llvm-svn: 58752

llvm-svn: 58750

priority function. Instead, just iterate over the AllNodes list, which is
already in topological order. This eliminates a fair amount of bookkeeping,
and speeds up the isel phase by about 15% on many testcases.

The impact on most targets is that AddToISelQueue calls can be simply removed.

In the x86 target, there are two additional notable changes.

The rule-bending AND+SHIFT optimization in MatchAddress that creates new
pre-isel nodes during isel is now a little more verbose, but more robust.
Instead of either creating an invalid DAG or creating an invalid topological
sort, as it has historically done, it can now just insert the new nodes into
the node list at a position where they will be consistent with the topological
ordering.

Also, the address-matching code has logic that checked to see if a node was
"already selected". However, when a node is selected, it has all its uses
taken away via ReplaceAllUsesWith or equivalent, so it won't recieve any
further visits from MatchAddress. This code is now removed.

llvm-svn: 58748

indirect gv reference. Please don't call it lazy.

llvm-svn: 58746

have its node id set. The new and and shift nodes are the nodes that need
the IDs. This fixes PR2982.

llvm-svn: 58655

adding a TargetMachine member to the base TargetAsmInfo class instead.

llvm-svn: 58624

llvm-svn: 58528

llvm-svn: 58523

Change x86 register allocation ordering to match that of gcc. Otherwise some tools get confused by prologue generated by llvm.

llvm-svn: 58517

callee-saved restore code. It could skip over conditional jumps
accidentally. Instead, just skip the "return" instructions.

llvm-svn: 58489

vector element 0 for a store, as it's smaller and faster.

llvm-svn: 58483

One will only see an effect if legalizetype is not active.  Will move
support to LegalizeType soon.

llvm-svn: 58426

llvm-svn: 58403

a memset using 16-byte XMM stores, but where the stack realignment code
didn't work.  Until it does (PR2962) disable use of xmm regs in memcpy
and memset formation for linux and other targets with insufficiently
aligned stacks.

This is part of PR2888

llvm-svn: 58317

Have TableGen emit setSubgraphColor calls under control of a -gen-debug
flag.  Then in a debugger developers can set breakpoints at these calls
to see waht is about to be selected and what the resulting subgraph
looks like.  This really helps when debugging instruction selection.

llvm-svn: 58278

For now, don't split live intervals around x87 stack register barriers. FpGET_ST0_80 must be right after a call instruction (and ADJCALLSTACKUP) so we need to find a way to prevent reload of x87 registers between them.

llvm-svn: 58230

target-independent code to target-specific code. This prevents it
from running on targets that aren't using fast-isel.

In addition to saving compile time, this addresses the problem
that not all targets are prepared for it. In order to use this
pass, all instructions must declare all their fixed uses and
defs of physical registers.

llvm-svn: 58144

variable is moved to the execution engine. The JIT calls the TargetJITInfo
to allocate thread local storage. Currently, only linux/x86 knows how to
allocate thread local global variables.

llvm-svn: 58142

llvm-svn: 58141

llvm-svn: 58104

LHS is a foldable load, then LHS and RHS are swapped
and SetCCOpcode is changed to SETUGT.  But the later
code is expecting operands to be the wrong way round
for SETUGT, but they are not in this case, resulting
in an inverted compare.  The solution is to move the
load normalization before the correction for SETUGT.
This bug was tickled by LegalizeTypes which happened
to legalize the testcase slightly differently to
LegalizeDAG.

llvm-svn: 58092

fixes a bunch of test-suite JIT failures on x86-64 in
-relocation-model=static mode.

llvm-svn: 58066

llvm-svn: 57987

assume that i64 has been turned into a BUILD_PAIR
node (when called from LegalizeTypes this hasn't
happened yet) and don't use a vector shuffle mask
with an illegal element type.

llvm-svn: 57972

names of LLVMCore and ARMCodeGen.

llvm-svn: 57943

llvm-svn: 57940

well, sort of.  (Algorithm by Ian Ollmann.)

llvm-svn: 57932

The same one Apple gcc uses, faster.  Also gets the
extreme case in gcc.c-torture/execute/ieee/rbug.c
correct which we weren't before; this is not
sufficient to get the test to pass though, there
is another bug.

llvm-svn: 57926

llvm-svn: 57915

in the 32-bit signed offset field of addresses. Even though this
may be intended, some linkers refuse to relocate code where the
relocated address computation overflows.

Also, fix the sign-extension of constant offsets to use the
actual pointer size, rather than the size of the GlobalAddress
node, which may be different, for example on x86-64 where MVT::i32
is used when the address is being fit into the 32-bit displacement
field.

llvm-svn: 57885

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

the copy instruction from the instruction list before asking the
target to create the new instruction. This gets the old instruction
out of the way so that it doesn't interfere with the target's
rematerialization code. In the case of x86, this helps it find
more cases where EFLAGS is not live.

Also, in the X86InstrInfo.cpp, teach isSafeToClobberEFLAGS to check
to see if it reached the end of the block after scanning each
instruction, instead of just before. This lets it notice when the
end of the block is only two instructions away, without doing any
additional scanning.

These changes allow rematerialization to clobber EFLAGS in more
cases, for example using xor instead of mov to set the return value
to zero in the included testcase.

llvm-svn: 57872

LowerOperation if it doesn't know what else to do.
This methods should probably be factorized some,
but this is good enough for the moment.  Have
LowerATOMIC_BINARY_64 use EXTRACT_ELEMENT rather
than assuming the operand is a BUILD_PAIR (if it
is then getNode will automagically simplify the
EXTRACT_ELEMENT).  This way LowerATOMIC_BINARY_64
usable from LegalizeTypes.

llvm-svn: 57831

and add a TargetLowering hook for it to use to determine when this
is legal (i.e. not in PIC mode, etc.)

This allows instruction selection to emit folded constant offsets
in more cases, such as the included testcase, eliminating the need
for explicit arithmetic instructions.

This eliminates the need for the C++ code in X86ISelDAGToDAG.cpp
that attempted to achieve the same effect, but wasn't as effective.

Also, fix handling of offsets in GlobalAddressSDNodes in several
places, including changing GlobalAddressSDNode's offset from
int to int64_t.

The Mips, Alpha, Sparc, and CellSPU targets appear to be
unaware of GlobalAddress offsets currently, so set the hook to
false on those targets.

llvm-svn: 57748

llvm-svn: 57733

Add implicit defs of XMM8 to XMM15 on 32-bit call instructions. While this is not technically true, it tells tblgen that these instructions "clobber" the entire XMM register file.

llvm-svn: 57723

llvm-svn: 57709

in 32-bit mode instead of assigning a register pair.  This has nothing to
do with PR2356, but I happened to notice it while working on it.

llvm-svn: 57704

Fix lfence and mfence encoding. These look like MRM5r and MRM6r instructions except they do not have any operands. The RegModRM byte is encoded with register number 0.

llvm-svn: 57692

llvm-svn: 57691