Added support for TRUNC v8i16 to v8i8 for X86 (MMX)

llvm-svn: 60916

llvm-svn: 60499

llvm-svn: 60487

llvm-svn: 58752

SSE2 registers as well as the MMX registers.

llvm-svn: 55436

llvm-svn: 55318

instructions on having SSE2.

llvm-svn: 55317

Is there way to avoid explicit target check?

llvm-svn: 55238

llvm-svn: 54026

load,store,call,return,bitcast.  This is enough to
make call and return work.

llvm-svn: 52691

llvm-svn: 51667

Note, some of the code will be moved into target independent part of DAG combiner in a subsequent patch.

llvm-svn: 50918

Handle vector move / load which zero the destination register top bits (i.e. movd, movq, movss (addr), movsd (addr)) with X86 specific dag combine.

llvm-svn: 50838

Add separate intrinsics for MMX / SSE shifts with i32 integer operands. This allow us to simplify the horribly complicated matching code.

llvm-svn: 50601

llvm-svn: 50291

llvm-svn: 50289

llvm-svn: 50278

llvm-svn: 50053

to 64-bit GPR registers on x86-64.

llvm-svn: 49757

llvm-svn: 48627

llvm-svn: 48569

Replace all target specific implicit def instructions with a target independent one: TargetInstrInfo::IMPLICIT_DEF.

llvm-svn: 48380

X86 lowering normalize vector 0 to v4i32. However DAGCombine can fold (sub x, x) -> 0 after legalization. It can create a zero vector of a type that's not expected (e.g. v8i16). We don't want to disable the optimization since leaving a (sub x, x) is really bad. Add isel patterns for other types of vector 0 to ensure correctness. It's highly unlikely to happen other than in bugpoint reduced test cases.

llvm-svn: 48279

llvm-svn: 47740

- When DAG combiner is folding a bit convert into a BUILD_VECTOR, it should check if it's essentially a SCALAR_TO_VECTOR. Avoid turning (v8i16) <10, u, u, u> to <10, 0, u, u, u, u, u, u>. Instead, simply convert it to a SCALAR_TO_VECTOR of the proper type.
- X86 now normalize SCALAR_TO_VECTOR to (BIT_CONVERT (v4i32 SCALAR_TO_VECTOR)). Get rid of X86ISD::S2VEC.

llvm-svn: 47290

x86 backend where instructions were not marked maystore/mayload, and perf issues where
instructions were not marked neverHasSideEffects.  It would be really nice if we could
write patterns for copy instructions.

I have audited all the x86 instructions down to MOVDQAmr.  The flags on others and on
other targets are probably not right in all cases, but no clients currently use this
info that are enabled by default.

llvm-svn: 45829

inferred from the instr patterns.

llvm-svn: 45824

llvm-svn: 45667

llvm-svn: 45418

based what flag to set on whether it was already marked as
"isRematerializable". If there was a further check to determine if it's "really"
rematerializable, then I marked it as "mayHaveSideEffects" and created a check
in the X86 back-end similar to the remat one.

llvm-svn: 45132

Implicit def instructions, e.g. X86::IMPLICIT_DEF_GR32, are always re-materializable and they should not be spilled.

llvm-svn: 44960

sometimes emit "zero" and "all one" vectors multiple times,
for example:

_test2:
	pcmpeqd	%mm0, %mm0
	movq	%mm0, _M1
	pcmpeqd	%mm0, %mm0
	movq	%mm0, _M2
	ret

instead of:

_test2:
	pcmpeqd	%mm0, %mm0
	movq	%mm0, _M1
	movq	%mm0, _M2
	ret

This patch fixes this by always arranging for zero/one vectors
to be defined as v4i32 or v2i32 (SSE/MMX) instead of letting them be
any random type.  This ensures they get trivially CSE'd on the dag.
This fix is also important for LegalizeDAGTypes, as it gets unhappy
when the x86 backend wants BUILD_VECTOR(i64 0) to be legal even when
'i64' isn't legal.

This patch makes the following changes:

1) X86TargetLowering::LowerBUILD_VECTOR now lowers 0/1 vectors into
   their canonical types.
2) The now-dead patterns are removed from the SSE/MMX .td files.
3) All the patterns in the .td file that referred to immAllOnesV or
   immAllZerosV in the wrong form now use *_bc to match them with a
   bitcast wrapped around them.
4) X86DAGToDAGISel::SelectScalarSSELoad is generalized to handle 
   bitcast'd zero vectors, which simplifies the code actually.
5) getShuffleVectorZeroOrUndef is updated to generate a shuffle that
   is legal, instead of generating one that is illegal and expecting
   a later legalize pass to clean it up.
6) isZeroShuffle is generalized to handle bitcast of zeros.
7) several other minor tweaks.

This patch is definite goodness, but has the potential to cause random
code quality regressions.  Please be on the lookout for these and let 
me know if they happen.

llvm-svn: 44310

llvm-svn: 41863

llvm-svn: 41595

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

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

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

llvm-svn: 37866

Still need to have JIT generate this code.

llvm-svn: 37863