1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 19:52:54 +01:00
llvm-mirror/test/CodeGen/X86
Dan Gohman 281881b8e2 Optimized FCMP_OEQ and FCMP_UNE for x86.
Where previously LLVM might emit code like this:

        ucomisd %xmm1, %xmm0
        setne   %al
        setp    %cl
        orb     %al, %cl
        jne     .LBB4_2

it now emits this:

        ucomisd %xmm1, %xmm0
        jne     .LBB4_2
        jp      .LBB4_2

It has fewer instructions and uses fewer registers, but it does
have more branches. And in the case that this code is followed by
a non-fallthrough edge, it may be followed by a jmp instruction,
resulting in three branch instructions in sequence. Some effort
is made to avoid this situation.

To achieve this, X86ISelLowering.cpp now recognizes FCMP_OEQ and
FCMP_UNE in lowered form, and replace them with code that emits
two branches, except in the case where it would require converting
a fall-through edge to an explicit branch.

Also, X86InstrInfo.cpp's branch analysis and transform code now
knows now to handle blocks with multiple conditional branches. It
uses loops instead of having fixed checks for up to two
instructions. It can now analyze and transform code generated
from FCMP_OEQ and FCMP_UNE.

llvm-svn: 57873
2008-10-21 03:29:32 +00:00
..
2002-12-23-LocalRAProblem.ll
2002-12-23-SubProblem.ll
2003-08-03-CallArgLiveRanges.ll
2003-08-23-DeadBlockTest.ll
2003-11-03-GlobalBool.ll
2004-02-12-Memcpy.ll
2004-02-13-FrameReturnAddress.ll
2004-02-14-InefficientStackPointer.ll
2004-02-22-Casts.ll
2004-03-30-Select-Max.ll
2004-04-09-SameValueCoalescing.ll
2004-04-13-FPCMOV-Crash.ll
2004-06-10-StackifierCrash.ll
2004-10-08-SelectSetCCFold.ll
2005-01-17-CycleInDAG.ll
2005-02-14-IllegalAssembler.ll
2005-05-08-FPStackifierPHI.ll
2006-01-19-ISelFoldingBug.ll
2006-03-01-InstrSchedBug.ll
2006-03-02-InstrSchedBug.ll
2006-04-04-CrossBlockCrash.ll
2006-04-27-ISelFoldingBug.ll
2006-05-01-SchedCausingSpills.ll
2006-05-02-InstrSched1.ll
2006-05-02-InstrSched2.ll
2006-05-08-CoalesceSubRegClass.ll
2006-05-08-InstrSched.ll
2006-05-11-InstrSched.ll
2006-05-17-VectorArg.ll
2006-05-22-FPSetEQ.ll
2006-05-25-CycleInDAG.ll
2006-07-10-InlineAsmAConstraint.ll
2006-07-12-InlineAsmQConstraint.ll
2006-07-19-ATTAsm.ll
2006-07-20-InlineAsm.ll
2006-07-28-AsmPrint-Long-As-Pointer.ll
2006-07-31-SingleRegClass.ll
2006-08-07-CycleInDAG.ll
2006-08-16-CycleInDAG.ll
2006-08-21-ExtraMovInst.ll
2006-09-01-CycleInDAG.ll
2006-10-02-BoolRetCrash.ll
2006-10-07-ScalarSSEMiscompile.ll
2006-10-09-CycleInDAG.ll
2006-10-10-FindModifiedNodeSlotBug.ll
2006-10-12-CycleInDAG.ll
2006-10-13-CycleInDAG.ll
2006-10-19-SwitchUnnecessaryBranching.ll
2006-11-12-CSRetCC.ll
2006-11-17-IllegalMove.ll
2006-11-27-SelectLegalize.ll
2006-11-28-Memcpy.ll
2006-12-19-IntelSyntax.ll
2007-01-08-InstrSched.ll
2007-01-13-StackPtrIndex.ll
2007-01-29-InlineAsm-ir.ll
2007-02-04-OrAddrMode.ll
2007-02-19-LiveIntervalAssert.ll
2007-02-25-FastCCStack.ll
2007-03-01-SpillerCrash.ll
2007-03-15-GEP-Idx-Sink.ll
2007-03-16-InlineAsm.ll
2007-03-18-LiveIntervalAssert.ll
2007-03-24-InlineAsmMultiRegConstraint.ll
2007-03-24-InlineAsmPModifier.ll
2007-03-24-InlineAsmVectorOp.ll
2007-03-24-InlineAsmXConstraint.ll
2007-03-26-CoalescerBug.ll
2007-04-08-InlineAsmCrash.ll
2007-04-11-InlineAsmVectorResult.ll
2007-04-17-LiveIntervalAssert.ll
2007-04-24-Huge-Stack.ll
2007-04-24-VectorCrash.ll
2007-04-25-MMX-PADDQ.ll
2007-04-27-InlineAsm-IntMemInput.ll
2007-05-05-VecCastExpand.ll
2007-05-07-InvokeSRet.ll
2007-05-14-LiveIntervalAssert.ll
2007-05-15-maskmovq.ll
2007-05-17-ShuffleISelBug.ll
2007-06-04-tailmerge4.ll
2007-06-04-X86-64-CtorAsmBugs.ll
2007-06-05-LSR-Dominator.ll
2007-06-14-branchfold.ll
2007-06-15-IntToMMX.ll
2007-06-28-X86-64-isel.ll
2007-06-29-DAGCombinerBug.ll
2007-06-29-VecFPConstantCSEBug.ll
2007-07-03-GR64ToVR64.ll
2007-07-10-StackerAssert.ll
2007-07-18-Vector-Extract.ll
2007-08-01-LiveVariablesBug.ll
2007-08-09-IllegalX86-64Asm.ll
2007-08-10-SignExtSubreg.ll
2007-08-13-AppendingLinkage.ll
2007-08-13-SpillerReuse.ll
2007-09-03-X86-64-EhSelector.ll
2007-09-05-InvalidAsm.ll
2007-09-06-ExtWeakAliasee.ll
2007-09-17-ObjcFrameEH.ll
2007-09-18-ShuffleXformBug.ll
2007-09-27-LDIntrinsics.ll
2007-10-04-AvoidEFLAGSCopy.ll
2007-10-05-3AddrConvert.ll
2007-10-12-CoalesceExtSubReg.ll
2007-10-12-SpillerUnfold1.ll
2007-10-12-SpillerUnfold2.ll
2007-10-14-CoalescerCrash.ll
2007-10-15-CoalescerCrash.ll
2007-10-16-CoalescerCrash.ll
2007-10-16-fp80_select.ll
2007-10-16-IllegalAsm.ll
2007-10-17-IllegalAsm.ll
2007-10-19-SpillerUnfold.ll
2007-10-28-inlineasm-q-modifier.ll
2007-10-29-ExtendSetCC.ll
2007-10-30-LSRCrash.ll
2007-10-31-extractelement-i64.ll
2007-11-01-ISelCrash.ll
2007-11-02-BadAsm.ll
2007-11-03-x86-64-q-constraint.ll
2007-11-04-LiveIntervalCrash.ll
2007-11-04-LiveVariablesBug.ll
2007-11-04-rip-immediate-constant.ll
2007-11-06-InstrSched.ll
2007-11-07-MulBy4.ll
2007-11-14-Coalescer-Bug.ll
2007-11-30-LoadFolding-Bug.ll
2007-11-30-TestLoadFolding.ll
2007-12-11-FoldImpDefSpill.ll
2007-12-16-BURRSchedCrash.ll
2007-12-18-LoadCSEBug.ll
2008-01-08-IllegalCMP.ll
2008-01-08-SchedulerCrash.ll
2008-01-09-LongDoubleSin.ll
2008-01-16-FPStackifierAssert.ll
2008-01-16-InvalidDAGCombineXform.ll
2008-01-16-Trampoline.ll
2008-01-25-EmptyFunction.ll
2008-02-05-ISelCrash.ll
2008-02-06-LoadFoldingBug.ll
2008-02-08-LoadFoldingBug.ll
2008-02-14-BitMiscompile.ll
2008-02-18-TailMergingBug.ll
2008-02-20-InlineAsmClobber.ll
2008-02-22-LocalRegAllocBug.ll
2008-02-22-ReMatBug.ll
2008-02-25-InlineAsmBug.ll
2008-02-25-X86-64-CoalescerBug.ll
2008-02-26-AsmDirectMemOp.ll
2008-02-27-DeadSlotElimBug.ll
2008-02-27-PEICrash.ll
2008-03-06-frem-fpstack.ll
2008-03-07-APIntBug.ll
2008-03-10-RegAllocInfLoop.ll
2008-03-12-ThreadLocalAlias.ll
2008-03-13-TwoAddrPassCrash.ll
2008-03-14-SpillerCrash.ll
2008-03-18-CoalescerBug.ll
2008-03-19-DAGCombinerBug.ll
2008-03-23-DarwinAsmComments.ll
2008-03-25-TwoAddrPassBug.ll
2008-03-31-SpillerFoldingBug.ll
2008-04-02-unnamedEH.ll
2008-04-08-CoalescerCrash.ll
2008-04-09-BranchFolding.ll
2008-04-15-LiveVariableBug.ll
2008-04-16-CoalescerBug.ll
2008-04-16-ReMatBug.ll
2008-04-17-CoalescerBug.ll
2008-04-24-MemCpyBug.ll
2008-04-24-pblendw-fold-crash.ll
2008-04-26-Asm-Optimize-Imm.ll
2008-04-28-CoalescerBug.ll
2008-04-28-CyclicSchedUnit.ll
2008-05-01-InvalidOrdCompare.ll
2008-05-06-SpillerBug.ll
2008-05-09-PHIElimBug.ll
2008-05-09-ShuffleLoweringBug.ll
2008-05-12-tailmerge-5.ll
2008-05-21-CoalescerBug.ll Remove -disable-fast-isel. Use cl::boolOrDefault with -fast-isel 2008-10-07 23:00:56 +00:00
2008-05-22-FoldUnalignedLoad.ll
2008-05-28-CoalescerBug.ll
2008-05-28-LocalRegAllocBug.ll
2008-06-04-MemCpyLoweringBug.ll
2008-06-13-NotVolatileLoadStore.ll
2008-06-13-VolatileLoadStore.ll
2008-06-16-SubregsBug.ll
2008-06-18-BadShuffle.ll
2008-06-25-VecISelBug.ll
2008-07-07-DanglingDeadInsts.ll
2008-07-09-ELFSectionAttributes.ll
2008-07-11-SHLBy1.ll
2008-07-11-SpillerBug.ll
2008-07-16-CoalescerCrash.ll
2008-07-19-movups-spills.ll
2008-07-22-CombinerCrash.ll
2008-07-23-VSetCC.ll
2008-08-05-SpillerBug.ll
2008-08-06-RewriterBug.ll
2008-08-17-UComiCodeGenBug.ll
2008-08-19-SubAndFetch.ll
2008-08-23-64Bit-maskmovq.ll
2008-08-23-X86-64AsmBug.ll
2008-08-25-AsmRegTypeMismatch.ll
2008-08-31-EH_RETURN32.ll
2008-08-31-EH_RETURN64.ll
2008-09-05-sinttofp-2xi32.ll
2008-09-09-LinearScanBug.ll
2008-09-10-SpillerBug2.ll
2008-09-11-CoalescerBug2.ll
2008-09-11-CoalescerBug.ll
2008-09-17-inline-asm-1.ll
2008-09-18-inline-asm-2.ll
2008-09-19-RegAllocBug.ll
2008-09-25-sseregparm-1.ll
2008-09-26-FrameAddrBug.ll
2008-09-29-ReMatBug.ll
2008-09-29-VolatileBug.ll
2008-10-02-Atomics32-2.ll
2008-10-06-MMXISelBug.ll
2008-10-06-x87ld-nan-1.ll
2008-10-06-x87ld-nan-2.ll
2008-10-07-SSEISelBug.ll
2008-10-11-CallCrash.ll Change CALLSEQ_BEGIN and CALLSEQ_END to take TargetConstant's as 2008-10-11 22:08:30 +00:00
2008-10-13-CoalescerBug.ll Also update sub-register intervals after a trivial computation is rematt'ed for a copy instruction. PR2775. 2008-10-13 18:35:52 +00:00
2008-10-16-SpillerBug.ll Fix a very subtle spiller bug: UpdateKills should not forget to track defs of aliases. 2008-10-17 06:16:07 +00:00
2008-10-16-VecUnaryOp.ll Testcase for PR2762. 2008-10-16 08:56:46 +00:00
2008-10-17-Asm64bitRConstraint.ll Fix a bug where the x86 backend would reject 64-bit r constraints when 2008-10-17 17:59:52 +00:00
2008-10-17-SpillerBug.ll Fix PR2898. Spiller delete a store for reuse before it knows for sure the reuse happened. 2008-10-17 20:56:41 +00:00
2008-10-20-AsmDoubleInI32.ll Fix gcc.c-torture/compile/920520-1.c by inserting bitconverts 2008-10-21 00:45:36 +00:00
add-trick32.ll Fun x86 encoding tricks: when adding an immediate value of 128, 2008-10-17 01:33:43 +00:00
add-trick64.ll Fun x86 encoding tricks: when adding an immediate value of 128, 2008-10-17 01:33:43 +00:00
aliases.ll
aligned-comm.ll
all-ones-vector.ll
alloca-align-rounding.ll
and-or-fold.ll
arg-cast.ll
asm-block-labels.ll
asm-global-imm.ll
asm-indirect-mem.ll
atomic_op.ll
Atomics-32.ll
Atomics-64.ll
bitcast2.ll
bitcast-int-to-vector.ll
bitcast.ll
bswap.ll
byval2.ll
byval3.ll
byval4.ll
byval5.ll
byval6.ll
byval7.ll
byval.ll
call-push.ll
clz.ll
cmp0.ll
cmp1.ll
cmp2.ll
cmp-test.ll
coalescer-commute1.ll
coalescer-commute2.ll
coalescer-commute3.ll
coalescer-commute4.ll
coalescer-commute5.ll
coalescer-remat.ll
combine-lds.ll
commute-intrinsic.ll
commute-two-addr.ll
compare_folding.ll
compare-add.ll
complex-fca.ll Add a test case for _Complex passed as a FCA. 2008-10-13 18:13:07 +00:00
constant-pool-remat-0.ll
copysign-zero.ll
dagcombine-cse.ll
darwin-bzero.ll
darwin-no-dead-strip.ll
darwin-stub.ll
dg.exp
div_const.ll
divrem.ll
dollar-name.ll
dyn-stackalloc.ll
epilogue.ll
extend.ll
extern_weak.ll
extmul64.ll
extmul128.ll
extractelement-from-arg.ll
extractelement-load.ll
extractps.ll Fix this test so it actually runs the grep lines. 2008-10-16 23:57:54 +00:00
fabs.ll
fast-cc-callee-pops.ll
fast-cc-merge-stack-adj.ll
fast-cc-pass-in-regs.ll
fast-isel-call.ll
fast-isel-mem.ll
fast-isel-phys.ll
fast-isel-trunc.ll
fast-isel.ll
fastcall-correct-mangling.ll
fastcc-2.ll
fastcc-sret.ll
fastcc.ll
field-extract-use-trunc.ll
fildll.ll
fold-and-shift.ll
fold-call-2.ll
fold-call.ll
fold-load.ll
fold-mul-lohi.ll
fp2sint.ll
fp_constant_op.ll
fp_load_cast_fold.ll
fp_load_fold.ll
fp-immediate-shorten.ll
fp-in-intregs.ll
fp-stack-2results.ll
fp-stack-compare.ll
fp-stack-direct-ret.ll
fp-stack-ret-conv.ll
fp-stack-ret-store.ll
fp-stack-ret.ll
fp-stack-retcopy.ll
fsxor-alignment.ll
ga-offset.ll Teach DAGCombine to fold constant offsets into GlobalAddress nodes, 2008-10-18 02:06:02 +00:00
hidden-vis.ll
i128-and-beyond.ll
i128-immediate.ll
i128-mul.ll
i128-ret.ll
i256-add.ll
iabs.ll
illegal-insert.ll
illegal-vector-args-return.ll
imp-def-copies.ll
imul-lea.ll
inline-asm-fpstack.ll
inline-asm-mrv.ll
inline-asm-pic.ll
inline-asm-x-scalar.ll
inline-asm.ll
ins_subreg_coalesce-1.ll
ins_subreg_coalesce-2.ll
ins_subreg_coalesce-3.ll
insertelement-copytoregs.ll
invalid-shift-immediate.ll
isel-sink.ll
isint.ll Optimized FCMP_OEQ and FCMP_UNE for x86. 2008-10-21 03:29:32 +00:00
isnan2.ll
isnan.ll
ispositive.ll
jump_sign.ll
ldzero.ll
lea-2.ll
lea-3.ll
lea-recursion.ll
lea.ll
lfence.ll
local-liveness.ll
long-setcc.ll
longlong-deadload.ll
loop-hoist.ll
loop-strength-reduce2.ll
loop-strength-reduce3.ll
loop-strength-reduce4.ll
loop-strength-reduce5.ll
loop-strength-reduce6.ll
loop-strength-reduce.ll
lsr-negative-stride.ll
memcpy-2.ll
memcpy.ll
memmove-0.ll
memmove-1.ll
memmove-2.ll
memmove-3.ll
memmove-4.ll
memset64-on-x86-32.ll
memset-2.ll
memset.ll
mfence.ll
mingw-alloca.ll
mmx-arg-passing2.ll
mmx-arg-passing.ll
mmx-arith.ll
mmx-bitcast-to-i64.ll
mmx-copy-gprs.ll
mmx-emms.ll
mmx-insert-element.ll
mmx-pinsrw.ll
mmx-punpckhdq.ll
mmx-s2v.ll
mmx-shift.ll
mmx-shuffle.ll
mul64.ll
mul128.ll
mul-legalize.ll
mul-remat.ll
mul-shift-reassoc.ll
multiple-return-values-cross-block.ll
multiple-return-values.ll
nancvt.ll
negative_zero.ll
negative-sin.ll
nofence.ll
opt-ext-uses.ll
optimize-smax.ll
or-branch.ll
overlap-shift.ll
packed_struct.ll
peep-vector-extract-concat.ll
peep-vector-extract-insert.ll
pic_jumptable.ll
pic-1.ll
pic-2.ll
pic-3.ll
pic-4.ll
pic-5.ll
pic-6.ll
pic-cpool.ll
pic-jtbl.ll
pic-load-remat.ll
pmul.ll
postalloc-coalescing.ll
pr1462.ll
pr1489.ll
pr1505.ll
pr1505b.ll
pr2177.ll
pr2182.ll
pr2326.ll
pr2623.ll
pr2656.ll
pr2849.ll When doing the very-late shift-and address-mode optimization, 2008-10-13 20:52:04 +00:00
prefetch.ll
rdtsc.ll
regpressure.ll
rem.ll
remat-constant.ll
remat-mov0.ll
ret-i64-0.ll When the coalescer is doing rematerializing, have it remove 2008-10-21 03:24:31 +00:00
rot16.ll Define patterns for shld and shrd that match immediate 2008-10-17 01:23:35 +00:00
rot32.ll Define patterns for shld and shrd that match immediate 2008-10-17 01:23:35 +00:00
rot64.ll Define patterns for shld and shrd that match immediate 2008-10-17 01:23:35 +00:00
rotate2.ll
rotate.ll
scalar_sse_minmax.ll
scalar-min-max-fill-operand.ll
select-zero-one.ll
select.ll
setoeq.ll - Add target lowering hooks that specify which setcc conditions are illegal, 2008-10-15 02:05:31 +00:00
setuge.ll
sext-load.ll
sext-select.ll
sext-trunc.ll
sfence.ll
shift-and.ll
shift-coalesce.ll
shift-codegen.ll
shift-combine.ll
shift-double.ll
shift-folding.ll
shift-one.ll
shl_elim.ll
shrink-fp-const1.ll
shrink-fp-const2.ll
sincos.ll
small-byval-memcpy.ll
split-select.ll
split-vector-rem.ll
sret.ll
sse41-extractps-bitcast-0.ll
sse41-extractps-bitcast-1.ll
sse41-pmovx.ll
sse_reload_fold.ll
sse-align-0.ll
sse-align-1.ll
sse-align-2.ll
sse-align-3.ll
sse-align-4.ll
sse-align-5.ll
sse-align-6.ll
sse-align-7.ll
sse-align-8.ll
sse-align-9.ll
sse-align-10.ll
sse-align-11.ll
sse-align-12.ll
sse-fcopysign.ll
sse-load-ret.ll
sse-varargs.ll
stack-align.ll
store_op_load_fold2.ll
store_op_load_fold.ll
store-fp-constant.ll
store-global-address.ll
storetrunc-fp.ll
stride-nine-with-base-reg.ll
stride-reuse.ll
subclass-coalesce.ll
subreg-to-reg-0.ll
subreg-to-reg-1.ll
tailcall1.ll
tailcall-stackalign.ll
tailcallbyval64.ll
tailcallbyval.ll
tailcallfp2.ll
tailcallfp.ll
tailcallpic1.ll
tailcallpic2.ll
tailcallstack64.ll
test-nofold.ll
tls1.ll
tls2.ll
trap.ll
trunc-to-bool.ll
twoaddr-pass-sink.ll
twoaddr-remat.ll
uint_to_fp.ll
urem-i8-constant.ll
v4f32-immediate.ll
variable-sized-darwin-bzero.ll
variadic-node-pic.ll
vec_add.ll
vec_align.ll
vec_call.ll
vec_clear.ll
vec_ctbits.ll
vec_extract-sse4.ll
vec_extract.ll
vec_fneg.ll
vec_ins_extract.ll
vec_insert_4.ll
vec_insert-2.ll
vec_insert-3.ll
vec_insert-5.ll
vec_insert-6.ll
vec_insert-7.ll
vec_insert.ll
vec_loadhl.ll
vec_logical.ll
vec_return.ll
vec_select.ll
vec_set-2.ll
vec_set-3.ll
vec_set-4.ll
vec_set-5.ll
vec_set-6.ll
vec_set-7.ll
vec_set-8.ll
vec_set-9.ll
vec_set-A.ll
vec_set-B.ll
vec_set-C.ll
vec_set-D.ll
vec_set-E.ll
vec_set-F.ll
vec_set-G.ll
vec_set-H.ll
vec_set-I.ll
vec_set-J.ll
vec_set.ll
vec_shift2.ll
vec_shift3.ll
vec_shift.ll
vec_shuffle-2.ll
vec_shuffle-3.ll
vec_shuffle-4.ll
vec_shuffle-5.ll
vec_shuffle-6.ll
vec_shuffle-7.ll
vec_shuffle-8.ll
vec_shuffle-9.ll
vec_shuffle-10.ll
vec_shuffle-11.ll
vec_shuffle-12.ll
vec_shuffle-13.ll
vec_shuffle-14.ll
vec_shuffle-15.ll
vec_shuffle-16.ll
vec_shuffle-17.ll
vec_shuffle-18.ll
vec_shuffle-19.ll
vec_shuffle-20.ll
vec_shuffle-21.ll
vec_shuffle-22.ll
vec_shuffle-23.ll
vec_shuffle-24.ll
vec_shuffle.ll
vec_splat-2.ll
vec_splat.ll
vec_ss_load_fold.ll
vec_zero_cse.ll
vec_zero-2.ll
vec_zero.ll
vector-intrinsics.ll
vector-rem.ll
vector-variable-idx.ll
vector.ll
vfcmp.ll
volatile.ll
vortex-bug.ll
weak.ll
x86-64-and-mask.ll
x86-64-arg.ll
x86-64-asm.ll
x86-64-dead-stack-adjust.ll
x86-64-frameaddr.ll
x86-64-gv-offset.ll
x86-64-mem.ll
x86-64-pic-1.ll
x86-64-pic-2.ll
x86-64-pic-3.ll
x86-64-pic-4.ll
x86-64-pic-5.ll
x86-64-pic-6.ll
x86-64-pic-7.ll
x86-64-pic-8.ll
x86-64-pic-9.ll
x86-64-pic-10.ll
x86-64-pic-11.ll
x86-64-ret0.ll
x86-64-shortint.ll
x86-64-sret-return.ll
x86-64-varargs.ll
x86-frameaddr2.ll
x86-frameaddr.ll
xmm-r64.ll
xor_not.ll
xor-undef.ll
xorl.ll
zero-remat.ll
zext-inreg-0.ll
zext-inreg-1.ll