API with my 176880 revision. If a bad Triple is passed in it can also assert.
In this case too it should just return 0 to indicate failure to create the
disassembler.
rdar://13955214
llvm-svn: 182542
There were bits & pieces of code lying around that may've given the
impression that debug info metadata supported the possibility that a
subprogram's type could be specified by a non-subroutine type describing
the return type of a void function. This support was incomplete &
unnecessary. Asserts & API have been changed to make the desired usage
more clear.
llvm-svn: 182532
Currently the fast-isel table generator recognizes registers, register
classes, and immediates for source pattern operands. ValueType
operands are not recognized. This is not a problem for existing
targets with fast-isel support, but will not work for targets like
PowerPC and SPARC that use types in source patterns.
The proposed patch allows ValueType operands and treats them in the
same manner as register classes. There is no convenient way to map
from a ValueType to a register class, but there's no need to do so.
The table generator already requires that all types in the source
pattern be identical, and we know the register class of the output
operand already. So we just assign that register class to any
ValueType operands we encounter.
No functional effect on existing targets. Testing deferred until the
PowerPC target implements fast-isel.
llvm-svn: 182512
Using PatLeaf rather than ImmLeaf when defining immediate predicates
prevents simple patterns using those predicates from being recognized
for fast instruction selection. This patch replaces the immSExt16
PatLeaf predicate with two ImmLeaf predicates, imm32SExt16 and
imm64SExt16, allowing a few more patterns to be recognized (ADDI,
ADDIC, MULLI, ADDI8, and ADDIC8). Using the new predicates does not
help for LI, LI8, SUBFIC, and SUBFIC8 because these are rejected for
other reasons, but I see no reason to retain the PatLeaf predicate.
No functional change intended, and thus no test cases yet. This is
preliminary work for enabling fast-isel support for PowerPC. When
that support is ready, we'll be able to test this function.
llvm-svn: 182510
We are not working on a DAG and I ran into a number of problems when I enabled the vectorizations of 'diamond-trees' (trees that share leafs).
* Imroved the numbering API.
* Changed the placement of new instructions to the last root.
* Fixed a bug with external tree users with non-zero lane.
* Fixed a bug in the placement of in-tree users.
llvm-svn: 182508
The earlier change list introduced the following inst combines:
B * (uitofp i1 C) —> select C, B, 0
A * (1 - uitofp i1 C) —> select C, 0, A
select C, 0, B + select C, A, 0 —> select C, A, B
Together these 3 changes would simplify :
A * (1 - uitofp i1 C) + B * uitofp i1 C
down to :
select C, B, A
In practice we found that the first two substitutions can have a
negative effect on performance, because they reduce opportunities to
use FMA contractions; between the two options FMAs are often the
better choice. This change list amends the previous one to enable
just these inst combines:
select C, B, 0 + select C, 0, A —> select C, B, A
A * (1 - uitofp i1 C) + B * uitofp i1 C —> select C, B, A
llvm-svn: 182499
The Value pointers we store in the induction variable list can be RAUW'ed by a
call to SCEVExpander::expandCodeFor, use a TrackingVH instead. Do the same thing
in some other places where we store pointers that could potentially be RAUW'ed.
Fixes PR16073.
llvm-svn: 182485
Addresses a review comment from Ulrich Weigand. No functional change intended.
I'm not sure whether the old TODO that this patch touches still holds,
but that's something we'd get to when adding a targetted scheduling
description.
llvm-svn: 182474
The original version of the pass could underestimate the length of a backward
branch in cases like:
alignment to N bytes or more
...
relaxable branch A
...
foo: (aligned to M<N bytes)
...
bar: (aligned to N bytes)
...
relaxable branch B to foo
We don't add any misalignment gap for "bar" because N bytes of alignment
had already been reached earlier in the function. In this case, assuming
that A is relaxed can push "foo" closer to "bar", and make B appear to be
in range. Similar problems can occur for forward branches.
I don't think it's possible to create blocks with mixed alignments as
things stand, not least because we haven't yet defined getPrefLoopAlignment()
for SystemZ (that would need benchmarking). So I don't think we can test
this yet.
Thanks to Rafael Espíndola for spotting the bug.
llvm-svn: 182460
the C API to provide their own way of allocating JIT memory (both code
and data) and finalizing memory permissions (page protections, cache
flush).
llvm-svn: 182448
Solaris doesn't have an endian.h header, but SPARC is the only
big-endian architecture that runs Solaris, so just use that to detect
endianness at compile time.
llvm-svn: 182419
libExecutionEngine. Move method implementations that aren't specific to
allocation out of SectionMemoryManager and into RTDyldMemoryManager.
This is in preparation for exposing RTDyldMemoryManager through the C
API.
This is a fixed version of r182407 and r182411. That first revision
broke builds because I forgot to move the conditional includes of
various POSIX headers from SectionMemoryManager into
RTDyldMemoryManager. Those includes are necessary because of how
getPointerToNamedFunction works around the glibc libc_nonshared.a thing.
The latter revision still broke things because I forgot to include
llvm/Config/config.h.
llvm-svn: 182418
libExecutionEngine. Move method implementations that aren't specific to
allocation out of SectionMemoryManager and into RTDyldMemoryManager.
This is in preparation for exposing RTDyldMemoryManager through the C
API.
This is a fixed version of r182407. That revision broke builds because I
forgot to move the conditional includes of various POSIX headers from
SectionMemoryManager into RTDyldMemoryManager. Those includes are
necessary because of how getPointerToNamedFunction works around the
glibc libc_nonshared.a thing.
llvm-svn: 182411
the C API to provide their own way of allocating JIT memory (both code
and data) and finalizing memory permissions (page protections, cache
flush).
llvm-svn: 182408
libExecutionEngine. Move method implementations that aren't specific to
allocation out of SectionMemoryManager and into RTDyldMemoryManager.
This is in preparation for exposing RTDyldMemoryManager through the C
API.
llvm-svn: 182407
Although I had added some support for the BDZ/BDNZ branches into the selector
(in r158204), I had not correctly adjusted the condition at the top of the
loop. As a result, these branches were still essentially unsupported.
This fixes PR16086. Unfortunately, any test case would be very large (because
it would need to force the loop backedge to exceed the range of the 16-bit
immediate).
llvm-svn: 182385
Revision r182233 partially reverted the change in r181200 to simplify
JIT unif test #ifdefs, because that change caused a link error on some
host operating systems where the export list requires the following
symbols to be defined:
JITTest_AvailableExternallyFunction
JITTest_AvailableExternallyGlobal
As discussed on the list, the commit reverts r182233 (and re-installs
the full r181200 change), and instead fixes the link problem by moving
those two symbols to the top of the file and unconditionally defining
them.
llvm-svn: 182367
This is to fix PR15408 where an undefined symbol Lline_table_start1 is used.
Since we do not generate the debug_line section when .loc is used,
Lline_table_start1 is not emitted and we can't refer to it when calculating
at_stmt_list for a compile unit.
llvm-svn: 182344
pic calls. These need to be there so we don't try and use helper
functions when we call those.
As part of this, make sure that we properly exclude helper functions in pic
mode when indirect calls are involved.
llvm-svn: 182343
Describe that they are assigned numbered label using the same counter
as for unnamed temporaries.
Based on http://llvm.org/bugs/show_bug.cgi?id=16043 and mailing list
discussion.
Patch by Paul Sokolovsky!
llvm-svn: 182332
This resolves the last of the PR14606 failures in the GDB 7.5 test
suite by implementing an optional name field for
DW_TAG_imported_modules/DIImportedEntities and using that to implement
C++ namespace aliases (eg: "namespace X = Y;").
llvm-svn: 182328
By default, a teq instruction is inserted after integer divide. No divide-by-zero
checks are performed if option "-mnocheck-zero-division" is used.
llvm-svn: 182306
Now that the preheader insertion logic in LoopSimplify is externally exposed,
use it, and remove the copy-and-pasted version.
No functionality change intended.
llvm-svn: 182300
Other passes, PPC counter-loop formation for example, also need to add loop
preheaders outside of the regular loop simplification pass. This makes
InsertPreheaderForLoop a global function so that it can be used by other
passes.
No functionality change intended.
llvm-svn: 182299
As the pairing of this instruction form with the bdnz/bdz branches is now
enforced by the verification pass, make it clear from the name that these
are used only for counter-based loops.
No functionality change intended.
llvm-svn: 182296
When asserts are enabled, this adds a verification pass for PPC counter-loop
formation. Unfortunately, without sacrificing code quality, there is no better
way of forming counter-based loops except at the (late) IR level. This means
that we need to recognize, at the IR level, anything which might turn into a
function call (or indirect branch). Because this is currently a finite set of
things, and because SelectionDAG lowering is basic-block local, this can be
done. Nevertheless, it is fragile, and failure results in a miscompile. This
verification pass checks that all (reachable) counter-based branches are
dominated by a loop mtctr instruction, and that no instructions in between
clobber the counter register. If these conditions are not satisfied, then an
ICE will be triggered.
In short, this is to help us sleep better at night.
llvm-svn: 182295
R600TextureIntrinsicsReplacer.cpp:232: warning: the address of ‘ArgsType’ will always evaluate as ‘true’
This doesn't have any effect on the output as a vararg intrinsic behaves the
same way as a non-vararg one.
llvm-svn: 182293
Before this change, the SystemZ backend would use BRCL for all branches
and only consider shortening them to BRC when generating an object file.
E.g. a branch on equal would use the JGE alias of BRCL in assembly output,
but might be shortened to the JE alias of BRC in ELF output. This was
a useful first step, but it had two problems:
(1) The z assembler isn't traditionally supposed to perform branch shortening
or branch relaxation. We followed this rule by not relaxing branches
in assembler input, but that meant that generating assembly code and
then assembling it would not produce the same result as going directly
to object code; the former would give long branches everywhere, whereas
the latter would use short branches where possible.
(2) Other useful branches, like COMPARE AND BRANCH, do not have long forms.
We would need to do something else before supporting them.
(Although COMPARE AND BRANCH does not change the condition codes,
the plan is to model COMPARE AND BRANCH as a CC-clobbering instruction
during codegen, so that we can safely lower it to a separate compare
and long branch where necessary. This is not a valid transformation
for the assembler proper to make.)
This patch therefore moves branch relaxation to a pre-emit pass.
For now, calls are still shortened from BRASL to BRAS by the assembler,
although this too is not really the traditional behaviour.
The first test takes about 1.5s to run, and there are likely to be
more tests in this vein once further branch types are added. The feeling
on IRC was that 1.5s is a bit much for a single test, so I've restricted
it to SystemZ hosts for now.
The patch exposes (and fixes) some typos in the main CodeGen/SystemZ tests.
A later patch will remove the {{g}}s from that directory.
llvm-svn: 182274
This converter currently only handles global variables in address space 0. For
these variables, they are promoted to address space 1 (global memory), and all
uses are updated to point to the result of a cvta.global instruction on the new
variable.
The motivation for this is address space 0 global variables are illegal since we
cannot declare variables in the generic address space. Instead, we place the
variables in address space 1 and explicitly convert the pointer to address
space 0. This is primarily intended to help new users who expect to be able to
place global variables in the default address space.
llvm-svn: 182254
Introduction:
In case when stack alignment is 8 and GPRs parameter part size is not N*8:
we add padding to GPRs part, so part's last byte must be recovered at
address K*8-1.
We need to do it, since remained (stack) part of parameter starts from
address K*8, and we need to "attach" "GPRs head" without gaps to it:
Stack:
|---- 8 bytes block ----| |---- 8 bytes block ----| |---- 8 bytes...
[ [padding] [GPRs head] ] [ ------ Tail passed via stack ------ ...
FIX:
Note, once we added padding we need to correct *all* Arg offsets that are going
after padded one. That's why we need this fix: Arg offsets were never corrected
before this patch. See new test-cases included in patch.
We also don't need to insert padding for byval parameters that are stored in GPRs
only. We need pad only last byval parameter and only in case it outsides GPRs
and stack alignment = 8.
Though, stack area, allocated for recovered byval params, must satisfy
"Size mod 8 = 0" restriction.
This patch reduces stack usage for some cases:
We can reduce ArgRegsSaveArea since inner N*4 bytes sized byval params my be
"packed" with alignment 4 in some cases.
llvm-svn: 182237
The export list for this test requires the following symbols to be available:
JITTest_AvailableExternallyFunction
JITTest_AvailableExternallyGlobal
The change in r181200 commented them out, which caused the test to fail to
link, at least on Darwin. I have only reverted the change for arm, since I
can't test the other targets and since it sounds like that change was fixing
real problems for those other targets. It should be possible to rearrange the
code to keep those definitions outside the #ifdefs, but that should be done by
someone who can reproduce the problems that r181200 was trying to fix.
llvm-svn: 182233
This fixes a bootstrapping problem with builds for Apple ARM targets.
Clang had the wrong prototype for __clear_cache with ARM targets. Rafael
fixed that in clang svn r181784 and r181810, but without those changes,
we can't build this code for ARM because clang reports an error about the
declaration in Memory.inc not matching the builtin declaration. Some of our
buildbots need to use an older compiler that doesn't have the clang fix.
Since __clear_cache is never used here when __APPLE__ is defined, I'm just
conditionalizing the declaration to match that. I also moved the declaration
of sys_icache_invalidate inside the conditional for __APPLE__ while I was at
it.
llvm-svn: 182223
AArch64 ELF uses .rela relocations so there's no need to actually make
use of the bits we're setting in the destination However, we should
make sure all bits are cleared properly since multiple runs of
resolveRelocations are possible and these could combine to produce
invalid results if stale versions remain in the code.
llvm-svn: 182214
lli's remote MCJIT code calls setExecutable just prior to running
code. In line with Darwin behaviour this seems to be the place to
invalidate any caches needed so that relocations can take effect
properly.
llvm-svn: 182213
On 32-bit hosts %p can print garbage when given a uint64_t, we should
use %llx instead. This only affects the output of the debugging text
produced by lli.
llvm-svn: 182209
We don't need to reject all inline asm as using the counter register (most does
not). Only those that explicitly clobber the counter register need to prevent
the transformation.
llvm-svn: 182191
The peephole tries to reorder MOV32r0 instructions such that they are
before the instruction that modifies EFLAGS.
The problem is that the peephole does not consider the case where the
instruction that modifies EFLAGS also depends on the previous state of
EFLAGS.
Instead, walk backwards until we find an instruction that has a def for
EFLAGS but does not have a use.
If we find such an instruction, insert the MOV32r0 before it.
If it cannot find such an instruction, skip the optimization.
llvm-svn: 182184
This patch matches GCC behavior: the code used to only allow unaligned
load/store on ARM for v6+ Darwin, it will now allow unaligned load/store
for v6+ Darwin as well as for v7+ on Linux and NaCl.
The distinction is made because v6 doesn't guarantee support (but LLVM
assumes that Apple controls hardware+kernel and therefore have
conformant v6 CPUs), whereas v7 does provide this guarantee (and
Linux/NaCl behave sanely).
The patch keeps the -arm-strict-align command line option, and adds
-arm-no-strict-align. They behave similarly to GCC's -mstrict-align and
-mnostrict-align.
I originally encountered this discrepancy in FastIsel tests which expect
unaligned load/store generation. Overall this should slightly improve
performance in most cases because of reduced I$ pressure.
llvm-svn: 182175
The errors were:
non-constant-expression cannot be narrowed from type 'int64_t' (aka 'long') to 'uint32_t' (aka 'unsigned int') in initializer list
and
non-constant-expression cannot be narrowed from type 'long' to 'uint32_t' (aka 'unsigned int') in initializer list
llvm-svn: 182168
Dot4 now uses 8 scalar operands instead of 2 vectors one which allows register
coalescer to remove some unneeded COPY.
This patch also defines some structures/functions that can be used to handle
every vector instructions (CUBE, Cayman special instructions...) in a similar
fashion.
llvm-svn: 182126
Almost all instructions that takes a 128 bits reg as input (fetch, export...)
have the abilities to swizzle their argument and output. Instead of printing
default swizzle for each 128 bits reg, rename T*.XYZW to T* and let instructions
print potentially optimized swizzles themselves.
llvm-svn: 182124
Shuffles that only move an element into position 0 of the vector are common in
the output of the loop vectorizer and often generate suboptimal code when SSSE3
is not available. Lower them to vector shifts if possible.
We still prefer palignr over psrldq because it has higher throughput on
sandybridge.
llvm-svn: 182102
This patch implements the equivalent change to r182091/r182092
in the old-style code emitter. Instead of having two separate
16-bit immediate encoding routines depending on the instruction,
this patch introduces a single encoder that checks the machine
operand flags to decide whether the low or high half of a
symbol address is required.
Since now both encoders make no further distinction between
"symbolLo" and "symbolHi", the .td operand can now use a
single getS16ImmEncoding method.
Tested by running the old-style JIT tests on 32-bit Linux.
llvm-svn: 182097
Now that fixup_ppc_ha16 and fixup_ppc_lo16 are being treated exactly
the same everywhere, it no longer makes sense to have two fixup types.
This patch merges them both into a single type fixup_ppc_half16,
and renames fixup_ppc_lo16_ds to fixup_ppc_half16ds for consistency.
(The half16 and half16ds names are taken from the description of
relocation types in the PowerPC ABI.)
No change in code generation expected.
llvm-svn: 182092
The current PowerPC MC back end distinguishes between fixup_ppc_ha16
and fixup_ppc_lo16, which are determined by the instruction the fixup
applies to, and uses this distinction to decide whether a fixup ought
to resolve to the high or the low part of a symbol address.
This isn't quite correct, however. It is valid -if unusual- assembler
to use, e.g.
li 1, symbol@ha
or
lis 1, symbol@l
Whether the high or the low part of the address is used depends solely
on the @ suffix, not on the instruction.
In addition, both
li 1, symbol
and
lis 1, symbol
are valid, assuming the symbol address fits into 16 bits; again, both
will then refer to the actual symbol value (so li will load the value
itself, while lis will load the value shifted by 16).
To fix this, two places need to be adapted. If the fixup cannot be
resolved at assembler time, a relocation needs to be emitted via
PPCELFObjectWriter::getRelocType. This routine already looks at
the VK_ type to determine the relocation. The only problem is that
will reject any _LO modifier in a ha16 fixup and vice versa. This
is simply incorrect; any of those modifiers ought to be accepted
for either fixup type.
If the fixup *can* be resolved at assembler time, adjustFixupValue
currently selects the high bits of the symbol value if the fixup
type is ha16. Again, this is incorrect; see the above example
lis 1, symbol
Now, in theory we'd have to respect a VK_ modifier here. However,
in fact common code never even attempts to resolve symbol references
using any nontrivial VK_ modifier at assembler time; it will always
fall back to emitting a reloc and letting the linker handle it.
If this ever changes, presumably there'd have to be a target callback
to resolve VK_ modifiers. We'd then have to handle @ha etc. there.
llvm-svn: 182091
This is a candidate for the stable branch.
Fixes: https://bugs.freedesktop.org/show_bug.cgi?id=64694
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 182084
Previously, three instructions were needed:
trunc.w.s $f0, $f2
mfc1 $4, $f0
sw $4, 0($2)
Now we need only two:
trunc.w.s $f0, $f2
swc1 $f0, 0($2)
llvm-svn: 182053
This patch removes alias definition for addiu $rs,$imm
and instead uses the TwoOperandAliasConstraint field in
the ArithLogicI instruction class.
This way all instructions that inherit ArithLogicI class
have the same macro defined.
The usage examples are added to test files.
Patch by Vladimir Medic
llvm-svn: 182048
Some IR-level instructions (such as FP <-> i64 conversions) are not chained
w.r.t. the mtctr intrinsic and yet may become function calls that clobber the
counter register. At the selection-DAG level, these might be reordered with the
mtctr intrinsic causing miscompiles. To avoid this situation, if an existing
preheader has instructions that might use the counter register, create a new
preheader for the mtctr intrinsic. This extra block will be remerged with the
old preheader at the MI level, but will prevent unwanted reordering at the
selection-DAG level.
llvm-svn: 182045
invalid instruction sequence.
Rather than emitting an int-to-FP move instruction and an int-to-FP conversion
instruction during instruction selection, we emit a pseudo instruction which gets
expanded post-RA. Without this change, register allocation can possibly insert a
floating point register move instruction between the two instructions, which is not
valid according to the ISA manual.
mtc1 $f4, $4 # int-to-fp move instruction.
mov.s $f2, $f4 # move contents of $f4 to $f2.
cvt.s.w $f0, $f2 # int-to-fp conversion.
llvm-svn: 182042
This patch adds bnez and beqz instructions which represent alias definitions for bne and beq instructions as follows:
bnez $rs,$imm => bne $rs,$zero,$imm
beqz $rs,$imm => beq $rs,$zero,$imm
The corresponding test cases are added.
Patch by Vladimir Medic
llvm-svn: 182040
This lane mask provides information about which register lanes
completely cover super-registers. See the block comment before
getCoveringLanes().
llvm-svn: 182034
This is the second part of the change to always return "true"
offset values from getPreIndexedAddressParts, tackling the
case of "memrix" type operands.
This is about instructions like LD/STD that only have a 14-bit
field to encode immediate offsets, which are implicitly extended
by two zero bits by the machine, so that in effect we can access
16-bit offsets as long as they are a multiple of 4.
The PowerPC back end currently handles such instructions by
carrying the 14-bit value (as it will get encoded into the
actual machine instructions) in the machine operand fields
for such instructions. This means that those values are
in fact not the true offset, but rather the offset divided
by 4 (and then truncated to an unsigned 14-bit value).
Like in the case fixed in r182012, this makes common code
operations on such offset values not work as expected.
Furthermore, there doesn't really appear to be any strong
reason why we should encode machine operands this way.
This patch therefore changes the encoding of "memrix" type
machine operands to simply contain the "true" offset value
as a signed immediate value, while enforcing the rules that
it must fit in a 16-bit signed value and must also be a
multiple of 4.
This change must be made simultaneously in all places that
access machine operands of this type. However, just about
all those changes make the code simpler; in many cases we
can now just share the same code for memri and memrix
operands.
llvm-svn: 182032
While testing some experimental code to add vector-scalar registers to
PowerPC, I noticed that a couple of independent instructions were
flipped by the scheduler. The new CHECK-DAG support is perfect for
avoiding this problem.
llvm-svn: 182020
DAGCombiner::CombineToPreIndexedLoadStore calls a target routine to
decompose a memory address into a base/offset pair. It expects the
offset (if constant) to be the true displacement value in order to
perform optional additional optimizations; in particular, to convert
other uses of the original pointer into uses of the new base pointer
after pre-increment.
The PowerPC implementation of getPreIndexedAddressParts, however,
simply calls SelectAddressRegImm, which returns a TargetConstant.
This value is appropriate for encoding into the instruction, but
it is not always usable as true displacement value:
- Its type is always MVT::i32, even on 64-bit, where addresses
ought to be i64 ... this causes the optimization to simply
always fail on 64-bit due to this line in DAGCombiner:
// FIXME: In some cases, we can be smarter about this.
if (Op1.getValueType() != Offset.getValueType()) {
- Its value is truncated to an unsigned 16-bit value if negative.
This causes the above opimization to generate wrong code.
This patch fixes both problems by simply returning the true
displacement value (in its original type). This doesn't
affect any other user of the displacement.
llvm-svn: 182012
getExceptionHandlingType is not ExceptionHandling::DwarfCFI on xcore, so
etFrameInstructions is never called. There is no point creating cfi
instructions if they are never used.
llvm-svn: 181979
Without this change nothing was covering this addFrameMove:
// For 64-bit SVR4 when we have spilled CRs, the spill location
// is SP+8, not a frame-relative slot.
if (Subtarget.isSVR4ABI()
&& Subtarget.isPPC64()
&& (PPC::CR2 <= Reg && Reg <= PPC::CR4)) {
MachineLocation CSDst(PPC::X1, 8);
MachineLocation CSSrc(PPC::CR2);
MMI.addFrameMove(Label, CSDst, CSSrc);
continue;
}
llvm-svn: 181976
This creates stubs that help Mips32 functions call Mips16
functions which have floating point parameters that are normally passed
in floating point registers.
llvm-svn: 181972
We only want to check this once, not for every conditional block in the loop.
No functionality change (except that we don't perform a check redudantly
anymore).
llvm-svn: 181942
Increase the number of instructions LLVM recognizes as setting the ZF
flag. This allows us to remove test instructions that redundantly
recalculate the flag.
llvm-svn: 181937
The old PPCCTRLoops pass, like the Hexagon pass version from which it was
derived, could only handle some simple loops in canonical form. We cannot
directly adapt the new Hexagon hardware loops pass, however, because the
Hexagon pass contains a fundamental assumption that non-constant-trip-count
loops will contain a guard, and this is not always true (the result being that
incorrect negative counts can be generated). With this commit, we replace the
pass with a late IR-level pass which makes use of SE to calculate the
backedge-taken counts and safely generate the loop-count expressions (including
any necessary max() parts). This IR level pass inserts custom intrinsics that
are lowered into the desired decrement-and-branch instructions.
The most fragile part of this new implementation is that interfering uses of
the counter register must be detected on the IR level (and, on PPC, this also
includes any indirect branches in addition to function calls). Also, to make
all of this work, we need a variant of the mtctr instruction that is marked
as having side effects. Without this, machine-code level CSE, DCE, etc.
illegally transform the resulting code. Hopefully, this can be improved
in the future.
This new pass is smaller than the original (and much smaller than the new
Hexagon hardware loops pass), and can handle many additional cases correctly.
In addition, the preheader-creation code has been copied from LoopSimplify, and
after we decide on where it belongs, this code will be refactored so that it
can be explicitly shared (making this implementation even smaller).
The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for
the new Hexagon pass. There are a few classes of loops that this pass does not
transform (noted by FIXMEs in the files), but these deficiencies can be
addressed within the SE infrastructure (thus helping many other passes as well).
llvm-svn: 181927
If the input operands to SETCC are promoted, we need to make sure that we
either use the promoted form of both operands (or neither); a mixture is not
allowed. This can happen, for example, if a target has a custom promoted
i1-returning intrinsic (where i1 is not a legal type). In this case, we need to
use the promoted form of both operands.
This change only augments the behavior of the existing logic in the case where
the input types (which may or may not have already been legalized) disagree,
and should not affect existing target code because this case would otherwise
cause an assert in the SETCC operand promotion code.
This will be covered by (essentially all of the) tests for the new PPCCTRLoops
infrastructure.
llvm-svn: 181926
IR optimisation passes can result in a basic block that contains:
llvm.lifetime.start(%buf)
...
llvm.lifetime.end(%buf)
...
llvm.lifetime.start(%buf)
Before this change, calculateLiveIntervals() was ignoring the second
lifetime.start() and was regarding %buf as being dead from the
lifetime.end() through to the end of the basic block. This can cause
StackColoring to incorrectly merge %buf with another stack slot.
Fix by removing the incorrect Starts[pos].isValid() and
Finishes[pos].isValid() checks.
Just doing:
Starts[pos] = Indexes->getMBBStartIdx(MBB);
Finishes[pos] = Indexes->getMBBEndIdx(MBB);
unconditionally would be enough to fix the bug, but it causes some
test failures due to stack slots not being merged when they were
before. So, in order to keep the existing tests passing, treat LiveIn
and LiveOut separately rather than approximating the live ranges by
merging LiveIn and LiveOut.
This fixes PR15707.
Patch by Mark Seaborn.
llvm-svn: 181922
We want the order to be deterministic on all platforms. NAKAMURA Takumi
fixed that in r181864. This patch is just two small cleanups:
* Move the function to the cpp file. It is only passed to array_pod_sort.
* Remove the ppc implementation which is now redundant
llvm-svn: 181910
This patch matches GCC behavior: the code used to only allow unaligned
load/store on ARM for v6+ Darwin, it will now allow unaligned load/store for
v6+ Darwin as well as for v7+ on other targets.
The distinction is made because v6 doesn't guarantee support (but LLVM assumes
that Apple controls hardware+kernel and therefore have conformant v6 CPUs),
whereas v7 does provide this guarantee (and Linux behaves sanely).
Overall this should slightly improve performance in most cases because of
reduced I$ pressure.
Patch by JF Bastien
llvm-svn: 181897
Now that PowerPC no longer uses adjustFixupOffset, and no other
back-end (ever?) did, we can remove the infrastructure itself
(incidentally addressing a FIXME to that effect).
llvm-svn: 181895
Now that applyFixup understands differently-sized fixups, we can define
fixup_ppc_lo16/fixup_ppc_lo16_ds/fixup_ppc_ha16 to properly be 2-byte
fixups, applied at an offset of 2 relative to the start of the
instruction text.
This has the benefit that if we actually need to generate a real
relocation record, its address will come out correctly automatically,
without having to fiddle with the offset in adjustFixupOffset.
Tested on both 64-bit and 32-bit PowerPC, using external and
integrated assembler.
llvm-svn: 181894
The PPCAsmBackend::applyFixup routine handles the case where a
fixup can be resolved within the same object file. However,
this routine is currently hard-coded to assume the size of
any fixup is always exactly 4 bytes.
This is sort-of correct for fixups on instruction text; even
though it only works because several of what really would be
2-byte fixups are presented as 4-byte fixups instead (requiring
another hack in PPCELFObjectWriter::adjustFixupOffset to clean
it up).
However, this assumption breaks down completely for fixups
on data, which legitimately can be of any size (1, 2, 4, or 8).
This patch makes applyFixup aware of fixups of varying sizes,
introducing a new helper routine getFixupKindNumBytes (along
the lines of what the ARM back end does). Note that in order
to handle fixups of size 8, we also need to fix the return type
of adjustFixupValue to uint64_t to avoid truncation.
Tested on both 64-bit and 32-bit PowerPC, using external and
integrated assembler.
llvm-svn: 181891
BitVector/SmallBitVector::reference::operator bool remain implicit since
they model more exactly a bool, rather than something else that can be
boolean tested.
The most common (non-buggy) case are where such objects are used as
return expressions in bool-returning functions or as boolean function
arguments. In those cases I've used (& added if necessary) a named
function to provide the equivalent (or sometimes negative, depending on
convenient wording) test.
One behavior change (YAMLParser) was made, though no test case is
included as I'm not sure how to reach that code path. Essentially any
comparison of llvm::yaml::document_iterators would be invalid if neither
iterator was at the end.
This helped uncover a couple of bugs in Clang - test cases provided for
those in a separate commit along with similar changes to `operator bool`
instances in Clang.
llvm-svn: 181868
It should fix llvm/test/CodeGen/ARM/ehabi-mc-compact-pr*.ll on some hosts.
RELOCATION RECORDS FOR [.ARM.exidx]:
0 R_ARM_PREL31 .text
0 R_ARM_NONE __aeabi_unwind_cpp_pr0
FIXME: I am not sure of the directions of extra comparators, in Type and Index.
For now, they are different from the direction in r_offset.
llvm-svn: 181864
InstCombine can be uncooperative to vectorization and sink loads into
conditional blocks. This prevents vectorization.
Undo this optimization if there are unconditional memory accesses to the same
addresses in the loop.
radar://13815763
llvm-svn: 181860
This is expanding Ben's original heuristic for short basic blocks to
also work for longer basic blocks and huge use lists.
Scan the basic block and the use list in parallel, terminating the
search when the shorter list ends. In almost all cases, either the basic
block or the use list is short, and the function returns quickly.
In one crazy test case with very long use chains, CodeGenPrepare runs
400x faster. When compiling ARMDisassembler.cpp it is 5x faster.
<rdar://problem/13840497>
llvm-svn: 181851
There were two problems that made llvm-objdump -r crash:
- for non-scattered relocations, the symbol/section index is actually in the
(aptly named) symbolnum field.
- sections are 1-indexed.
llvm-svn: 181843
The transformation happening here is that we want to turn a
"mul(ext(X), ext(X))" into a "vmull(X, X)", stripping off the extension. We have
to make sure that X still has a valid vector type - possibly recreate an
extension to a smaller type. In case of a extload of a memory type smaller than
64 bit we used create a ext(load()). The problem with doing this - instead of
recreating an extload - is that an illegal type is exposed.
This patch fixes this by creating extloads instead of ext(load()) sequences.
Fixes PR15970.
radar://13871383
llvm-svn: 181842
CXAAtExitFn was set outside a loop and before optimizations where functions
can be deleted. This patch will set CXAAtExitFn inside the loop and after
optimizations.
Seg fault when running LTO because of accesses to a deleted function.
rdar://problem/13838828
llvm-svn: 181838