This is a band-aid to fix the most severe regressions we're seeing from basing
spill decisions on block frequencies, until we have a better solution.
llvm-svn: 184835
This makes it possible to write unit tests that are less susceptible
to minor code motion, particularly copy placement. block-placement.ll
covers this case with -pre-RA-sched=source which will soon be
default. One incorrectly named block is already fixed, but without
this fix, enabling new coalescing and scheduling would cause more
failures.
llvm-svn: 184680
We have no targets on trunk that bundle before regalloc. However, we
have been advertising regalloc as bundle safe for use with out-of-tree
targets. We need to at least contain the parts of the code that are
still unsafe.
llvm-svn: 184620
A FastISel optimization was causing us to emit no information for such
parameters & when they go missing we end up emitting a different
function type. By avoiding that shortcut we not only get types correct
(very important) but also location information (handy) - even if it's
only live at the start of a function & may be clobbered later.
Reviewed/discussion by Evan Cheng & Dan Gohman.
llvm-svn: 184604
Live intervals for dead physregs may be created during coalescing. We
need to update these in the event that their instruction goes away.
crash.ll is the unit test that catches it when MI sched is enabled on
X86.
llvm-svn: 184572
Fix up three tests - one that was relying on abbreviation number,
another relying on a location list in this case (& testing raw asm,
changed that to use dwarfdump on the debug_info now that that's where
the location is), and another which was added in r184368 - exposing a
bug in that fix that is exposed when we emit the location inline rather
than through a location list. Fix that bug while I'm here.
llvm-svn: 184387
We had been papering over a problem with location info for non-trivial
types passed by value by emitting their type as references (this caused
the debugger to interpret the location information correctly, but broke
the type of the function). r183329 corrected the type information but
lead to the debugger interpreting the pointer parameter as the value -
the debug info describing the location needed an extra dereference.
Use a new flag in DIVariable to add the extra indirection (either by
promoting an existing DW_OP_reg (parameter passed in a register) to
DW_OP_breg + 0 or by adding DW_OP_deref to an existing DW_OP_breg + n
(parameter passed on the stack).
llvm-svn: 184368
value is zero.
This allows optmizations to kick in more easily.
Fix some test cases so that they remain meaningful (i.e., not completely dead
coded) when optimizations apply.
<rdar://problem/14096009> superfluous multiply by high part of zero-extended
value.
llvm-svn: 184222
The main advantages here are way better heuristics, taking into account not
just loop depth but also __builtin_expect and other static heuristics and will
eventually learn how to use profile info. Most of the work in this patch is
pushing the MachineBlockFrequencyInfo analysis into the right places.
This is good for a 5% speedup on zlib's deflate (x86_64), there were some very
unfortunate spilling decisions in its hottest loop in longest_match(). Other
benchmarks I tried were mostly neutral.
This changes register allocation in subtle ways, update the tests for it.
2012-02-20-MachineCPBug.ll was deleted as it's very fragile and the instruction
it looked for was gone already (but the FileCheck pattern picked up unrelated
stuff).
llvm-svn: 184105
Frame index handling is now target-agnostic, so delete the target hooks
for creation & asm printing of target-specific addressing in DBG_VALUEs
and any related functions.
llvm-svn: 184067
Rather than using the full power of target-specific addressing modes in
DBG_VALUEs with Frame Indicies, simply use Frame Index + Offset. This
reduces the complexity of debug info handling down to two
representations of values (reg+offset and frame index+offset) rather
than three or four.
Ideally we could ensure that frame indicies had been eliminated by the
time we reached an assembly or dwarf generation, but I haven't spent the
time to figure out where the FIs are leaking through into that & whether
there's a good place to convert them. Some FI+offset=>reg+offset
conversion is done (see PrologEpilogInserter, for example) which is
necessary for some SelectionDAG assumptions about registers, I believe,
but it might be possible to make this a more thorough conversion &
ensure there are no remaining FIs no matter how instruction selection
is performed.
llvm-svn: 184066
Replace the ill-defined MinLatency and ILPWindow properties with
with straightforward buffer sizes:
MCSchedMode::MicroOpBufferSize
MCProcResourceDesc::BufferSize
These can be used to more precisely model instruction execution if desired.
Disabled some misched tests temporarily. They'll be reenabled in a few commits.
llvm-svn: 184032
"Counts" refer to scaled resource counts within a region. CurrMOps is
simply the number of micro-ops to be issue in the current cycle.
llvm-svn: 184031
Heuristics compare the critical path in the scheduled code, called
ExpectedLatency, with the latency of instructions remaining to be
scheduled. There are two ways to look at remaining latency:
(1) Dependent latency includes the latency between unscheduled and
scheduled instructions.
(2) Independent latency is simply the height (bottom-up) or depth
(top-down) of instructions currently in the ready Q.
llvm-svn: 184029
When we're rematerializing into a not-quite-right register we already add the
real definition as an imp-def, but we should also be marking the "official"
register as dead, since nothing else is going to use it as a result of this
remat.
Not doing this can affect pressure tracking.
rdar://problem/14158833
llvm-svn: 184002
in functions which call __builtin_unwind_init()
__builtin_unwind_init() is an undocumented gcc intrinsic which has this effect,
and is used in libgcc_eh.
Goes part of the way toward fixing PR8541.
llvm-svn: 183984
operator<< so that functions are printed as just their name instead of as their
entire definition, which is excessively verbose in this context.
llvm-svn: 183871
instantiation issue with non-standard type.
Add a backend option to warn on a given stack size limit.
Option: -mllvm -warn-stack-size=<limit>
Output (if limit is exceeded):
warning: Stack size limit exceeded (<actual size>) in <functionName>.
The longer term plan is to hook that to a clang warning.
PR:4072
<rdar://problem/13987214>.
llvm-svn: 183595
Option: -mllvm -warn-stack-size=<limit>
Output (if limit is exceeded):
warning: Stack size limit exceeded (<actual size>) in <functionName>.
The longer term plan is to hook that to a clang warning.
PR:4072
<rdar://problem/13987214>
llvm-svn: 183552
Fix an assertion when the compiler encounters big constants whose bit width is
not a multiple of 64-bits.
Although clang would never generate something like this, the backend should be
able to handle any legal IR.
<rdar://problem/13363576>
llvm-svn: 183544
OpenBSD's stack smashing protection differs slightly from other
platforms:
1. The smash handler function is "__stack_smash_handler(const char
*funcname)" instead of "__stack_chk_fail(void)".
2. There's a hidden "long __guard_local" object that gets linked
into each executable and DSO.
Patch by Matthew Dempsky.
llvm-svn: 183533
Seems we emit the parameter ordering number (spuriously named 'arg
number') in the debug info, so there's no need to search through the
variable list to figure out the parameter ordering. This implementation
does 'always' do the work, even in non-optimized debug info (the
previous implementation checked the existence of the 'variables' list on
the subprogram which is only present in optimized builds).
No intended functionality change.
llvm-svn: 183446
The TargetLoweringInfo object is owned by the TargetMachine. In the future, the
TargetMachine object may change, which may also change the TargetLoweringInfo
object.
llvm-svn: 183356
When a function is inlined we lazily construct the variables
representing the function's parameters. After that, we add any remaining
unused parameters.
If the function doesn't use all the parameters, or uses them out of
order, then the DWARF would produce them in that order, producing a
parameter order that doesn't match the source.
This fix causes us to always keep the arg variables at the start of the
variable list & in the original order from the source.
llvm-svn: 183297
(4.58s vs 3.2s on an oldish Mac Tower).
The corresponding src is excerpted bellow. The lopp accounts for about 90% of execution time.
--------------------
cat -n test-suite/MultiSource/Benchmarks/Olden/em3d/make_graph.c
90
91 for (k=0; k<j; k++)
92 if (other_node == cur_node->to_nodes[k]) break;
The defective layout is sketched bellow, where the two branches need to swap.
------------------------------------------------------------------------
L:
...
if (cond) goto out-of-loop
goto L
While this code sequence is defective, I don't understand why it incurs 1/3 of
execution time. CPU-event-profiling indicates the poor laoyout dose not increase
in br-misprediction; it dosen't increase stall cycle at all, and it dosen't
prevent the CPU detect the loop (i.e. Loop-Stream-Detector seems to be working fine
as well)...
The root cause of the problem is that the layout pass calls AnalyzeBranch()
with basic-block which is not updated to reflect its current layout.
rdar://13966341
llvm-svn: 183174
Account for the cost of scaling factor in Loop Strength Reduce when rating the
formulae. This uses a target hook.
The default implementation of the hook is: if the addressing mode is legal, the
scaling factor is free.
<rdar://problem/13806271>
llvm-svn: 183045
r182872 introduced a bug in how the register-coalescer's rematerialization
handled defining a physical register. It relied on the output of the
coalescer's setRegisters method to determine whether the replacement
instruction needed an implicit-def. However, this value isn't necessarily the
same as the CopyMI's actual destination register which is what the rest of the
basic-block expects us to be defining.
The commit changes the rematerializer to use the actual register attached to
CopyMI in its decision.
This will be tested soon by an X86 patch which moves everything to using
MOV32r0 instead of other sizes.
llvm-svn: 182925
Fixes PR16146: gdb.base__call-ar-st.exp fails after
pre-RA-sched=source fixes.
Patch by Xiaoyi Guo!
This also fixes an unsupported dbg.value test case. Codegen was
previously incorrect but the test was passing by luck.
llvm-svn: 182885
This allows rematerialization during register coalescing to handle
more cases involving operations like SUBREG_TO_REG which might need to
be rematerialized using sub-register indices.
For example, code like:
v1(GPR64):sub_32 = MOVZ something
v2(GPR64) = COPY v1(GPR64)
should be convertable to:
v2(GPR64):sub_32 = MOVZ something
but previously we just gave up in places like this
llvm-svn: 182872
Since the testing case uses ref_addr, which requires version 3+ to work,
we will solve the dwarf version issue first.
This patch also causes failures in one of the bots. I will update the patch
accordingly in my next attempt.
rdar://13926659
llvm-svn: 182867
from a different CU.
We used to print out an error message and fail to generate inlined_subroutine.
If we use ref_addr in the generated DWARF, the DWARF version should be 3 or
above.
rdar://13926659
llvm-svn: 182791
When -ffast-math is in effect (on Linux, at least), clang defines
__FINITE_MATH_ONLY__ > 0 when including <math.h>. This causes the
preprocessor to include <bits/math-finite.h>, which renames the sqrt functions.
For instance, "sqrt" is renamed as "__sqrt_finite".
This patch adds the 3 new names in such a way that they will be treated
as equivalent to their respective original names.
llvm-svn: 182739
Use a field in the SelectionDAGNode object to track its IR ordering.
This adds fields and utility classes without changing existing
interfaces or functionality.
llvm-svn: 182701
Now that the LiveDebugVariables pass is running *after* register
coalescing, the ConnectedVNInfoEqClasses class needs to deal with
DBG_VALUE instructions.
This only comes up when rematerialization during coalescing causes the
remaining live range of a virtual register to separate into two
connected components.
llvm-svn: 182592
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
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
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
This lane mask provides information about which register lanes
completely cover super-registers. See the block comment before
getCoveringLanes().
llvm-svn: 182034
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
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
The personality function is user defined and may have an arbitrary result type.
The code assumes always i8*. This results in an assertion failure if a different
type is used. A bitcast to i8* is added to prevent this failure.
Reviewed by: Renato Golin, Bob Wilson
llvm-svn: 181802
It was just a less powerful and more confusing version of
MCCFIInstruction. A side effect is that, since MCCFIInstruction uses
dwarf register numbers, calls to getDwarfRegNum are pushed out, which
should allow further simplifications.
I left the MachineModuleInfo::addFrameMove interface unchanged since
this patch was already fairly big.
llvm-svn: 181680
This is only tested for global variables at the moment (& includes tests
for the unnamed parameter case, since apparently this entire function
was completely untested previously)
llvm-svn: 181632
for constructors and destructors since the original declaration given
by the AT_specification both won't and can't.
Patch by Yacine Belkadi, I've cleaned up the testcases.
llvm-svn: 181471
This provides basic functionality for imported declarations. For
subprograms and types some amount of lazy construction is supported (so
the definition of a function can proceed the using declaration), but it
still doesn't handle declared-but-not-defined functions (since we don't
generally emit function declarations).
Variable support is really rudimentary at the moment - simply looking up
the existing definition with no support for out of order (declaration,
imported_module, then definition).
llvm-svn: 181392
DIBuilder::createImportedDeclaration isn't fully plumbed through (note,
lacking in AsmPrinter/DwarfDebug support) but this seemed like a
sufficiently useful division of code to make the subsequent patch(es)
easier to follow.
llvm-svn: 181364
Apparently we didn't keep an association of Compile Unit metadata nodes
to DIEs so looking up that parental context failed & thus caused no
DW_TAG_imported_modules to be emitted at the CU scope. Fix this by
adding the mapping & sure up the test case to verify this.
llvm-svn: 181339
Now even the small structures could be passed within byval (small enough
to be stored in GPRs).
In regression tests next function prototypes are checked:
PR15293:
%artz = type { i32 }
define void @foo(%artz* byval %s)
define void @foo2(%artz* byval %s, i32 %p, %artz* byval %s2)
foo: "s" stored in R0
foo2: "s" stored in R0, "s2" stored in R2.
Next AAPCS rules are checked:
5.5 Parameters Passing, C.4 and C.5,
"ParamSize" is parameter size in 32bit words:
-- NSAA != 0, NCRN < R4 and NCRN+ParamSize > R4.
Parameter should be sent to the stack; NCRN := R4.
-- NSAA != 0, and NCRN < R4, NCRN+ParamSize < R4.
Parameter stored in GPRs; NCRN += ParamSize.
llvm-svn: 181148
at all of the operands. Previously it was skipping over implicit operands which
cause infinite looping when the two-address pass try to reschedule a
two-address instruction below the kill of tied operand.
I'm unable to come up with a reasonably sized test case.
rdar://13747577
llvm-svn: 180906
the things, and renames it to CBindingWrapping.h. I also moved
CBindingWrapping.h into Support/.
This new file just contains the macros for defining different wrap/unwrap
methods.
The calls to those macros, as well as any custom wrap/unwrap definitions
(like for array of Values for example), are put into corresponding C++
headers.
Doing this required some #include surgery, since some .cpp files relied
on the fact that including Wrap.h implicitly caused the inclusion of a
bunch of other things.
This also now means that the C++ headers will include their corresponding
C API headers; for example Value.h must include llvm-c/Core.h. I think
this is harmless, since the C API headers contain just external function
declarations and some C types, so I don't believe there should be any
nasty dependency issues here.
llvm-svn: 180881
report a fatal error. This allows us to continue processing the translation
unit. Test case to come on the clang side because we need an inline asm
diagnostics handler in place.
rdar://13446483
llvm-svn: 180873
register-indirect address with an offset of 0.
It used to be that a DBG_VALUE is a register-indirect value if the offset
(operand 1) is nonzero. The new convention is that a DBG_VALUE is
register-indirect if the first operand is a register and the second
operand is an immediate. For plain registers use the combination reg, reg.
rdar://problem/13658587
llvm-svn: 180816
First, taking advantage of the fact that the virtual base registers are allocated in order of the local frame offsets, remove the quadratic register-searching behavior. Because of the ordering, we only need to check the last virtual base register created.
Second, store the frame index in the FrameRef structure, and get the frame index and the local offset from this structure at the top of the loop iteration. This allows us to de-nest the loops in insertFrameReferenceRegisters (and I think makes the code cleaner). I also moved the needsFrameBaseReg check into the first loop over instructions so that we don't bother pushing FrameRefs for instructions that don't want a virtual base register anyway.
Lastly, and this is the only functionality change, avoid the creation of single-use virtual base registers. These are currently not useful because, in general, they end up replacing what would be one r+r instruction with an add and a r+i instruction. Committing this removes the XFAIL in CodeGen/PowerPC/2007-09-07-LoadStoreIdxForms.ll
Jim has okayed this off-list.
llvm-svn: 180799
The `llvm.tls_init_funcs' (created by the front-end) holds pointers to the TLS
initialization functions. These need to be placed into the correct section so
that they are run before `main()'.
<rdar://problem/13733006>
llvm-svn: 180737
to determine whether or not we're on a darwin platform for debug code
emitting.
Solves the problem of a module with no triple on the command line
and no triple in the module using non-gdb ok features on darwin. Fix
up the member-pointers test to check the correct things for cross
platform (DW_FORM_flag is a good prefix).
Unfortunately no testcase because I have no ideas how to test something
without a triple and without a triple in the module yet check
precisely on two platforms. Ideas welcome.
llvm-svn: 180660
Clarify documentation and API to make the difference between register and
register-indirect addressed locations more explicit. Put in a comment
to point out that with the current implementation we cannot specify
a register-indirect location with offset 0 (a breg 0 in DWARF).
No functionality change intended.
rdar://problem/13658587
llvm-svn: 180641
This already helps SSE2 x86 a lot because it lacks an efficient way to
represent a vector select. The long term goal is to enable the backend to match
a canonicalized pattern into a single instruction (e.g. vabs or pabs).
llvm-svn: 180597
Summary:
This is modelled on the Mach-O linker options implementation and should
support a Clang implementation of #pragma comment(lib/linker).
Reviewers: rafael
CC: llvm-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D724
llvm-svn: 180569
Fixes PR15838. Need to check for blocks with nothing but dbg.value.
I'm not sure how to force this situation with a unit test. I tried to
reduce the test case in PR15838 (1k lines of metadata) but gave up.
llvm-svn: 180227
For now, we just reschedule instructions that use the copied vregs and
let regalloc elliminate it. I would really like to eliminate the
copies on-the-fly during scheduling, but we need a complete
implementation of repairIntervalsInRange() first.
The general strategy is for the register coalescer to eliminate as
many global copies as possible and shrink live ranges to be
extended-basic-block local. The coalescer should not have to worry
about resolving local copies (e.g. it shouldn't attemp to reorder
instructions). The scheduler is a much better place to deal with local
interference. The coalescer side of this equation needs work.
llvm-svn: 180193
When MachineScheduler is enabled, this functionality can be
removed. Until then, provide a way to disable it for test cases and
designing MachineScheduler heuristics.
llvm-svn: 180192
This exposed an issue with PowerPC AltiVec where it appears it was setting the wrong vector boolean contents. The included change
fixes the PowerPC tests, and was OK'd by Hal.
llvm-svn: 180129
1) Disallow 'returned' on parameter that is also 'sret' (no sensible semantics, as far as I can tell).
2) Conservatively disallow tail calls through 'returned' parameters that also are 'zext' or 'sext' (for consistency with treatment of other zero-extending and sign-extending operations in tail call position detection...can be revised later to handle situations that can be determined to be safe).
This is a new attribute that is not yet used, so there is no impact.
llvm-svn: 180118
This reverts commit r179840 with a fix to test/DebugInfo/two-cus-from-same-file.ll
I'm not sure why that test only failed on ARM & MIPS and not X86 Linux, even
though the debug info was clearly invalid on all of them, but this ought to fix
it.
llvm-svn: 179996
Rather than just splitting the input type and hoping for the best, apply
a bit more cleverness. Just splitting the types until the source is
legal often leads to an illegal result time, which is then widened and a
scalarization step is introduced which leads to truly horrible code
generation. With the loop vectorizer, these sorts of operations are much
more common, and so it's worth extra effort to do them well.
Add a legalization hook for the operands of a TRUNCATE node, which will
be encountered after the result type has been legalized, but if the
operand type is still illegal. If simple splitting of both types
ends up with the result type of each half still being legal, just
do that (v16i16 -> v16i8 on ARM, for example). If, however, that would
result in an illegal result type (v8i32 -> v8i8 on ARM, for example),
we can get more clever with power-two vectors. Specifically,
split the input type, but also widen the result element size, then
concatenate the halves and truncate again. For example on ARM,
To perform a "%res = v8i8 trunc v8i32 %in" we transform to:
%inlo = v4i32 extract_subvector %in, 0
%inhi = v4i32 extract_subvector %in, 4
%lo16 = v4i16 trunc v4i32 %inlo
%hi16 = v4i16 trunc v4i32 %inhi
%in16 = v8i16 concat_vectors v4i16 %lo16, v4i16 %hi16
%res = v8i8 trunc v8i16 %in16
This allows instruction selection to generate three VMOVN instructions
instead of a sequences of moves, stores and loads.
Update the ARMTargetTransformInfo to take this improved legalization
into account.
Consider the simplified IR:
define <16 x i8> @test1(<16 x i32>* %ap) {
%a = load <16 x i32>* %ap
%tmp = trunc <16 x i32> %a to <16 x i8>
ret <16 x i8> %tmp
}
define <8 x i8> @test2(<8 x i32>* %ap) {
%a = load <8 x i32>* %ap
%tmp = trunc <8 x i32> %a to <8 x i8>
ret <8 x i8> %tmp
}
Previously, we would generate the truly hideous:
.syntax unified
.section __TEXT,__text,regular,pure_instructions
.globl _test1
.align 2
_test1: @ @test1
@ BB#0:
push {r7}
mov r7, sp
sub sp, sp, #20
bic sp, sp, #7
add r1, r0, #48
add r2, r0, #32
vld1.64 {d24, d25}, [r0:128]
vld1.64 {d16, d17}, [r1:128]
vld1.64 {d18, d19}, [r2:128]
add r1, r0, #16
vmovn.i32 d22, q8
vld1.64 {d16, d17}, [r1:128]
vmovn.i32 d20, q9
vmovn.i32 d18, q12
vmov.u16 r0, d22[3]
strb r0, [sp, #15]
vmov.u16 r0, d22[2]
strb r0, [sp, #14]
vmov.u16 r0, d22[1]
strb r0, [sp, #13]
vmov.u16 r0, d22[0]
vmovn.i32 d16, q8
strb r0, [sp, #12]
vmov.u16 r0, d20[3]
strb r0, [sp, #11]
vmov.u16 r0, d20[2]
strb r0, [sp, #10]
vmov.u16 r0, d20[1]
strb r0, [sp, #9]
vmov.u16 r0, d20[0]
strb r0, [sp, #8]
vmov.u16 r0, d18[3]
strb r0, [sp, #3]
vmov.u16 r0, d18[2]
strb r0, [sp, #2]
vmov.u16 r0, d18[1]
strb r0, [sp, #1]
vmov.u16 r0, d18[0]
strb r0, [sp]
vmov.u16 r0, d16[3]
strb r0, [sp, #7]
vmov.u16 r0, d16[2]
strb r0, [sp, #6]
vmov.u16 r0, d16[1]
strb r0, [sp, #5]
vmov.u16 r0, d16[0]
strb r0, [sp, #4]
vldmia sp, {d16, d17}
vmov r0, r1, d16
vmov r2, r3, d17
mov sp, r7
pop {r7}
bx lr
.globl _test2
.align 2
_test2: @ @test2
@ BB#0:
push {r7}
mov r7, sp
sub sp, sp, #12
bic sp, sp, #7
vld1.64 {d16, d17}, [r0:128]
add r0, r0, #16
vld1.64 {d20, d21}, [r0:128]
vmovn.i32 d18, q8
vmov.u16 r0, d18[3]
vmovn.i32 d16, q10
strb r0, [sp, #3]
vmov.u16 r0, d18[2]
strb r0, [sp, #2]
vmov.u16 r0, d18[1]
strb r0, [sp, #1]
vmov.u16 r0, d18[0]
strb r0, [sp]
vmov.u16 r0, d16[3]
strb r0, [sp, #7]
vmov.u16 r0, d16[2]
strb r0, [sp, #6]
vmov.u16 r0, d16[1]
strb r0, [sp, #5]
vmov.u16 r0, d16[0]
strb r0, [sp, #4]
ldm sp, {r0, r1}
mov sp, r7
pop {r7}
bx lr
Now, however, we generate the much more straightforward:
.syntax unified
.section __TEXT,__text,regular,pure_instructions
.globl _test1
.align 2
_test1: @ @test1
@ BB#0:
add r1, r0, #48
add r2, r0, #32
vld1.64 {d20, d21}, [r0:128]
vld1.64 {d16, d17}, [r1:128]
add r1, r0, #16
vld1.64 {d18, d19}, [r2:128]
vld1.64 {d22, d23}, [r1:128]
vmovn.i32 d17, q8
vmovn.i32 d16, q9
vmovn.i32 d18, q10
vmovn.i32 d19, q11
vmovn.i16 d17, q8
vmovn.i16 d16, q9
vmov r0, r1, d16
vmov r2, r3, d17
bx lr
.globl _test2
.align 2
_test2: @ @test2
@ BB#0:
vld1.64 {d16, d17}, [r0:128]
add r0, r0, #16
vld1.64 {d18, d19}, [r0:128]
vmovn.i32 d16, q8
vmovn.i32 d17, q9
vmovn.i16 d16, q8
vmov r0, r1, d16
bx lr
llvm-svn: 179989
I think it's almost impossible to fold atomic fences profitably under
LLVM/C++11 semantics. As a result, this is now unused and just
cluttering up the target interface.
llvm-svn: 179940
Benjamin Kramer