aligned address. Based on patch by David Peixotto.
Also use vld1.64 / vst1.64 with 128-bit alignment to take advantage of alignment
hints. rdar://12090772, rdar://12238782
llvm-svn: 164089
Add LIS::pruneValue() and extendToIndices(). These two functions are
used by the register coalescer when merging two live ranges requires
more than a trivial value mapping as supported by LiveInterval::join().
The pruneValue() function can remove the part of a value number that is
going to conflict in join(). Afterwards, extendToIndices can restore the
live range, using any new dominating value numbers and updating the SSA
form.
Use this complex value mapping to support merging a register into a
vector lane that has a conflicting value, but the clobbered lane is
undef.
llvm-svn: 164074
These extra operands are not needed by register allocators using
VirtRegRewriter, and RAFast don't need them any longer.
By omitting the <imp-def> operands, it becomes possible for the new
register coalescer to track which lanes are valid and which are undef.
llvm-svn: 164073
Map the CodeGenSchedule object model onto data tables. The structure
of the data tables is defined in MC, so for convenience we include
MCSchedule.h. The alternative is maintaining a redundant copy of the
table structure definitions. Mapping the object model onto data tables
is sufficiently complicated that it should not be interleaved with
emitting source code. This avoids major problem with the backend for
itinerary generation.
llvm-svn: 164059
Keep GCC's warnings happy. It can't reason out that the state machine won't
ever hit the potentially uninitialized use in OPC_FilterValue.
llvm-svn: 164041
partition use lists a bit. No functionality changed.
These visitors are actually visiting a tuple of a Use and an offset into
the alloca. However, we use the InstVisitor to handle the dispatch over
the users, and so the Use and Offset are stored in class member
variables and set just before each call to visit(). This is fairly
awkward and makes the functions a bit harder to read, but its the only
real option we have until InstVisitor can be rewritten to use variadic
templates.
However, this pattern shouldn't be followed on the helper member
functions where there is no interface constraint from the visitor. We
already were passing the instruction as a normal parameter rather than
use the Use to get at it, start passing the offset as well. This will
become more important in subsequent patches as the offset will in some
cases change while visiting a single instruction.
llvm-svn: 164003
It had patterns for zext-loading and extending. This commit adds patterns for loading a wide type, performing a bitcast,
and extending. This is an odd pattern, but it is commonly used when writing code with intrinsics.
rdar://11897677
llvm-svn: 163995
The live range of an SSA value forms a sub-tree of the dominator tree.
That means the live ranges of two values overlap if and only if the def
of one value lies within the live range of the other.
This can be used to simplify the interference checking a bit: Visit each
def in the two registers about to be joined. Check for interference
against the value that is live in the other register at the def point
only. It is not necessary to scan the set of overlapping live ranges,
this interference check can be done while computing the value mapping
required for the final live range join.
The new algorithm is prepared to handle more complicated conflict
resolution - We can allow overlapping live ranges with different values
as long as the differing lanes are undef or unused in the other
register.
The implementation in this patch doesn't do that yet, it creates code
that is nearly identical to the old algorithm's, except:
- The new stripCopies() function sees through multiple copies while
the old RegistersDefinedFromSameValue() only can handle one.
- There are a few rare cases where the new algorithm can erase an
IMPLICIT_DEF instuction that RegistersDefinedFromSameValue() couldn't
handle.
llvm-svn: 163991
A value that is live in to a basic block should be returned by valueIn()
in LiveRangeQuery(getMBBStartIdx(MBB)), unless it is a PHI-def which
should be returned by valueDefined() instead.
Current code isn't using this functionality. Future code will.
llvm-svn: 163990
Kill flags are removed more and more aggressively during the register
allocation passes, it is better to get information from LiveIntervals.
llvm-svn: 163972
If a PHI value happens to be live out from the layout predecessor of its
def block, the def slot index will be in the middle of the segment:
%vreg11 = [192r,240B:0)[352r,416B:2)[416B,496r:1) 0@192r 1@480B-phi %2@352r
A LiveRangeQuery for 480 should return NULL from valueIn() since the
PHI value is defined at the block entry, not live in to the block.
No test case, future code depends on this functionality.
llvm-svn: 163971
new one, and add support for running the new pass in that mode and in
that slot of the pass manager. With this the new pass can completely
replace the old one within the pipeline.
The strategy for enabling or disabling the SSAUpdater logic is to do it
by making the requirement of the domtree analysis optional. By default,
it is required and we get the standard mem2reg approach. This is usually
the desired strategy when run in stand-alone situations. Within the
CGSCC pass manager, we disable requiring of the domtree analysis and
consequentially trigger fallback to the SSAUpdater promotion.
In theory this would allow the pass to re-use a domtree if one happened
to be available even when run in a mode that doesn't require it. In
practice, it lets us have a single pass rather than two which was
simpler for me to wrap my head around.
There is a hidden flag to force the use of the SSAUpdater code path for
the purpose of testing. The primary testing strategy is just to run the
existing tests through that path. One notable difference is that it has
custom code to handle lifetime markers, and one of the tests has been
enhanced to exercise that code.
This has survived a bootstrap and the test suite without serious
correctness issues, however my run of the test suite produced *very*
alarming performance numbers. I don't entirely understand or trust them
though, so more investigation is on-going.
To aid my understanding of the performance impact of the new SROA now
that it runs throughout the optimization pipeline, I'm enabling it by
default in this commit, and will disable it again once the LNT bots have
picked up one iteration with it. I want to get those bots (which are
much more stable) to evaluate the impact of the change before I jump to
any conclusions.
NOTE: Several Clang tests will fail because they run -O3 and check the
result's order of output. They'll go back to passing once I disable it
again.
llvm-svn: 163965
use load/store fragments defined in TargetSelectionDAG.td in place of them.
Unaligned loads/stores are either expanded or lowered to target-specific nodes,
so instruction selection should see only aligned load/store nodes.
No changes in functionality.
llvm-svn: 163960
destination.
Updated previous implementation to fix a case not covered:
// PBI: br i1 %x, TrueDest, BB
// BI: br i1 %y, TrueDest, FalseDest
The other case was handled correctly.
// PBI: br i1 %x, BB, FalseDest
// BI: br i1 %y, TrueDest, FalseDest
Also tried to use 64-bit arithmetic instead of APInt with scale to simplify the
computation. Let me know if you have other opinions about this.
llvm-svn: 163954
- The current_pos function is supposed to return all the written bytes, not the
current position of the underlying stream.
- This caused tell() to be broken whenever the underlying stream had buffered
content.
llvm-svn: 163948
This models the A9 processor at the level of instruction operands, as
opposed to the itinerary, which models each operation at the level of
pipeline stages.
The two primary motivations are:
1) Allow MachineScheduler to model A9 as an out-of-order processor. It
can now distinguish between hazards that force interlocking vs.
buffered resources.
2) Reduce long-term maintenance by allowing the itinerary and target
hooks to eventually be removed. Note that almost all of the complexity
in the new model exists to model instruction variants, which the
itinerary cannot handle. Instead the scheduler previously relied on
processor-specific target hooks which are incomplete and buggy.
llvm-svn: 163921
This patch introduces a possibility for Hexagon MI scheduler
to perform some target specific post- processing on the scheduling
DAG prior to scheduling.
llvm-svn: 163903
* wrap code blocks in \code ... \endcode;
* refer to parameter names in paragraphs correctly (\arg is not what most
people want -- it starts a new paragraph);
* use \param instead of \arg to document parameters in order to be consistent
with the rest of the codebase.
llvm-svn: 163902
pointless checks in here, bad asserts, and just confusing code. I've
also added a bit more to the comment to clarify what this function is
really trying to do as it was not obvious to Duncan when studying it.
Thanks to Duncan for helping me dig through the issue.
No real functionality changed here in practical cases, and certainly no
test case. This is just cleanup spotted by inspection.
llvm-svn: 163897
inspection by Duncan during review. My suspicion is that we would still
have returned 0 anyways in this case, but doing it sooner is better.
llvm-svn: 163895
deeply suspicious and likely to go away eventually. Also fix a bogus
comment about one of the checks in the vector GEP analysis. Based on
review from Duncan.
llvm-svn: 163894
Originally I had anticipated needing to thread this through more bits of
the SROA pass itself, but that ended up not happening. In the end, this
is a much simpler way to manange the variable.
llvm-svn: 163893
This is essentially a ground up re-think of the SROA pass in LLVM. It
was initially inspired by a few problems with the existing pass:
- It is subject to the bane of my existence in optimizations: arbitrary
thresholds.
- It is overly conservative about which constructs can be split and
promoted.
- The vector value replacement aspect is separated from the splitting
logic, missing many opportunities where splitting and vector value
formation can work together.
- The splitting is entirely based around the underlying type of the
alloca, despite this type often having little to do with the reality
of how that memory is used. This is especially prevelant with unions
and base classes where we tail-pack derived members.
- When splitting fails (often due to the thresholds), the vector value
replacement (again because it is separate) can kick in for
preposterous cases where we simply should have split the value. This
results in forming i1024 and i2048 integer "bit vectors" that
tremendously slow down subsequnet IR optimizations (due to large
APInts) and impede the backend's lowering.
The new design takes an approach that fundamentally is not susceptible
to many of these problems. It is the result of a discusison between
myself and Duncan Sands over IRC about how to premptively avoid these
types of problems and how to do SROA in a more principled way. Since
then, it has evolved and grown, but this remains an important aspect: it
fixes real world problems with the SROA process today.
First, the transform of SROA actually has little to do with replacement.
It has more to do with splitting. The goal is to take an aggregate
alloca and form a composition of scalar allocas which can replace it and
will be most suitable to the eventual replacement by scalar SSA values.
The actual replacement is performed by mem2reg (and in the future
SSAUpdater).
The splitting is divided into four phases. The first phase is an
analysis of the uses of the alloca. This phase recursively walks uses,
building up a dense datastructure representing the ranges of the
alloca's memory actually used and checking for uses which inhibit any
aspects of the transform such as the escape of a pointer.
Once we have a mapping of the ranges of the alloca used by individual
operations, we compute a partitioning of the used ranges. Some uses are
inherently splittable (such as memcpy and memset), while scalar uses are
not splittable. The goal is to build a partitioning that has the minimum
number of splits while placing each unsplittable use in its own
partition. Overlapping unsplittable uses belong to the same partition.
This is the target split of the aggregate alloca, and it maximizes the
number of scalar accesses which become accesses to their own alloca and
candidates for promotion.
Third, we re-walk the uses of the alloca and assign each specific memory
access to all the partitions touched so that we have dense use-lists for
each partition.
Finally, we build a new, smaller alloca for each partition and rewrite
each use of that partition to use the new alloca. During this phase the
pass will also work very hard to transform uses of an alloca into a form
suitable for promotion, including forming vector operations, speculating
loads throguh PHI nodes and selects, etc.
After splitting is complete, each newly refined alloca that is
a candidate for promotion to a scalar SSA value is run through mem2reg.
There are lots of reasonably detailed comments in the source code about
the design and algorithms, and I'm going to be trying to improve them in
subsequent commits to ensure this is well documented, as the new pass is
in many ways more complex than the old one.
Some of this is still a WIP, but the current state is reasonbly stable.
It has passed bootstrap, the nightly test suite, and Duncan has run it
successfully through the ACATS and DragonEgg test suites. That said, it
remains behind a default-off flag until the last few pieces are in
place, and full testing can be done.
Specific areas I'm looking at next:
- Improved comments and some code cleanup from reviews.
- SSAUpdater and enabling this pass inside the CGSCC pass manager.
- Some datastructure tuning and compile-time measurements.
- More aggressive FCA splitting and vector formation.
Many thanks to Duncan Sands for the thorough final review, as well as
Benjamin Kramer for lots of review during the process of writing this
pass, and Daniel Berlin for reviewing the data structures and algorithms
and general theory of the pass. Also, several other people on IRC, over
lunch tables, etc for lots of feedback and advice.
llvm-svn: 163883
This is mostly documentation for the new machine model. It is designed
to be flexible, easy to incrementally refine for a subtarget, and
provide all the information that MachineScheduler will need.
If all goes well, I will follow up with an example of the new model in
use for ARM.
llvm-svn: 163877
- Enhance the fix to PR12312 to support wider integer, such as 256-bit
integer. If more than 1 fully evaluated vectors are found, POR them
first followed by the final PTEST.
llvm-svn: 163832
- Find a legal vector type before casting and extracting element from it.
- As the new vector type may have more than 2 elements, build the final
hi/lo pair by BFS pairing them from bottom to top.
llvm-svn: 163830
Add a PatFrag to match X86tcret using 6 fixed registers or less. This
avoids folding loads into TCRETURNmi64 using 7 or more volatile
registers.
<rdar://problem/12282281>
llvm-svn: 163819
48-bit if necessary, in order to reduce the generated code size.
We have 900 cases not covered by OpcodeInfo in ATT AsmWriter and more in Intel
AsmWriter and ARM AsmWriter.
This patch reduced the clang Release build size by 50k, running on a Mac Pro.
llvm-svn: 163814
by xoring the high-bit. This fails if the source operand is a vector because we need to negate
each of the elements in the vector.
Fix rdar://12281066 PR13813.
llvm-svn: 163802
are within the lifetime zone. Sometime legitimate usages of allocas are
hoisted outside of the lifetime zone. For example, GEPS may calculate the
address of a member of an allocated struct. This commit makes sure that
we only check (abort regions or assert) for instructions that read and write
memory using stack frames directly. Notice that by allowing legitimate
usages outside the lifetime zone we also stop checking for instructions
which use derivatives of allocas. We will catch less bugs in user code
and in the compiler itself.
llvm-svn: 163791
* wrap code blocks in \code ... \endcode;
* refer to parameter names in paragraphs correctly (\arg is not what most
people want -- it starts a new paragraph).
llvm-svn: 163790
The assumption that the target address for the relocation will always be
sizeof(intptr_t) and will always contain an addend for the relocation
value is very wrong. Default to no addend for now.
rdar://12157052
llvm-svn: 163765
When comparing to the macho relocation type enum value, make sure we're only
comparing against the bits in the RelType that correspond.
llvm-svn: 163764
We don't have enough GR64_TC registers when calling a varargs function
with 6 arguments. Since %al holds the number of vector registers used,
only %r11 is available as a scratch register.
This means that addressing modes using both base and index registers
can't be folded into TCRETURNmi64.
<rdar://problem/12282281>
llvm-svn: 163761
This function writes out the current values of the counters and then resets
them. This can be used similarly to the __gcov_flush function to sync the
counters when need be. For instance, in a situation where the application
doesn't exit.
<rdar://problem/12185886>
llvm-svn: 163757
Add some support for dealing with an object pointer on arguments.
Part of rdar://9797999
which now supports adding the object pointer attribute to the
subprogram as it should.
llvm-svn: 163754
- BlockAddress has no support of BA + offset form and there is no way to
propagate that offset into machine operand;
- Add BA + offset support and a new interface 'getTargetBlockAddress' to
simplify target block address forming;
- All targets are modified to use new interface and X86 backend is enhanced to
support BA + offset addressing.
llvm-svn: 163743
nonvolatile condition register fields across calls under the SVR4 ABIs.
* With the 64-bit ABI, the save location is at a fixed offset of 8 from
the stack pointer. The frame pointer cannot be used to access this
portion of the stack frame since the distance from the frame pointer may
change with alloca calls.
* With the 32-bit ABI, the save location is just below the general
register save area, and is accessed via the frame pointer like the rest
of the save areas. This is an optional slot, so it must only be created
if any of CR2, CR3, and CR4 were modified.
* For both ABIs, save/restore logic is generated only if one of the
nonvolatile CR fields were modified.
I also took this opportunity to clean up an extra FIXME in
PPCFrameLowering.h. Save area offsets for 32-bit GPRs are meaningless
for the 64-bit ABI, so I removed them for correctness and efficiency.
Fixes PR13708 and partially also PR13623. It lets us enable exception handling
on PPC64.
Patch by William J. Schmidt!
llvm-svn: 163713
SelectionDAG::getConstantFP(double Val, EVT VT, bool isTarget);
should not be used when Val is not a simple constant (as the comment in
SelectionDAG.h indicates). This patch avoids using this function
when folding an unknown constant through a bitcast, where it cannot be
guaranteed that Val will be a simple constant.
llvm-svn: 163703
The search for liveness is clipped to a specific number of instructions around the target MachineInstr, in order to avoid degenerating into an O(N^2) algorithm. It tries to use various clues about how instructions around (both before and after) a given MachineInstr use that register, to determine its state at the MachineInstr.
llvm-svn: 163695
was printing a newline that doesn't occur when printing other kinds
of LLVM values. Move the printing of that newline elsewhere, making
globals print the same as other values while leaving the output when
printing an entire module unchanged. Patch by Saša Tomić.
llvm-svn: 163693
findLastUseBefore was previous considering virtreg liveness only, leading to
incorrect live intervals for reg units when instrs with physreg operands were
moved up.
llvm-svn: 163685
The input program may contain intructions which are not inside lifetime
markers. This can happen due to a bug in the compiler or due to a bug in
user code (for example, returning a reference to a local variable).
This commit adds checks that all of the instructions in the function and
invalidates lifetime ranges which do not contain all of the instructions.
llvm-svn: 163678
a pair of switch/branch where both depend on the value of the same variable and
the default case of the first switch/branch goes to the second switch/branch.
Code clean up and fixed a few issues:
1> handling the case where some cases of the 2nd switch are invalidated
2> correctly calculate the weight for the 2nd switch when it is a conditional eq
Testing case is modified from Alastair's original patch.
llvm-svn: 163635
Sub-register lane masks are bitmasks that can be used to determine if
two sub-registers of a virtual register will overlap. For example, ARM's
ssub0 and ssub1 sub-register indices don't overlap each other, but both
overlap dsub0 and qsub0.
The lane masks will be accurate on most targets, but on targets that use
sub-register indexes in an irregular way, the masks may conservatively
report that two sub-register indices overlap when the eventually
allocated physregs don't.
Irregular register banks also mean that the bits in a lane mask can't be
mapped onto register units, but the concept is similar.
llvm-svn: 163630
Preserve the Composites map in the CodeGenSubRegIndex class so it can be
used to determine which sub-register indices can actually be composed.
llvm-svn: 163629
Apparently, NumSubRegIndices was completely unused before. Adjust it by
one to include the null subreg index, just like getNumRegs() includes
the null register.
llvm-svn: 163628
The Hexagon target decided to use a lot of functionality from the
target-independent scheduler. That's fine, and other targets should be
able to do the same. This reorg and API update makes that easy.
For the record, ScheduleDAGMI was not meant to be subclassed. Instead,
new scheduling algorithms should be able to implement
MachineSchedStrategy and be done. But if need be, it's nice to be
able to extend ScheduleDAGMI, so I also made that easier. The target
scheduler is somewhat more apt to break that way though.
llvm-svn: 163580
The ARM backend can eliminate cmp instructions by reusing flags from a
nearby sub instruction with similar arguments.
Don't do that if the sub is predicated - the flags are not written
unconditionally.
<rdar://problem/12263428>
llvm-svn: 163535
Craig Topper