Make tail duplication of indirect branches much more aggressive (for targets
that indicate that it is profitable), based on further experience with
this transformation. I compiled 3 large applications with and without
this more aggressive tail duplication and measured minimal changes in code
size. ("size" on Darwin seems to round the text size up to the nearest
page boundary, so I can only say that any code size increase was less than
one 4k page.) Radar 7421267.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89814 91177308-0d34-0410-b5e6-96231b3b80d8
This violates the ABI (that area is "reserved"), and
while it is safe if all code is generated with current
compilers, there is some very old code around that uses
that slot for something else, and breaks if it is stored
into. Adjust testcases looking for current behavior.
I've verified that the stack frame size is right in all
testcases, whether it changed or not. 7311323.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89811 91177308-0d34-0410-b5e6-96231b3b80d8
than doing the same via constpool:
1. Load from constpool costs 3 cycles on A9, movt/movw pair - just 2.
2. Load from constpool might stall up to 300 cycles due to cache miss.
3. Movt/movw does not use load/store unit.
4. Less constpool entries => better compiler performance.
This is only enabled on ELF systems, since darwin does not have needed
relocations (yet).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89720 91177308-0d34-0410-b5e6-96231b3b80d8
way for each TargetJITInfo subclass to allocate its own stubs. This
means stubs aren't as exactly-sized anymore, but it lets us get rid of
TargetJITInfo::emitFunctionStubAtAddr(), which lets ARM and PPC
support the eager JIT, fixing http://llvm.org/PR4816.
* Rename the JITEmitter's stub creation functions to describe the kind
of stub they create. So far, all of them create lazy-compilation
stubs, but they sometimes get used when far-call stubs are needed.
Fixing http://llvm.org/PR5201 will involve fixing this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89715 91177308-0d34-0410-b5e6-96231b3b80d8
Note that "hasDotLocAndDotFile"-style debug info was already broken;
people wanting this functionality should implement it in the
AsmPrinter/DwarfWriter code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89711 91177308-0d34-0410-b5e6-96231b3b80d8
It's probably better in the long run to replace the
indirect-GlobalVariable system. That'll be done after a subsequent
patch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89708 91177308-0d34-0410-b5e6-96231b3b80d8
This fixes the NEON asm printing so the "predicate" field is printed between the opcode and the data type suffix.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89706 91177308-0d34-0410-b5e6-96231b3b80d8
VDUPLND and VDUPLNQ to derive from N2V instead of N2VDup. VDUPLND and VDUPLNQ
now expect op19_18 and op17_16 as the first two args.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89699 91177308-0d34-0410-b5e6-96231b3b80d8
of SelectionDAGBuild.h/cpp into its own files, to help separate
general lowering logic from SelectionDAG-specific lowering logic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89667 91177308-0d34-0410-b5e6-96231b3b80d8
out of its run function and into its doInitialization method, so
that it does the dump once instead of once per function.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89660 91177308-0d34-0410-b5e6-96231b3b80d8
ConstantExpr, not just the top-level operator. This allows it to
fold many more constants.
Also, make GlobalOpt call ConstantFoldConstantExpression on
GlobalVariable initializers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89659 91177308-0d34-0410-b5e6-96231b3b80d8
the body to not pass the name for the isSigned parameter. However it
seems that changing prototypes is a big-no-no, so here I revert the
previous change and pass "true" for isSigned, meaning this always does
a signed cast, which was the previous behaviour assuming the name was
not NULL! Some other C function needs to be introduced for the general
case of signed or unsigned casts. This hopefully unbreaks the ocaml
binding.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89648 91177308-0d34-0410-b5e6-96231b3b80d8
tell debug info which base register to use to reference a frame index on a
per-index basis. This is useful, for example, in the presence of dynamic
stack realignment when local variables are indexed via the stack pointer and
stack-based arguments via the frame pointer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89620 91177308-0d34-0410-b5e6-96231b3b80d8
The hasNoModRefInfoForCalls isn't worth it as a filter because
basicaa provides m/r info and everything chains to it, so remove
it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89599 91177308-0d34-0410-b5e6-96231b3b80d8
When splitting a critical edge, the registers live through the edge are:
- Used in a PHI instruction, or
- Live out from the predecessor, and
- Live in to the successor.
This allows the coalescer to eliminate even more phi joins.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89530 91177308-0d34-0410-b5e6-96231b3b80d8
DIEs are created from MDNode, which are already uniqued. And DwarfDebug already uses ValueMaps to find and use existing DIE for a given MDNode.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89518 91177308-0d34-0410-b5e6-96231b3b80d8
Also fixed the corresponding testcase, and the PALIGNR
intrinsic (tested for correctness with llvm-gcc).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89491 91177308-0d34-0410-b5e6-96231b3b80d8
it may be used in contexts where preheader insertion may have failed due
to an indirectbr.
Make LoopSimplify's LoopSimplify::SeparateNestedLoop properly fail in
the case that it would require splitting an indirectbr edge.
These fix PR5502.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89484 91177308-0d34-0410-b5e6-96231b3b80d8
constant pool ranges, as CPEIsInRange() makes conservative assumptions about
the potential alignment changes from branch adjustments. The verification,
on the other hand, runs after those branch adjustments are made, so the
effects on alignment are known and already taken into account. The sanity
check in verify should check the range directly instead.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89473 91177308-0d34-0410-b5e6-96231b3b80d8
same object to be a non-capture; Duncan pointed out a way that such
a comparison could be a capture.
Make the rule that considers a comparison against null more specific,
and only consider noalias return values compared against null. This
still supports test/Transforms/GVN/nonescaping-malloc.ll, and is not
susceptible to the problem Duncan pointed out with noalias arguments.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89468 91177308-0d34-0410-b5e6-96231b3b80d8
Makes '--comma-separated val1,val2' mean the same thing as
'--comma-separated=val1,val2' (that is, 'val1' and 'val2' are not lumped
together as 'val1,val2'). Also declutters the main loop a bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89463 91177308-0d34-0410-b5e6-96231b3b80d8
tests/Transforms/InstCombine/shufflemask-undef.ll. If
anyone cares, the use of 2*e here (and the equivalent
all over the place in instcombine) seems wrong, though
harmless: it should really be twice the length of the
input vector. I think shufflevector used to require
that the mask have the same length as the input, but I
don't think that's true any more. I don't care enough
about vectors to do anything about this...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89456 91177308-0d34-0410-b5e6-96231b3b80d8
which was an expensive checks failure due to a bug in the checking. This
patch in essence reverts the original fix for PR3393, and refixes it by a
tweak to the way expensive checking is done.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89454 91177308-0d34-0410-b5e6-96231b3b80d8
because if the results from getUnderlyingObject match, the values must
be from the same underlying object, even if we don't know what that
object is.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89434 91177308-0d34-0410-b5e6-96231b3b80d8
careful about crazy methods of capturing pointers using comparisons.
Comparisons of identified objects with null in the default address
space are not captures. And, comparisons of two pointers within the
same identified object are not captures.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89421 91177308-0d34-0410-b5e6-96231b3b80d8
assembly can confuse things utterly, as it's assumed that instructions in
inline assembly are 4 bytes wide. For Thumb mode, that's often not true,
so the calculations for when alignment padding will be present get thrown off,
ultimately leading to out of range constant pool entry references. Making
more conservative assumptions that padding may be necessary when inline asm
is present avoids this situation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89403 91177308-0d34-0410-b5e6-96231b3b80d8
if it is not ultimately captured. Teach BasicAliasAnalysis that a
local object address which does not escape and is never stored does
not alias with a value resulting from a load.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89398 91177308-0d34-0410-b5e6-96231b3b80d8
critical edges in PHIElimination.
This has a huge impact on regalloc performance, and we recover almost all of
the 10% compile time regression that edge splitting introduced.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89381 91177308-0d34-0410-b5e6-96231b3b80d8
fully specified at this level. Subclasses of NLdStLN can specify selective
bit(s) for Inst{7-4}, as is done for VLD[234]LN* and VST[234]LN* inside
ARMInstrNEON.td.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89377 91177308-0d34-0410-b5e6-96231b3b80d8
they are lowered to instruction sequences more complex than a simple
load, such that CodeGen cannot rematerialize them, a reload from a
spill slot is likely to be cheaper than the complex sequence.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89374 91177308-0d34-0410-b5e6-96231b3b80d8
Add a -linearscan-skip-count argument (default to 0) that tells the
allocator to remember the last N registers it allocated and skip them
when looking for a register candidate. This tends to spread out
register usage and free up post-allocation scheduling at the cost of
slightly more register pressure. The primary benefit is the ability
to backschedule reloads.
This is turned off by default.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89356 91177308-0d34-0410-b5e6-96231b3b80d8
All spiller calls in RegAllocLinearScan now go through the new Spiller interface.
The "-new-spill-framework" command line option has been removed. To use the trivial in-place spiller you should now pass "-spiller=trivial -rewriter=trivial".
(Note the trivial spiller/rewriter are only meant to serve as examples of the new in-place modification work. Enabling them will yield terrible, though hopefully functional, code).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89311 91177308-0d34-0410-b5e6-96231b3b80d8
for uses inside the loop. This works better with LSR. Disabled behind
-simplify-iv-users while benchmarking.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89299 91177308-0d34-0410-b5e6-96231b3b80d8
When TwoAddressInstructionPass deletes a dead instruction, make sure that all
register kills are accounted for. The 2-addr register does not get special
treatment.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89246 91177308-0d34-0410-b5e6-96231b3b80d8
when LiveVariables is available.
The -split-phi-edges is now gone, and so is the hack to disable it when using
the local register allocator. The PHIElimination pass no longer has
LiveVariables as a prerequisite - that is what broke the local allocator.
Instead we do critical edge splitting when possible - that is when
LiveVariables is available.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89213 91177308-0d34-0410-b5e6-96231b3b80d8
contents of the block to be duplicated. Use this for ARM Cortex A8/9 to
be more aggressive tail duplicating indirect branches, since it makes it
much more likely that they will be predicted in the branch target buffer.
Testcase coming soon.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89187 91177308-0d34-0410-b5e6-96231b3b80d8
This is probably not confined to *just* these two things.
Anyway, the llvm-gcc front-end may look up the structure layout information for
an abstract type. That information will be stored into a table with the FE's
TD. Instruction combine can come along and also ask for information on that
abstract type, but for a separate TD (the one associated with the pass manager).
After the type is refined, the old structure layout information in the pass
manager's TD file is out of date. If a new type is allocated in the same space
as the old-unrefined type, then the structure type information in the pass
manager's TD file will be wrong, but won't know it.
Fix this by making the TD's structure type information an abstract type user.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89176 91177308-0d34-0410-b5e6-96231b3b80d8
The local register allocator doesn't like it when LiveVariables is run.
We should also disable edge splitting under -O0, but that has to wait a bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89125 91177308-0d34-0410-b5e6-96231b3b80d8
unnecessary. It is broken because the "isIdenticalTo" check should be
negated. If that is fixed, this code causes the CodeGen/X86/tail-opts.ll
test to fail, in the dont_merge_oddly function. And, I confirmed that the
regression is real -- the generated code is worse. As far as I can tell,
that tail-opts.ll test is checking for what this code is supposed to handle
and we're doing the right thing anyway.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89121 91177308-0d34-0410-b5e6-96231b3b80d8
libffi support and that the interpreter can't call external functions without
it. Patch by Timo Juhani Lindfors! Fixes PR5466.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89062 91177308-0d34-0410-b5e6-96231b3b80d8
unconditional branches or fallthroghes. Instcombine/SimplifyCFG
should be simplifying branches with known conditions.
This fixes some problems caused by these transformations not
updating the MachineBasicBlock CFG.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89017 91177308-0d34-0410-b5e6-96231b3b80d8
0b1110 (ALways). This is so that the disassembler decoder can distinguish among
BX_RET, BRIND, and BXr9.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89000 91177308-0d34-0410-b5e6-96231b3b80d8
The large code model is documented at
http://www.x86-64.org/documentation/abi.pdf and says that calls should
assume their target doesn't live within the 32-bit pc-relative offset
that fits in the call instruction.
To do this, we turn off the global-address->target-global-address
conversion in X86TargetLowering::LowerCall(). The first attempt at
this broke the lazy JIT because it can separate the movabs(imm->reg)
from the actual call instruction. The lazy JIT receives the address of
the movabs as a relocation and needs to record the return address from
the call; and then when that call happens, it needs to patch the
movabs with the newly-compiled target. We could thread the call
instruction into the relocation and record the movabs<->call mapping
explicitly, but that seems to require at least as much new
complication in the code generator as this change.
To fix this, we make lazy functions _always_ go through a call
stub. You'd think we'd only have to force lazy calls through a stub on
difficult platforms, but that turns out to break indirect calls
through a function pointer. The right fix for that is to distinguish
between calls and address-of operations on uncompiled functions, but
that's complex enough to leave for someone else to do.
Another attempt at this defined a new CALL64i pseudo-instruction,
which expanded to a 2-instruction sequence in the assembly output and
was special-cased in the X86CodeEmitter's emitInstruction()
function. That broke indirect calls in the same way as above.
This patch also removes a hack forcing Darwin to the small code model.
Without far-call-stubs, the small code model requires things of the
JITMemoryManager that the DefaultJITMemoryManager can't provide.
Thanks to echristo for lots of testing!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88984 91177308-0d34-0410-b5e6-96231b3b80d8
The Mask and LHSMask may not be of the same size, so don't do the
transformation if they're different.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88972 91177308-0d34-0410-b5e6-96231b3b80d8
Have the asm printer emit a comment if an instruction is a spill or
reload and have the spiller mark copies it introdues so the asm printer
can also annotate those.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88911 91177308-0d34-0410-b5e6-96231b3b80d8
Make sure when ProcessImplicitDefs removes a copy which kills its source reg that it
removes the copy from said reg's Kills list.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88881 91177308-0d34-0410-b5e6-96231b3b80d8
This allows JT to eliminate a ton of infeasible edges when
handling code like the templates in PatternMatch.h
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88869 91177308-0d34-0410-b5e6-96231b3b80d8