llvm-svn: 40754

X86InstrInfo::isReallyTriviallyReMaterializable knows how to handle
with the isReMaterializable flag so that it is given a chance to handle
them. Without hoisting constant-pool loads from loops this isn't very
visible, though it does keep CodeGen/X86/constant-pool-remat-0.ll from
making a copy of the constant pool on the stack.

llvm-svn: 40736

llvm-svn: 40691

mnemonics from their operands instead of single spaces. This makes the
assembly output a little more consistent with various other compilers
(f.e. GCC), and slightly easier to read. Also, update the regression
tests accordingly.

llvm-svn: 40648

Redo and generalize previously removed opt for pinsrw: (vextract (v4i32 bc (v4f32 s2v (f32 load ))), 0) -> (i32 load )

llvm-svn: 40628

Make the alignedload and alignedstore patterns always require 16-byte
alignment. This way when they are used in the "Fs" instructions, in which
a vector instruction is used for a scalar purpose, they can still require
the full vector alignment. And add a regression test for this.

llvm-svn: 40555

llvm-svn: 40547

llvm-svn: 40528

x86 target, replacing them with the new alignment attributes on memory
references.

llvm-svn: 40504

code that cross integer / floating point domains (e.g. generate pxor / pand for
logical ops on floating point value, movdqa to load / store floating point SSE
values). Given that, it's better to use movaps instead of movdqa and movups
instead of movdqu. They have the same latency but the "aps" variants are one
byte shorter.
If the domain crossing problem is a real performance issue, then we will have to
fix it with dynamic programming based isel.

llvm-svn: 40076

Fix patterns so we isel the xorps, etc. for floating pt logical SSE ops. DAG combiner may fold away the (bit_convert (load)).

llvm-svn: 40070

InOperandList. This gives one piece of important information: # of results
produced by an instruction.
An example of the change:
def ADD32rr  : I<0x01, MRMDestReg, (ops GR32:$dst, GR32:$src1, GR32:$src2),
                 "add{l} {$src2, $dst|$dst, $src2}",
                 [(set GR32:$dst, (add GR32:$src1, GR32:$src2))]>;
=>
def ADD32rr  : I<0x01, MRMDestReg, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
                 "add{l} {$src2, $dst|$dst, $src2}",
                 [(set GR32:$dst, (add GR32:$src1, GR32:$src2))]>;

llvm-svn: 40033

and stores that have a specified alignment of less than 16 bytes now use
instructions that support misaligned memory references.

llvm-svn: 40015

in addition to the intrinsic forms. Add spill-folding entries for these new
instructions, and for the scalar min and max instrinsic instructions which
were missing. And add some preliminary ISelLowering code for using the new
non-intrinsic vector sqrt instruction, and fneg and fabs.

llvm-svn: 38478

model to include f32 variants.  Some factoring
improvments forthcoming.

llvm-svn: 37847

instruction flag, and use the flag along with a virtual member function
hook for targets to override if there are instructions that are only
trivially rematerializable with specific operands (i.e. constant pool
loads).

llvm-svn: 37728

between SSE1 instructions and their respective SSE2 analogues.

llvm-svn: 37718

llvm-svn: 37717

with a general target hook to identify rematerializable instructions. Some
instructions are only rematerializable with specific operands, such as loads
from constant pools, while others are always rematerializable. This hook
allows both to be identified as being rematerializable with the same
mechanism.

llvm-svn: 37644

llvm-svn: 37172

for SSE1, SSE2, SSE3, and SSSE3.

llvm-svn: 36656

llvm-svn: 36256

llvm-svn: 35869

llvm-svn: 35230

llvm-svn: 34905

llvm-svn: 34434

  or'ing in the sign bit of operand 1.
- Tweaking: rather than left shift the sign bit, fp_extend operand 1 first
  before taking its sign bit if its type is smaller than that of operand 0.

llvm-svn: 32932

llvm-svn: 32900

- Add MOVDI2SSrm and MOVSS2DImr to fold load / store for i32 <-> f32 bit_convert
  patterns.

llvm-svn: 32582

This compiles bitcast.ll:test3/test4 into:

_test3:
        movd %xmm0, %eax
        ret
_test4:
        movd %edi, %xmm0
        ret

llvm-svn: 32230

Correct instructions for moving data between GR64 and SSE registers; also correct load i64 / store i64 from v2i64.

llvm-svn: 31795

take v4f32 / v2f64 operands and may end up causing larger spills / restores.
Added X86 specific nodes X86ISD::FMAX, X86ISD::FMIN instead.

This fixes PR996.

llvm-svn: 31645

shuffle v, undef, <2, ?, 3, ?>
to movhlps
It should match to unpckhps instead.

Added proper matching code for
shuffle v, undef, <2, 3, 2, 3>

llvm-svn: 31519

llvm-svn: 31435

llvm-svn: 31343

llvm-svn: 31228

llvm-svn: 31185

llvm-svn: 30892

folding first.

llvm-svn: 30848

llvm-svn: 30844