This reverts commit e8fd20964798ca6d46d2729dd3a789707a6416da in an
attempt to appease the GlobalISel buildbot, which fails in the
test-suite with errors like
fpcmp: files differ without tolerance allowance
llvm-svn: 311151
If a struct would end up half in GPRs and half on SP the ABI says it should
actually go entirely on the stack. We were getting this wrong in GlobalISel
before, causing compatibility issues.
llvm-svn: 311137
Two issues identified by buildbots were addressed:
- The pass no longer forwards COPYs to physical register uses, since
doing so can break code that implicitly relies on the physical
register number of the use.
- The pass no longer forwards COPYs to undef uses, since doing so
can break the machine verifier by creating LiveRanges that don't
end on a use (since the undef operand is not considered a use).
[MachineCopyPropagation] Extend pass to do COPY source forwarding
This change extends MachineCopyPropagation to do COPY source forwarding.
This change also extends the MachineCopyPropagation pass to be able to
be run during register allocation, after physical registers have been
assigned, but before the virtual registers have been re-written, which
allows it to remove virtual register COPY LiveIntervals that become dead
through the forwarding of all of their uses.
Reviewers: qcolombet, javed.absar, MatzeB, jonpa
Subscribers: jyknight, nemanjai, llvm-commits, nhaehnle, mcrosier, mgorny
Differential Revision: https://reviews.llvm.org/D30751
llvm-svn: 311135
Summary:
Support the case where an operand of a pattern is also the whole of the
result pattern. In this case the original result and all its uses must be
replaced by the operand. However, register class restrictions can require
a COPY. This patch handles both cases by always emitting the copy and
leaving it for the register allocator to optimize.
The previous commit failed on Windows machines due to a flaw in the sort
predicate which allowed both A < B < C and B == C to be satisfied
simultaneously. The cause of this was some sloppiness in the priority order of
G_CONSTANT instructions compared to other instructions. These had equal priority
because it makes no difference, however there were operands had higher priority
than G_CONSTANT but lower priority than any other instruction. As a result, a
priority order between G_CONSTANT and other instructions must be enforced to
ensure the predicate defines a strict weak order.
Reviewers: ab, t.p.northover, qcolombet, rovka, aditya_nandakumar
Subscribers: javed.absar, kristof.beyls, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D36084
llvm-svn: 311076
This reverts commit r311038.
Several buildbots are breaking, and at least one appears to be due to
the forwarding of physical regs enabled by this change. Reverting while
I investigate further.
llvm-svn: 311062
This change extends MachineCopyPropagation to do COPY source forwarding.
This change also extends the MachineCopyPropagation pass to be able to
be run during register allocation, after physical registers have been
assigned, but before the virtual registers have been re-written, which
allows it to remove virtual register COPY LiveIntervals that become dead
through the forwarding of all of their uses.
Reviewers: qcolombet, javed.absar, MatzeB, jonpa
Subscribers: jyknight, nemanjai, llvm-commits, nhaehnle, mcrosier, mgorny
Differential Revision: https://reviews.llvm.org/D30751
llvm-svn: 311038
r310825 caused the clang-ppc64le-linux-lnt bot to go red
(http://lab.llvm.org:8011/builders/clang-ppc64le-linux-lnt/builds/5712)
because of a test-suite failure of
SingleSource/UnitTests/2003-07-09-SignedArgs
This reverts commit 0028f6a87224fb595a1c19c544cde9b003035996.
llvm-svn: 311008
As expected, this failed on the windows bots but the instrumentation showed
something interesting. The ADD8ri and INC8r rules are never directly compared
on the windows machines. That implies that the issue lies in transitivity of
the Compare predicate. I believe I've already verified that but maybe I missed
something.
llvm-svn: 310922
Summary:
Support the case where an operand of a pattern is also the whole of the
result pattern. In this case the original result and all its uses must be
replaced by the operand. However, register class restrictions can require
a COPY. This patch handles both cases by always emitting the copy and
leaving it for the register allocator to optimize.
The previous commit failed on the windows bots and this one is likely to fail
on those same bots. However, the added instrumentation should reveal a particular
isHigherPriorityThan() evaluation which I'm expecting to expose that
these machines are weighing priority of two rules differently from the
non-windows machines.
Reviewers: ab, t.p.northover, qcolombet, rovka, aditya_nandakumar
Subscribers: javed.absar, kristof.beyls, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D36084
llvm-svn: 310919
Two of the Windows bots are failing test\CodeGen\X86\GlobalISel\select-inc.mir
which should not have been affected by the change. Reverting while I investigate.
Also reverted r310735 because it builds on r310716.
llvm-svn: 310745
Summary:
Support the case where an operand of a pattern is also the whole of the
result pattern. In this case the original result and all its uses must be
replaced by the operand. However, register class restrictions can require
a COPY. This patch handles both cases by always emitting the copy and
leaving it for the register allocator to optimize.
Depends on D35833
Reviewers: ab, t.p.northover, qcolombet, rovka, aditya_nandakumar
Subscribers: javed.absar, kristof.beyls, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D36084
llvm-svn: 310716
Before, the outliner would mark all instructions that read from/modify LR as
illegal. This doesn't handle W30, which overlaps with LR. This shouldn't be
outlined.
This commit fixes that by making modifiesRegister() and readsRegister() look at
W30 + take in a TRI argument. This makes sure that modifiesRegister() and
readsRegister() won't outline either of W30 and LR.
https://reviews.llvm.org/D36435
llvm-svn: 310422
Summary:
This patch enables the import of rules containing 'imm' operands that do not
constrain the acceptable values using predicates. Support for ImmLeaf will
arrive in a later patch.
Depends on D35681
Reviewers: ab, t.p.northover, qcolombet, rovka, aditya_nandakumar
Reviewed By: rovka
Subscribers: kristof.beyls, javed.absar, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D35833
llvm-svn: 310343
Relanding after case to insert explicit truncation as necessary.
Allow SCALAR_TO_VECTOR of EXTRACT_VECTOR_ELT to reduce to
EXTRACT_SUBVECTOR of vector shuffle when output is smaller. Marginally
improves vector shuffle computations.
Reviewers: efriedma, RKSimon, spatel
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D35566
llvm-svn: 310256
The NewNodesMustHaveLegalTypes flag is set to false at the beginning of CodeGenAndEmitDAG, and set to true after legalizing types.
But before calling CodeGenAndEmitDAG we build the DAG for the basic block.
So for the first basic block NewNodesMustHaveLegalTypes would be 'false' during the SDAG building, and for all other basic blocks it would be 'true'.
This patch sets the flag to false before SDAG building each basic block.
Differential Revision:
https://reviews.llvm.org/D33435
llvm-svn: 310239
Add memory synchronization semantics to LSE Atomics.
The memory semantics feature will be added in a subsequent patch.
In this patch, several corrections were added to the existing LSE Atomics
implementation, based on the ARM Errata D11904 from 05/12/2017.
Patch by: steleman
Differential Revision: https://reviews.llvm.org/D35319
llvm-svn: 310167
Summary: Move test/CodeGen/AArch64/reg-bank-128bit.mir to test/CodeGen/AArch64/GlobalISel/reg-bank-128bit.mir so that the test is executed only when global-isel is enabled. lit.local.cfg under test/CodeGen/AArch64/GlobalISel checks if 'global-isel' is in the available_features while the same file under test/CodeGen/AArch64 doesn't.
Reviewers: qcolombet, davide
Reviewed By: davide
Subscribers: davide, aemerson, javed.absar, igorb, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D36282
llvm-svn: 309985
This pattern shows up when lowering byval copies on AMDGPU.
The byval object access is split into 4-byte chunks, adding a
constant offset to the FixedStack base. When some of the offsets
turn into ors, this prevents combining the constant offsets.
This makes it not apparent that the object is there when matching
addressing modes, so it ends up using a scratch wave offset
relative access and the lengthy frame index expansion for that.
llvm-svn: 309775
The previous attempt, which made do with a single offset in
computeCalleeSaveRegisterPairs, wasn't quite enough. The previous
attempt only worked as long as CombineSPBump == true (since the
offset would be adjusted later in fixupCalleeSaveRestoreStackOffset).
Instead include the size for the fixed stack area used for win64
varargs in calculations in emitPrologue/emitEpilogue. The stack
consists of mainly three parts;
- AFI->getLocalStackSize()
- AFI->getCalleeSavedStackSize()
- FixedObject
Most of the places in the code which previously used the CSStackSize
now use PrologueSaveSize instead, which is the sum of the latter
two, while some cases which need exactly the middle one use
AFI->getCalleeSavedStackSize() explicitly instead of a local variable.
In addition to moving the offsetting into emitPrologue/emitEpilogue
(which fixes functions with CombineSPBump == false), also set the
frame pointer to point to the right location, where the frame pointer
and link register actually are stored. In addition to the prologue/epilogue,
this also requires changes to resolveFrameIndexReference.
Add tests for a function that keeps a frame pointer and another one
that uses a VLA.
Differential Revision: https://reviews.llvm.org/D35919
llvm-svn: 309744
Summary:
Most CPUs implementing AES fusion require instruction pairs of the form
AESE Vn, _
AESMC Vn, Vn
and
AESD Vn, _
AESIMC Vn, Vn
The constraint is added to AES(I)MC instructions which use the result of
an AES(E|D) instruction by using AES(I)MCTrr pseudo instructions, which
constraint source and destination registers to be the same.
A nice side effect of this change is that now all possible pairs are
scheduled back-to-back on the exynos-m1 for the misched-fusion-aes.ll
test case.
I had to update aes_load_store. The version I added initially was very
reduced and with the new constraint, AESE/AESMC could not be scheduled
back-to-back. I updated the test to be more realistic and still expose
the same scheduling problem as the initial test case.
Reviewers: t.p.northover, rengolin, evandro, kristof.beyls, silviu.baranga
Reviewed By: t.p.northover, evandro
Subscribers: aemerson, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D35299
llvm-svn: 309495
Summary:
This change gives a 0.25% speedup on execution time, a 0.82% improvement
in benchmark scores and a 0.20% increase in binary size on a Cortex-A53.
These numbers are the geomean results on a wide range of benchmarks from
the test-suite and a range of proprietary suites.
Reviewers: t.p.northover, aadg, silviu.baranga, mcrosier, rengolin
Reviewed By: rengolin
Subscribers: grimar, davide, aemerson, rengolin, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D35568
llvm-svn: 309494
The (seldom-used) TBI-aware optimization had a typo lying dormant since
it was first introduced, in r252573: when asking for demanded bits, it
told TLI that it was running after legalize, where the opposite was
true.
This is an important piece of information, that the demanded bits
analysis uses to make assumptions about the node. r301019 added such an
assumption, which was broken by the TBI combine.
Instead, pass the correct flags to TLO.
llvm-svn: 309323
Create a dummy 8 byte fixed object for the unused slot below the first
stored vararg.
Alternative ideas tested but skipped: One could try to align the whole
fixed object to 16, but I haven't found how to add an offset to the stack
frame used in LowerWin64_VASTART.
If only the size of the fixed stack object size is padded but not the offset, via
MFI.CreateFixedObject(alignTo(GPRSaveSize, 16), -(int)GPRSaveSize, false),
PrologEpilogInserter crashes due to "Attempted to reset backwards range!".
This fixes misconceptions about where registers are spilled, since
AArch64FrameLowering.cpp assumes the offset from fixed objects is
aligned to 16 bytes (and the Win64 case there already manually aligns
the offset to 16 bytes).
This fixes cases where local stack allocations could overwrite callee
saved registers on the stack.
Differential Revision: https://reviews.llvm.org/D35720
llvm-svn: 308950
This patch removes unnecessary zero copies in BBs that are targets of b.eq/b.ne
and we know the result of the compare instruction is zero. For example,
BB#0:
subs w0, w1, w2
str w0, [x1]
b.ne .LBB0_2
BB#1:
mov w0, wzr ; <-- redundant
str w0, [x2]
.LBB0_2
Differential Revision: https://reviews.llvm.org/D35075
llvm-svn: 308849
It revealed a bug in the Localizer pass which has now been fixed.
This includes the fix for SUBREG_TO_REG committed separately last time.
llvm-svn: 308688
If the localizer pass puts one of its constants before the label that tells the
unwinder "jump here to handle your exception" then control-flow will skip it,
leaving uninitialized registers at runtime. That's bad.
llvm-svn: 308687
On AMDGPU SGPR spills are really spilled to another register.
The spiller creates the spills to new frame index objects,
which is used as a placeholder.
This will eventually be replaced with a reference to a position
in a VGPR to write to and the frame index deleted. It is
most likely not a real stack location that can be shared
with another stack object.
This is a problem when StackSlotColoring decides it should
combine a frame index used for a normal VGPR spill with
a real stack location and a frame index used for an SGPR.
Add an ID field so that StackSlotColoring has a way
of knowing the different frame index types are
incompatible.
llvm-svn: 308673
Add optimization remarks support to the PrologueEpilogueInserter. For
now, emit the stack size as an analysis remark, but more additions wrt
shrink-wrapping may be added.
https://reviews.llvm.org/D35645
llvm-svn: 308556
Summary:
When simplifying unconditional branches from empty blocks, we pre-test if the
BB belongs to a set of loop headers and keep the block to prevent passes from
destroying canonical loop structure. However, the current algorithm fails if
the destination of the branch is a loop header. Especially when such a loop's
latch block is folded into loop header it results in additional backedges and
LoopSimplify turns it into a nested loop which prevent later optimizations
from being applied (e.g., loop unrolling and loop interleaving).
This patch augments the existing algorithm by further checking if the
destination of the branch belongs to a set of loop headers and defer
eliminating it if yes to LateSimplifyCFG.
Fixes PR33605: https://bugs.llvm.org/show_bug.cgi?id=33605
Reviewers: efriedma, mcrosier, pacxx, hsung, davidxl
Reviewed By: efriedma
Subscribers: ashutosh.nema, gberry, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D35411
llvm-svn: 308422
Re-recommiting after landing DAG extension-crash fix.
Recommiting after adding check to avoid miscomputing alias information
on addresses of the same base but different subindices.
Memory accesses offset from frame indices may alias, e.g., we
may merge write from function arguments passed on the stack when they
are contiguous. As a result, when checking aliasing, we consider the
underlying frame index's offset from the stack pointer.
Static allocs are realized as stack objects in SelectionDAG, but its
offset is not set until post-DAG causing DAGCombiner's alias check to
consider access to static allocas to frequently alias. Modify isAlias
to consider access between static allocas and access from other frame
objects to be considered aliasing.
Many test changes are included here. Most are fixes for tests which
indirectly relied on our aliasing ability and needed to be modified to
preserve their original intent.
The remaining tests have minor improvements due to relaxed
ordering. The exception is CodeGen/X86/2011-10-19-widen_vselect.ll
which has a minor degradation dispite though the pre-legalized DAG is
improved.
Reviewers: rnk, mkuper, jonpa, hfinkel, uweigand
Reviewed By: rnk
Subscribers: sdardis, nemanjai, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33345
llvm-svn: 308350
Summary:
G_FMA was recently added to GlobalISel which enables the import of rules
involving fma. Add the mapping to allow it.
Reviewers: ab, t.p.northover, qcolombet, rovka, aditya_nandakumar
Reviewed By: rovka
Subscribers: kristof.beyls, javed.absar, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D35130
llvm-svn: 308308
Rename the enum value from X86_64_Win64 to plain Win64.
The symbol exposed in the textual IR is changed from 'x86_64_win64cc'
to 'win64cc', but the numeric value is kept, keeping support for
old bitcode.
Differential Revision: https://reviews.llvm.org/D34474
llvm-svn: 308208
Restricting register class to PointerRegClass for memory operands.
Also fix the PointerRegClass for AArch64 from GPR64 to GPR64sp, since
XZR cannot hold a memory pointer while SP is.
Fixes PR33134.
Differential Revision: https://reviews.llvm.org/D34999
llvm-svn: 308060
Summary:
This patch is the first step in reducing HW prefetcher instruction tag
collisions in inner loops for Falkor. It adds a pass that annotates IR
loads with metadata to indicate that they are known to be strided loads,
and adds a target lowering hook that translates this metadata to a
target-specific MachineMemOperand flag.
A follow on change will use this MachineMemOperand flag to re-write
instructions to reduce tag collisions.
Reviewers: mcrosier, t.p.northover
Subscribers: aemerson, rengolin, mgorny, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D34963
llvm-svn: 308059
Recommiting after adding check to avoid miscomputing alias information
on addresses of the same base but different subindices.
Memory accesses offset from frame indices may alias, e.g., we
may merge write from function arguments passed on the stack when they
are contiguous. As a result, when checking aliasing, we consider the
underlying frame index's offset from the stack pointer.
Static allocs are realized as stack objects in SelectionDAG, but its
offset is not set until post-DAG causing DAGCombiner's alias check to
consider access to static allocas to frequently alias. Modify isAlias
to consider access between static allocas and access from other frame
objects to be considered aliasing.
Many test changes are included here. Most are fixes for tests which
indirectly relied on our aliasing ability and needed to be modified to
preserve their original intent.
The remaining tests have minor improvements due to relaxed
ordering. The exception is CodeGen/X86/2011-10-19-widen_vselect.ll
which has a minor degradation dispite though the pre-legalized DAG is
improved.
Reviewers: rnk, mkuper, jonpa, hfinkel, uweigand
Reviewed By: rnk
Subscribers: sdardis, nemanjai, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33345
llvm-svn: 308025
Pass parameters properly in calls to such functions (pass all
floats in integer registers), and handle va_start properly (allocate
stack immediately below the arguments on the stack, to save the
register arguments into a single continuous array).
Differential Revision: https://reviews.llvm.org/D35006
llvm-svn: 307928
A generic variant of IMPLICIT_DEF was added in r306875, but this
survives to selection and hits a `Cannot Select`. Add handling that
converts the note to a regular IMPLICIT_DEF.
llvm-svn: 307817
OpenCL 2.0 introduces the notion of memory scopes in atomic operations to
global and local memory. These scopes restrict how synchronization is
achieved, which can result in improved performance.
This change extends existing notion of synchronization scopes in LLVM to
support arbitrary scopes expressed as target-specific strings, in addition to
the already defined scopes (single thread, system).
The LLVM IR and MIR syntax for expressing synchronization scopes has changed
to use *syncscope("<scope>")*, where <scope> can be "singlethread" (this
replaces *singlethread* keyword), or a target-specific name. As before, if
the scope is not specified, it defaults to CrossThread/System scope.
Implementation details:
- Mapping from synchronization scope name/string to synchronization scope id
is stored in LLVM context;
- CrossThread/System and SingleThread scopes are pre-defined to efficiently
check for known scopes without comparing strings;
- Synchronization scope names are stored in SYNC_SCOPE_NAMES_BLOCK in
the bitcode.
Differential Revision: https://reviews.llvm.org/D21723
llvm-svn: 307722
TreePatternNode considers them to be plain integers but MachineInstr considers
them to be a distinct kind of operand.
The tweak to AArch64InstrInfo.td to produce a simple test case is a NFC for
everything except GlobalISelEmitter (confirmed by diffing the tablegenerated
files). GlobalISelEmitter is currently unable to infer the type of operands in
the Dst pattern from the operands in the Src pattern.
llvm-svn: 307634
Reverting as it breaks tramp3d-v4 in the llvm test-suite. I added some
comments to https://reviews.llvm.org/D33345 about it.
This reverts commit r307546.
llvm-svn: 307589
Memory accesses offset from frame indices may alias, e.g., we
may merge write from function arguments passed on the stack when they
are contiguous. As a result, when checking aliasing, we consider the
underlying frame index's offset from the stack pointer.
Static allocs are realized as stack objects in SelectionDAG, but its
offset is not set until post-DAG causing DAGCombiner's alias check to
consider access to static allocas to frequently alias. Modify isAlias
to consider access between static allocas and access from other frame
objects to be considered aliasing.
Many test changes are included here. Most are fixes for tests which
indirectly relied on our aliasing ability and needed to be modified to
preserve their original intent.
The remaining tests have minor improvements due to relaxed
ordering. The exception is CodeGen/X86/2011-10-19-widen_vselect.ll
which has a minor degradation dispite though the pre-legalized DAG is
improved.
Reviewers: rnk, mkuper, jonpa, hfinkel, uweigand
Reviewed By: rnk
Subscribers: sdardis, nemanjai, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33345
llvm-svn: 307546
Summary:
This change gives a 0.89% speed on execution time, a 0.94% improvement
in benchmark scores and a 0.62% increase in binary size on a Cortex-A57.
These numbers are the geomean results on a wide range of benchmarks from
the test-suite, SPEC2000, SPEC2006 and a range of proprietary suites.
The software optimization guide for the Cortex-A57 recommends 16 byte
branch alignment.
Reviewers: t.p.northover, mcrosier, javed.absar, kristof.beyls, sbaranga
Reviewed By: kristof.beyls
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D34954
llvm-svn: 307389
Summary:
This change gives a 0.34% speed on execution time, a 0.61% improvement
in benchmark scores and a 0.57% increase in binary size on a Cortex-A72.
These numbers are the geomean results on a wide range of benchmarks from
the test-suite, SPEC2000, SPEC2006 and a range of proprietary suites.
The software optimization guide for the Cortex-A72 recommends 16 byte
branch alignment.
Reviewers: t.p.northover, kristof.beyls, rengolin, sbaranga, mcrosier, javed.absar
Reviewed By: kristof.beyls
Subscribers: llvm-commits, aemerson
Differential Revision: https://reviews.llvm.org/D34961
llvm-svn: 307380
Summary:
Add an option to prevent diagnostics that do not meet a minimum hotness
threshold from being output. When generating optimization remarks for
large codebases with a ton of cold code paths, this option can be used
to limit the optimization remark output at a reasonable size. Discussion of
this change can be read here:
http://lists.llvm.org/pipermail/llvm-dev/2017-June/114377.html
Reviewers: anemet, davidxl, hfinkel
Reviewed By: anemet
Subscribers: qcolombet, javed.absar, fhahn, eraman, llvm-commits
Differential Revision: https://reviews.llvm.org/D34867
llvm-svn: 306912
It looks like there are two target-independent but not GISel instructions that
need legalization, IMPLICIT_DEF and PHI. These are already anomalies since
their operands have important LLTs attached, so to make things more uniform it
seems like a good idea to add generic variants. Starting with G_IMPLICIT_DEF.
llvm-svn: 306875
Some conditional branch instructions generated by this pass are checking
the wrong condition code. The instructions TBZ and TBNZ are transformed
into B.GE and B.LT instead of B.PL and B.MI respectively. They should
only be checking the Negative bit.
Differential Revision: https://reviews.llvm.org/D34743
llvm-svn: 306550
Without this check, COPY instructions can actually be one of the generic casts
in disguise. That's confusing and bad.
At some point during ISel this restriction has to be relaxed since the fully
selected instructions will usually use COPY for those purposes. Right now I
think it's possible that relaxation occurs during RegBankSelect (hence the
change there). I'm not convinced that's where it belongs long-term though.
llvm-svn: 306470
This patch modifies the conditional compares pass so that it keeps successor
probabilities up-to-date after the conversion. Previously, successor
probabilities were being normalized to a uniform distribution, even though they
may have been heavily biased prior to the conversion (e.g., if one of the edges
was the back edge of a loop). This loss of information affected passes later in
the pipeline.
Differential Revision: https://reviews.llvm.org/D34109
llvm-svn: 306412
Summary:
After this patch, we finally have test cases that require multiple
instruction emission.
Depends on D33590
Reviewers: ab, qcolombet, t.p.northover, rovka, kristof.beyls
Subscribers: javed.absar, llvm-commits, igorb
Differential Revision: https://reviews.llvm.org/D33596
llvm-svn: 306388
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
This patch contains a pass that transforms CBZ/CBNZ/TBZ/TBNZ instructions into a
conditional branch (Bcc), when the NZCV flags can be set for "free". This is
preferred on targets that have more flexibility when scheduling Bcc
instructions as compared to CBZ/CBNZ/TBZ/TBNZ (assuming all other variables are
equal). This can reduce register pressure and is also the default behavior for
GCC.
A few examples:
add w8, w0, w1 -> cmn w0, w1 ; CMN is an alias of ADDS.
cbz w8, .LBB_2 -> b.eq .LBB0_2 ; single def/use of w8 removed.
add w8, w0, w1 -> adds w8, w0, w1 ; w8 has multiple uses.
cbz w8, .LBB1_2 -> b.eq .LBB1_2
sub w8, w0, w1 -> subs w8, w0, w1 ; w8 has multiple uses.
tbz w8, #31, .LBB6_2 -> b.ge .LBB6_2
In looking at all current sub-target machine descriptions, this transformation
appears to be either positive or neutral.
Differential Revision: https://reviews.llvm.org/D34220.
llvm-svn: 306144
It was trying to do too many things. The basic lumping together of values for
legalization purposes is now handled by G_MERGE_VALUES. More complex things
involving gaps and odd sizes are handled by G_INSERT sequences.
llvm-svn: 306120
G_SEQUENCE is going away soon so as a first step the MachineIRBuilder needs to
be taught how to emulate it with alternatives. We use G_MERGE_VALUES where
possible, and a sequence of G_INSERTs if not.
llvm-svn: 306119
Added test file for ARMv8.1 LSE Atomics that I forgot to include in
commit r305893.
Patch by Ananth Jasty.
Differential Revision: https://reviews.llvm.org/D33586
Change-Id: Ic1ad8ed87c1b584c4c791b459a686c866a3c3087
llvm-svn: 305918
Summary:
This patch updates promoteLoadFromStore to use the store MachineOperand as the
source operand of the of the new instruction instead of creating a new
register MachineOperand. This way, the existing register flags are
preserved.
This fixes PR33468 (https://bugs.llvm.org/show_bug.cgi?id=33468).
Reviewers: MatzeB, t.p.northover, junbuml
Reviewed By: MatzeB
Subscribers: aemerson, rengolin, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D34402
llvm-svn: 305885
Add support for combining a build vector to a shuffle.
When the build vector is of extracted elements from 2 vectors (vec1, vec2) where vec2 is 2 times smaller than vec1.
llvm-svn: 305883
Summary:
When we're building with XRay instrumentation, we use a trick that
preserves references from the function to a function sled index. This
index table lives in a separate section, and without this trick the
linker is free to garbage-collect this section and all the segments it
refers to. Until we're able to tell the linkers to preserve these
sections, we use this reference trick to keep around both the index and
the entries in the instrumentation map.
Before this change we emitted both a synthetic reference to the label in
the instrumentation map, and to the entry in the function map index.
This change removes the first synthetic reference and only emits one
synthetic reference to the index -- the index entry has the references
to the labels in the instrumentation map, so the linker will still
preserve those if the function itself is preserved.
This reduces the amount of synthetic references we emit from 16 bytes to
just 8 bytes in x86_64, and similarly to other platforms.
Reviewers: dblaikie
Subscribers: javed.absar, kpw, pelikan, llvm-commits
Differential Revision: https://reviews.llvm.org/D34340
llvm-svn: 305880
This does some improvements/cleanup to the recently introduced
scavengeRegisterBackwards() functionality:
- Rewrite findSurvivorBackwards algorithm to use the existing
LiveRegUnit::accumulateBackward() code. This also avoids the Available
and Candidates bitset and just need 1 LiveRegUnit instance
(= 1 bitset).
- Pick registers in allocation order instead of register number order.
llvm-svn: 305817
Summary:
As part of this
* Emitted instructions now have named MachineInstr variables associated
with them. This isn't particularly important yet but it's a small step
towards multiple-insn emission.
* constrainSelectedInstRegOperands() is no longer hardcoded. It's now added
as the ConstrainOperandsToDefinitionAction() action. COPY_TO_REGCLASS uses
an alternate constraint mechanism ConstrainOperandToRegClassAction() which
supports arbitrary constraints such as that defined by COPY_TO_REGCLASS.
Reviewers: ab, qcolombet, t.p.northover, rovka, kristof.beyls, aditya_nandakumar
Reviewed By: ab
Subscribers: javed.absar, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D33590
llvm-svn: 305791
Re-apply r276044/r279124/r305516. Fixed a problem where we would refuse
to place spills as the very first instruciton of a basic block and thus
artifically increase pressure (test in
test/CodeGen/PowerPC/scavenging.mir:spill_at_begin)
This is a variant of scavengeRegister() that works for
enterBasicBlockEnd()/backward(). The benefit of the backward mode is
that it is not affected by incomplete kill flags.
This patch also changes
PrologEpilogInserter::doScavengeFrameVirtualRegs() to use the register
scavenger in backwards mode.
Differential Revision: http://reviews.llvm.org/D21885
llvm-svn: 305625
Revert because of reports of some PPC input starting to spill when it
was predicted that it wouldn't and no spillslot was reserved.
This reverts commit r305516.
llvm-svn: 305566
Re-apply r276044/r279124. Trying to reproduce or disprove the ppc64
problems reported in the stage2 build last time, which I cannot
reproduce right now.
This is a variant of scavengeRegister() that works for
enterBasicBlockEnd()/backward(). The benefit of the backward mode is
that it is not affected by incomplete kill flags.
This patch also changes
PrologEpilogInserter::doScavengeFrameVirtualRegs() to use the register
scavenger in backwards mode.
Differential Revision: http://reviews.llvm.org/D21885
llvm-svn: 305516
The code assumed that we process instructions in basic block order. FastISel
processes instructions in reverse basic block order. We need to pre-assign
virtual registers before selecting otherwise we get def-use relationships wrong.
This only affects code with swifterror registers.
rdar://32659327
llvm-svn: 305484
Summary:
Scheduling AESE/AESMC and AESD/AESIMC instruction pairs back-to-back
gives a double digit speedup on benchmarks using those instructions on
Cortex-A processors. In GCC, this optimization is part of the generic
processor model as well.
This change should not have a major performance impact on processors
that do not optimize AES instruction pairs, although I only had access
to Cortex-A processors for benchmarking.
Reviewers: rengolin, kristof.beyls, javed.absar, evandro, silviu.baranga, MatzeB, mcrosier, joelkevinjones, joel_k_jones, bmakam, t.p.northover
Reviewed By: evandro
Subscribers: sbaranga, aemerson, llvm-commits
Differential Revision: https://reviews.llvm.org/D33836
llvm-svn: 305457
Summary:
When legalizing G_LOAD/G_STORE using NarrowScalar, we should avoid emitting
%0 = G_CONSTANT ty 0
%1 = G_GEP %x, %0
since it's cheaper to not emit the redundant instructions than it is to fold them
away later.
Reviewers: qcolombet, t.p.northover, ab, rovka, aditya_nandakumar, kristof.beyls
Reviewed By: qcolombet
Subscribers: javed.absar, llvm-commits, igorb
Differential Revision: https://reviews.llvm.org/D32746
llvm-svn: 305340
The "Add/sub (shifted reg)" instructions use the 31 encoding for xzr and wzr
rather than the SP, so we need to use different variants.
Situations where this actually comes up are rare enough (see test-case) that I
think falling back to DAG is fine.
llvm-svn: 305230
Summary:
This change enables the sin(x) cos(x) -> sincos(x) optimization on GNU
target triples. This optimization was being inhibited when -ffast-math
wasn't set because sincos in GLibC does not set errno, while sin and cos
do. However, this optimization will only run if the attributes on the
sin/cos calls include readnone, which is how clang represents the fact
that it doesn't care about the errno values set by these functions (via
the -fno-math-errno flag).
Reviewers: hfinkel, bogner
Subscribers: mcrosier, javed.absar, llvm-commits, paul.redmond
Differential Revision: https://reviews.llvm.org/D32921
llvm-svn: 305204
Summary:
- Fix assertion failures on F16 to/from int types in FastISel by falling
back to regular ISel
- Add a testcase of various conversion cases with FastISel (-O0)
Reviewers: kristof.beyls, jmolloy, SjoerdMeijer
Reviewed By: SjoerdMeijer
Subscribers: SjoerdMeijer, llvm-commits, srhines, pirama, aemerson, rengolin, javed.absar, kristof.beyls
Differential Revision: https://reviews.llvm.org/D33734
llvm-svn: 305127
If -simplify-mir option is passed then MIRPrinter will not print such fields.
This change also required some lit test cases in CodeGen directory to be changed.
Reviewed By: MatzeB
Differential Revision: https://reviews.llvm.org/D32304
llvm-svn: 304779
Althought it is not wrong to spill undef values, it is useless and harms
both code size and runtime. Before spilling a value, check that its
content actually matters.
http://www.llvm.org/PR33311
llvm-svn: 304752
Correct references to alignment of store which may be deleted in a
previous iteration of merge. Instead use first store that would be
merged.
Corrects pr33172's use-after-poison caught by ASan.
Reviewers: spatel, hfinkel, RKSimon
Reviewed By: RKSimon
Subscribers: thegameg, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33686
llvm-svn: 304299
There is no guarantee that the first use of a constant that is traversed
is actually the first in the related basic block. Thus, if we use that
as the insertion point we may end up with definitions that don't
dominate there use.
llvm-svn: 304244
If we have (extract_subvector(load wide vector)) with no other users,
that can just be (load narrow vector). This is intentionally conservative.
Follow-ups may loosen the one-use constraint to account for the extract cost
or just remove the one-use check.
The memop chain updating is based on code that already exists multiple times
in x86 lowering, so that should be pulled into a helper function as a follow-up.
Background: this is a potential improvement noticed via regressions caused by
making x86's peekThroughBitcasts() not loop on consecutive bitcasts (see
comments in D33137).
Differential Revision: https://reviews.llvm.org/D33578
llvm-svn: 304072
This reverts commit r299287 plus clean-ups.
The localizer pass is a helper pass that could be run at O0 in the GISel
pipeline to work around the deficiency of the fast register allocator.
It basically shortens the live-ranges of the constants so that the
allocator does not spill all over the place.
Long term fix would be to make the greedy allocator fast.
llvm-svn: 304051
- Rewrite livein calculation to use the computeLiveIns() helper
function. This is slightly less efficient but easier to reason about
and doesn't unnecessarily add pristine and reserved registers[1]
- Zero the status register at the beginning of the loop to make sure it
has a defined value.
- Remove kill flags of values that need to stay alive throughout the loop.
[1] An upcoming commit of mine will tighten the MachineVerifier to catch
these.
llvm-svn: 304048
Rename the DEBUG_TYPE to match the names of corresponding passes where
it makes sense. Also establish the pattern of simply referencing
DEBUG_TYPE instead of repeating the passname where possible.
llvm-svn: 303921
Summary:
This is used in the Linux kernel, and effectively just means "print an
address". This brings back r193593.
Reviewed by: Renato Golin
Reviewers: t.p.northover, rengolin, richard.barton.arm, kristof.beyls
Subscribers: aemerson, javed.absar, llvm-commits, eraman
Differential Revision: https://reviews.llvm.org/D33558
llvm-svn: 303901
Summary:
This patch makes instruction fusion more aggressive by
* adding artificial edges between the successors of FirstSU and
SecondSU, similar to BaseMemOpClusterMutation::clusterNeighboringMemOps.
* updating PostGenericScheduler::tryCandidate to keep clusters together,
similar to GenericScheduler::tryCandidate.
This change increases the number of AES instruction pairs generated on
Cortex-A57 and Cortex-A72. This doesn't change code at all in
most benchmarks or general code, but we've seen improvement on kernels
using AESE/AESMC and AESD/AESIMC.
Reviewers: evandro, kristof.beyls, t.p.northover, silviu.baranga, atrick, rengolin, MatzeB
Reviewed By: evandro
Subscribers: aemerson, rengolin, MatzeB, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33230
llvm-svn: 303618
This commit fixes a bug introduced in r301019 where optimizeLogicalImm
would replace a logical node's immediate operand that was CSE'd and
was also an operand of another node.
This commit fixes the bug by replacing the logical node instead of its
immediate operand.
rdar://problem/32295276
llvm-svn: 303607
Summary: Moving LiveRangeShrink to x86 as this pass is mostly useful for archtectures with great register pressure.
Reviewers: MatzeB, qcolombet
Reviewed By: qcolombet
Subscribers: jholewinski, jyknight, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33294
llvm-svn: 303292
Summary:
In SelectionDAG, when a store is immediately chained to another store
to the same address, elide the first store as it has no observable
effects. This is causes small improvements dealing with intrinsics
lowered to stores.
Test notes:
* Many testcases overwrite store addresses multiple times and needed
minor changes, mainly making stores volatile to prevent the
optimization from optimizing the test away.
* Many X86 test cases optimized out instructions associated with
associated with va_start.
* Note that test_splat in CodeGen/AArch64/misched-stp.ll no longer has
dependencies to check and can probably be removed and potentially
replaced with another test.
Reviewers: rnk, john.brawn
Subscribers: aemerson, rengolin, qcolombet, jyknight, nemanjai, nhaehnle, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D33206
llvm-svn: 303198
We don't use section-relative relocations on AArch64, so all symbols must be at
least visible to the linker (i.e. properly global or l_whatever, but not
L_whatever).
llvm-svn: 303118
This caused PR33053.
Original commit message:
> The new experimental reduction intrinsics can now be used, so I'm enabling this
> for AArch64. We will need this for SVE anyway, so it makes sense to do this for
> NEON reductions as well.
>
> The existing code to match shufflevector patterns are replaced with a direct
> lowering of the reductions to AArch64-specific nodes. Tests updated with the
> new, simpler, representation.
>
> Differential Revision: https://reviews.llvm.org/D32247
llvm-svn: 303115
This patch enables fusing dependent AESE/AESMC and AESD/AESIMC
instruction pairs on Cortex-A72, as recommended in the Software
Optimization Guide, section 4.10.
llvm-svn: 303073
Summary: LiveRangeShrink pass moves instruction right after the definition with the same BB if the instruction and its operands all have more than one use. This pass is inexpensive and guarantees optimal live-range within BB.
Reviewers: davidxl, wmi, hfinkel, MatzeB, andreadb
Reviewed By: MatzeB, andreadb
Subscribers: hiraditya, jyknight, sanjoy, skatkov, gberry, jholewinski, qcolombet, javed.absar, krytarowski, atrick, spatel, RKSimon, andreadb, MatzeB, mehdi_amini, mgorny, efriedma, davide, dberlin, llvm-commits
Differential Revision: https://reviews.llvm.org/D32563
llvm-svn: 302938
For stores, check if the stored value is defined by a floating point
instruction and if yes, we return a default mapping with FPR instead
of GPR.
llvm-svn: 302679
The new experimental reduction intrinsics can now be used, so I'm enabling this
for AArch64. We will need this for SVE anyway, so it makes sense to do this for
NEON reductions as well.
The existing code to match shufflevector patterns are replaced with a direct
lowering of the reductions to AArch64-specific nodes. Tests updated with the
new, simpler, representation.
Differential Revision: https://reviews.llvm.org/D32247
llvm-svn: 302678
Using arguments with attribute inalloca creates problems for verification
of machine representation. This attribute instructs the backend that the
argument is prepared in stack prior to CALLSEQ_START..CALLSEQ_END
sequence (see http://llvm.org/docs/InAlloca.htm for details). Frame size
stored in CALLSEQ_START in this case does not count the size of this
argument. However CALLSEQ_END still keeps total frame size, as caller can
be responsible for cleanup of entire frame. So CALLSEQ_START and
CALLSEQ_END keep different frame size and the difference is treated by
MachineVerifier as stack error. Currently there is no way to distinguish
this case from actual errors.
This patch adds additional argument to CALLSEQ_START and its
target-specific counterparts to keep size of stack that is set up prior to
the call frame sequence. This argument allows MachineVerifier to calculate
actual frame size associated with frame setup instruction and correctly
process the case of inalloca arguments.
The changes made by the patch are:
- Frame setup instructions get the second mandatory argument. It
affects all targets that use frame pseudo instructions and touched many
files although the changes are uniform.
- Access to frame properties are implemented using special instructions
rather than calls getOperand(N).getImm(). For X86 and ARM such
replacement was made previously.
- Changes that reflect appearance of additional argument of frame setup
instruction. These involve proper instruction initialization and
methods that access instruction arguments.
- MachineVerifier retrieves frame size using method, which reports sum of
frame parts initialized inside frame instruction pair and outside it.
The patch implements approach proposed by Quentin Colombet in
https://bugs.llvm.org/show_bug.cgi?id=27481#c1.
It fixes 9 tests failed with machine verifier enabled and listed
in PR27481.
Differential Revision: https://reviews.llvm.org/D32394
llvm-svn: 302527
This fixes PR32550, in a way that does not imply running the greedy
mode at O0.
The fix consists in checking if a load is used by any floating point
instruction and if yes, we return a default mapping with FPR instead
of GPR.
llvm-svn: 302453
- MIParser: If the successor list is not specified successors will be
added based on basic block operands in the block and possible
fallthrough.
- MIRPrinter: Adds a new `simplify-mir` option, with that option set:
Skip printing of block successor lists in cases where the
parser is guaranteed to reconstruct it. This means we still print the
list if some successor cannot be determined (happens for example for
jump tables), if the successor order changes or branch probabilities
being unequal.
Differential Revision: https://reviews.llvm.org/D31262
llvm-svn: 302289
Summary:
This change adds a new section to the xray-instrumented binary that
stores an index into ranges of the instrumentation map, where sleds
associated with the same function can be accessed as an array. At
runtime, we can get access to this index by function ID offset allowing
for selective patching and unpatching by function ID.
Each entry in this new section (xray_fn_idx) will include two pointers
indicating the start and one past the end of the sleds associated with
the same function. These entries will be 16 bytes long on x86 and
aarch64. On arm, we align to 16 bytes anyway so the runtime has to take
that into consideration.
__{start,stop}_xray_fn_idx will be the symbols that the runtime will
look for when we implement the selective patching/unpatching by function
id APIs. Because XRay synthesizes the function id's in a monotonically
increasing manner at runtime now, implementations (and users) can use
this table to look up the sleds associated with a specific function.
This is useful in implementations that want to do things like:
- Implement coverage mode for functions by patching everything
pre-main, then as functions are encountered, the installed handler
can unpatch the function that's been encountered after recording
that it's been called.
- Do "learning mode", so that the implementation can figure out some
statistical information about function calls by function id for a
time being, and then determine which functions are worth
uninstrumenting at runtime.
- Do "selective instrumentation" where an implementation can
specifically instrument only certain function id's at runtime
(either based on some external data, or through some other
heuristics) instead of patching all the instrumented functions at
runtime.
Reviewers: dblaikie, echristo, chandlerc, javed.absar
Subscribers: pelikan, aemerson, kpw, llvm-commits, rengolin
Differential Revision: https://reviews.llvm.org/D32693
llvm-svn: 302109
Remove "_NC" suffix and semantics from TLSDESC_LD{64,32}_LO12 and
TLSDESC_ADD_LO12 relocations
Rearrange ordering in AArch64.def to follow relocation encoding
Fix name:
R_AARCH64_P32_LD64_GOT_LO12_NC => R_AARCH64_P32_LD32_GOT_LO12_NC
Add support for several "TLS", "TLSGD", and "TLSLD" relocations for
ILP32
Fix return values from isNonILP32reloc
Add implementations for
R_AARCH64_ADR_PREL_PG_HI21_NC, R_AARCH64_P32_LD32_GOT_LO12_NC,
R_AARCH64_P32_TLSIE_LD32_GOTTPREL_LO12_NC,
R_AARCH64_P32_TLSDESC_LD32_LO12, R_AARCH64_LD64_GOT_LO12_NC,
*TLSLD_LDST128_DTPREL_LO12, *TLSLD_LDST128_DTPREL_LO12_NC,
*TLSLE_LDST128_TPREL_LO12, *TLSLE_LDST128_TPREL_LO12_NC
Modify error messages to give name of equivalent relocation in the
ABI not being used, along with better checking for non-existent
requested relocations.
Added assembler support for "pg_hi21_nc"
Relocation definitions added without implementations:
R_AARCH64_P32_TLSDESC_ADR_PREL21, R_AARCH64_P32_TLSGD_ADR_PREL21,
R_AARCH64_P32_TLSGD_ADD_LO12_NC, R_AARCH64_P32_TLSLD_ADR_PREL21,
R_AARCH64_P32_TLSLD_ADR_PAGE21, R_AARCH64_P32_TLSLD_ADD_LO12_NC,
R_AARCH64_P32_TLSLD_LD_PREL19, R_AARCH64_P32_TLSDESC_LD_PREL19,
R_AARCH64_P32_TLSGD_ADR_PAGE21, R_AARCH64_P32_TLS_DTPREL,
R_AARCH64_P32_TLS_DTPMOD, R_AARCH64_P32_TLS_TPREL,
R_AARCH64_P32_TLSDESC
Fix encoding:
R_AARCH64_P32_TLSDESC_ADR_PAGE21
Reviewers: Peter Smith
Patch by: Joel Jones (jjones@cavium.com)
Differential Revision: https://reviews.llvm.org/D32072
llvm-svn: 301980
TLSDESC_ADD_LO12 relocations
Rearrange ordering in AArch64.def to follow relocation encoding
Fix name:
R_AARCH64_P32_LD64_GOT_LO12_NC => R_AARCH64_P32_LD32_GOT_LO12_NC
Add support for several "TLS", "TLSGD", and "TLSLD" relocations for
ILP32
Fix return values from isNonILP32reloc
Add implementations for
R_AARCH64_ADR_PREL_PG_HI21_NC, R_AARCH64_P32_LD32_GOT_LO12_NC,
R_AARCH64_P32_TLSIE_LD32_GOTTPREL_LO12_NC,
R_AARCH64_P32_TLSDESC_LD32_LO12, R_AARCH64_LD64_GOT_LO12_NC,
*TLSLD_LDST128_DTPREL_LO12, *TLSLD_LDST128_DTPREL_LO12_NC,
*TLSLE_LDST128_TPREL_LO12, *TLSLE_LDST128_TPREL_LO12_NC
Modify error messages to give name of equivalent relocation in the
ABI not being used, along with better checking for non-existent
requested relocations.
Added assembler support for "pg_hi21_nc"
Relocation definitions added without implementations:
R_AARCH64_P32_TLSDESC_ADR_PREL21, R_AARCH64_P32_TLSGD_ADR_PREL21,
R_AARCH64_P32_TLSGD_ADD_LO12_NC, R_AARCH64_P32_TLSLD_ADR_PREL21,
R_AARCH64_P32_TLSLD_ADR_PAGE21, R_AARCH64_P32_TLSLD_ADD_LO12_NC,
R_AARCH64_P32_TLSLD_LD_PREL19, R_AARCH64_P32_TLSDESC_LD_PREL19,
R_AARCH64_P32_TLSGD_ADR_PAGE21, R_AARCH64_P32_TLS_DTPREL,
R_AARCH64_P32_TLS_DTPMOD, R_AARCH64_P32_TLS_TPREL,
R_AARCH64_P32_TLSDESC
Fix encoding:
R_AARCH64_P32_TLSDESC_ADR_PAGE21
Reviewers: Peter Smith
Patch by: Joel Jones (jjones@cavium.com)
Differential Revision: https://reviews.llvm.org/D32072
llvm-svn: 301939
Summary:
In some cases LLVM (especially the SLP vectorizer) will create vectors
that are 256 bytes (or larger). Given that this is intentional[0] is
likely to get more common, this patch updates the StackMap binary
format to deal with the spill locations for said vectors.
This change also bumps the stack map version from 2 to 3.
[0]: https://reviews.llvm.org/D32533#738350
Reviewers: reames, kavon, skatkov, javed.absar
Subscribers: mcrosier, nemanjai, llvm-commits
Differential Revision: https://reviews.llvm.org/D32629
llvm-svn: 301615
canMutate() was returning true when the operands were all in the same order as
the matched instruction. However, it wasn't checking the operands were actually
on that instruction. This worked when we could only match a single instruction
but the addition of nested instruction matching led to cases where the operands
could be split across multiple instructions. canMutate() now returns false if
operands belong to instructions other than the root of the match.
llvm-svn: 301077
The code assumed that when saving an additional CSR register
(ExtraCSSpill==true) we would have a free register throughout the
function. This was not true if this CSR register is also used to pass
values as in the swiftself case.
rdar://31451816
llvm-svn: 301057
immediate operands.
This commit adds an AArch64 dag-combine that optimizes code generation
for logical instructions taking immediate operands. The optimization
uses demanded bits to change a logical instruction's immediate operand
so that the immediate can be folded into the immediate field of the
instruction.
This recommits r300932 and r300930, which was causing dag-combine to
loop forever. The problem was that optimizeLogicalImm was returning
true even when there was no change to the immediate node (which happened
when the immediate was all zeros or ones), which caused dag-combine to
push and pop the same node to the work list over and over again without
making any progress.
This commit fixes the bug by returning false early in optimizeLogicalImm
if the immediate is all zeros or ones. Also, it changes the code to
compare the immediate with 0 or Mask rather than calling
countPopulation.
rdar://problem/18231627
Differential Revision: https://reviews.llvm.org/D5591
llvm-svn: 301019
It seems that r300930 was creating an infinite loop in dag-combine when
compling the following file:
MultiSource/Benchmarks/MiBench/consumer-typeset/z21.c
llvm-svn: 300940
immediate operands.
This commit adds an AArch64 dag-combine that optimizes code generation
for logical instructions taking immediate operands. The optimization
uses demanded bits to change a logical instruction's immediate operand
so that the immediate can be folded into the immediate field of the
instruction.
This recommits r300913, which broke bots because I didn't fix a call to
ShrinkDemandedConstant in SIISelLowering.cpp after changing the APIs of
TargetLoweringOpt and TargetLowering.
rdar://problem/18231627
Differential Revision: https://reviews.llvm.org/D5591
llvm-svn: 300930
immediate operands.
This commit adds an AArch64 dag-combine that optimizes code generation
for logical instructions taking immediate operands. The optimization
uses demanded bits to change a logical instruction's immediate operand
so that the immediate can be folded into the immediate field of the
instruction.
rdar://problem/18231627
Differential Revision: https://reviews.llvm.org/D5591
llvm-svn: 300913
This fixes PR32471.
As comment 10 on that bug report highlights
(https://bugs.llvm.org//show_bug.cgi?id=32471#c10), there are quite a
few different defendable design tradeoffs that could be made, including
not representing pointers at all in LLT.
I decided to go for representing vector-of-pointer as a concept in LLT,
while keeping the size of the LLT type 64 bits (this is an increase from
48 bits before). My rationale for keeping pointers explicit is that on
some targets probably it's very handy to have the distinction between
pointer and non-pointer (e.g. 68K has a different register bank for
pointers IIRC). If we keep a scalar pointer, it probably is easiest to
also have a vector-of-pointers to keep LLT relatively conceptually clean
and orthogonal, while we don't have a very strong reason to break that
orthogonality. Once we gain more experience on the use of LLT, we can
of course reconsider this direction.
Rejecting vector-of-pointer types in the IRTranslator is also an option
to avoid the crash reported in PR32471, but that is only a very
short-term solution; also needs quite a bit of code tweaks in places,
and is probably fragile. Therefore I didn't consider this the best
option.
llvm-svn: 300664
Remove non-consecutive stores from store merge candidate search as
they cannot be merged and will prevent us from finding subsequent
mergeable store cases.
Reviewers: jyknight, bogner, javed.absar, spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D32086
llvm-svn: 300561
This reverts r300535 and r300537.
The newly added tests in test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll
produces slightly different code between LLVM versions being built with different compilers.
E.g., dependent on the compiler LLVM is built with, either one of the following
can be produced:
remark: <unknown>:0:0: unable to legalize instruction: %vreg0<def>(p0) = G_EXTRACT_VECTOR_ELT %vreg1, %vreg2; (in function: vector_of_pointers_extractelement)
remark: <unknown>:0:0: unable to legalize instruction: %vreg2<def>(p0) = G_EXTRACT_VECTOR_ELT %vreg1, %vreg0; (in function: vector_of_pointers_extractelement)
Non-determinism like this is clearly a bad thing, so reverting this until
I can find and fix the root cause of the non-determinism.
llvm-svn: 300538
This fixes PR32471.
As comment 10 on that bug report highlights
(https://bugs.llvm.org//show_bug.cgi?id=32471#c10), there are quite a
few different defendable design tradeoffs that could be made, including
not representing pointers at all in LLT.
I decided to go for representing vector-of-pointer as a concept in LLT,
while keeping the size of the LLT type 64 bits (this is an increase from
48 bits before). My rationale for keeping pointers explicit is that on
some targets probably it's very handy to have the distinction between
pointer and non-pointer (e.g. 68K has a different register bank for
pointers IIRC). If we keep a scalar pointer, it probably is easiest to
also have a vector-of-pointers to keep LLT relatively conceptually clean
and orthogonal, while we don't have a very strong reason to break that
orthogonality. Once we gain more experience on the use of LLT, we can
of course reconsider this direction.
Rejecting vector-of-pointer types in the IRTranslator is also an option
to avoid the crash reported in PR32471, but that is only a very
short-term solution; also needs quite a bit of code tweaks in places,
and is probably fragile. Therefore I didn't consider this the best
option.
llvm-svn: 300535
It's basically a terrible idea anyway but objc_msgSend gets emitted like that.
We can decide on a better way to deal with it in the unlikely event that anyone
actually uses it.
llvm-svn: 300474
It's almost certainly not a good idea to actually use it in most cases (there's
a pretty large code size overhead on AArch64), but we can't do those
experiments until it's supported.
llvm-svn: 300462
This further improves Ahmed's change in rL299482. See the new comment for the
rationale.
The patch recovers most of the regression for bzip2 after D31965. We're down
to +2.68% from +6.97%.
Differential Revision: https://reviews.llvm.org/D32028
llvm-svn: 300276
Summary: Legalize only if the type is marked as Legal or Custom. If not, return Unsupported as LegalizerHelper is not able to handle non-power-of-2 types right now.
Reviewers: qcolombet, aditya_nandakumar, dsanders, t.p.northover, kristof.beyls, javed.absar, ab
Reviewed By: kristof.beyls, ab
Subscribers: dberris, rovka, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D31711
llvm-svn: 299929
Qin may be large, and Succ may be more frequent than BB. Take these both into
account when deciding if tail-duplication is profitable.
llvm-svn: 299891
The original instruction might get legalized and erased and expanded
into intermediate instructions and the intermediate instructions might
fail legalization. This end up in reporting GISelFailure on the erased
instruction.
Instead report GISelFailure on the intermediate instruction which failed
legalization.
Reviewed by: ab
llvm-svn: 299802
When using -ffixed-x18, the x18 (or w18) register can safely be used
with the "global register variable" GCC extension, but the backend
fails to recognize it.
Patch by Roland McGrath.
Differential Revision: https://reviews.llvm.org/D31793
llvm-svn: 299799
The new codepath has been in the tree for years, and there isn't any
reason to use two codepaths here.
Differential Revision: https://reviews.llvm.org/D30596
llvm-svn: 299723
This is a follow-on to r299096 which added support for fmadd.
Subtract does not have the case where with two multiply operands we commute in
order to fuse with the multiply with the fewer uses.
llvm-svn: 299572
This improves upon r246462: that prevented FMOVs from being emitted
for the cross-class INSERT_SUBREGs by disabling the formation of
INSERT_SUBREGs of LOAD. But the ld1.s that we started selecting
caused us to introduce partial dependencies on the vector register.
Avoid that by using SCALAR_TO_VECTOR: it's a first-class citizen that
is folded away by many patterns, including the scalar LDRS that we
want in this case.
Credit goes to Adam for finding the issue!
llvm-svn: 299482
This mode is just like -mcmodel=small except that it moves the
thread pointer from TPIDR_EL0 to TPIDR_EL1.
Patch by Roland McGrath.
Differential Revision: https://reviews.llvm.org/D31624
llvm-svn: 299462
Summary:
Lift the restrictions that prevented the tree walking introduced in the
previous change and add support for patterns like:
(G_ADD (G_MUL (G_SEXT $src1), (G_SEXT $src2)), $src3) -> SMADDWrrr $dst, $src1, $src2, $src3
Also adds support for G_SEXT and G_ZEXT to support these cases.
One particular aspect of this that I should draw attention to is that I've
tried to be overly conservative in determining the safety of matches that
involve non-adjacent instructions and multiple basic blocks. This is intended
to be used as a cheap initial check and we may add a more expensive check in
the future. The current rules are:
* Reject if any instruction may load/store (we'd need to check for intervening
memory operations.
* Reject if any instruction has implicit operands.
* Reject if any instruction has unmodelled side-effects.
See isObviouslySafeToFold().
Reviewers: t.p.northover, javed.absar, qcolombet, aditya_nandakumar, ab, rovka
Reviewed By: ab
Subscribers: igorb, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30539
llvm-svn: 299430
Summary:
Move the aarch64-type-promotion pass within the existing type promotion framework in CGP.
This change also support forking sexts when a new sext is required for promotion.
Note that change is based on D27853 and I am submitting this out early to provide a better idea on D27853.
Reviewers: jmolloy, mcrosier, javed.absar, qcolombet
Reviewed By: qcolombet
Subscribers: llvm-commits, aemerson, rengolin, mcrosier
Differential Revision: https://reviews.llvm.org/D28680
llvm-svn: 299379
REG_SEQUENCE falls into the same category as COPY for operands mapping:
- They don't have MCInstrDesc with register constraints
- The input variable could use whatever register classes
- It is possible to have register class already assigned to the operands
In particular, given REG_SEQUENCE are always target specific because of
the subreg indices. Those indices must apply to the register class of
the definition of the REG_SEQUENCE and therefore, the target must set a
register class to that definition. As a result, the generic code can
always use that register class to derive a valid mapping for a
REG_SEQUENCE.
llvm-svn: 299285
Summary:
This feature enables folding of logical shift operations of up to 3 places into addressing mode on Kryo and Falkor that have a fastpath LSL.
Reviewers: mcrosier, rengolin, t.p.northover
Subscribers: junbuml, gberry, llvm-commits, aemerson
Differential Revision: https://reviews.llvm.org/D31113
llvm-svn: 299240
Now alternatively to the TargetOption.AllowFPOpFusion global flag, FMUL->FADD
can also use the per operation FMF to allow fusion.
The idea here is not to port everything to the new scheme (e.g. fused
multiply-and-sub will be ported later) but that this work all the way from
clang.
The transformation is conditionalized on *both* the FADD and the FMUL having
the FMF contract flag.
Differential Revision: https://reviews.llvm.org/D31169
llvm-svn: 299096
In the long-term, we want to replace statistics with something
finer-grained that lets us gather per-function data.
Remarks are that replacement.
Create an ORE instance in SelectionDAGISel, and pass it to
SelectionDAG.
SelectionDAG was used so that we can emit remarks from all
SelectionDAG-related code, including TargetLowering and DAGCombiner.
This isn't used in the current patch but Adam tells me he's interested
for the fp-contract combines.
Use the ORE instance to emit FastISel failures as remarks (instead of
the mix of dbgs() dumps and statistics that we currently have).
Eventually, we want to have an API that tells us whether remarks are
enabled (http://llvm.org/PR32352) so that we don't emit expensive
remarks (in this case, dumping IR) when it's not needed. For now, use
'isEnabled' as a crude replacement.
This does mean that the replacement for '-fast-isel-verbose' is now
'-pass-remarks-missed=isel'. Additionally, clang users also need to
enable remark diagnostics, using '-Rpass-missed=isel'.
This also removes '-fast-isel-verbose2': there are no static statistics
that we want to only enable in asserts builds, so we can always use
the remarks regardless of the build type.
Differential Revision: https://reviews.llvm.org/D31405
llvm-svn: 299093
We're not to the point of supporting the load/store patterns yet
(because they extensively use PatFrags).
But in the meantime, we can implement some of the simplest addressing
modes.
llvm-svn: 298863
CBZ/CBNZ represent a substantial portion of all conditional branches.
Look through G_ICMP to select them.
We can't use tablegen yet because the existing patterns match an
AArch64ISD node.
llvm-svn: 298856
Among other things, this allows Machine LICM to hoist a costly 'mrs'
instruction from within a loop.
Differential Revision: http://reviews.llvm.org/D31151
llvm-svn: 298851
This patch changes the behavior of IRTranslating intrinsics where we
now create VREG + G_CONSTANT for ConstantInt values. We already do this
for FloatingPoint values. This makes it easier for the backends to
select code and it won't have to de-duplicate creation+selection of
constants.
Reviewed by: ab
llvm-svn: 298473
Quentin points out that r298358 would cause us to emit different code
with debug info. That's a big no-no; also erase the instructions that
only live thanks to DBG_VALUE users.
Adrian explained how this is an existing problem and an OK thing to do:
clang has allocas for all variables so shouldn't be affected at -O0, but
swift uses a bit of inlineasm to explicitly keep values live for the
purpose of debug info quality. I'm not sure there is a better scheme.
llvm-svn: 298460
MI can represent fallthrough to layout successor blocks, and our
post-isel representation uses that extensively.
We might as well use it too, to avoid translating and carrying along
unnecessary branches.
llvm-svn: 298459
A bool is represented by a single byte, which the ARM ABI requires to be either
0 or 1. So we cannot use G_ANYEXT when legalizing the type.
llvm-svn: 298439
This commit adds a parameter that lets us pass in the calling convention
of the call to CallLowering::lowerCall. This allows us to handle
situations where the calling convetion of the callee is different from
that of the caller.
Differential Revision: https://reviews.llvm.org/D31039
llvm-svn: 298254
Folding instructions when selecting can cause them to become dead.
Don't select these dead instructions (if they don't have other side
effects, and don't define physical registers).
Preserve existing tests by adding COPYs.
In some tests, the G_CONSTANT vregs never get constrained to a class:
the only use of the vreg was folded into another instruction, so the
G_CONSTANT, now dead, never gets selected.
llvm-svn: 298224
And remove some redundant bitcast tests.
Also split the test functions themselves: it makes it obvious to see
what's tested where and what isn't, it makes the tests much easier to
read and manually update, and, most importantly, it makes them almost
trivial to update using tooling. Yes, it's obnoxiously verbose, but
said tooling helps upgrade to better MIR syntax whenever available.
llvm-svn: 298222
This commit adds the necessary target hooks for outlining in AArch64. It also
refactors the switch statement used in `getMemOpBaseRegImmOfsWidth` into a
more general function, `getMemOpInfo`. This allows the outliner to share that
code without copying and pasting it.
The AArch64 outliner can be run using -mllvm -enable-machine-outliner, as with
the X86-64 outliner.
The test for this pass verifies that the outliner does, in fact outline
functions, fixes up the stack accesses properly, and can correctly generate a
tail call. In the future, this test should be replaced with a MIR test, so that
we can properly test immediate offset overflows in fixed-up instructions.
llvm-svn: 298162
Summary:
Instead of just looking for a load which is mergable with Ext to form ExtLoad, trying to promote Exts as long as the cost is acceptable. This change is not a NFC as it continue promoting Exts even after finding a load during promotions; the change in arm64-codegen-prepare-extload.ll described in 2.b might show the case.
This change was motivated from D26524. Based on this change, I will move the transformation performed in aarch64-type-promotion into CGP.
Reviewers: jmolloy, qcolombet, mcrosier, javed.absar
Reviewed By: qcolombet
Subscribers: rengolin, llvm-commits, aemerson
Differential Revision: https://reviews.llvm.org/D27853
llvm-svn: 298114
Earlier stages of GlobalISel always use ConstantInt in G_CONSTANT so that's
what we should check for.
This fixes a crash introduced in r297782.
llvm-svn: 297968
Currently, we create a G_CONSTANT for every "synthetic" integer
constant operand (for instance, for the G_GEP offset).
Instead, share the G_CONSTANTs we might have created by going through
the ValueToVReg machinery.
When we're emitting synthetic constants, we do need to get Constants from
the context. One could argue that we shouldn't modify the context at
all (for instance, this means that we're going to use a tad more memory
if the constant wasn't used elsewhere), but constants are mostly
harmless. We currently do this for extractvalue and all.
For constant fcmp, this does mean we'll emit an extra COPY, which is not
necessarily more optimal than an extra materialized constant.
But that preserves the current intended design of uniqued G_CONSTANTs,
and the rematerialization problem exists elsewhere and should be
resolved with a single coherent solution.
llvm-svn: 297875
Now that we preserve the IR layout, we would end up with all the newly
synthesized switch comparison blocks at the end of the function.
Instead, use a hopefully more reasonable layout, with the comparison
blocks immediately following the switch comparison blocks.
llvm-svn: 297869
It makes the output function layout more predictable; the layout has
an effect on performance, we don't want it to be at the mercy of the
translator's visitation order and such.
The predictable output is also easier to digest.
getOrCreateBB isn't appropriately named anymore, as it never needs to
create anything. Rename it and extract the MBB creation logic out of it.
A couple tests were sensitive to the order. Update them.
llvm-svn: 297868
Reduced from a mixture of PR32273 and David Green's test cases showing SelectionDAG::ComputeNumSignBits not correctly handling BUILD_VECTOR implicit truncation of inputs.
llvm-svn: 297847
On MachO platforms that use subsections-via-symbols dead code stripping will
drop prefix data. Unfortunately there is no great way to convey the relationship
between a function and its prefix data to the linker. We are forced to use a bit
of a hack: we give the prefix data it’s own symbol, and mark the actual function
entry an .alt_entry.
Patch by Moritz Angermann!
Differential Revision: https://reviews.llvm.org/D30770
llvm-svn: 297804
Summary:
<1 x Ty> is not a legal vector type in LLT, we shouldn’t build G_MERGE_VALUES
instruction for them.
Reviewers: qcolombet, aditya_nandakumar, dsanders, t.p.northover, ab, javed.absar
Reviewed By: qcolombet
Subscribers: dberris, rovka, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D30948
llvm-svn: 297792
Summary:
Adds a new kind of MachineOperand: MO_Placeholder.
This operand must not appear in the MIR and only exists as a way of
creating an 'uninitialized' operand until a matcher function overwrites it.
Depends on D30046, D29712
Reviewers: t.p.northover, ab, rovka, aditya_nandakumar, javed.absar, qcolombet
Reviewed By: qcolombet
Subscribers: dberris, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D30089
llvm-svn: 297782
Recommiting with compiler time improvements
Recommitting after fixup of 32-bit aliasing sign offset bug in DAGCombiner.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 297695
Summary:
A53 scheduler causes an assertion failure on all CRC instructions:
include/llvm/CodeGen/MachineInstr.h:280: const llvm::MachineOperand
&llvm::MachineInstr::getOperand(unsigned int) const: Assertion `i <
getNumOperands() && "getOperand() out of range!"' failed.
The case statements corresponding to CRC instructions are incorrect and should
be removed.
Also adding a testcase while on this.
Reviewers: t.p.northover, javed.absar, apazos, rengolin
Reviewed By: rengolin
Subscribers: evandro, aemerson, llvm-commits, rengolin
Differential Revision: https://reviews.llvm.org/D30274
llvm-svn: 297582
The good reason to do this is that static allocas are pretty simple to handle
(especially at -O0) and avoiding tracking DBG_VALUEs throughout the pipeline
should give some kind of performance benefit.
The bad reason is that the debug pipeline is an unholy mess of implicit
contracts, where determining whether "DBG_VALUE %reg, imm" actually implies a
load or not involves the services of at least 3 soothsayers and the sacrifice
of at least one chicken. And it still gets it wrong if the variable is at SP
directly.
llvm-svn: 297410
We were calculating incorrect extract/insert offsets by trying to be too
tricksy with min/max. It's clearer to just split the logic up into "register
starts before this segment" vs "after".
llvm-svn: 297226
Some intrinsics take metadata parameters. These all need custom
handling of some form, and cannot possibly be lowered generically to
G_INTRINSIC calls with vreg operands.
Reject them, instead of hitting an assert later in getOrCreateVReg.
llvm-svn: 297209
When we translate a no-op (same type) bitcast, we try to be clever and
only emit a COPY if we already assigned a vreg to the defined value.
However, when we didn't, we tried to assign to a reference into the
ValToVReg DenseMap, even though the RHS of the assignment
(getOrCreateVReg) could potentially grow that DenseMap, invalidating the
reference.
Avoid that by getting the source vreg first.
I audited the rest of the translator; this is the only tricky case.
The test is quite unwieldy, as the problem is caused by the DenseMap
growing, which happens after the 47th mapped value.
llvm-svn: 297208
For vector operands, the `select` instruction supports both vector and
non-vector conditions. The MIR builder had an overly restrictive
assertion, that only accepted vector conditions for vector selects
(in effect implementing ISD::VSELECT).
Make it possible to express the full range of G_SELECTs.
llvm-svn: 297207
When computing the mapping for non-generic instructions, we skipped
%noreg operands, because we can't always reason about their banks.
Also skip them when applying the mapping. Otherwise, we could end
up with mappings that we can't apply.
While there, duplicate an assert to distinguish between the two
error conditions.
llvm-svn: 297201
When a dbg_value has a constant operand that isn't representable in MI,
there isn't much we can do. Use %noreg (0) for those situations.
This matches the SelectionDAG behavior.
llvm-svn: 297200
Broadcom Vulcan is now Cavium ThunderX2T99.
LLVM Bugzilla: http://bugs.llvm.org/show_bug.cgi?id=32113
Minor fixes for the alignments of loops and functions for
ThunderX T81/T83/T88 (better performance).
Patch was tested with SpecCPU2006.
Patch by Stefan Teleman
Differential Revision: https://reviews.llvm.org/D30510
llvm-svn: 297190
A bit more painful than G_INSERT because it was more widely used, but this
should simplify the handling of extract operations in most locations.
llvm-svn: 297100
This patch extends the current functionality of the AArch64 redundant copy
elimination pass to handle CMN instructions as well as a shifted
immediates.
Differential Revision: https://reviews.llvm.org/D30576.
llvm-svn: 297078
Before, we were producing G_INSERT instructions that were actually closer to a
cast or even a COPY when both input and output sizes are the same. This doesn't
really make sense and means that everything interpreting a G_INSERT also has to
handle all these kinds of casts.
So now we detect these degenerate cases and emit real casts instead.
llvm-svn: 297051
Now that G_INSERT instructions can only insert one register, this code was
overly general. In another direction it didn't handle registers that crossed
split boundaries properly, which needed to be fixed.
llvm-svn: 297042
These are simplified variants of the current G_SEQUENCE and G_EXTRACT, which
assume the individual parts will be contiguous, homogeneous, and occupy the
entirity of the larger register. This makes reasoning about them much easer
since you only have to look at the first register being merged and the result
to know what the instruction is doing.
I intend to gradually replace all uses of the more complicated sequence/extract
with these (or single-element insert/extracts), and then remove the older
variants. For now we start with legalization.
llvm-svn: 296921
This patch causes compile times for some patterns to explode. I have
a (large, unreduced) test case that slows down by more than 20x and
several test cases slow down by 2x. I'm sending some of the test cases
directly to Nirav and following up with more details in the review log,
but this should unblock anyone else hitting this.
llvm-svn: 296862
This patch extends the current functionality of the AArch64 redundant copy
elimination pass to handle non-zero cases such as:
BB#0:
cmp x0, #1
b.eq .LBB0_1
.LBB0_1:
orr x0, xzr, #0x1 ; <-- redundant copy; x0 known to hold #1.
Differential Revision: https://reviews.llvm.org/D29344
llvm-svn: 296809
The CallingConv.td rules allocate 8 bytes for these kinds of arguments
on AAPCS targets, but we were only recording the smaller amount. The
difference is theoretical on AArch64 because we don't actually store
more than the smaller amount, but it's still much better to have these
two components in agreement.
Based on Diana Picus's ARM equivalent patch (where it matters a lot
more).
llvm-svn: 296754
Until now, we've had to use -global-isel to enable GISel. But using
that on other targets that don't support it will result in an abort, as we
can't build a full pipeline.
Additionally, we want to experiment with enabling GISel by default for
some targets: we can't just enable GISel by default, even among those
target that do have some support, because the level of support varies.
This first step adds an override for the target to explicitly define its
level of support. For AArch64, do that using
a new command-line option (I know..):
-aarch64-enable-global-isel-at-O=<N>
Where N is the opt-level below which GISel should be used.
Default that to -1, so that we still don't enable GISel anywhere.
We're not there yet!
While there, remove a couple LLVM_UNLIKELYs. Building the pipeline is
such a cold path that in practice that shouldn't matter at all.
llvm-svn: 296710
Summary:
Avoids tons of prologue boilerplate when arguments are passed in memory
and left in memory. This can happen in a debug build or in a release
build when an argument alloca is escaped. This will dramatically affect
the code size of x86 debug builds, because X86 fast isel doesn't handle
arguments passed in memory at all. It only handles the x86_64 case of up
to 6 basic register parameters.
This is implemented by analyzing the entry block before ISel to identify
copy elision candidates. A copy elision candidate is an argument that is
used to fully initialize an alloca before any other possibly escaping
uses of that alloca. If an argument is a copy elision candidate, we set
a flag on the InputArg. If the the target generates loads from a fixed
stack object that matches the size and alignment requirements of the
alloca, the SelectionDAG builder will delete the stack object created
for the alloca and replace it with the fixed stack object. The load is
left behind to satisfy any remaining uses of the argument value. The
store is now dead and is therefore elided. The fixed stack object is
also marked as mutable, as it may now be modified by the user, and it
would be invalid to rematerialize the initial load from it.
Supersedes D28388
Fixes PR26328
Reviewers: chandlerc, MatzeB, qcolombet, inglorion, hans
Subscribers: igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D29668
llvm-svn: 296683
Resubmit r295336 after the bug with non-zero offset patterns on BE targets is fixed (r296336).
Support {a|s}ext, {a|z|s}ext load nodes as a part of load combine patters.
Reviewed By: filcab
Differential Revision: https://reviews.llvm.org/D29591
llvm-svn: 296651
When SDAGISel (top-down) selects a tail-call, it skips the remainder
of the block.
If, before that, FastISel (bottom-up) selected some of the (no-op) next
few instructions, we can end up with dead instructions following the
terminator (selected by SDAGISel).
We need to erase them, as we know they aren't necessary (in addition to
being incorrect).
We already do this when FastISel falls back on the tail-call itself.
Also remove the FastISel-emitted code if we fallback on the
instructions between the tail-call and the return.
llvm-svn: 296552
Iterating on the use-list we're modifying doesn't work: after the first
iteration, the use-list iterator will point to a MachineOperand
referencing the new register. This caused us to skip the other uses to
replace.
Instead, use MRI.replaceRegWith(), which accounts for this behavior.
llvm-svn: 296551
Recommiting after fixup of 32-bit aliasing sign offset bug in DAGCombiner.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 296476
This pattern is essentially a i16 load from p+1 address:
%p1.i16 = bitcast i8* %p to i16*
%p2.i8 = getelementptr i8, i8* %p, i64 2
%v1 = load i16, i16* %p1.i16
%v2.i8 = load i8, i8* %p2.i8
%v2 = zext i8 %v2.i8 to i16
%v1.shl = shl i16 %v1, 8
%res = or i16 %v1.shl, %v2
Current implementation would identify %v1 load as the first byte load and would mistakenly emit a i16 load from %p1.i16 address. This patch adds a check that the first byte is loaded from a non-zero offset of the first load address. This way this address can be used as the base address for the combined value. Otherwise just give up combining.
llvm-svn: 296336
Recommiting after fixup of 32-bit aliasing sign offset bug in DAGCombiner.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 296252
All G_CONSTANTS created by the MachineIRBuilder have an operand of type CImm
(i.e. a ConstantInt), so that's what the selector needs to look for.
llvm-svn: 296176
Summary:
This isn't testable for AArch64 by itself so this patch also adds
support for constant immediates in the pattern and physical
register uses in the result.
The new IntOperandMatcher matches the constant in patterns such as
'(set $rd:GPR32, (G_XOR $rs:GPR32, -1))'. It's always safe to fold
immediates into an instruction so this is the first rule that will match
across multiple BB's.
The Renderer hierarchy is responsible for adding operands to the result
instruction. Renderers can copy operands (CopyRenderer) or add physical
registers (in particular %wzr and %xzr) to the result instruction
in any order (OperandMatchers now import the operand names from
SelectionDAG to allow renderers to access any operand). This allows us to
emit the result instruction for:
%1 = G_XOR %0, -1 --> %1 = ORNWrr %wzr, %0
%1 = G_XOR -1, %0 --> %1 = ORNWrr %wzr, %0
although the latter is untested since the matcher/importer has not been
taught about commutativity yet.
Added BuildMIAction which can build new instructions and mutate them where
possible. W.r.t the mutation aspect, MatchActions are now told the name of
an instruction they can recycle and BuildMIAction will emit mutation code
when the renderers are appropriate. They are appropriate when all operands
are rendered using CopyRenderer and the indices are the same as the matcher.
This currently assumes that all operands have at least one matcher.
Finally, this change also fixes a crash in
AArch64InstructionSelector::select() caused by an immediate operand
passing isImm() rather than isCImm(). This was uncovered by the other
changes and was detected by existing tests.
Depends on D29711
Reviewers: t.p.northover, ab, qcolombet, rovka, aditya_nandakumar, javed.absar
Reviewed By: rovka
Subscribers: aemerson, dberris, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D29712
llvm-svn: 296131
The Fuchsia ABI defines slots from the thread pointer where the
stack-guard value for stack-protector, and the unsafe stack pointer
for safe-stack, are stored. This parallels the Android ABI support.
Patch by Roland McGrath
Differential Revision: https://reviews.llvm.org/D30237
llvm-svn: 296081
Having more fine-grained information on the specific construct that
caused us to fallback is valuable for large-scale data collection.
We still have the fallback warning, that's also used for FastISel.
We still need to remove the fallback warning, and teach FastISel to also
emit remarks (it currently has a combination of the warning, stats, and
debug prints: the remarks could unify all three).
The abort-on-fallback path could also be better handled using remarks:
one could imagine a "-Rpass-error", analoguous to "-Werror", which would
promote missed/failed remarks to errors. It's not clear whether that
would be useful for other remarks though, so we're not there yet.
llvm-svn: 296013
Summary:
Extend AArch64RedundantCopyElimination to catch cases where the register
that is known to be zero is COPY'd in the predecessor block. Before
this change, this pass would catch cases like:
CBZW %W0, <BB#1>
BB#1:
%W0 = COPY %WZR // removed
After this change, cases like the one below are also caught:
%W0 = COPY %W1
CBZW %W1, <BB#1>
BB#1:
%W0 = COPY %WZR // removed
This change results in a 4% increase in static copies removed by this
pass when compiling the llvm test-suite. It also fixes regressions
caused by doing post-RA copy propagation (a separate change to be put up
for review shortly).
Reviewers: junbuml, mcrosier, t.p.northover, qcolombet, MatzeB
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D30113
llvm-svn: 295863
Summary:
Rework the code that was sinking/duplicating (icmp and, 0) sequences
into blocks where they were being used by conditional branches to form
more tbz instructions on AArch64. The new code is more general in that
it just looks for 'and's that have all icmp 0's as users, with a target
hook used to select which subset of 'and' instructions to consider.
This change also enables 'and' sinking for X86, where it is more widely
beneficial than on AArch64.
The 'and' sinking/duplicating code is moved into the optimizeInst phase
of CodeGenPrepare, where it can take advantage of the fact the
OptimizeCmpExpression has already sunk/duplicated any icmps into the
blocks where they are used. One minor complication from this change is
that optimizeLoadExt needed to be updated to always mark 'and's it has
determined should be in the same block as their feeding load in the
InsertedInsts set to avoid an infinite loop of hoisting and sinking the
same 'and'.
This change fixes a regression on X86 in the tsan runtime caused by
moving GVNHoist to a later place in the optimization pipeline (see
PR31382).
Reviewers: t.p.northover, qcolombet, MatzeB
Subscribers: aemerson, mcrosier, sebpop, llvm-commits
Differential Revision: https://reviews.llvm.org/D28813
llvm-svn: 295746
When promoting the Load of a Store-Load pair to a COPY all kill flags
between the store and the load need to be cleared.
rdar://30402435
Differential Revision: https://reviews.llvm.org/D30110
llvm-svn: 295512
Resubmit -r295314 with PowerPC and AMDGPU tests updated.
Support {a|s}ext, {a|z|s}ext load nodes as a part of load combine patters.
Reviewed By: filcab
Differential Revision: https://reviews.llvm.org/D29591
llvm-svn: 295336
Support {a|s}ext, {a|z|s}ext load nodes as a part of load combine patters.
Reviewed By: filcab
Differential Revision: https://reviews.llvm.org/D29591
llvm-svn: 295314
Uses a Custom implementation because the slot sizes being a multiple of the
pointer size isn't really universal, even for the architectures that do have a
simple "void *" va_list.
llvm-svn: 295255
Lay out trellis-shaped CFGs optimally.
A trellis of the shape below:
A B
|\ /|
| \ / |
| X |
| / \ |
|/ \|
C D
would be laid out A; B->C ; D by the current layout algorithm. Now we identify
trellises and lay them out either A->C; B->D or A->D; B->C. This scales with an
increasing number of predecessors. A trellis is a a group of 2 or more
predecessor blocks that all have the same successors.
because of this we can tail duplicate to extend existing trellises.
As an example consider the following CFG:
B D F H
/ \ / \ / \ / \
A---C---E---G---Ret
Where A,C,E,G are all small (Currently 2 instructions).
The CFG preserving layout is then A,B,C,D,E,F,G,H,Ret.
The current code will copy C into B, E into D and G into F and yield the layout
A,C,B(C),E,D(E),F(G),G,H,ret
define void @straight_test(i32 %tag) {
entry:
br label %test1
test1: ; A
%tagbit1 = and i32 %tag, 1
%tagbit1eq0 = icmp eq i32 %tagbit1, 0
br i1 %tagbit1eq0, label %test2, label %optional1
optional1: ; B
call void @a()
br label %test2
test2: ; C
%tagbit2 = and i32 %tag, 2
%tagbit2eq0 = icmp eq i32 %tagbit2, 0
br i1 %tagbit2eq0, label %test3, label %optional2
optional2: ; D
call void @b()
br label %test3
test3: ; E
%tagbit3 = and i32 %tag, 4
%tagbit3eq0 = icmp eq i32 %tagbit3, 0
br i1 %tagbit3eq0, label %test4, label %optional3
optional3: ; F
call void @c()
br label %test4
test4: ; G
%tagbit4 = and i32 %tag, 8
%tagbit4eq0 = icmp eq i32 %tagbit4, 0
br i1 %tagbit4eq0, label %exit, label %optional4
optional4: ; H
call void @d()
br label %exit
exit:
ret void
}
here is the layout after D27742:
straight_test: # @straight_test
; ... Prologue elided
; BB#0: # %entry ; A (merged with test1)
; ... More prologue elided
mr 30, 3
andi. 3, 30, 1
bc 12, 1, .LBB0_2
; BB#1: # %test2 ; C
rlwinm. 3, 30, 0, 30, 30
beq 0, .LBB0_3
b .LBB0_4
.LBB0_2: # %optional1 ; B (copy of C)
bl a
nop
rlwinm. 3, 30, 0, 30, 30
bne 0, .LBB0_4
.LBB0_3: # %test3 ; E
rlwinm. 3, 30, 0, 29, 29
beq 0, .LBB0_5
b .LBB0_6
.LBB0_4: # %optional2 ; D (copy of E)
bl b
nop
rlwinm. 3, 30, 0, 29, 29
bne 0, .LBB0_6
.LBB0_5: # %test4 ; G
rlwinm. 3, 30, 0, 28, 28
beq 0, .LBB0_8
b .LBB0_7
.LBB0_6: # %optional3 ; F (copy of G)
bl c
nop
rlwinm. 3, 30, 0, 28, 28
beq 0, .LBB0_8
.LBB0_7: # %optional4 ; H
bl d
nop
.LBB0_8: # %exit ; Ret
ld 30, 96(1) # 8-byte Folded Reload
addi 1, 1, 112
ld 0, 16(1)
mtlr 0
blr
The tail-duplication has produced some benefit, but it has also produced a
trellis which is not laid out optimally. With this patch, we improve the layouts
of such trellises, and decrease the cost calculation for tail-duplication
accordingly.
This patch produces the layout A,C,E,G,B,D,F,H,Ret. This layout does have
back edges, which is a negative, but it has a bigger compensating
positive, which is that it handles the case where there are long strings
of skipped blocks much better than the original layout. Both layouts
handle runs of executed blocks equally well. Branch prediction also
improves if there is any correlation between subsequent optional blocks.
Here is the resulting concrete layout:
straight_test: # @straight_test
; BB#0: # %entry ; A (merged with test1)
mr 30, 3
andi. 3, 30, 1
bc 12, 1, .LBB0_4
; BB#1: # %test2 ; C
rlwinm. 3, 30, 0, 30, 30
bne 0, .LBB0_5
.LBB0_2: # %test3 ; E
rlwinm. 3, 30, 0, 29, 29
bne 0, .LBB0_6
.LBB0_3: # %test4 ; G
rlwinm. 3, 30, 0, 28, 28
bne 0, .LBB0_7
b .LBB0_8
.LBB0_4: # %optional1 ; B (Copy of C)
bl a
nop
rlwinm. 3, 30, 0, 30, 30
beq 0, .LBB0_2
.LBB0_5: # %optional2 ; D (Copy of E)
bl b
nop
rlwinm. 3, 30, 0, 29, 29
beq 0, .LBB0_3
.LBB0_6: # %optional3 ; F (Copy of G)
bl c
nop
rlwinm. 3, 30, 0, 28, 28
beq 0, .LBB0_8
.LBB0_7: # %optional4 ; H
bl d
nop
.LBB0_8: # %exit
Differential Revision: https://reviews.llvm.org/D28522
llvm-svn: 295223
This instruction clears the low bits of a pointer without requiring (possibly
dodgy if pointers aren't ints) conversions to and from an integer. Since (as
far as I'm aware) all masks are statically known, the instruction takes an
immediate operand rather than a register to specify the mask.
llvm-svn: 295103
Backends don't support this yet. They would have to move to the swifterror
register before the tail call to make sure it is live-in to the call.
rdar://30495920
llvm-svn: 294982
The recommit includes some changes of testcases. No functional change to the patch.
In RateRegister of existing LSR, if a formula contains a Reg which is a SCEVAddRecExpr,
and this SCEVAddRecExpr's loop is an outerloop, the formula will be marked as Loser
and dropped.
Suppose we have an IR that %for.body is outerloop and %for.body2 is innerloop. LSR only
handle inner loop now so only %for.body2 will be handled.
Using the logic above, formula like
reg(%array) + reg({1,+, %size}<%for.body>) + 1*reg({0,+,1}<%for.body2>) will be dropped
no matter what because reg({1,+, %size}<%for.body>) is a SCEVAddRecExpr type reg related
with outerloop. Only formula like
reg(%array) + 1*reg({{1,+, %size}<%for.body>,+,1}<nuw><nsw><%for.body2>) will be kept
because the SCEVAddRecExpr related with outerloop is folded into the initial value of the
SCEVAddRecExpr related with current loop.
But in some cases, we do need to share the basic induction variable
reg{0 ,+, 1}<%for.body2> among LSR Uses to reduce the final total number of induction
variables used by LSR, so we don't want to drop the formula like
reg(%array) + reg({1,+, %size}<%for.body>) + 1*reg({0,+,1}<%for.body2>) unconditionally.
From the existing comment, it tries to avoid considering multiple level loops at the same time.
However, existing LSR only handles innermost loop, so for any SCEVAddRecExpr with a loop other
than current loop, it is an invariant and will be simple to handle, and the formula doesn't have
to be dropped.
Differential Revision: https://reviews.llvm.org/D26429
llvm-svn: 294814
Summary:
Fix two bugs in SelectionDAGBuilder::FindMergedConditions reported by
Mikael Holmen. Handle non-canonicalized xor not operation
correctly (was assuming operand 0 was always the non-constant operand)
and check that the negated condition is also in the same block as the
original and/or instruction (as is done for and/or operands already)
before proceeding with optimization.
Reviewers: bogner, MatzeB, qcolombet
Subscribers: mcrosier, uabelho, llvm-commits
Differential Revision: https://reviews.llvm.org/D29680
llvm-svn: 294605
If some of the trailing or leading bytes of a load combine pattern are zeroes we can combine the pattern to a load + zext and shift. Currently we don't support it, so the tests check the current codegen without load combine. This change will make the patch to support this kind of combine a bit more clear.
llvm-svn: 294591
Functions that have a dynamic alloca require a base register which is defined to
be X19 on AArch64 and r6 on ARM. We have defined the swifterror register to be
the same register. Use a different callee save register for swifterror instead:
X21 on AArch64
R8 on ARM
rdar://30433803
llvm-svn: 294551
It'll usually be immediately legalized back to a libcall, but occasionally
something can be done with it so we'd just as well enable that flexibility from
the start.
llvm-svn: 294530
We mark X0 as preserved by a call that passes the returned parameter.
x0 = ...
fun(x0) // no implicit def of x0
This no longer is valid if we pass the parameter in a different register then
the returned value as is the case with a swiftself parameter (passed in x20).
x20 = ...
fun(x20) // there should be an implict def of x8
rdar://30425845
llvm-svn: 294527
AArch64 has specific instructions to multiply two numbers at double the width
and produce the high part of the result. These can be used to implement LLVM's
mul.with.overflow instructions fairly simply. Helps with C++ operator new[].
llvm-svn: 294519
The AAPCS ABI is substantially more complicated so that's coming in a separate
patch. For now we can generate correct code for iOS though.
llvm-svn: 294493
This patch checks the number of operands in the resulting
instruction instead of just the alias, then skips over
tied operands when generating the printing method.
This allows us to generate the preferred assembly syntax
for the AArch64 'ins' instruction, which should always be
displayed as 'mov' according to the ARMARM.
Several unit tests have changed as a result, but only to
reflect the preferred disassembly.
Some other InstAlias patterns (movk/bic/orr) needed a
slight adjustment to stop them becoming the default
and breaking other unit tests.
Patch by Graham Hunter.
Differential Revision: https://reviews.llvm.org/D29219
llvm-svn: 294437
Currently we don't support these nodes, so the tests check the current codegen without load combine. This change makes the review of the change to support these nodes more clear.
Separated from https://reviews.llvm.org/D29591 review.
llvm-svn: 294305
joinReservedPhysReg() can only deal with a liverange in a single basic
block when copying from a vreg into a physreg.
See also rdar://30306405
Differential Revision: https://reviews.llvm.org/D29436
llvm-svn: 294268
AArch64 was asserting when it was asked to provide a register-bank of a size it
couldn't deal with (in this case an s128 IMPLICIT_DEF). But we want a robust
fallback path so this isn't allowed.
llvm-svn: 294248
We don't handle all cases yet (see arm64-fallback.ll for an example), but this
is enough to cover most common C++ code so it's a good place to start.
llvm-svn: 294247
When splitting up one store into several in splitStoreSplat we have to
make sure we get the MachinePointerInfo right, otherwise alias
analysis thinks they all store to the same location. This can then
cause invalid scheduling later on.
Differential Revision: https://reviews.llvm.org/D29446
llvm-svn: 294203
Summary:
Without this change, the getVR() call would hit an assert since it was
being passed a physical register.
Update the AArch64/ldst-opt.ll test with a case that triggers this
behavior by adding a run with strict-align, which causes an unaligned
STR XZR instruction to be split into byte stores, creating an
EXTRACT_SUBREG of XZR that triggers the original problem.
Reviewers: bogner, qcolombet, MatzeB, atrick
Subscribers: aemerson, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D29495
llvm-svn: 294129
Summary:
llc would hit a fatal error for errors in inline assembly. The
diagnostics message is now printed.
Reviewers: rengolin, MatzeB, javed.absar, anemet
Reviewed By: anemet
Subscribers: jyknight, nemanjai, llvm-commits
Differential Revision: https://reviews.llvm.org/D29408
llvm-svn: 293999
Recommiting after fixing X86 inc/dec chain bug.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 293893
This patch moves the class for scheduling adjacent instructions,
MacroFusion, to the target.
In AArch64, it also expands the fusion to all instructions pairs in a
scheduling block, beyond just among the predecessors of the branch at the
end.
Differential revision: https://reviews.llvm.org/D28489
llvm-svn: 293737
When choosing the best successor for a block, ordinarily we would have preferred
a block that preserves the CFG unless there is a strong probability the other
direction. For small blocks that can be duplicated we now skip that requirement
as well, subject to some simple frequency calculations.
Differential Revision: https://reviews.llvm.org/D28583
llvm-svn: 293716
Well, sort of. But the lower-level code that invoke used to be using completely
botched the handling of varargs functions, which hopefully won't be possible if
they're using the same code.
llvm-svn: 293670
For some reason the exception selector register must be a pointer (that's
assumed by SDag); on the other hand, it gets moved into an IR-level type which
might be entirely different (i32 on AArch64). IRTranslator needs to be aware of
this.
llvm-svn: 293546
When the OperandsMapper creates virtual registers, it used to just create
plain scalar register with the right size. This may confuse the
instruction selector because we lose the information of the instruction
using those registers what supposed to do. The MachineVerifier complains
about that already.
With this patch, the OperandsMapper still creates plain scalar register,
but the expectation is for the mapping function to remap the type
properly. The default mapping function has been updated to do that.
rdar://problem/30231850
llvm-svn: 293362
The interleaved access pass is an IR-to-IR transformation that runs before code
generation. It matches interleaved memory operations to target-specific
intrinsics (that are later lowered to load and store multiple instructions on
ARM/AArch64). We place tests for similar passes (e.g., GlobalMergePass) under
test/Transforms. This patch moves the InterleavedAccessPass tests out of
test/CodeGen and into target-specific directories under
test/Transforms/InterleavedAccess.
Although the pass is an IR pass, many of the existing tests were llc tests
rather opt tests. For example, the tests would check for ldN/stN instructions
generated by llc rather than the intrinsic calls the pass actually inserts.
Thus, this patch updates all tests to be opt tests that check for the inserted
intrinsics. We already have separate CodeGen tests that ensure we lower the
interleaved access intrinsics to their corresponding ldN/stN instructions. In
addition to migrating the tests to opt, this patch also performs some minor
clean-up (to ensure consistent naming, etc.).
Differential Revision: https://reviews.llvm.org/D29184
llvm-svn: 293309
Summary: This change prevent the signed value of cost from being negative as the value is passed as an unsigned argument.
Reviewers: mcrosier, jmolloy, qcolombet, javed.absar
Reviewed By: mcrosier, qcolombet
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28871
llvm-svn: 293307
The translation scheme is mostly cribbed from FastISel, and it's not entirely
convincing semantically. But it does seem to work in the common cases and allow
variables to be printed so it can't be all wrong.
llvm-svn: 293228
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 293184
This allows MIR passes to emit optimization remarks with the same level
of functionality that is available to IR passes.
It also hooks up the greedy register allocator to report spills. This
allows for interesting use cases like increasing interleaving on a loop
until spilling of registers is observed.
I still need to experiment whether reporting every spill scales but this
demonstrates for now that the functionality works from llc
using -pass-remarks*=<pass>.
Differential Revision: https://reviews.llvm.org/D29004
llvm-svn: 293110
Summary:
This patch prepares more for tail call support in XRay. Until the logging part supports tail calls, this is just staging, so it seems LLVM part is mostly ready with this patch.
Related: https://reviews.llvm.org/D28948 (compiler-rt)
Reviewers: dberris, rengolin
Reviewed By: dberris
Subscribers: llvm-commits, iid_iunknown, aemerson
Differential Revision: https://reviews.llvm.org/D28947
llvm-svn: 293080
The previous patch (https://reviews.llvm.org/rL289538) got reverted because of a bug. Chandler also requested some changes to the algorithm.
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20161212/413479.html
This is an updated patch. The key difference is that collectBitProviders (renamed to calculateByteProvider) now collects the origin of one byte, not the whole value. It simplifies the implementation and allows to stop the traversal earlier if we know that the result won't be used.
From the original commit:
Match a pattern where a wide type scalar value is loaded by several narrow loads and combined by shifts and ors. Fold it into a single load or a load and a bswap if the targets supports it.
Assuming little endian target:
i8 *a = ...
i32 val = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24)
=>
i32 val = *((i32)a)
i8 *a = ...
i32 val = (a[0] << 24) | (a[1] << 16) | (a[2] << 8) | a[3]
=>
i32 val = BSWAP(*((i32)a))
This optimization was discussed on llvm-dev some time ago in "Load combine pass" thread. We came to the conclusion that we want to do this transformation late in the pipeline because in presence of atomic loads load widening is irreversible transformation and it might hinder other optimizations.
Eventually we'd like to support folding patterns like this where the offset has a variable and a constant part:
i32 val = a[i] | (a[i + 1] << 8) | (a[i + 2] << 16) | (a[i + 3] << 24)
Matching the pattern above is easier at SelectionDAG level since address reassociation has already happened and the fact that the loads are adjacent is clear. Understanding that these loads are adjacent at IR level would have involved looking through geps/zexts/adds while looking at the addresses.
The general scheme is to match OR expressions by recursively calculating the origin of individual bytes which constitute the resulting OR value. If all the OR bytes come from memory verify that they are adjacent and match with little or big endian encoding of a wider value. If so and the load of the wider type (and bswap if needed) is allowed by the target generate a load and a bswap if needed.
Reviewed By: RKSimon, filcab, chandlerc
Differential Revision: https://reviews.llvm.org/D27861
llvm-svn: 293036
This surprisingly isn't NFC because there are patterns to select GPR
sub to SUBSWrr (rather than SUBWrr/rs); SUBS is later optimized to
SUB if NZCV is dead. From ISel's perspective, both are fine.
llvm-svn: 293010
There was a bug here where we were using p0 instead of s32 for the
selector type in the landingpad. Instead of hardcoding these types we
should get the types from the landingpad instruction directly.
Note that we replicate an assert from SDAG here to only support
two-valued landingpads.
llvm-svn: 292995
In order to follow the pattern of the existing 'slow-misaligned-128store'
option, rename the option 'no-quad-ldst-pairs' to 'slow-paired-128'.
llvm-svn: 292954
Summary:
When conditional branches with complex conditions are split into
multiple branches in SelectionDAGBuilder::FindMergedConditions, also
handle inverted conditions. These may sometimes appear without having
been optimized by InstCombine when CodeGenPrepare decides to sink and
duplicate cmp instructions, causing them to have only one use. This
problem can be increased by e.g. GVNHoist hiding more cmps from
InstCombine by combining equivalent cmps from different blocks.
For example codegen X & !(Y | Z) as:
jmp_if_X TmpBB
jmp FBB
TmpBB:
jmp_if_notY Tmp2BB
jmp FBB
Tmp2BB:
jmp_if_notZ TBB
jmp FBB
Reviewers: bogner, MatzeB, qcolombet
Subscribers: llvm-commits, hiraditya, mcrosier, sebpop
Differential Revision: https://reviews.llvm.org/D28380
llvm-svn: 292944
A register unit may be allocatable and non-reserved but some of the
register(tuples) built with it are reserved. We still need to calculate
liveness in this case.
Note to out of tree targets: If you start seeing machine verifier errors
with this commit, it probably means that you do not properly mark super
registers of reserved register as reserved. See for example r292836 or
r292870 for example on how to fix that.
rdar://29996737
Differential Revision: https://reviews.llvm.org/D28881
llvm-svn: 292871
Since we're now avoiding operations using narrow scalar integer types,
we have to legalize the integer side of the FP conversions.
This requires teaching the legalizer how to do that.
llvm-svn: 292828
Since r279760, we've been marking as legal operations on narrow integer
types that have wider legal equivalents (for instance, G_ADD s8).
Compared to legalizing these operations, this reduced the amount of
extends/truncates required, but was always a weird legalization decision
made at selection time.
So far, we haven't been able to formalize it in a way that permits the
selector generated from SelectionDAG patterns to be sufficient.
Using a wide instruction (say, s64), when a narrower instruction exists
(s32) would introduce register class incompatibilities (when one narrow
generic instruction is selected to the wider variant, but another is
selected to the narrower variant).
It's also impractical to limit which narrow operations are matched for
which instruction, as restricting "narrow selection" to ranges of types
clashes with potentially incompatible instruction predicates.
Concerns were also raised regarding MIPS64's sign-extended register
assumptions, as well as wrapping behavior.
See discussions in https://reviews.llvm.org/D26878.
Instead, legalize the operations.
Should we ever revert to selecting these narrow operations, we should
try to represent this more accurately: for instance, by separating
a "concrete" type on operations, and an "underlying" type on vregs, we
could move the "this narrow-looking op is really legal" decision to the
legalizer, and let the selector use the "underlying" vreg type only,
which would be guaranteed to map to a register class.
In any case, we eventually should mitigate:
- the performance impact by selecting no-op extract/truncates to COPYs
(which we currently do), and the COPYs to register reuses (which we
don't do yet).
- the compile-time impact by optimizing away extract/truncate sequences
in the legalizer.
llvm-svn: 292827
Kill flags need to be updated correctly when moving stores up/down to
form store pair instructions.
Those invalid flags have been ignored before but as of r290014 they are
recognized when using -mllvm -verify-machineinstrs.
Also simplifies test/CodeGen/AArch64/ldst-opt-dbg-limit.mir, renames it
to ldst-opt.mir test and adds a new tests for this change.
Differential Revision: https://reviews.llvm.org/D28875
llvm-svn: 292625
Big functions with large vreg # are quite unwieldy to update.
Change it to have one function per test (it does increase boilerplate,
but makes the core hopefully more readable and maintanable).
llvm-svn: 292552
Big functions with large vreg # are quite unwieldy to update. This test
also relied on legal s8 operations which we're considering removing.
Change it to have one function per test (it does increase boilerplate,
but makes the core hopefully more readable and maintanable), and use
100% legal operations throughout.
llvm-svn: 292551
Summary:
The SDNodeOrder is saved in the IROrder field in the SDNode, and this
field may affects scheduling. Thus, letting dbg.value/declare increase
the order numbers may in turn affect scheduling.
Because of this change we also need to update the code deciding when
dbg values should be output, in ScheduleDAGSDNodes.cpp/ProcessSDDbgValues.
Dbg values now have the same order as the SDNode they are connected to,
not the following orders.
Test cases provided by Florian Hahn.
Reviewers: bogner, aprantl, sunfish, atrick
Reviewed By: atrick
Subscribers: fhahn, probinson, andreadb, llvm-commits, MatzeB
Differential Revision: https://reviews.llvm.org/D25318
llvm-svn: 292485
ARM seems to prefer that long literals be formed from their little end in
order to promote the fusion of the instrs pairs MOV/MOVK and MOVK/MOVK on
Cortex A57 and others (v. "Cortex A57 Software Optimisation Guide", section
4.14).
Differential revision: https://reviews.llvm.org/D28697
llvm-svn: 292422
Diana Picus