ADRPs won't be outlined.
llvm-svn: 330783
|
| |
|
|
|
|
|
|
|
|
|
|
| |
We were previously prefering ZEXTLOAD over EXTLOAD if it is legal. This triggers during X86's promotion of i16->i32. Not sure about other targets.
Using ZEXTLOAD can prevent folding it to SEXTLOAD later if we were to promote a sign extended operand like we would need for SRA. However, X86 doesn't currently promote i16 SRA. I was looking into doing that which is how I found this issue.
This is also blocking our ability to fold 4 byte aligned EXTLOADs with "loadi32". This is what caused most of the test changes here.
Differential Revision: https://reviews.llvm.org/D45585#inline-402825
llvm-svn: 330781
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previously, _any_ store or load instruction was considered to be
operating on a spill if it had a frameindex as an operand, and thus
was fair game for optimisations such as "StackSlotColoring". This
usually works, except on architectures where spills can be partially
restored, for example on X86 where a spilt vector can have a single
component loaded (zeroing the rest of the target register). This can be
mis-interpreted and the zero extension unsoundly eliminated, see
pr30821.
To avoid this, this commit optionally provides the caller to
isLoadFromStackSlot and isStoreToStackSlot with the number of bytes
spilt/loaded by the given instruction. Optimisations can then determine
that a full spill followed by a partial load (or vice versa), for
example, cannot necessarily be commuted.
Patch by Jeremy Morse!
Differential Revision: https://reviews.llvm.org/D44782
llvm-svn: 330778
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary: This is no longer used by mesa since its 18.0.0 release.
Reviewers: nhaehnle
Reviewed By: nhaehnle
Subscribers: arsenm, kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D45988
llvm-svn: 330775
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Reviewers: arsenm, nhaehnle
Reviewed By: nhaehnle
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D45843
llvm-svn: 330774
|
| |
|
|
|
|
|
|
|
| |
Summary:
The PointerMayBeCapturedBefore function's DomTree arg should be
const instead of non-const. There are no non-const uses of it
in the function.
llvm-svn: 330769
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Reviewers: arsenm
Reviewed By: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D45837
llvm-svn: 330767
|
| |
|
|
|
|
|
| |
Found with MSan. This was causing all the WASM MC tests to fail about
10% of the time.
llvm-svn: 330764
|
| |
|
|
| |
llvm-svn: 330760
|
| |
|
|
|
|
| |
This also fixes Jaguar's schedule which was treating it as the WriteVecIMul default.
llvm-svn: 330756
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
If a packed inline constant is sign extended it must be truncated
after the shift. I.e. a constant (0xH0000, 0xHBC00), will be represented
as 0xFFFFFFFFBC000000 in the IR because the immediate is sign extended
to 64 bit. After the value shifted right by 16 to use it in a low part
with op_sel_hi it becomes 0xFFFFFFFFBC00 and does not qualify as inline
constant any longer.
Fixed the error and added verification code. Without the fix and with
the verification bug is causing pk_max_f16_literal.ll to fail.
Differential Revision: https://reviews.llvm.org/D45987
llvm-svn: 330752
|
| |
|
|
| |
llvm-svn: 330751
|
| |
|
|
|
|
|
|
|
|
|
| |
Rather than referring to sections my their code, use the
absolute index of the target section within the module.
See https://github.com/WebAssembly/tool-conventions/issues/52
Differential Revision: https://reviews.llvm.org/D45980
llvm-svn: 330749
|
| |
|
|
|
|
| |
These variants all take an immediate shuffle mask value and should be scheduled as such.
llvm-svn: 330747
|
| |
|
|
|
|
|
|
|
|
|
| |
Removes one subprocess and one temp file from the build for each tablegen
invocation.
No intended behavior change.
https://reviews.llvm.org/D45899
llvm-svn: 330742
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is part of fixing the instruction predicates for MIPS.
Reviewers: atanasyan, abeserminji
Differential Revision: https://reviews.llvm.org/D44212
This patch relands r327409, hopefully without the problematic part of the
tests that cause FileCheck to assert on the windows expensive checks bot.
llvm-svn: 330741
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Patch #2 from VPlan Outer Loop Vectorization Patch Series #1
(RFC: http://lists.llvm.org/pipermail/llvm-dev/2017-December/119523.html).
This patch introduces the basic infrastructure to detect, legality check
and process outer loops annotated with hints for explicit vectorization.
All these changes are protected under the feature flag
-enable-vplan-native-path. This should make this patch NFC for the existing
inner loop vectorizer.
Reviewers: hfinkel, mkuper, rengolin, fhahn, aemerson, mssimpso.
Differential Revision: https://reviews.llvm.org/D42447
llvm-svn: 330739
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
After D43236, we started interchanging loops with empty dependence
matrices. In isProfitableForVectorization, we try to determine if
interchanging makes the loop dependences more friendly to the
vectorizer. If there are no dependences, we should not interchange,
based on that heuristic.
Reviewers: efriedma, mcrosier, karthikthecool, blitz.opensource
Reviewed By: mcrosier
Differential Revision: https://reviews.llvm.org/D45208
llvm-svn: 330738
|
| |
|
|
|
|
| |
Fixes the classification of VCVTPS2PHmr/VCVTPS2PHYmr which were tagged as WriteCvtF2FLd_WriteRMW (PR36887)
llvm-svn: 330737
|
| |
|
|
|
|
| |
These are stores, not loads, so don't need to account for load latency.
llvm-svn: 330735
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Current code does not check that a register number is in the 0-31 range.
Sometimes the parser checks that later for some kinds of instructions,
but that leads to unclear / incorrect error messages like that:
% cat test.s
.text
lb $4, 8($32)
% llvm-mc test.s -triple=mips64-unknown-linux
test.s:2:10: error: expected memory with 16-bit signed offset
lb $4, 8($32)
^
Sometimes the parser just crashes:
% cat test.s
.text
lw $4, 8($32)
% llvm-mc test.s -triple=mips64-unknown-linux
This patch resolves the problem by checking that register number after
'$' sign is in the 0-31 range. If the number is out of the range the
parser shows the `invalid register number` error, but treats invalid
register number as a normal one to continue parsing and catch other
possible errors.
Differential Revision: https://reviews.llvm.org/D45919
llvm-svn: 330732
|
| |
|
|
|
|
| |
- s/SWaitcnt/Waitcnt s/WaitCnt/Waitcnt
llvm-svn: 330730
|
| |
|
|
| |
llvm-svn: 330726
|
| |
|
|
|
|
|
|
|
| |
The memory location an invariant load is using can never be clobbered by
any store, so it's safe to move the load ahead of the store.
Differential Revision: https://reviews.llvm.org/D46011
llvm-svn: 330725
|
| |
|
|
| |
llvm-svn: 330720
|
| |
|
|
|
|
|
|
| |
While not necessary for correctness, it is preferable for
performance reasons on all architectures we currently support
to align functions to 16-byte boundaries by default.
llvm-svn: 330718
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Split off pinsr/pextr and extractps instructions.
(Mostly) fixes PR36887.
Note: It might be worth adding a WriteFInsertLd class as well in the future.
Differential Revision: https://reviews.llvm.org/D45929
llvm-svn: 330714
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
If attribute "use-soft-float"="true" is set then X86ISelLowering.cpp sets
'Promote' action for ISD::SINT_TO_FP operation on type i32.
But 'Promote' action is not proper in this case since lib function
__floatsidf is available for casting from signed int to float type.
Thus Expand action is more suitable here.
The Expand action should be set for ISD::UINT_TO_FP for soft float as well.
If function attribute "use-soft-float"="true" is set then infinite looping
can happen in DAG combining, function visitSINT_TO_FP() replaces SINT_TO_FP
node with UINT_TO_FP node and function combineUIntToFP() replace vice versa in cycle.
The fix prevents it.
Patch by vrybalov
Differential Revision: https://reviews.llvm.org/D45572
llvm-svn: 330711
|
| |
|
|
|
|
|
|
|
|
|
|
| |
If available, print the file, line and column of the DebugLoc attached
to the MachineInstr:
MOV16mr $rbp, 1, $noreg, -112, $noreg, killed renamable $ax, debug-location !56 :: (store 2 into %ir.._value12); stepping.swift:10:17
renamable $edx = MOVZX32rm16 $rbp, 1, $noreg, -112, $noreg, debug-location !62 :: (dereferenceable load 2 from %ir.._value13); stepping.swift:10:17
Differential Revision: https://reviews.llvm.org/D45992
llvm-svn: 330709
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
loop unswitch.
This code incorrectly added the header to the loop block set early. As
a consequence we would incorrectly conclude that a nested loop body had
already been visited when the header of the outer loop was the preheader
of the nested loop. In retrospect, adding the header eagerly doesn't
really make sense. It seems nicer to let the cycle be formed naturally.
This will catch crazy bugs in the CFG reconstruction where we can't
correctly form the cycle earlier rather than later, and makes the rest
of the logic just fall out.
I've also added various asserts that make these issues *much* easier to
debug.
llvm-svn: 330707
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch aims to provide correct dwarf unwind information in function
epilogue for X86.
It consists of two parts. The first part inserts CFI instructions that set
appropriate cfa offset and cfa register in emitEpilogue() in
X86FrameLowering. This part is X86 specific.
The second part is platform independent and ensures that:
* CFI instructions do not affect code generation (they are not counted as
instructions when tail duplicating or tail merging)
* Unwind information remains correct when a function is modified by
different passes. This is done in a late pass by analyzing information
about cfa offset and cfa register in BBs and inserting additional CFI
directives where necessary.
Added CFIInstrInserter pass:
* analyzes each basic block to determine cfa offset and register are valid
at its entry and exit
* verifies that outgoing cfa offset and register of predecessor blocks match
incoming values of their successors
* inserts additional CFI directives at basic block beginning to correct the
rule for calculating CFA
Having CFI instructions in function epilogue can cause incorrect CFA
calculation rule for some basic blocks. This can happen if, due to basic
block reordering, or the existence of multiple epilogue blocks, some of the
blocks have wrong cfa offset and register values set by the epilogue block
above them.
CFIInstrInserter is currently run only on X86, but can be used by any target
that implements support for adding CFI instructions in epilogue.
Patch by Violeta Vukobrat.
Differential Revision: https://reviews.llvm.org/D42848
llvm-svn: 330706
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Guard the MIPS64 variant correctly for i64, mark the MIPS32 version as not
in microMIPS and provide the microMIPS version.
Additionally, remove a related stale XFAIL'd test as bswap has its own test
case providing coverage.
Reviewers: smaksimovic, abeserminji, atanasyan
Differential Revision: https://reviews.llvm.org/D45816
llvm-svn: 330705
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
The pass is supposed to scalarize such intrinsics if the target does not support
them natively, so if the scalarization does not happen instruction selection
crashes due to inability to lower these intrinsics.
Reviewers: andrew.w.kaylor, craig.topper
Reviewed By: andrew.w.kaylor
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D45947
llvm-svn: 330700
|
| |
|
|
| |
llvm-svn: 330699
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
(scalar+scalar) load instructions.
Reviewers: fhahn, rengolin, samparker, SjoerdMeijer, t.p.northover, echristo, evandro, javed.absar
Reviewed By: rengolin
Subscribers: tschuett, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D45946
llvm-svn: 330697
|
| |
|
|
| |
llvm-svn: 330688
|
| |
|
|
| |
llvm-svn: 330683
|
| |
|
|
|
|
| |
This encoding is recognized by the CPU, but the behavior is undefined. This makes the disassembler handle it correctly so we don't print bswapl with a 16-bit register.
llvm-svn: 330682
|
| |
|
|
|
|
|
|
|
|
| |
This code path can very clearly be called in a context where we have
baselined all the cloned blocks to a particular loop and are trying to
handle nested subloops. There is no harm in this, so just relax the
assert. I've added a test case that will make sure we actually exercise
this code path.
llvm-svn: 330680
|
| |
|
|
| |
llvm-svn: 330678
|
| |
|
|
| |
llvm-svn: 330677
|
| |
|
|
| |
llvm-svn: 330676
|
| |
|
|
|
|
| |
No functional change intended.
llvm-svn: 330675
|
| |
|
|
|
|
|
|
| |
(notionally Scalar.h is part of libLLVMScalarOpts, so it shouldn't be
included by InstCombine which doesn't/shouldn't need to depend on
ScalarOpts)
llvm-svn: 330669
|