The bundle_iterator::operator++ function now doesn't need to dig out the
basic block and check against end(). It can use the isBundledWithSucc()
flag to find the last bundled instruction safely.
Similarly, MachineInstr::isBundled() no longer needs to look at
iterators etc. It only has to look at flags.
llvm-svn: 170473
The bundle-related MI flags need to be kept in sync with the neighboring
instructions. Don't allow the bulk flag-setting setFlags() function to
change them.
Also don't copy MI flags when cloning an instruction. The clone's bundle
flags will be set when it is explicitly inserted into a bundle.
llvm-svn: 170459
Remove the instr_iterator versions of the splice() functions. It doesn't
seem useful to be able to splice sequences of instructions that don't
consist of full bundles.
The normal splice functions that take MBB::iterator arguments are not
changed, and they can move whole bundles around without any problems.
llvm-svn: 170456
The normal insert() function takes an MBB::iterator position, and
inserts a stand-alone MachineInstr as before.
The insert() function that takes an MBB::instr_iterator position can
insert instructions inside a bundle, and will now update the bundle
flags correctly when that happens.
When the insert position is between two bundles, it is unclear whether
the instruction should be appended to the previous bundle, prepended to
the next bundle, or stand on its own. The MBB::insert() function doesn't
bundle the instruction in that case, use the MIBundleBuilder class for
that.
llvm-svn: 170437
A register can be associated with several distinct register classes.
For example, on PPC, the floating point registers are each associated with
both F4RC (which holds f32) and F8RC (which holds f64). As a result, this code
would fail when provided with a floating point register and an f64 operand
because it would happen to find the register in the F4RC class first and
return that. From the F4RC class, SDAG would extract f32 as the register
type and then assert because of the invalid implied conversion between
the f64 value and the f32 register.
Instead, search all register classes. If a register class containing the
the requested register has the requested type, then return that register
class. Otherwise, as before, return the first register class found that
contains the requested register.
llvm-svn: 170436
Most code is oblivious to bundles and uses the MBB::iterator which only
visits whole bundles. MBB::erase() operates on whole bundles at a time
as before.
MBB::remove() now refuses to remove bundled instructions. It is not safe
to remove all instructions in a bundle without deleting them since there
is no way of returning pointers to all the removed instructions.
MBB::remove_instr() and MBB::erase_instr() will now update bundle flags
correctly, lifting individual instructions out of bundles while leaving
the remaining bundle intact.
The MachineInstr convenience functions are updated so
eraseFromParent() erases a whole bundle as before
eraseFromBundle() erases a single instruction, leaving the rest of its bundle.
removeFromParent() refuses to operate on bundled instructions, and
removeFromBundle() lifts a single instruction out of its bundle.
These functions will no longer accidentally split or coalesce bundles -
bundle flags are updated to preserve the existing bundling, and explicit
bundleWith* / unbundleFrom* functions should be used to change the
instruction bundling.
This API update is still a work in progress. I am going to update APIs
first so they maintain bundle flags automatically when possible. Then
I'll add stricter verification of the bundle flags.
llvm-svn: 170384
TargetLowering::getRegClassFor).
Some isSimple() guards were missing, or getSimpleVT() were hoisted too
far, resulting in asserts on valid LLVM assembly input.
llvm-svn: 170336
Mips16 is really a processor decoding mode (ala thumb 1) and in the same
program, mips16 and mips32 functions can exist and can call each other.
If a jal type instruction encounters an address with the lower bit set, then
the processor switches to mips16 mode (if it is not already in it). If the
lower bit is not set, then it switches to mips32 mode.
The linker knows which functions are mips16 and which are mips32.
When relocation is performed on code labels, this lower order bit is
set if the code label is a mips16 code label.
In general this works just fine, however when creating exception handling
tables and dwarf, there are cases where you don't want this lower order
bit added in.
This has been traditionally distinguished in gas assembly source by using a
different syntax for the label.
lab1: ; this will cause the lower order bit to be added
lab2=. ; this will not cause the lower order bit to be added
In some cases, it does not matter because in dwarf and debug tables
the difference of two labels is used and in that case the lower order
bits subtract each other out.
To fix this, I have added to mcstreamer the notion of a debuglabel.
The default is for label and debug label to be the same. So calling
EmitLabel and EmitDebugLabel produce the same result.
For various reasons, there is only one set of labels that needs to be
modified for the mips exceptions to work. These are the "$eh_func_beginXXX"
labels.
Mips overrides the debug label suffix from ":" to "=." .
This initial patch fixes exceptions. More changes most likely
will be needed to DwarfCFException to make all of this work
for actual debugging. These changes will be to emit debug labels in some
places where a simple label is emitted now.
Some historical discussion on this from gcc can be found at:
http://gcc.gnu.org/ml/gcc-patches/2008-08/msg00623.htmlhttp://gcc.gnu.org/ml/gcc-patches/2008-11/msg01273.html
llvm-svn: 170279
The new API is higher level than just manipulating the bundle flags
directly, and the setIsInsideBundle() function will disappear soon.
llvm-svn: 170159
Accordingly, add helper funtions getSimpleValueType (in parallel to
getValueType) in SDValue, SDNode, and TargetLowering.
This is the first, in a series of patches.
This is the second attempt. In the first attempt (r169837), a few
getSimpleVT() were hoisted too far, detected by bootstrap failures.
llvm-svn: 170104
mention the inline memcpy / memset expansion code is a mess?
This patch split the ZeroOrLdSrc argument into two: IsMemset and ZeroMemset.
The first indicates whether it is expanding a memset or a memcpy / memmove.
The later is whether the memset is a memset of zero. It's totally possible
(likely even) that targets may want to do different things for memcpy and
memset of zero.
llvm-svn: 169959
Also added more comments to explain why it is generally ok to return true.
- Rename getOptimalMemOpType argument IsZeroVal to ZeroOrLdSrc. It's meant to
be true for loaded source (memcpy) or zero constants (memset). The poor name
choice is probably some kind of legacy issue.
llvm-svn: 169954
ScalarTargetTransformInfo::getIntImmCost() instead. "Legal" is a poorly defined
term for something like integer immediate materialization. It is always possible
to materialize an integer immediate. Whether to use it for memcpy expansion is
more a "cost" conceern.
llvm-svn: 169929
Accordingly, add helper funtions getSimpleValueType (in parallel to
getValueType) in SDValue, SDNode, and TargetLowering.
This is the first, in a series of patches.
llvm-svn: 169837
try to reduce the width of this load, and would end up transforming:
(truncate (lshr (sextload i48 <ptr> as i64), 32) to i32)
to
(truncate (zextload i32 <ptr+4> as i64) to i32)
We lost the sext attached to the load while building the narrower i32
load, and replaced it with a zext because lshr always zext's the
results. Instead, bail out of this combine when there is a conflict
between a sextload and a zext narrowing. The rest of the DAG combiner
still optimize the code down to the proper single instruction:
movswl 6(...),%eax
Which is exactly what we wanted. Previously we read past the end *and*
missed the sign extension:
movl 6(...), %eax
llvm-svn: 169802
This shouldn't affect codegen for -O0 compiles as tail call markers are not
emitted in unoptimized compiles. Testing with the external/internal nightly
test suite reveals no change in compile time performance. Testing with -O1,
-O2 and -O3 with fast-isel enabled did not cause any compile-time or
execution-time failures. All tests were performed on my x86 machine.
I'll monitor our arm testers to ensure no regressions occur there.
In an upcoming clang patch I will be marking the objc_autoreleaseReturnValue
and objc_retainAutoreleaseReturnValue as tail calls unconditionally. While
it's theoretically true that this is just an optimization, it's an
optimization that we very much want to happen even at -O0, or else ARC
applications become substantially harder to debug.
Part of rdar://12553082
llvm-svn: 169796
controls each of the abbreviation sets (only a single one at the
moment) and computes offsets separately as well for each set
of DIEs.
No real function change, ordering of abbreviations for the skeleton
CU changed but only because we're computing in a separate order. Fix
the testcase not to care.
llvm-svn: 169793
1. Teach it to use overlapping unaligned load / store to copy / set the trailing
bytes. e.g. On 86, use two pairs of movups / movaps for 17 - 31 byte copies.
2. Use f64 for memcpy / memset on targets where i64 is not legal but f64 is. e.g.
x86 and ARM.
3. When memcpy from a constant string, do *not* replace the load with a constant
if it's not possible to materialize an integer immediate with a single
instruction (required a new target hook: TLI.isIntImmLegal()).
4. Use unaligned load / stores more aggressively if target hooks indicates they
are "fast".
5. Update ARM target hooks to use unaligned load / stores. e.g. vld1.8 / vst1.8.
Also increase the threshold to something reasonable (8 for memset, 4 pairs
for memcpy).
This significantly improves Dhrystone, up to 50% on ARM iOS devices.
rdar://12760078
llvm-svn: 169791
InitSections is called before the MCContext is initialized it could cause
duplicate temporary symbols to be emitted later (after context initialization
resets the temporary label counter).
llvm-svn: 169785
misched used GetUnderlyingObject in order to break false load/store
dependencies, and the -enable-aa-sched-mi feature similarly relied on
GetUnderlyingObject in order to ensure it is safe to use the aliasing analysis.
Unfortunately, GetUnderlyingObject does not recurse through phi nodes, and so
(especially due to LSR) all of these mechanisms failed for
induction-variable-dependent loads and stores inside loops.
This change replaces uses of GetUnderlyingObject with GetUnderlyingObjects
(which will recurse through phi and select instructions) in misched.
Andy reviewed, tested and simplified this patch; Thanks!
llvm-svn: 169744
This is still a work in progress. The purpose is to make bundling and
unbundling operations explicit, and to catch errors where bundles are
broken or created inadvertently.
The old IsInsideBundle flag is replaced by two MI flags: BundledPred
which has the same meaning as IsInsideBundle, and BundledSucc which is
set on instructions that are bundled with a successor. Having two flags
provdes redundancy to detect when a bundle is inadvertently torn by a
splice() or insert(), and it makes it possible to write bundle iterators
that don't need to peek at adjacent instructions.
The new flags can't be manipulated directly (once setIsInsideBundle is
gone). Instead there are MI functions to make and break bundle bonds.
The setIsInsideBundle function will be removed in a future commit. It
should be replaced by bundleWithPred().
llvm-svn: 169583
original change description:
change MCContext to work on the doInitialization/doFinalization model
reviewed by Evan Cheng <evan.cheng@apple.com>
llvm-svn: 169553
understand target implementation of any_extend / extload, just generate
zero_extend in place of any_extend for liveouts when the target knows the
zero_extend will be implicit (e.g. ARM ldrb / ldrh) or folded (e.g. x86 movz).
rdar://12771555
llvm-svn: 169536
Some languages, e.g. Ada and Pascal, allow you to specify that the array bounds
are different from the default (1 in these cases). If we have a lower bound
that's non-default, then we emit the lower bound. We also calculate the correct
upper bound in those cases.
llvm-svn: 169484
This is much simpler to reason about, more efficient, and
fixes some corner cases involving implicit super-register defs.
Fixed rdar://12797931.
llvm-svn: 169425
A MachineInstr can only ever be constructed by CreateMachineInstr() and
CloneMachineInstr(), and those factories don't use the removed
constructors.
llvm-svn: 169395
- fixed ordering of calls to doFinalization to be the reverse of the pass run order due to potential dependencies
- fixed machine module info to operate in the doInitialization/doFinalization model, also fixes some FIXMEs
reviewed by Evan Cheng <evan.cheng@apple.com>
llvm-svn: 169391
The count attribute is more accurate with regards to the size of an array. It
also obviates the upper bound attribute in the subrange. We can also better
handle an unbound array by setting the count to -1 instead of the lower bound to
1 and upper bound to 0.
llvm-svn: 169312
This reapplies the fix for PR13303 now with more justification. Based on my
execution of the GDB 7.5 test suite this results in:
expected passes: 16101 -> 20890 (+30%)
unexpected failures: 4826 -> 637 (-77%)
There are 23 checks that used to pass and now fail. They are all in
gdb.reverse. Investigating a few looks like they were accidentally passing
due to extra breakpoints being set by this bug. They're generally due to the
difference in end location between gcc and clang, the test suite is trying to
set breakpoints on the closing '}' that clang doesn't associate with any
instructions.
llvm-svn: 169304
missed in the first pass because the script didn't yet handle include
guards.
Note that the script is now able to handle all of these headers without
manual edits. =]
llvm-svn: 169224
The count field is necessary because there isn't a difference between the 'lo'
and 'hi' attributes for a one-element array and a zero-element array. When the
count is '0', we know that this is a zero-element array. When it's >=1, then
it's a normal constant sized array. When it's -1, then the array is unbounded.
llvm-svn: 169218
the alignment is clamped to TargetFrameLowering.getStackAlignment if the target
does not support stack realignment or the option "realign-stack" is off.
This will cause miscompile if the address is treated as aligned and add is
replaced with or in DAGCombine.
Added a bool StackRealignable to TargetFrameLowering to check whether stack
realignment is implemented for the target. Also added a bool RealignOption
to MachineFrameInfo to check whether the option "realign-stack" is on.
rdar://12713765
llvm-svn: 169197
Now that there can be multiple hint registers from targets, it doesn't
make sense to have a function that returns 'the' preferred register.
llvm-svn: 169190
Targets can provide multiple hints now, so getRegAllocPref() doesn't
make sense any longer because it only returns one preferred register.
Replace it with getSimpleHint() in the remaining heuristics. This
function only
llvm-svn: 169188
Virtual registers with a known preferred register are prioritized by
RAGreedy. This function makes the condition explicit without depending
on getRegAllocPref().
llvm-svn: 169179
The TargetRegisterInfo::getRegAllocationHints() function is going to
replace the existing mechanisms for providing target-dependent hints to
the register allocator: ResolveRegAllocHint() and
getRawAllocationOrder().
The new hook is more flexible because it allows the target to provide
multiple preferred candidate registers for each virtual register, and it
is easier to use because targets are not required to return a reference
to a constant array like getRawAllocationOrder().
An optional VirtRegMap argument can be used to provide target-dependent
hints that depend on the provisional assignments of other virtual
registers.
llvm-svn: 169154
Sooooo many of these had incorrect or strange main module includes.
I have manually inspected all of these, and fixed the main module
include to be the nearest plausible thing I could find. If you own or
care about any of these source files, I encourage you to take some time
and check that these edits were sensible. I can't have broken anything
(I strictly added headers, and reordered them, never removed), but they
may not be the headers you'd really like to identify as containing the
API being implemented.
Many forward declarations and missing includes were added to a header
files to allow them to parse cleanly when included first. The main
module rule does in fact have its merits. =]
llvm-svn: 169131
The TwoAddressInstructionPass takes the machine code out of SSA form by
expanding REG_SEQUENCE instructions into copies. It is no longer
necessary to rewrite the registers used by a REG_SEQUENCE instruction
because the new coalescer algorithm can do it now.
REG_SEQUENCE is just converted to a sequence of sub-register copies now.
llvm-svn: 169067
MachineCopyPropagation doesn't understand super-register liveness well
enough to be able to remove implicit defs of super-registers.
This fixes a problem in ARM/2012-01-26-CopyPropKills.ll that is exposed
by an future TwoAddressInstructionPass change. The KILL instructions are
removed before the machine code is emitted.
llvm-svn: 169060
The original patch removed a bunch of code that the SjLjEHPrepare pass placed
into the entry block if all of the landing pads were removed during the
CodeGenPrepare class. The more natural way of doing things is to run the CGP
*before* we run the SjLjEHPrepare pass.
Make it so!
llvm-svn: 169044
This was found by MSVC10's STL debug mode on a test from the test suite. Sadly
std::is_heap isn't standard so there is no way to assert this without writing
our own heap verify, which looks like overkill to me.
llvm-svn: 168885
If we need to split the operand of a VSELECT, it must be the mask operand. We
split the entire VSELECT operand with EXTRACT_SUBVECTOR.
llvm-svn: 168883
No functional change, just moved header files.
Targets can inject custom passes between register allocation and
rewriting. This makes it possible to tweak the register allocation
before rewriting, using the full global interference checking available
from LiveRegMatrix.
llvm-svn: 168806
This is a simple, cheap infrastructure for analyzing the shape of a
DAG. It recognizes uniform DAGs that take the shape of bottom-up
subtrees, such as the included matrix multiplication example. This is
useful for heuristics that balance register pressure with ILP. Two
canonical expressions of the heuristic are implemented in scheduling
modes: -misched-ilpmin and -misched-ilpmax.
llvm-svn: 168773
This fixes a hole in the "cheap" alias analysis logic implemented within
the DAG builder itself, regardless of whether proper alias analysis is
enabled. It now handles this pattern produced by LSR+CodeGenPrepare.
%sunkaddr1 = ptrtoint * %obj to i64
%sunkaddr2 = add i64 %sunkaddr1, %lsr.iv
%sunkaddr3 = inttoptr i64 %sunkaddr2 to i32*
store i32 %v, i32* %sunkaddr3
llvm-svn: 168768
The Target library is not allowed to depend on the large CodeGen
library, but the TRI and TII classes provide abstract interfaces that
require both caller and callee to link to CodeGen.
The implementation files for these classes provide default
implementations of some of the hooks. These methods may need to
reference CodeGen, so they belong in that library.
We already have a number of methods implemented in the
TargetInstrInfoImpl sub-class because of that. I will merge that class
into the parent next.
llvm-svn: 168758
boundaries.
Given the following case:
BB0
%vreg1<def> = SUBrr %vreg0, %vreg7
%vreg2<def> = COPY %vreg7
BB1
%vreg10<def> = SUBrr %vreg0, %vreg2
We should be able to CSE between SUBrr in BB0 and SUBrr in BB1.
rdar://12462006
llvm-svn: 168717
argument. Instead, use a pair of .local and .comm directives.
This avoids spurious differences between binaries built by the
integrated assembler vs. those built by the external assembler,
since the external assembler may impose alignment requirements
on .lcomm symbols where the integrated assembler does not.
llvm-svn: 168704
r168627), we no longer need to call the freezeReservedRegs() function a second
time. Previously, this pass was conservatively adding the FP to the set of
reserved registers, requiring the second update to the reserved registers.
rdar://12719844
llvm-svn: 168631
r168627), we no longer need to call the freezeReservedRegs() function a second
time. Previously, this pass was conservatively adding the FP to the set of
reserved registers, requiring the second update to the reserved registers.
rdar://12719844
llvm-svn: 168630
positive.
In this particular case, R6 was being spilled by the register scavenger when it
was in fact dead. The isUsed function reported R6 as used because the R6_R7
alias was reserved (due to the fact that we've reserved R7 as the FP). The
solution is to only check if the original register (i.e., R6) isReserved and
not the aliases. The aliases are only checked to make sure they're available.
The test case is derived from one of the nightly tester benchmarks and is rather
intractable and difficult to reproduce, so I haven't included it.
rdar://12592448
llvm-svn: 168054
Jakub Staszak spotted this in review. I don't notice these things
until I manually rerun benchmarks. But reducing unit tests is a very
high priority.
llvm-svn: 168021
physical register as candidate for common subexpression elimination
in MachineCSE.
This fixes a bug on PowerPC in MultiSource/Applications/oggenc/oggenc
caused by MachineCSE invalidly merging two separate DYNALLOC insns.
llvm-svn: 167855
This allows me to begin enabling (or backing out) misched by default
for one subtarget at a time. To run misched we typically want to:
- Disable SelectionDAG scheduling (use the source order scheduler)
- Enable more aggressive coalescing (until we decide to always run the coalescer this way)
- Enable MachineScheduler pass itself.
Disabling PostRA sched may follow for some subtargets.
llvm-svn: 167826
This adds the -join-globalcopies option which can be enabled by
default once misched is also enabled.
Ideally, the register coalescer would be able to split local live
ranges in a way that produces copies that can be easily resolved by
the scheduler. Until then, this heuristic should be good enough to at
least allow the scheduler to run after coalescing.
llvm-svn: 167825
If we have a type 'int a[1]' and a type 'int b[0]', the generated DWARF is the
same for both of them because we use the 'upper_bound' attribute. Instead use
the 'count' attrbute, which gives the correct number of elements in the array.
<rdar://problem/12566646>
llvm-svn: 167806
This teaches the register coalescer to be less prone to split critical
edges. I am currently benchmarking this with the new (post-coalescer)
scheduler. I plan to enable this by default and remove the option as
soon as misched is enabled.
llvm-svn: 167758
Uses the infrastructure from r167742 to support clustering instructure
that the target processor can "fuse". e.g. cmp+jmp.
Next step: target hook implementations with test cases, and enable.
llvm-svn: 167744
This infrastructure is generally useful for any target that wants to
strongly prefer two instructions to be adjacent after scheduling.
A following checkin will add target-specific hooks with unit
tests. Then this feature will be enabled by default with misched.
llvm-svn: 167742
This adds support for weak DAG edges to the general scheduling
infrastructure in preparation for MachineScheduler support for
heuristics based on weak edges.
llvm-svn: 167738
The RegMaskSlots contains 'r' slots while NewIdx and OldIdx are 'B'
slots. This broke the checks in the assertions.
This fixes PR14302.
llvm-svn: 167625
misched is disabled by default. With -enable-misched, these heuristics
balance the schedule to simultaneously avoid saturating processor
resources, expose ILP, and minimize register pressure. I've been
analyzing the performance of these heuristics on everything in the
llvm test suite in addition to a few other benchmarks. I would like
each heuristic check to be verified by a unit test, but I'm still
trying to figure out the best way to do that. The heuristics are still
in considerable flux, but as they are refined we should be rigorous
about unit testing the improvements.
llvm-svn: 167527
updating an abstract DIE or not. If we are, then we use that. Its children will
be added on later, as well as the object pointer attribute. Otherwise, this
function may be called with a concrete DIE twice and adding the children and
object pointer attribute to it twice.
<rdar://problem/12401423&12600340>
llvm-svn: 167524
register masks. This is an obvious and necessary fix for a soon to be committed
patch. No test case possible at this time. Reviewed by Jakob.
llvm-svn: 167498
Expose the processor resources defined by the machine model to the
scheduler and other clients through the TargetSchedule interface.
Normalize each resource count with respect to other kinds of
resources. This allows scheduling heuristics to balance resources
against other kinds of resources and latency.
llvm-svn: 167444
r165941: Resubmit the changes to llvm core to update the functions to
support different pointer sizes on a per address space basis.
Despite this commit log, this change primarily changed stuff outside of
VMCore, and those changes do not carry any tests for correctness (or
even plausibility), and we have consistently found questionable or flat
out incorrect cases in these changes. Most of them are probably correct,
but we need to devise a system that makes it more clear when we have
handled the address space concerns correctly, and ideally each pass that
gets updated would receive an accompanying test case that exercises that
pass specificaly w.r.t. alternate address spaces.
However, from this commit, I have retained the new C API entry points.
Those were an orthogonal change that probably should have been split
apart, but they seem entirely good.
In several places the changes were very obvious cleanups with no actual
multiple address space code added; these I have not reverted when
I spotted them.
In a few other places there were merge conflicts due to a cleaner
solution being implemented later, often not using address spaces at all.
In those cases, I've preserved the new code which isn't address space
dependent.
This is part of my ongoing effort to clean out the partial address space
code which carries high risk and low test coverage, and not likely to be
finished before the 3.2 release looms closer. Duncan and I would both
like to see the above issues addressed before we return to these
changes.
llvm-svn: 167222
getIntPtrType support for multiple address spaces via a pointer type,
and also introduced a crasher bug in the constant folder reported in
PR14233.
These commits also contained several problems that should really be
addressed before they are re-committed. I have avoided reverting various
cleanups to the DataLayout APIs that are reasonable to have moving
forward in order to reduce the amount of churn, and minimize the number
of commits that were reverted. I've also manually updated merge
conflicts and manually arranged for the getIntPtrType function to stay
in DataLayout and to be defined in a plausible way after this revert.
Thanks to Duncan for working through this exact strategy with me, and
Nick Lewycky for tracking down the really annoying crasher this
triggered. (Test case to follow in its own commit.)
After discussing with Duncan extensively, and based on a note from
Micah, I'm going to continue to back out some more of the more
problematic patches in this series in order to ensure we go into the
LLVM 3.2 branch with a reasonable story here. I'll send a note to
llvmdev explaining what's going on and why.
Summary of reverted revisions:
r166634: Fix a compiler warning with an unused variable.
r166607: Add some cleanup to the DataLayout changes requested by
Chandler.
r166596: Revert "Back out r166591, not sure why this made it through
since I cancelled the command. Bleh, sorry about this!
r166591: Delete a directory that wasn't supposed to be checked in yet.
r166578: Add in support for getIntPtrType to get the pointer type based
on the address space.
llvm-svn: 167221
the MachineInstr MayLoad/MayLoad flags are based on the tablegen implementation.
For inline assembly, however, we need to compute these based on the constraints.
Revert r166929 as this is no longer needed, but leave the test case in place.
rdar://12033048 and PR13504
llvm-svn: 167040
checks to avoid performing compile-time arithmetic on PPCDoubleDouble.
Now that APFloat supports arithmetic on PPCDoubleDouble, those checks
are no longer needed, and we can treat the type like any other.
llvm-svn: 166958
Partial copies can show up even when CoalescerPair.isPartial() returns
false. For example:
%vreg24:dsub_0<def> = COPY %vreg31:dsub_0; QPR:%vreg24,%vreg31
Such a partial-partial copy is not good enough for the transformation
adjustCopiesBackFrom() needs to do.
llvm-svn: 166944
wrapper returns a vector of integers when passed a vector of pointers) by having
getIntPtrType itself return a vector of integers in this case. Outside of this
wrapper, I didn't find anywhere in the codebase that was relying on the old
behaviour for vectors of pointers, so give this a whirl through the buildbots.
llvm-svn: 166939
incorrect instruction sequence due to it not being aware that an
inline assembly instruction may reference memory.
This patch fixes the problem by causing the scheduler to always assume that any
inline assembly code instruction could access memory. This is necessary because
the internal representation of the inline instruction does not include
any information about memory accesses.
This should fix PR13504.
llvm-svn: 166929
- If more than 1 elemennts are defined and target supports the vectorized
conversion, use the vectorized one instead to reduce the strength on
conversion operation.
llvm-svn: 166546
which is supposed to consistently raise SIGTRAP across all systems. In contrast,
__builtin_trap() behave differently on different systems. e.g. it raises SIGTRAP on ARM, and
SIGILL on X86. The purpose of __builtin_debugtrap() is to consistently provide "trap"
functionality, in the mean time preserve the compatibility with on gcc on __builtin_trap().
The X86 backend is already able to handle debugtrap(). This patch is to:
1) make front-end recognize "__builtin_debugtrap()" (emboddied in the one-line change to Clang).
2) In DAG legalization phase, by default, "debugtrap" will be replaced with "trap", which
make the __builtin_debugtrap() "available" to all existing ports without the hassle of
changing their code.
3) If trap-function is specified (via -trap-func=xyz to llc), both __builtin_debugtrap() and
__builtin_trap() will be expanded into the function call of the specified trap function.
This behavior may need change in the future.
The provided testing-case is to make sure 2) and 3) are working for ARM port, and we
already have a testing case for x86.
llvm-svn: 166300
When merging stack slots, if StackColoring::remapInstructions gets a
value back from GetUnderlyingObject that it does not know about or is
not itself a stack slot, clear the memory operand in case it aliases
the merged slot. This prevents the introduction of incorrect aliasing
information.
Author: Matthew Curtis <mcurtis@codeaurora.org>
llvm-svn: 166216
This more accurately reflects what is actually being stored in the
field.
No functionality change intended.
Author: Matthew Curtis <mcurtis@codeaurora.org>
llvm-svn: 166215
The TargetTransform changes are breaking LTO bootstraps of clang. I am
working with Nadav to figure out the problem, but I am reverting it for now
to get our buildbots working.
This reverts svn commits: 165665 165669 165670 165786 165787 165997
and I have also reverted clang svn 165741
llvm-svn: 166168
- Folding (trunc (concat ... X )) to (concat ... (trunc X) ...) is valid
when '...' are all 'undef's.
- r166125 relies on this transformation.
llvm-svn: 166155
- If the extracted vector has the same type of all vectored being concatenated
together, it should be simplified directly into v_i, where i is the index of
the element being extracted.
llvm-svn: 166125
any scheduling heuristics nor does it build up any scheduling data structure
that other heuristics use. It essentially linearize by doing a DFA walk but
it does handle glues correctly.
IMPORTANT: it probably can't handle all the physical register dependencies so
it's not suitable for x86. It also doesn't deal with dbg_value nodes right now
so it's definitely is still WIP.
rdar://12474515
llvm-svn: 166122
All callers of these functions really want the isPhysRegOrOverlapUsed()
functionality which also checks aliases. For historical reasons, targets
without register aliases were calling isPhysRegUsed() instead.
Change isPhysRegUsed() to also check aliases, and switch all
isPhysRegOrOverlapUsed() callers to isPhysRegUsed().
llvm-svn: 166117
This is just as fast, and it makes it possible to avoid leaking the
UsedPhysRegs BitVector implementation through
MachineRegisterInfo::addPhysRegsUsed().
llvm-svn: 166083
PR14098 contains an example where we would rematerialize a MOV8ri
immediately after the original instruction:
%vreg7:sub_8bit<def> = MOV8ri 9; GR32_ABCD:%vreg7
%vreg22:sub_8bit<def> = MOV8ri 9; GR32_ABCD:%vreg7
Besides being pointless, it is also wrong since the original instruction
only redefines part of the register, and the value read by the new
instruction is wrong.
The problem was the LiveRangeEdit::allUsesAvailableAt() didn't
special-case OrigIdx == UseIdx and found the wrong SSA value.
llvm-svn: 166068
Stack is formed improperly for long structures passed as byval arguments for
EABI mode.
If we took AAPCS reference, we can found the next statements:
A: "If the argument requires double-word alignment (8-byte), the NCRN (Next
Core Register Number) is rounded up to the next even register number." (5.5
Parameter Passing, Stage C, C.3).
B: "The alignment of an aggregate shall be the alignment of its most-aligned
component." (4.3 Composite Types, 4.3.1 Aggregates).
So if we have structure with doubles (9 double fields) and 3 Core unused
registers (r1, r2, r3): caller should use r2 and r3 registers only.
Currently r1,r2,r3 set is used, but it is invalid.
Callee VA routine should also use r2 and r3 regs only. All is ok here. This
behaviour is guessed by rounding up SP address with ADD+BFC operations.
Fix:
Main fix is in ARMTargetLowering::HandleByVal. If we detected AAPCS mode and
8 byte alignment, we waste odd registers then.
P.S.:
I also improved LDRB_POST_IMM regression test. Since ldrb instruction will
not generated by current regression test after this patch.
llvm-svn: 166018
Also provide an MRI::getReservedRegs() function to access the frozen
register set, and isReserved() and isAllocatable() methods to test
individual registers.
The various implementations of TRI::getReservedRegs() are quite
complicated, and many passes need to look at the reserved register set.
This patch makes it possible for these passes to use the cached copy in
MRI, avoiding a lot of malloc traffic and repeated calculations.
llvm-svn: 165982
The new coalescer can merge a dead def into an unused lane of an
otherwise live vector register.
Clear the <dead> flag when that happens since the flag refers to the
full virtual register which is still live after the partial dead def.
This fixes PR14079.
llvm-svn: 165877
It is possible that the live range of the value being pruned loops back
into the kill MBB where the search started. When that happens, make sure
that the beginning of KillMBB is also pruned.
Instead of starting a DFS at KillMBB and skipping the root of the
search, start a DFS at each KillMBB successor, and allow the search to
loop back to KillMBB.
This fixes PR14078.
llvm-svn: 165872
Completely update one interval at a time instead of collecting live
range fragments to be updated. This avoids building data structures,
except for a single SmallPtrSet of updated intervals.
Also share code between handleMove() and handleMoveIntoBundle().
Add support for moving dead defs across other live values in the
interval. The MI scheduler can do that.
llvm-svn: 165824
PHIElimination inserts IMPLICIT_DEF instructions to guarantee that all
PHI predecessors have a live-out value. These IMPLICIT_DEF values are
not considered to be real interference when coalescing virtual
registers:
%vreg1 = IMPLICIT_DEF
%vreg2 = MOV32r0
When joining %vreg1 and %vreg2, the IMPLICIT_DEF instruction and its
value number should simply be erased since the %vreg2 value number now
provides a live-out value for the PHI predecesor block.
llvm-svn: 165813
On PowerPC, a bitcast of <16 x i8> to i128 may run through a code
path in ExpandRes_BITCAST that attempts to do an intermediate
bitcast to a <4 x i32> vector, and then construct the Hi and Lo parts
of the resulting i128 by pairing up two of those i32 vector elements
each. The code already recognizes that on a big-endian system, the
first two vector elements form the Hi part, and the final two vector
elements form the Lo part (vice-versa from the little-endian situation).
However, we also need to take endianness into account when forming each
of those separate pairs: on a big-endian system, vector element 0 is
the *high* part of the pair making up the Hi part of the result, and
vector element 1 is the low part of the pair. The code currently always
uses vector element 0 as the low part and vector element 1 as the high
part, as is appropriate for little-endian platforms only.
This patch fixes this by swapping the vector elements as they are
paired up as appropriate.
llvm-svn: 165802
not legal. However, it should use a div instruction + mul + sub if divide is
legal. The rem legalization code was missing a check and incorrectly uses a
divrem libcall even when div is legal.
rdar://12481395
llvm-svn: 165778
Not all instructions define a virtual register in their first operand.
Specifically, INLINEASM has a different format.
<rdar://problem/12472811>
llvm-svn: 165721
The minimum set of required instructions is ISD::AND, ISD::OR, ISD::SETO(or ISD::SETOEQ) and ISD::SETUO(or ISD::SETUNE). Everything is expanded into one of two patterns:
Pattern 1: (LHS CC1 RHS) Opc (LHS CC2 RHS)
Pattern 2: (LHS CC1 LHS) Opc (RHS CC2 RHS)
llvm-svn: 165655
- Due to the current matching vector elements constraints in ISD::FP_EXTEND,
rounding from v2f32 to v2f64 is scalarized. Add a customized v2f32 widening
to convert it into a target-specific X86ISD::VFPEXT to work around this
constraints. This patch also reverts a previous attempt to fix this issue by
recovering the scalarized ISD::FP_EXTEND pattern and thus significantly
reduces the overhead of supporting non-power-2 vector FP extend.
llvm-svn: 165625
SchedulerDAGInstrs::buildSchedGraph ignores dependencies between FixedStack
objects and byval parameters. So loading byval parameters from stack may be
inserted *before* it will be stored, since these operations are treated as
independent.
Fix:
Currently ARMTargetLowering::LowerFormalArguments saves byval registers with
FixedStack MachinePointerInfo. To fix the problem we need to store byval
registers with MachinePointerInfo referenced to first the "byval" parameter.
Also commit adds two new fields to the InputArg structure: Function's argument
index and InputArg's part offset in bytes relative to the start position of
Function's argument. E.g.: If function's argument is 128 bit width and it was
splitted onto 32 bit regs, then we got 4 InputArg structs with same arg index,
but different offset values.
llvm-svn: 165616
Allows the new machine model to be used for NumMicroOps and OutputLatency.
Allows the HazardRecognizer to be disabled along with itineraries.
llvm-svn: 165603
This wasn't contributing anything significant to postRA heuristics except compile time (by my measurements) and will be replaced by a more general heuristic for cross-region dependencies within the scheduler itself.
llvm-svn: 165563
We use the enums to query whether an Attributes object has that attribute. The
opaque layer is responsible for knowing where that specific attribute is stored.
llvm-svn: 165488
This class is used by LSR and a number of places in the codegen.
This is the first step in de-coupling LSR from TLI, and creating
a new interface in between them.
llvm-svn: 165455
When the CFG contains a loop with multiple entry blocks, the traces
computed by MachineTraceMetrics don't always have the same nice
properties. Loop back-edges are normally excluded from traces, but
MachineLoopInfo doesn't recognize loops with multiple entry blocks, so
those back-edges may be included.
Avoid asserting when that happens by adding an isEarlierInSameTrace()
function that accurately determines if a dominating block is part of the
same trace AND is above the currrent block in the trace.
llvm-svn: 165434
a) frame setup instructions define the prologue
b) we shouldn't change our location mid-stream
Add a test to make sure that the stack adjustment stays within
the prologue.
llvm-svn: 165250
multiple stores with a single load. We create the wide loads and stores (and their chains)
before we remove the scalar loads and stores and fix the DAG chain. We attempted to merge
loads with a different chain. When that happened, the assumption that it is safe to RAUW
broke and a cycle was introduced.
llvm-svn: 165148
is not profitable in many cases because modern processors perform multiple stores
in parallel and merging stores prior to merging requires extra work. We handle two main cases:
1. Store of multiple consecutive constants:
q->a = 3;
q->4 = 5;
In this case we store a single legal wide integer.
2. Store of multiple consecutive loads:
int a = p->a;
int b = p->b;
q->a = a;
q->b = b;
In this case we load/store either ilegal vector registers or legal wide integer registers.
llvm-svn: 165125
Enable the pass by default for targets that request it, and change the
-enable-early-ifcvt to the opposite -disable-early-ifcvt.
There are still some x86 regressions when enabling early if-conversion
because of the missing machine models. Disable the pass for x86 until
machine models are added.
llvm-svn: 165075
Reserved register live ranges look like a set of dead defs - any uses of
reserved registers are ignored.
Instead of skipping the updating of reserved register operands entirely,
just ignore the use operands and treat the def operands normally.
No test case, handleMove() is not commonly used yet.
llvm-svn: 165060
JoinVals::pruneValues() calls LIS->pruneValue() to avoid conflicts when
overlapping two different values. This produces a set of live range end
points that are used to reconstruct the live range (with SSA update)
after joining the two registers.
When a value is pruned twice, the set of end points was insufficient:
v1 = DEF
v1 = REPLACE1
v1 = REPLACE2
KILL v1
The end point at KILL would only reconstruct the live range from
REPLACE2 to KILL, leaving the range REPLACE1-REPLACE2 dead.
Add REPLACE2 as an end point in this case so the full live range is
reconstructed.
This fixes PR13999.
llvm-svn: 165056
because moden processos can store multiple values in parallel, and preparing the consecutive store requires
some work. We only handle these cases:
1. Consecutive stores where the values and consecutive loads. For example:
int a = p->a;
int b = p->b;
q->a = a;
q->b = b;
2. Consecutive stores where the values are constants. Foe example:
q->a = 4;
q->b = 5;
llvm-svn: 164910
buildbots. Original commit message:
A DAGCombine optimization for merging consecutive stores. This optimization is not profitable in many cases
because moden processos can store multiple values in parallel, and preparing the consecutive store requires
some work. We only handle these cases:
1. Consecutive stores where the values and consecutive loads. For example:
int a = p->a;
int b = p->b;
q->a = a;
q->b = b;
2. Consecutive stores where the values are constants. Foe example:
q->a = 4;
q->b = 5;
llvm-svn: 164890
because moden processos can store multiple values in parallel, and preparing the consecutive store requires
some work. We only handle these cases:
1. Consecutive stores where the values and consecutive loads. For example:
int a = p->a;
int b = p->b;
q->a = a;
q->b = b;
2. Consecutive stores where the values are constants. Foe example:
q->a = 4;
q->b = 5;
llvm-svn: 164885
The new coalescer can turn a full virtual register definition into a
partial redef by merging another value into an unused vector lane.
Make sure to clear the <read-undef> flag on such defs.
llvm-svn: 164807
The fix is obvious and the only test case I have is horrible, so I am
not including it. The problem shows up when self-hosting clang on i386
with -new-coalescer enabled.
llvm-svn: 164793
scalar-to-vector conversion that we cannot handle. For instance, when an invalid
constraint is used in an inline asm statement.
<rdar://problem/12284092>
llvm-svn: 164662
scalar-to-vector conversion that we cannot handle. For instance, when an invalid
constraint is used in an inline asm statement.
<rdar://problem/12284092>
llvm-svn: 164657
Provide interface in TargetLowering to set or get the minimum number of basic
blocks whereby jump tables are generated for switch statements rather than an
if sequence.
getMinimumJumpTableEntries() defaults to 4.
setMinimumJumpTableEntries() allows target configuration.
This patch changes the default for the Hexagon architecture to 5
as it improves performance on some benchmarks.
llvm-svn: 164628
Even out-of-line jump tables can be in the code section, so mark them
as data-regions for those targets which support the directives.
rdar://12362871&12362974
llvm-svn: 164571
care about it being an argument variable so that we can decide
that captured block and lambda vars that don't happen to
be arguments could be an argument pointer.
Add the object pointer for one case onto the subprogram die.
rdar://12001329
llvm-svn: 164419
A PHI can't create interference on its own. If two live ranges interfere
at a PHI, they must also interfere when leaving one of the PHI
predecessors.
llvm-svn: 164330
The old-fashioned many-to-one value mapping doesn't always work when
merging vector lanes. A value can map to multiple different values, and
it can even be necessary to insert new PHIs.
When a value number is defined by a copy from a value number that
required SSa update, include the live range of the copied value number
in the SSA update as well. It is not necessarily a copy of the original
value number any longer.
llvm-svn: 164329
A common coalescing conflict in vector code is lane insertion:
%dst = FOO
%src = BAR
%dst:ssub0 = COPY %src
The live range of %src interferes with the ssub0 lane of %dst, but that
lane is never read after %src would have clobbered it. That makes it
safe to merge the live ranges and eliminate the COPY:
%dst = FOO
%dst:ssub0 = BAR
This patch teaches the new coalescer to resolve conflicts where dead
vector lanes would be clobbered, at least as long as the clobbered
vector lanes don't escape the basic block.
llvm-svn: 164250
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
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
Kill flags are removed more and more aggressively during the register
allocation passes, it is better to get information from LiveIntervals.
llvm-svn: 163972
- 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
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
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
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
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
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
This folding happens as early as possible for performance reasons, and to make sure it isn't foiled by other transforms (e.g. forming FMAs).
llvm-svn: 163519
Previously we checked if the register is def'd in a block via the def/use list a
nd walked the list of kills to check if the register is killed in a block. Both
of these checks can be made much cheaper by walking the block first and
recording all defs and kills.
This reduces the compile time of the test case from PR13651 from 40s to 15s at
-O2. The compile time is still dominated by LV updating but now the main culprit
is SparseBitVector's slowness.
llvm-svn: 163478
For some reason .lcomm uses byte alignment and .comm log2 alignment so we can't
use the same setting for both. Fix this by reintroducing the LCOMM enum.
I verified this against mingw's gcc.
llvm-svn: 163420
- Darwin lied about not supporting .lcomm and turned it into zerofill in the
asm parser. Push the zerofill-conversion down into macho-specific code.
- This makes the tri-state LCOMMType enum superfluous, there are no targets
without .lcomm.
- Do proper error reporting when trying to use .lcomm with alignment on a target
that doesn't support it.
- .comm and .lcomm alignment was parsed in bytes on COFF, should be power of 2.
- Fixes PR13755 (.lcomm crashes on ELF).
llvm-svn: 163395
The RegisterCoalescer understands overlapping live ranges where one
register is defined as a copy of the other. With this change, register
allocators using LiveRegMatrix can do the same, at least for copies
between physical and virtual registers.
When a physreg is defined by a copy from a virtreg, allow those live
ranges to overlap:
%CL<def> = COPY %vreg11:sub_8bit; GR32_ABCD:%vreg11
%vreg13<def,tied1> = SAR32rCL %vreg13<tied0>, %CL<imp-use,kill>
We can assign %vreg11 to %ECX, overlapping the live range of %CL.
llvm-svn: 163336
We will soon allow virtual register live ranges to overlap regunit live
ranges when the physreg is defined as a copy of the virtreg:
%EAX = COPY %vreg5
FOO %vreg5
BAR %EAX<kill>
There is no real interference since %vreg5 and %EAX have the same value
where they overlap.
This patch prevents addKillFlags from adding virtreg kill flags to FOO
where the assigned physreg is overlapping the virtual register live
range.
llvm-svn: 163335
Kill flags are difficult to maintain, and liveness queries are better
handled by live intervals.
Kill flags are reinserted after register allocation by addKillFlags().
llvm-svn: 163334
The MachineOperand::TiedTo field was maintained, but not used.
This patch enables it in isRegTiedToDefOperand() and
isRegTiedToUseOperand() which are the actual functions use by the
register allocator.
llvm-svn: 163153
After much agonizing, use a full 4 bits of precious MachineOperand space
to encode this. This uses existing padding, and doesn't grow
MachineOperand beyond its current 32 bytes.
This allows tied defs among the first 15 operands on a normal
instruction, just like the current MCInstrDesc constraint encoding.
Inline assembly needs to be able to tie more than the first 15 operands,
and gets special treatment.
Tied uses can appear beyond 15 operands, as long as they are tied to a
def that's in range.
llvm-svn: 163151
- CodeGenPrepare pass for identifying div/rem ops
- Backend specifies the type mapping using addBypassSlowDivType
- Enabled only for Intel Atom with O2 32-bit -> 8-bit
- Replace IDIV with instructions which test its value and use DIVB if the value
is positive and less than 256.
- In the case when the quotient and remainder of a divide are used a DIV
and a REM instruction will be present in the IR. In the non-Atom case
they are both lowered to IDIVs and CSE removes the redundant IDIV instruction,
using the quotient and remainder from the first IDIV. However,
due to this optimization CSE is not able to eliminate redundant
IDIV instructions because they are located in different basic blocks.
This is overcome by calculating both the quotient (DIV) and remainder (REM)
in each basic block that is inserted by the optimization and reusing the result
values when a subsequent DIV or REM instruction uses the same operands.
- Test cases check for the presents of the optimization when calculating
either the quotient, remainder, or both.
Patch by Tyler Nowicki!
llvm-svn: 163150
This reverts commit 5dd9e214fb92847e947f9edab170f9b4e52b908f.
Thanks to Duncan for explaining how this should have been done.
Conflicts:
test/CodeGen/X86/vec_select.ll
llvm-svn: 163064
Manage tied operands entirely internally to MachineInstr. This makes it
possible to change the representation of tied operands, as I will do
shortly.
The constraint that tied uses and defs must be in the same order was too
restrictive.
llvm-svn: 163021
because it does not support CMOV of vectors. To implement this efficientlyi, we broadcast the condition bit and use a sequence of NAND-OR
to select between the two operands. This is the same sequence we use for targets that don't have vector BLENDs (like SSE2).
rdar://12201387
llvm-svn: 162926
When a MachineInstr is constructed, its implicit operands are added
first, then the explicit operands are inserted before the implicits.
MCInstrDesc has oprand flags like early clobber and operand ties that
apply to the explicit operands.
Don't look at those flags when the implicit operands are first added in
the explicit operands's positions.
llvm-svn: 162910
When there are multiple tied use-def pairs on an inline asm instruction,
the tied uses must appear in the same order as the defs.
It is possible to write an LLVM IR inline asm instruction that breaks
this constraint, but there is no reason for a front end to emit the
operands out of order.
The gnu inline asm syntax specifies tied operands as a single read/write
constraint "+r", so ouf of order operands are not possible.
llvm-svn: 162878
For normal instructions, isTied() is set automatically by addOperand(),
based on MCInstrDesc, but inline asm has tied operands outside the
descriptor.
llvm-svn: 162869
Ordered memory operations are more constrained than volatile loads and
stores because they must be ordered with respect to all other memory
operations.
llvm-svn: 162861
It is technically allowed to move a normal load across a volatile load,
but probably not a good idea.
It is not allowed to move a load across an atomic load with
Ordering > Monotonic, and we model those with MOVolatile as well.
I recently removed the mayStore flag from atomic load instructions, so
they don't need a pseudo-opcode. This patch makes up for the difference.
llvm-svn: 162857
The operands on an INLINEASM machine instruction are divided into groups
headed by immediate flag operands. Verify this structure.
Extract verifyTiedOperands(), and only call it for non-inlineasm
instructions.
llvm-svn: 162849
WHen running with -verify-machineinstrs, check that tied operands come
in matching use/def pairs, and that they are consistent with MCInstrDesc
when it applies.
llvm-svn: 162816
The isTied bit is set automatically when a tied use is added and
MCInstrDesc indicates a tied operand. The tie is broken when one of the
tied operands is removed.
llvm-svn: 162814
While in SSA form, a MachineInstr can have pairs of tied defs and uses.
The tied operands are used to represent read-modify-write operands that
must be assigned the same physical register.
Previously, tied operand pairs were computed from fixed MCInstrDesc
fields, or by using black magic on inline assembly instructions.
The isTied flag makes it possible to add tied operands to any
instruction while getting rid of (some of) the inlineasm magic.
Tied operands on normal instructions are needed to represent predicated
individual instructions in SSA form. An extra <tied,imp-use> operand is
required to represent the output value when the instruction predicate is
false.
Adding a predicate to:
%vreg0<def> = ADD %vreg1, %vreg2
Will look like:
%vreg0<tied,def> = ADD %vreg1, %vreg2, pred:3, %vreg7<tied,imp-use>
The virtual register %vreg7 is the value given to %vreg0 when the
predicate is false. It will be assigned the same physreg as %vreg0.
This commit adds the isTied flag and sets it based on MCInstrDesc when
building an instruction. The flag is not used for anything yet.
llvm-svn: 162774
Register operands are manipulated by a lot of target-independent code,
and it is not always possible to preserve target flags. That means it is
not safe to use target flags on register operands.
None of the targets in the tree are using register operand target flags.
External targets should be using immediate operands to annotate
instructions with operand modifiers.
llvm-svn: 162770
These extra flags are not required to properly order the atomic
load/store instructions. SelectionDAGBuilder chains atomics as if they
were volatile, and SelectionDAG::getAtomic() sets the isVolatile bit on
the memory operands of all atomic operations.
The volatile bit is enough to order atomic loads and stores during and
after SelectionDAG.
This means we set mayLoad on atomic_load, mayStore on atomic_store, and
mayLoad+mayStore on the remaining atomic read-modify-write operations.
llvm-svn: 162733
In SelectionDAGLegalize::ExpandLegalINT_TO_FP, expand INT_TO_FP nodes without
using any f64 operations if f64 is not a legal type.
Patch by Stefan Kristiansson.
llvm-svn: 162728
the case of multiple edges from one block to another.
A simple example is a switch statement with multiple values to the same
destination. The definition of an edge is modified from a pair of blocks to
a pair of PredBlock and an index into the successors.
Also set the weight correctly when building SelectionDAG from LLVM IR,
especially when converting a Switch.
IntegersSubsetMapping is updated to calculate the weight for each cluster.
llvm-svn: 162572
output (we're emitting a specification already and the information
isn't changing) and we're not in old gdb compat mode.
Saves 1% on the debug information for a build of llvm.
Fixes rdar://11043421
llvm-svn: 162493
The logic for recomputing latency based on a ScheduleDAG edge was
shady. This bypasses the problem by requiring the client to provide
operand indices. This ensures consistent use of the machine model's
API.
llvm-svn: 162420
Based on CR feedback from r162301 and Craig Topper's refactoring in r162347
here are a few other places that could use the same API (& in one instance drop
a Function.h dependency).
llvm-svn: 162367
SelectionDAG's 'init' has not been called when the SelectionDAGBuilder is
constructed (in SelectionDAGISel's constructor), so this was previously always
initialized with 0.
llvm-svn: 162333
Even looking at the revision history I couldn't quite piece together why this
cast was ever written in the first place, but I assume it was because of some
change in the inheritance, perhaps this function was reimplemented in a
derived type & this caller was meant to get the base version (& it wasn't
virtual)?
llvm-svn: 162301
The getSumForBlock function was quadratic in the number of successors
because getSuccWeight would perform a linear search for an already known
iterator.
This patch was originally committed as r161460, but reverted again
because of assertion failures. Now that duplicate Machine CFG edges have
been eliminated, this works properly.
llvm-svn: 162233
IR that hasn't been through SimplifyCFG can look like this:
br i1 %b, label %r, label %r
Make sure we don't create duplicate Machine CFG edges in this case.
Fix the machine code verifier to accept conditional branches with a
single CFG edge.
llvm-svn: 162230
The DAGCombiner tries to optimise a BUILD_VECTOR by checking if it
consists purely of get_vector_elts from one or two source vectors. If
so, it either makes a concat_vectors node or a shufflevector node.
However, it doesn't check the element type width of the underlying
vector, so if you have this sequence:
Node0: v4i16 = ...
Node1: i32 = extract_vector_elt Node0
Node2: i32 = extract_vector_elt Node0
Node3: v16i8 = BUILD_VECTOR Node1, Node2, ...
It will attempt to:
Node0: v4i16 = ...
NewNode1: v16i8 = concat_vectors Node0, ...
Where this is actually invalid because the element width is completely
different. This causes an assertion failure on DAG legalization stage.
Fix:
If output item type of BUILD_VECTOR differs from input item type.
Make concat_vectors based on input element type and then bitcast it to the output vector type. So the case described above will transformed to:
Node0: v4i16 = ...
NewNode1: v8i16 = concat_vectors Node0, ...
NewNode2: v16i8 = bitcast NewNode1
llvm-svn: 162195
make it more consistent with its intended semantics.
The `linker_private_weak_def_auto' linkage type was meant to automatically hide
globals which never had their addresses taken. It has nothing to do with the
`linker_private' linkage type, which outputs the symbols with a `l' (ell) prefix
among other things.
The intended semantic is more like the `linkonce_odr' linkage type.
Change the name of the linkage type to `linkonce_odr_auto_hide'. And therefore
changing the semantics so that it produces the correct output for the linker.
Note: The old linkage name `linker_private_weak_def_auto' will still parse but
is not a synonym for `linkonce_odr_auto_hide'. This should be removed in 4.0.
<rdar://problem/11754934>
llvm-svn: 162114
Increment the MBB iterator at the top of the loop to properly handle the
current (and previous) instructions getting erased.
This fixes PR13625.
llvm-svn: 162099
Select instructions pick one of two virtual registers based on a
condition, like x86 cmov. On targets like ARM that support predication,
selects can sometimes be eliminated by predicating the instruction
defining one of the operands.
Teach PeepholeOptimizer to recognize select instructions, and ask the
target to optimize them.
llvm-svn: 162059
It never does anything when running 'make check', and it get's in the
way of updating live intervals in 2-addr.
The hook was originally added to help form IT blocks in Thumb2 code
before register allocation, but the pass ordering has changed since
then, and we run if-conversion after register allocation now.
When the MI scheduler is enabled, there will be no less than two
schedulers between 2-addr and Thumb2ITBlockPass, so this hook is
unlikely to help anything.
llvm-svn: 161794
It is still possible to if-convert if the tail block has extra
predecessors, but the tail phis must be rewritten instead of being
removed.
llvm-svn: 161781
Detect when there is not enough available ILP, so if-conversion can't
speculate instructions for free.
Compute the lengthening of the critical path when inserting a select
instruction that depends on the condition as well as both sides of the
if.
Reject conversions that would stretch the critical path by more than
half a mispredict penalty.
llvm-svn: 161713
Trace::getResourceLength() computes the number of cycles required to
execute the trace when ignoring data dependencies. The number can be
compared to the critical path to estimate the trace ILP.
Trace::getPHIDepth() computes the data dependency depth of a PHI in a
trace successor that isn't necessarily part of the trace.
llvm-svn: 161711
When a trace ends with a back-edge, include PHIs in the loop header in
the height computations. This makes the critical path through a loop
more accurate by including the latencies of the last instructions in the
loop.
llvm-svn: 161688
When replacing Old with New, it can happen that New is already a
successor. Add the old and new edge weights instead of creating a
duplicate edge.
llvm-svn: 161653
This makes it possible to speed up def_iterator by stopping at the first
use. This makes def_empty() and getUniqueVRegDef() much faster when
there are many uses.
In a +Asserts build, LiveVariables is 100x faster in one case because
getVRegDef() has an assertion that would scan to the end of a
def_iterator chain.
Spill weight calculation is significantly faster (300x in one case)
because isTriviallyReMaterializable() calls MRI->isConstantPhysReg(%RIP)
which calls def_empty(%RIP).
llvm-svn: 161634
Use a more conventional doubly linked list where the Prev pointers form
a cycle. This means it is no longer necessary to adjust the Prev
pointers when reallocating the VRegInfo array.
The test changes are required because the register allocation hint is
using the use-list order to break ties.
llvm-svn: 161633
Register MachineOperands are kept in linked lists accessible via MRI's
reg_iterator interfaces. The linked list management was handled partly
by MachineOperand methods, partly by MRI methods.
Move all of the list management into MRI, delete
MO::AddRegOperandToRegInfo() and MO::RemoveRegOperandFromRegInfo().
Be more explicit about handling the cases where an MRI pointer isn't
available.
llvm-svn: 161632
We filter out MachineLoop back-edges during the trace-building PO
traversals, but it is possible to have CFG cycles that aren't natural
loops, and MachineLoopInfo doesn't include such cycles.
Use a standard visited set to detect such CFG cycles, and completely
ignore them when picking traces.
llvm-svn: 161532
We perform the following:
1> Use SUB instead of CMP for i8,i16,i32 and i64 in ISel lowering.
2> Modify MachineCSE to correctly handle implicit defs.
3> Convert SUB back to CMP if possible at peephole.
Removed pattern matching of (a>b) ? (a-b):0 and like, since they are handled
by peephole now.
rdar://11873276
llvm-svn: 161462
The getSumForBlock function was quadratic in the number of successors
because getSuccWeight would perform a linear search for an already known
iterator.
llvm-svn: 161460
This adds support for TargetIndex operands during isel. The meaning of
these (index, offset, flags) operands is entirely defined by the target.
llvm-svn: 161453
A target index operand looks a lot like a constant pool reference, but
it is completely target-defined. It contains the 8-bit TargetFlags, a
32-bit index, and a 64-bit offset. It is preserved by all code generator
passes.
TargetIndex operands can be used to carry target-specific information in
cases where immediate operands won't suffice.
llvm-svn: 161441
Compare the critical paths of the two traces through an if-conversion
candidate. If the difference is larger than the branch brediction
penalty, reject the if-conversion. If would never pay.
llvm-svn: 161433
Previously, MBP essentially aligned every branch target it could. This
bloats code quite a bit, especially non-looping code which has no real
reason to prefer aligned branch targets so heavily.
As Andy said in review, it's still a bit odd to do this without a real
cost model, but this at least has much more plausible heuristics.
Fixes PR13265.
llvm-svn: 161409
If the result of a common subexpression is used at all uses of the candidate
expression, CSE should not increase the live range of the common subexpression.
rdar://11393714 and rdar://11819721
llvm-svn: 161396
This patch is mostly just refactoring a bunch of copy-and-pasted code, but
it also adds a check that the call instructions are readnone or readonly.
That check was already present for sin, cos, sqrt, log2, and exp2 calls, but
it was missing for the rest of the builtins being handled in this code.
llvm-svn: 161282
This option runs LiveIntervals before TwoAddressInstructionPass which
will eventually learn to exploit and update the analysis.
Eventually, LiveIntervals will run before PHIElimination, and we can get
rid of LiveVariables.
llvm-svn: 161270
The previous change caused fast isel to not attempt handling any calls to
builtin functions. That included things like "printf" and caused some
noticable regressions in compile time. I wanted to avoid having fast isel
keep a separate list of functions that had to be kept in sync with what the
code in SelectionDAGBuilder.cpp was handling. I've resolved that here by
moving the list into TargetLibraryInfo. This is somewhat redundant in
SelectionDAGBuilder but it will ensure that we keep things consistent.
llvm-svn: 161263
I noticed that SelectionDAGBuilder::visitCall was missing a check for memcmp
in TargetLibraryInfo, so that it would use custom code for memcmp calls even
with -fno-builtin. I also had to add a new -disable-simplify-libcalls option
to llc so that I could write a test for this.
llvm-svn: 161262
The 'unused' state of a value number can be represented as an invalid
def SlotIndex. This also exposed code that shouldn't have been looking
at unused value VNInfos.
llvm-svn: 161258
The only real user of the flag was removeCopyByCommutingDef(), and it
has been switched to LiveIntervals::hasPHIKill().
All the code changed by this patch was only concerned with computing and
propagating the flag.
llvm-svn: 161255
The VNInfo::HAS_PHI_KILL is only half supported. We precompute it in
LiveIntervalAnalysis, but it isn't properly updated by live range
splitting and functions like shrinkToUses().
It is only used in one place: RegisterCoalescer::removeCopyByCommutingDef().
This patch changes that function to use a new LiveIntervals::hasPHIKill()
function that computes the flag for a given value number.
llvm-svn: 161254
Fast isel doesn't currently have support for translating builtin function
calls to target instructions. For embedded environments where the library
functions are not available, this is a matter of correctness and not
just optimization. Most of this patch is just arranging to make the
TargetLibraryInfo available in fast isel. <rdar://problem/12008746>
llvm-svn: 161232
Add more comments and use early returns to reduce nesting in isLoadFoldable.
Also disable folding for V_SET0 to avoid introducing a const pool entry and
a const pool load.
rdar://10554090 and rdar://11873276
llvm-svn: 161207
Whenever both instruction depths and instruction heights are known in a
block, it is possible to compute the length of the critical path as
max(depth+height) over the instructions in the block.
The stored live-in lists make it possible to accurately compute the
length of a critical path that bypasses the current (small) block.
llvm-svn: 161197
LiveRangeEdit::eliminateDeadDefs() can delete a dead instruction that
reads unreserved physregs. This would leave the corresponding regunit
live interval dangling because we don't have shrinkToUses() for physical
registers.
Fix this problem by turning the instruction into a KILL instead of
deleting it. This happens in a landing pad in
test/CodeGen/X86/2012-05-19-CoalescerCrash.ll:
%vreg27<def,dead> = COPY %EDX<kill>; GR32:%vreg27
becomes:
KILL %EDX<kill>
An upcoming fix to the machine verifier will catch problems like this by
verifying regunit live intervals.
This fixes PR13498. I am not including the test case from the PR since
we already have one exposing the problem once the verifier is fixed.
llvm-svn: 161182
Machine CSE and other optimizations can remove instructions so folding
is possible at peephole while not possible at ISel.
This patch is a rework of r160919 and was tested on clang self-host on my local
machine.
rdar://10554090 and rdar://11873276
llvm-svn: 161152
The height on an instruction is the minimum number of cycles from the
instruction is issued to the end of the trace. Heights are computed for
all instructions in and below the trace center block.
The method for computing heights is different from the depth
computation. As we visit instructions in the trace bottom-up, heights of
used instructions are pushed upwards. This way, we avoid scanning long
use lists, looking for uses in the current trace.
At each basic block boundary, a list of live-in registers and their
minimum heights is saved in the trace block info. These live-in lists
are used when restarting depth computations on a trace that
converges with an already computed trace. They will also be used to
accurately compute the critical path length.
llvm-svn: 161138
Assuming infinite issue width, compute the earliest each instruction in
the trace can issue, when considering the latency of data dependencies.
The issue cycle is record as a 'depth' from the beginning of the trace.
This is half the computation required to find the length of the critical
path through the trace. Heights are next.
llvm-svn: 161074
One motivating example is to sink an instruction from a basic block which has
two successors: one outside the loop, the other inside the loop. We should try
to sink the instruction outside the loop.
rdar://11980766
llvm-svn: 161062
We are extending live ranges, so kill flags are not accurate. They
aren't needed until they are recomputed after RA anyway.
<rdar://problem/11950722>
llvm-svn: 161023
We branch to the successor with higher edge weight first.
Convert from
je LBB4_8 --> to outer loop
jmp LBB4_14 --> to inner loop
to
jne LBB4_14
jmp LBB4_8
PR12750
rdar: 11393714
llvm-svn: 161018
This lets traces include the final iteration of a nested loop above the
center block, and the first iteration of a nested loop below the center
block.
We still don't allow traces to contain backedges, and traces are
truncated where they would leave a loop, as seen from the center block.
llvm-svn: 161003
When computing a trace, all the candidates for pred/succ must have been
visited. Filter out back-edges first, though. The PO traversal ignores
them.
Thanks to Andy for spotting this in review.
llvm-svn: 160995
This is a cleaned up version of the isFree() function in
MachineTraceMetrics.cpp.
Transient instructions are very unlikely to produce any code in the
final output. Either because they get eliminated by RegisterCoalescing,
or because they are pseudo-instructions like labels and debug values.
llvm-svn: 160977
A->isPredecessor(B) is the same as B->isSuccessor(A), but it can
tolerate a B that is null or dangling. This shouldn't happen normally,
but it it useful for verification code.
llvm-svn: 160968
Machine CSE and other optimizations can remove instructions so folding
is possible at peephole while not possible at ISel.
rdar://10554090 and rdar://11873276
llvm-svn: 160919
Craig Topper