llvm-6502/test/CodeGen/ARM
Evan Cheng 376642ed62 Some enhancements for memcpy / memset inline expansion.
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


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169791 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-10 23:21:26 +00:00
..
2006-11-10-CycleInDAG.ll
2007-01-19-InfiniteLoop.ll
2007-03-07-CombinerCrash.ll
2007-03-13-InstrSched.ll
2007-03-21-JoinIntervalsCrash.ll
2007-03-27-RegScavengerAssert.ll
2007-03-30-RegScavengerAssert.ll
2007-04-02-RegScavengerAssert.ll
2007-04-03-PEIBug.ll
2007-04-03-UndefinedSymbol.ll
2007-04-30-CombinerCrash.ll
2007-05-03-BadPostIndexedLd.ll
2007-05-07-tailmerge-1.ll
2007-05-09-tailmerge-2.ll
2007-05-14-InlineAsmCstCrash.ll
2007-05-14-RegScavengerAssert.ll
2007-05-22-tailmerge-3.ll
2007-05-23-BadPreIndexedStore.ll
2007-08-15-ReuseBug.ll
2008-02-04-LocalRegAllocBug.ll
2008-02-29-RegAllocLocal.ll
2008-03-05-SxtInRegBug.ll
2008-03-07-RegScavengerAssert.ll
2008-04-04-ScavengerAssert.ll
2008-04-10-ScavengerAssert.ll
2008-04-11-PHIofImpDef.ll
2008-05-19-LiveIntervalsBug.ll
2008-05-19-ScavengerAssert.ll
2008-07-17-Fdiv.ll
2008-07-24-CodeGenPrepCrash.ll
2008-08-07-AsmPrintBug.ll
2008-09-17-CoalescerBug.ll
2008-11-18-ScavengerAssert.ll
2009-02-16-SpillerBug.ll
2009-02-22-SoftenFloatVaArg.ll
2009-02-27-SpillerBug.ll
2009-03-07-SpillerBug.ll
2009-03-09-AddrModeBug.ll
2009-04-06-AsmModifier.ll
2009-04-08-AggregateAddr.ll
2009-04-08-FloatUndef.ll
2009-04-08-FREM.ll
2009-04-09-RegScavengerAsm.ll
2009-05-05-DAGCombineBug.ll
2009-05-07-RegAllocLocal.ll
2009-05-11-CodePlacementCrash.ll
2009-05-18-InlineAsmMem.ll
2009-06-02-ISelCrash.ll
2009-06-04-MissingLiveIn.ll
2009-06-15-RegScavengerAssert.ll
2009-06-19-RegScavengerAssert.ll
2009-06-22-CoalescerBug.ll
2009-06-30-RegScavengerAssert2.ll
2009-06-30-RegScavengerAssert3.ll
2009-06-30-RegScavengerAssert4.ll
2009-06-30-RegScavengerAssert5.ll
2009-06-30-RegScavengerAssert.ll
2009-07-01-CommuteBug.ll
2009-07-09-asm-p-constraint.ll
2009-07-18-RewriterBug.ll
2009-07-22-ScavengerAssert.ll
2009-07-22-SchedulerAssert.ll
2009-07-29-VFP3Registers.ll
2009-08-02-RegScavengerAssert-Neon.ll
2009-08-04-RegScavengerAssert-2.ll
2009-08-04-RegScavengerAssert.ll
2009-08-15-RegScavenger-EarlyClobber.ll
2009-08-15-RegScavengerAssert.ll
2009-08-21-PostRAKill2.ll
2009-08-21-PostRAKill3.ll
2009-08-21-PostRAKill.ll
2009-08-23-linkerprivate.ll
2009-08-26-ScalarToVector.ll
2009-08-27-ScalarToVector.ll
2009-08-29-ExtractEltf32.ll
2009-08-29-TooLongSplat.ll
2009-08-31-LSDA-Name.ll
2009-08-31-TwoRegShuffle.ll
2009-09-09-AllOnes.ll
2009-09-09-fpcmp-ole.ll
2009-09-10-postdec.ll
2009-09-13-InvalidSubreg.ll
2009-09-13-InvalidSuperReg.ll
2009-09-20-LiveIntervalsBug.ll
2009-09-21-LiveVariablesBug.ll
2009-09-22-LiveVariablesBug.ll
2009-09-23-LiveVariablesBug.ll
2009-09-24-spill-align.ll
2009-09-27-CoalescerBug.ll
2009-09-28-LdStOptiBug.ll
2009-10-02-NEONSubregsBug.ll
2009-10-16-Scope.ll
2009-10-21-InvalidFNeg.ll
2009-10-27-double-align.ll
2009-10-30.ll
2009-11-01-NeonMoves.ll
2009-11-02-NegativeLane.ll
2009-11-07-SubRegAsmPrinting.ll
2009-11-13-CoalescerCrash.ll
2009-11-13-ScavengerAssert2.ll
2009-11-13-ScavengerAssert.ll
2009-11-13-VRRewriterCrash.ll
2009-11-30-LiveVariablesBug.ll
2009-12-02-vtrn-undef.ll
2010-03-04-eabi-fp-spill.ll
2010-03-04-stm-undef-addr.ll
2010-03-18-ldm-rtrn.ll
2010-04-07-DbgValueOtherTargets.ll
2010-04-09-NeonSelect.ll
2010-04-13-v2f64SplitArg.ll
2010-04-14-SplitVector.ll
2010-04-15-ScavengerDebugValue.ll
2010-05-14-IllegalType.ll
2010-05-17-FastAllocCrash.ll
2010-05-18-LocalAllocCrash.ll
2010-05-18-PostIndexBug.ll
2010-05-19-Shuffles.ll
2010-05-20-NEONSpillCrash.ll
2010-05-21-BuildVector.ll
2010-06-11-vmovdrr-bitcast.ll
2010-06-21-LdStMultipleBug.ll
2010-06-21-nondarwin-tc.ll
2010-06-25-Thumb2ITInvalidIterator.ll
2010-06-29-PartialRedefFastAlloc.ll
2010-06-29-SubregImpDefs.ll
2010-07-26-GlobalMerge.ll
2010-08-04-EHCrash.ll
2010-08-04-StackVariable.ll
2010-09-21-OptCmpBug.ll
2010-09-29-mc-asm-header-test.ll
2010-10-19-mc-elf-objheader.ll
2010-10-25-ifcvt-ldm.ll
2010-11-15-SpillEarlyClobber.ll
2010-11-29-PrologueBug.ll
2010-11-30-reloc-movt.ll Added Mapping Symbols for ARM ELF 2012-12-07 16:50:23 +00:00
2010-12-07-PEIBug.ll
2010-12-08-tpsoft.ll
2010-12-15-elf-lcomm.ll
2010-12-17-LocalStackSlotCrash.ll
2011-01-19-MergedGlobalDbg.ll
2011-02-04-AntidepMultidef.ll
2011-02-07-AntidepClobber.ll
2011-03-10-DAGCombineCrash.ll
2011-03-15-LdStMultipleBug.ll
2011-03-23-PeepholeBug.ll
2011-04-07-schediv.ll
2011-04-11-MachineLICMBug.ll
2011-04-12-AlignBug.ll
2011-04-12-FastRegAlloc.ll
2011-04-15-AndVFlagPeepholeBug.ll
2011-04-15-RegisterCmpPeephole.ll
2011-04-26-SchedTweak.ll
2011-04-27-IfCvtBug.ll
2011-05-04-MultipleLandingPadSuccs.ll
2011-06-09-TailCallByVal.ll
2011-06-16-TailCallByVal.ll
2011-06-29-MergeGlobalsAlign.ll
2011-07-10-GlobalMergeBug.ll
2011-08-02-MergedGlobalDbg.ll
2011-08-12-vmovqqqq-pseudo.ll
2011-08-25-ldmia_ret.ll
2011-08-29-ldr_pre_imm.ll
2011-08-29-SchedCycle.ll
2011-09-09-OddVectorDivision.ll
2011-09-19-cpsr.ll
2011-09-28-CMovCombineBug.ll
2011-10-26-ExpandUnalignedLoadCrash.ll
2011-10-26-memset-inline.ll
2011-10-26-memset-with-neon.ll Some enhancements for memcpy / memset inline expansion. 2012-12-10 23:21:26 +00:00
2011-11-07-PromoteVectorLoadStore.ll
2011-11-09-BitcastVectorDouble.ll
2011-11-09-IllegalVectorFPIntConvert.ll
2011-11-14-EarlyClobber.ll
2011-11-28-DAGCombineBug.ll
2011-11-29-128bitArithmetics.ll
2011-11-30-MergeAlignment.ll
2011-12-14-machine-sink.ll
2011-12-19-sjlj-clobber.ll
2012-01-23-PostRA-LICM.ll
2012-01-24-RegSequenceLiveRange.ll
2012-01-26-CoalescerBug.ll
2012-01-26-CopyPropKills.ll
2012-02-01-CoalescerBug.ll
2012-03-05-FPSCR-bug.ll
2012-03-13-DAGCombineBug.ll
2012-03-26-FoldImmBug.ll
2012-04-02-TwoAddrInstrCrash.ll
2012-04-10-DAGCombine.ll
2012-04-24-SplitEHCriticalEdge.ll
2012-05-04-vmov.ll
2012-05-10-PreferVMOVtoVDUP32.ll
2012-05-29-TailDupBug.ll
2012-06-12-SchedMemLatency.ll
2012-08-04-DtripleSpillReload.ll
2012-08-08-legalize-unaligned.ll
2012-08-09-neon-extload.ll
2012-08-13-bfi.ll
2012-08-23-legalize-vmull.ll
2012-08-27-CopyPhysRegCrash.ll
2012-08-30-select.ll
2012-09-18-ARMv4ISelBug.ll
2012-09-25-InlineAsmScalarToVectorConv2.ll
2012-09-25-InlineAsmScalarToVectorConv.ll
2012-10-04-AAPCS-byval-align8.ll
2012-10-04-FixedFrame-vs-byval.ll
2012-10-04-LDRB_POST_IMM-Crash.ll
2012-10-18-PR14099-ByvalFrameAddress.ll
2012-11-14-subs_carry.ll
a15-mla.ll
a15.ll
addrmode.ll
aliases.ll
align.ll
alloc-no-stack-realign.ll
alloca.ll
argaddr.ll
arguments2.ll
arguments3.ll
arguments4.ll
arguments5.ll
arguments6.ll
arguments7.ll
arguments8.ll
arguments_f64_backfill.ll
arguments-nosplit-double.ll
arguments-nosplit-i64.ll
arguments.ll
arm-and-tst-peephole.ll
arm-asm.ll
arm-frameaddr.ll
arm-modifier.ll
arm-negative-stride.ll
arm-returnaddr.ll
arm-ttype-target2.ll
armv4.ll
atomic-64bit.ll
atomic-cmp.ll
atomic-load-store.ll
atomic-op.ll
atomicrmw_minmax.ll
available_externally.ll
avoid-cpsr-rmw.ll
bfc.ll
bfi.ll
bfx.ll
bic.ll
bicZext.ll
bits.ll
bswap-inline-asm.ll
bx_fold.ll
call_nolink.ll
call-noret-minsize.ll
call-noret.ll
call-tc.ll
call.ll
carry.ll
clz.ll
cmn.ll
coalesce-subregs.ll
code-placement.ll
commute-movcc.ll
compare-call.ll
constants.ll
crash-greedy-v6.ll
crash-greedy.ll
crash-O0.ll
crash-shufflevector.ll
crash.ll
cse-call.ll
cse-libcalls.ll
ctor_order.ll
ctors_dtors.ll
ctz.ll
dagcombine-anyexttozeroext.ll
darwin-section-order.ll
data-in-code-annotations.ll
debug-info-arg.ll
debug-info-blocks.ll
debug-info-branch-folding.ll Use the 'count' attribute to calculate the upper bound of an array. 2012-12-04 21:34:03 +00:00
debug-info-d16-reg.ll
debug-info-qreg.ll Use the 'count' attribute to calculate the upper bound of an array. 2012-12-04 21:34:03 +00:00
debug-info-s16-reg.ll
debug-info-sreg2.ll
deps-fix.ll
div.ll
divmod.ll
domain-conv-vmovs.ll Fix typos in CHECK lines. 2012-12-06 21:24:47 +00:00
dyn-stackalloc.ll
eh-resume-darwin.ll
ehabi-filters.ll
ehabi-no-landingpad.ll
ehabi-unwind.ll
elf-lcomm-align.ll
extload-knownzero.ll Properly fix the tes. 2012-12-06 02:29:29 +00:00
extloadi1.ll
fabs-neon.ll
fabss.ll
fadds.ll
fast-isel-binary.ll
fast-isel-br-const.ll
fast-isel-br-phi.ll
fast-isel-call-multi-reg-return.ll
fast-isel-call.ll
fast-isel-cmp-imm.ll
fast-isel-conversion.ll
fast-isel-crash2.ll
fast-isel-crash.ll
fast-isel-deadcode.ll
fast-isel-fold.ll
fast-isel-frameaddr.ll
fast-isel-GEP-coalesce.ll
fast-isel-icmp.ll
fast-isel-indirectbr.ll
fast-isel-intrinsic.ll [arm fast-isel] Make the fast-isel implementation of memcpy respect alignment. 2012-12-06 01:34:31 +00:00
fast-isel-ldr-str-arm.ll
fast-isel-ldr-str-thumb-neg-index.ll
fast-isel-ldrh-strh-arm.ll
fast-isel-mvn.ll
fast-isel-pic.ll
fast-isel-pred.ll
fast-isel-redefinition.ll
fast-isel-ret.ll
fast-isel-select.ll
fast-isel-shifter.ll
fast-isel-static.ll
fast-isel.ll
fcopysign.ll
fdivs.ll
fixunsdfdi.ll
flag-crash.ll
floorf.ll
fmacs.ll
fmdrr-fmrrd.ll
fmscs.ll
fmuls.ll
fnegs.ll
fnmacs.ll
fnmscs.ll
fnmul.ll
fnmuls.ll
fold-const.ll
formal.ll
fp16.ll
fp_convert.ll
fp-arg-shuffle.ll
fp-fast.ll
fp.ll
fparith.ll
fpcmp_ueq.ll
fpcmp-opt.ll
fpcmp.ll
fpconsts.ll
fpconv.ll
fpmem.ll
fpow.ll
fpowi.ll
fptoint.ll
fsubs.ll
fusedMAC.ll
global-merge.ll
globals.ll
gv-stubs-crash.ll
hardfloat_neon.ll
hello.ll
hidden-vis-2.ll
hidden-vis-3.ll
hidden-vis.ll
iabs.ll
ifcvt1.ll
ifcvt2.ll
ifcvt3.ll
ifcvt4.ll
ifcvt5.ll
ifcvt6.ll
ifcvt7.ll
ifcvt8.ll
ifcvt9.ll
ifcvt10.ll
ifcvt11.ll
ifcvt12.ll
illegal-vector-bitcast.ll
imm.ll
indirectbr-2.ll
indirectbr.ll
inlineasm2.ll
inlineasm3.ll
inlineasm4.ll
inlineasm-imm-arm.ll
inlineasm.ll
insn-sched1.ll
int-to-fp.ll
integer_insertelement.ll
intrinsics.ll
ispositive.ll
jumptable-label.ll
large-stack.ll
ldm.ll
ldr_ext.ll
ldr_frame.ll
ldr_post.ll
ldr_pre.ll
ldr.ll
ldrd-memoper.ll
ldrd.ll
ldst-f32-2-i32.ll
ldstrexd.ll
lit.local.cfg
load_i1_select.ll
load-global.ll
load.ll
log2_not_readnone.ll
long_shift.ll
long-setcc.ll
long.ll
longMAC.ll
lsr-code-insertion.ll
lsr-icmp-imm.ll
lsr-scale-addr-mode.ll
lsr-unfolded-offset.ll
machine-cse-cmp.ll
machine-licm.ll
mem.ll
memcpy-inline.ll Some enhancements for memcpy / memset inline expansion. 2012-12-10 23:21:26 +00:00
memfunc.ll
memset-inline.ll Some enhancements for memcpy / memset inline expansion. 2012-12-10 23:21:26 +00:00
mls.ll
movt-movw-global.ll
movt.ll
mul_const.ll
mul.ll
mulhi.ll
mult-alt-generic-arm.ll
mvn.ll
neon_arith1.ll
neon_div.ll
neon_fpconv.ll
neon_ld1.ll
neon_ld2.ll
neon_minmax.ll
neon_shift.ll
neon_spill.ll
neon-fma.ll
odr_comdat.ll
opt-shuff-tstore.ll
pack.ll
peephole-bitcast.ll
phi.ll
popcnt.ll ARM custom lower ctpop for vector types. Patch by Pete Couperus. 2012-12-04 22:41:50 +00:00
pr3502.ll
pr13249.ll
prefetch.ll
private.ll
reg_sequence.ll
ret0.ll
ret_arg1.ll
ret_arg2.ll
ret_arg3.ll
ret_arg4.ll
ret_arg5.ll
ret_f32_arg2.ll
ret_f32_arg5.ll
ret_f64_arg2.ll
ret_f64_arg_reg_split.ll
ret_f64_arg_split.ll
ret_f64_arg_stack.ll
ret_i64_arg2.ll
ret_i64_arg3.ll
ret_i64_arg_split.ll
ret_i128_arg2.ll
ret_sret_vector.ll
ret_void.ll
rev.ll
sbfx.ll
section.ll
select_xform.ll
select-imm.ll
select.ll
shifter_operand.ll
shuffle.ll
smml.ll
smul.ll
spill-q.ll
stack-frame.ll
stm.ll
str_post.ll
str_pre-2.ll
str_pre.ll
str_trunc.ll
struct_byval.ll
sub-cmp-peephole.ll
sub.ll
subreg-remat.ll
sxt_rot.ll
t2-imm.ll
tail-dup.ll
tail-opts.ll
test-sharedidx.ll
thread_pointer.ll
thumb1-varalloc.ll
thumb2-it-block.ll
tls1.ll
tls2.ll
tls3.ll
tls-models.ll
trap.ll
trunc_ldr.ll
truncstore-dag-combine.ll
tst_teq.ll
twoaddrinstr.ll
uint64tof64.ll
umulo-32.ll
unaligned_load_store_vector.ll
unaligned_load_store.ll
undef-sext.ll
unord.ll
unsafe-fsub.ll
uxt_rot.ll
uxtb.ll
va_arg.ll
vaba.ll
vabd.ll
vabs.ll
vadd.ll
vargs_align.ll
vargs.ll
vbits.ll
vbsl-constant.ll
vbsl.ll
vceq.ll
vcge.ll
vcgt.ll
vcnt.ll
vcombine.ll
vcvt_combine.ll
vcvt.ll
vdiv_combine.ll
vdup.ll
vector-DAGCombine.ll
vector-extend-narrow.ll
vext.ll
vfcmp.ll
vfp.ll
vget_lane.ll
vhadd.ll
vhsub.ll
vicmp.ll
vld1.ll
vld2.ll
vld3.ll
vld4.ll
vlddup.ll
vldlane.ll
vminmax.ll
vmla.ll
vmls.ll
vmov.ll
vmul.ll
vneg.ll
vpadal.ll
vpadd.ll
vpminmax.ll
vqadd.ll
vqdmul.ll
vqshl.ll
vqshrn.ll
vqsub.ll
vrec.ll
vrev.ll
vselect_imax.ll
vshift.ll
vshiftins.ll
vshl.ll
vshll.ll
vshrn.ll
vsra.ll
vst1.ll
vst2.ll
vst3.ll
vst4.ll
vstlane.ll
vsub.ll
vtbl.ll
vtrn.ll
vuzp.ll
vzip.ll
weak2.ll
weak.ll
widen-vmovs.ll