value. Adjust other code to deal with that correctly. Make
DAGTypeLegalizer::PromoteIntRes_EXTRACT_VECTOR_ELT take advantage of
this new flexibility to simplify the code and make it deal with unusual
vectors (like <4 x i1>) correctly. Fixes PR3037.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75176 91177308-0d34-0410-b5e6-96231b3b80d8
registers based on dynamic conditions. For example, X86 EBP/RBP, when used as
frame register has to be spilled in the first fixed object. It should inform
PEI this so it doesn't get allocated another stack object. Also, it should not
be spilled as other callee-saved registers but rather its spilling and restoring
are being handled by emitPrologue and emitEpilogue. Avoid spilling it twice.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75116 91177308-0d34-0410-b5e6-96231b3b80d8
* remove some old code that was needed when we'd put ESP in the scale instead of
the base of some instructions.
* Fix a bug with the P modifier in inline asm that caused us to drop it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75077 91177308-0d34-0410-b5e6-96231b3b80d8
VSETCC must define all bits, which is different than it was documented
to before. Since all targets that implement VSETCC already have this
behavior, and we don't optimize based on this, just change the
documentation. We now get nice code for vec_compare.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74978 91177308-0d34-0410-b5e6-96231b3b80d8
finishes off enough support for vector compares to get the icmp/fcmp
version of 2008-07-23-VSetCC.ll passing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74961 91177308-0d34-0410-b5e6-96231b3b80d8
Avoid unnecessary duplication of operand 0 of X86::FpSET_ST0_80. This duplication would
cause one register to remain on the stack at the function return.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74534 91177308-0d34-0410-b5e6-96231b3b80d8
Not sure I understand how the temp register gets used,
but this fixes a bug and introduces no regressions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74446 91177308-0d34-0410-b5e6-96231b3b80d8
implementation primarily differs from the former in that the asmprinter
doesn't make a zillion decisions about whether or not something will be
RIP relative or not. Instead, those decisions are made by isel lowering
and propagated through to the asm printer. To achieve this, we:
1. Represent RIP relative addresses by setting the base of the X86 addr
mode to X86::RIP.
2. When ISel Lowering decides that it is safe to use RIP, it lowers to
X86ISD::WrapperRIP. When it is unsafe to use RIP, it lowers to
X86ISD::Wrapper as before.
3. This removes isRIPRel from X86ISelAddressMode, representing it with
a basereg of RIP instead.
4. The addressing mode matching logic in isel is greatly simplified.
5. The asmprinter is greatly simplified, notably the "NotRIPRel" predicate
passed through various printoperand routines is gone now.
6. The various symbol printing routines in asmprinter now no longer infer
when to emit (%rip), they just print the symbol.
I think this is a big improvement over the previous situation. It does have
two small caveats though: 1. I implemented a horrible "no-rip" modifier for
the inline asm "P" constraint modifier. This is a short term hack, there is
a much better, but more involved, solution. 2. I had to xfail an
-aggressive-remat testcase because it isn't handling the use of RIP in the
constant-pool reading instruction. This specific test is easy to fix without
-aggressive-remat, which I intend to do next.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74372 91177308-0d34-0410-b5e6-96231b3b80d8
trip counts in more cases.
Generalize ScalarEvolution's isLoopGuardedByCond code to recognize
And and Or conditions, splitting the code out into an
isNecessaryCond helper function so that it can evaluate Ands and Ors
recursively, and make SCEVExpander be much more aggressive about
hoisting instructions out of loops.
test/CodeGen/X86/pr3495.ll has an additional instruction now, but
it appears to be due to an arbitrary register allocation difference.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74048 91177308-0d34-0410-b5e6-96231b3b80d8
a global with that gets printed with the :mem modifier. All operands to lea's
should be handled with the lea32mem operand kind, and this allows the TLS stuff
to do this. There are several better ways to do this, but I went for the minimal
change since I can't really test this (beyond make check).
This also makes the use of EBX explicit in the operand list in the 32-bit,
instead of implicit in the instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73834 91177308-0d34-0410-b5e6-96231b3b80d8
as signed max tests. Along with r73717, this helps CodeGen avoid
emitting code for a maximum operation for this class of loop.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73718 91177308-0d34-0410-b5e6-96231b3b80d8
casted induction variables in cases where the cast
isn't foldable. It ended up being a pessimization in
many cases. This could be fixed, but it would require
a bunch of complicated code in IVUsers' clients. The
advantages of this approach aren't visible enough to
justify it at this time.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73706 91177308-0d34-0410-b5e6-96231b3b80d8
support for x86, and UMULO/SMULO for many architectures, including PPC
(PR4201), ARM, and Cell. The resulting expansion isn't perfect, but it's
not bad.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73477 91177308-0d34-0410-b5e6-96231b3b80d8
incomming chain of the RETURN node. The incomming chain must
be the outgoing chain of the CALL node. This causes the
backend to identify tail calls that are not tail calls. This
patch fixes this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73387 91177308-0d34-0410-b5e6-96231b3b80d8
out of sync with regular cc.
The only difference between the tail call cc and the normal
cc was that one parameter register - R9 - was reserved for
calling functions through a function pointer. After time the
tail call cc has gotten out of sync with the regular cc.
We can use R11 which is also caller saved but not used as
parameter register for potential function pointers and
remove the special tail call cc on x86-64.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73233 91177308-0d34-0410-b5e6-96231b3b80d8
on x86 to handle more cases. Fix a bug in said code that would cause it
to read past the end of an object. Rewrite the code in
SelectionDAGLegalize::ExpandBUILD_VECTOR to be a bit more general.
Remove PerformBuildVectorCombine, which is no longer necessary with
these changes. In addition to simplifying the code, with this change,
we can now catch a few more cases of consecutive loads.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73012 91177308-0d34-0410-b5e6-96231b3b80d8
nodes for vectors with an i16 element type. Add an optimization for
building a vector which is all zeros/undef except for the bottom
element, where the bottom element is an i8 or i16.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72988 91177308-0d34-0410-b5e6-96231b3b80d8
build vectors with i64 elements will only appear on 32b x86 before legalize.
Since vector widening occurs during legalize, and produces i64 build_vector
elements, the dag combiner is never run on these before legalize splits them
into 32b elements.
Teach the build_vector dag combine in x86 back end to recognize consecutive
loads producing the low part of the vector.
Convert the two uses of TLI's consecutive load recognizer to pass LoadSDNodes
since that was required implicitly.
Add a testcase for the transform.
Old:
subl $28, %esp
movl 32(%esp), %eax
movl 4(%eax), %ecx
movl %ecx, 4(%esp)
movl (%eax), %eax
movl %eax, (%esp)
movaps (%esp), %xmm0
pmovzxwd %xmm0, %xmm0
movl 36(%esp), %eax
movaps %xmm0, (%eax)
addl $28, %esp
ret
New:
movl 4(%esp), %eax
pmovzxwd (%eax), %xmm0
movl 8(%esp), %eax
movaps %xmm0, (%eax)
ret
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72957 91177308-0d34-0410-b5e6-96231b3b80d8
integer and floating-point opcodes, introducing
FAdd, FSub, and FMul.
For now, the AsmParser, BitcodeReader, and IRBuilder all preserve
backwards compatability, and the Core LLVM APIs preserve backwards
compatibility for IR producers. Most front-ends won't need to change
immediately.
This implements the first step of the plan outlined here:
http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72897 91177308-0d34-0410-b5e6-96231b3b80d8
Update code generator to use this attribute and remove DisableRedZone target option.
Update llc to set this attribute when -disable-red-zone command line option is used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72894 91177308-0d34-0410-b5e6-96231b3b80d8
relocation model on x86-64. Higher level logic should override
the relocation model to PIC on x86_64-apple-darwin.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72746 91177308-0d34-0410-b5e6-96231b3b80d8
e.g.
orl $65536, 8(%rax)
=>
orb $1, 10(%rax)
Since narrowing is not always a win, e.g. i32 -> i16 is a loss on x86, dag combiner consults with the target before performing the optimization.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72507 91177308-0d34-0410-b5e6-96231b3b80d8
The DAGCombiner created a negative shiftamount, stored in an
unsigned variable. Later the optimizer eliminated the shift entirely as being
undefined.
Example: (srl (shl X, 56) 48). ShiftAmt is 4294967288.
Fix it by checking that the shiftamount is positive, and storing in a signed
variable.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72331 91177308-0d34-0410-b5e6-96231b3b80d8
and it wasn't generating calls through @PLT for these functions.
hasLocalLinkage() is now false for available_externally,
I attempted to fix the inliner and dce to handle available_externally properly.
It passed make check.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72328 91177308-0d34-0410-b5e6-96231b3b80d8
When a test fails with more than a pipeful of output on stdout AND stderr, one
of the DejaGnu programs blocks. The problem can be avoided by redirecting
stdout to a file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@71919 91177308-0d34-0410-b5e6-96231b3b80d8
and generalize it so that it can be used by IndVarSimplify. Implement the
base IndVarSimplify transformation code using IVUsers. This removes
TestOrigIVForWrap and associated code, as ScalarEvolution now has enough
builtin overflow detection and folding logic to handle all the same cases,
and more. Run "opt -iv-users -analyze -disable-output" on your favorite
loop for an example of what IVUsers does.
This lets IndVarSimplify eliminate IV casts and compute trip counts in
more cases. Also, this happens to finally fix the remaining testcases
in PR1301.
Now that IndVarSimplify is being more aggressive, it occasionally runs
into the problem where ScalarEvolutionExpander's code for avoiding
duplicate expansions makes it difficult to ensure that all expanded
instructions dominate all the instructions that will use them. As a
temporary measure, IndVarSimplify now uses a FixUsesBeforeDefs function
to fix up instructions inserted by SCEVExpander. Fortunately, this code
is contained, and can be easily removed once a more comprehensive
solution is available.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@71535 91177308-0d34-0410-b5e6-96231b3b80d8
Also, if the compare is the only use, LSR would place the iv increment instruction before the compare instead in the latch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@71485 91177308-0d34-0410-b5e6-96231b3b80d8
type, rather than assume that it does. If the operand is not vector, it
shouldn't be run through ScalarizeVectorOp. This fixes one of the
testcases in PR3886.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@71453 91177308-0d34-0410-b5e6-96231b3b80d8
count down to 0 instead, under very restricted
circumstances. Adjust 4 testcases in which this
optimization fires.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@71439 91177308-0d34-0410-b5e6-96231b3b80d8
allow it to have multiple CFG edges to that block. This is needed
to allow MachineBasicBlock::isOnlyReachableByFallthrough to work
correctly. This fixes PR4126.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@71018 91177308-0d34-0410-b5e6-96231b3b80d8
of returning a list of pointers to Values that are deleted. This was
unsafe, because the pointers in the list are, by nature of what
RecursivelyDeleteDeadInstructions does, always dangling. Replace this
with a simple callback mechanism. This may eventually be removed if
all clients can reasonably be expected to use CallbackVH.
Use this to factor out the dead-phi-cycle-elimination code from LSR
utility function, and generalize it to use the
RecursivelyDeleteTriviallyDeadInstructions utility function.
This makes LSR more aggressive about eliminating dead PHI cycles;
adjust tests to either be less trivial or to simply expect fewer
instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70636 91177308-0d34-0410-b5e6-96231b3b80d8
memory operands otherwise the writebacks get lost when the inline asm
doesn't otherwise have side effects. This fixes rdar://6839427, though
clang really shouldn't generate these anymore.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70455 91177308-0d34-0410-b5e6-96231b3b80d8
Massive check in. This changes the "-fast" flag to "-O#" in llc. If you want to
use the old behavior, the flag is -O0. This change allows for finer-grained
control over which optimizations are run at different -O levels.
Most of this work was pretty mechanical. The majority of the fixes came from
verifying that a "fast" variable wasn't used anymore. The JIT still uses a
"Fast" flag. I'll change the JIT with a follow-up patch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70343 91177308-0d34-0410-b5e6-96231b3b80d8
use the old behavior, the flag is -O0. This change allows for finer-grained
control over which optimizations are run at different -O levels.
Most of this work was pretty mechanical. The majority of the fixes came from
verifying that a "fast" variable wasn't used anymore. The JIT still uses a
"Fast" flag. I'm not 100% sure if it's necessary to change it there...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70270 91177308-0d34-0410-b5e6-96231b3b80d8
information to simplify [sz]ext({a,+,b}) to {zext(a),+,[zs]ext(b)},
as appropriate.
These functions and the trip count code each call into the other, so
this requires careful handling to avoid infinite recursion. During
the initial trip count computation, conservative SCEVs are used,
which are subsequently discarded once the trip count is actually
known.
Among other benefits, this change lets LSR automatically eliminate
some unnecessary zext-inreg and sext-inreg operation where the
operand is an induction variable.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70241 91177308-0d34-0410-b5e6-96231b3b80d8
PR2957
ISD::VECTOR_SHUFFLE now stores an array of integers representing the shuffle
mask internal to the node, rather than taking a BUILD_VECTOR of ConstantSDNodes
as the shuffle mask. A value of -1 represents UNDEF.
In addition to eliminating the creation of illegal BUILD_VECTORS just to
represent shuffle masks, we are better about canonicalizing the shuffle mask,
resulting in substantially better code for some classes of shuffles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70225 91177308-0d34-0410-b5e6-96231b3b80d8
the trunc is directly replaced with the smaller load, so don't
try to create a new sext node. This fixes PR4050.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70179 91177308-0d34-0410-b5e6-96231b3b80d8
ISD::VECTOR_SHUFFLE now stores an array of integers representing the shuffle
mask internal to the node, rather than taking a BUILD_VECTOR of ConstantSDNodes
as the shuffle mask. A value of -1 represents UNDEF.
In addition to eliminating the creation of illegal BUILD_VECTORS just to
represent shuffle masks, we are better about canonicalizing the shuffle mask,
resulting in substantially better code for some classes of shuffles.
A clean up of x86 shuffle code, and some canonicalizing in DAGCombiner is next.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69952 91177308-0d34-0410-b5e6-96231b3b80d8
This fixes a very subtle bug. vr defined by an implicit_def is allowed overlap with any register since it doesn't actually modify anything. However, if it's used as a two-address use, its live range can be extended and it can be spilled. The spiller must take care not to emit a reload for the vn number that's defined by the implicit_def. This is both a correctness and performance issue.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69743 91177308-0d34-0410-b5e6-96231b3b80d8
%reg1498<def> = MOV32rm %reg1024, 1, %reg0, 12, %reg0, Mem:LD(4,4) [sunkaddr39 + 0]
%reg1506<def> = MOV32rm %reg1024, 1, %reg0, 8, %reg0, Mem:LD(4,4) [sunkaddr42 + 0]
%reg1486<def> = MOV32rr %reg1506
%reg1486<def> = XOR32rr %reg1486, %reg1498, %EFLAGS<imp-def,dead>
%reg1510<def> = MOV32rm %reg1024, 1, %reg0, 4, %reg0, Mem:LD(4,4) [sunkaddr45 + 0]
=>
%reg1498<def> = MOV32rm %reg2036, 1, %reg0, 12, %reg0, Mem:LD(4,4) [sunkaddr39 + 0]
%reg1506<def> = MOV32rm %reg2037, 1, %reg0, 8, %reg0, Mem:LD(4,4) [sunkaddr42 + 0]
%reg1486<def> = MOV32rr %reg1506
%reg1486<def> = XOR32rr %reg1486, %reg1498, %EFLAGS<imp-def,dead>
%reg1510<def> = MOV32rm %reg2038, 1, %reg0, 4, %reg0, Mem:LD(4,4) [sunkaddr45 + 0]
From linearscan's point of view, each of reg2036, 2037, and 2038 are separate registers, each is "killed" after a single use. The reloaded register is available and it's often clobbered right away. e.g. In thise case reg1498 is allocated EAX while reg2036 is allocated RAX. This means we end up with multiple reloads from the same stack slot in the same basic block.
Now linearscan recognize there are other reloads from same SS in the same BB. So it'll "downgrade" RAX (and its aliases) after reg2036 is allocated until the next reload (reg2037) is done. This greatly increase the likihood reloads from SS are reused.
This speeds up sha1 from OpenSSL by 5.8%. It is also an across the board win for SPEC2000 and 2006.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69585 91177308-0d34-0410-b5e6-96231b3b80d8
for the optimization it's testing to kick in (although
it improves the code, getting rid of all spills).
I don't understand the optimization well enough to
rescue the test, so XFAILing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69409 91177308-0d34-0410-b5e6-96231b3b80d8
leaq foo@TLSGD(%rip), %rdi
as part of the instruction sequence. Using a register other than %rdi and then
copying it to %rdi is not valid.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69350 91177308-0d34-0410-b5e6-96231b3b80d8
register is available and when it's profitable.
e.g.
xorq %r12<kill>, %r13
addq %rax, -184(%rbp)
addq %r13, -184(%rbp)
==>
xorq %r12<kill>, %r13
movq -184(%rbp), %r12
addq %rax, %r12
addq %r13, %r12
movq %r12, -184(%rbp)
Two more instructions, but fewer memory accesses. It can also open up
opportunities for more optimizations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69341 91177308-0d34-0410-b5e6-96231b3b80d8
have pointer types, though in contrast to C pointer types, SCEV
addition is never implicitly scaled. This not only eliminates the
need for special code like IndVars' EliminatePointerRecurrence
and LSR's own GEP expansion code, it also does a better job because
it lets the normal optimizations handle pointer expressions just
like integer expressions.
Also, since LLVM IR GEPs can't directly index into multi-dimensional
VLAs, moving the GEP analysis out of client code and into the SCEV
framework makes it easier for clients to handle multi-dimensional
VLAs the same way as other arrays.
Some existing regression tests show improved optimization.
test/CodeGen/ARM/2007-03-13-InstrSched.ll in particular improved to
the point where if-conversion started kicking in; I turned it off
for this test to preserve the intent of the test.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69258 91177308-0d34-0410-b5e6-96231b3b80d8
operator is used by a CopyToReg to export the value to a different
block, don't reuse the CopyToReg's register for the subreg operation
result if the register isn't precisely the right class for the
subreg operation.
Also, rename the h-registers.ll test, now that there are more
than one.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@69087 91177308-0d34-0410-b5e6-96231b3b80d8
- Add patterns for h-register extract, which avoids a shift and mask,
and in some cases a temporary register.
- Add address-mode matching for turning (X>>(8-n))&(255<<n), where
n is a valid address-mode scale value, into an h-register extract
and a scaled-offset address.
- Replace X86's MOV32to32_ and related instructions with the new
target-independent COPY_TO_SUBREG instruction.
On x86-64 there are complicated constraints on h registers, and
CodeGen doesn't currently provide a high-level way to express all of them,
so they are handled with a bunch of special code. This code currently only
supports extracts where the result is used by a zero-extend or a store,
though these are fairly common.
These transformations are not always beneficial; since there are only
4 h registers, they sometimes require extra move instructions, and
this sometimes increases register pressure because it can force out
values that would otherwise be in one of those registers. However,
this appears to be relatively uncommon.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@68962 91177308-0d34-0410-b5e6-96231b3b80d8
