Commit Graph

64 Commits

Author SHA1 Message Date
Evan Cheng
f26ffe987c Implement vector shift up / down and insert zero with ps{rl}lq / ps{rl}ldq.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@51667 91177308-0d34-0410-b5e6-96231b3b80d8
2008-05-29 08:22:04 +00:00
Evan Cheng
d880b97257 Handle a few more cases of folding load i64 into xmm and zero top bits.
Note, some of the code will be moved into target independent part of DAG combiner in a subsequent patch.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50918 91177308-0d34-0410-b5e6-96231b3b80d8
2008-05-09 21:53:03 +00:00
Evan Cheng
7e2ff77ef0 Handle vector move / load which zero the destination register top bits (i.e. movd, movq, movss (addr), movsd (addr)) with X86 specific dag combine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50838 91177308-0d34-0410-b5e6-96231b3b80d8
2008-05-08 00:57:18 +00:00
Evan Cheng
22b942aa4d Add separate intrinsics for MMX / SSE shifts with i32 integer operands. This allow us to simplify the horribly complicated matching code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50601 91177308-0d34-0410-b5e6-96231b3b80d8
2008-05-03 00:52:09 +00:00
Evan Cheng
082948df9b Fix illegal MMX_MOVDQ2Qrr pattern. vector_extract result must be a scalar value.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50291 91177308-0d34-0410-b5e6-96231b3b80d8
2008-04-25 20:12:46 +00:00
Evan Cheng
10e864276b Special handling for MMX values being passed in either GPR64 or lower 64-bits of XMM registers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50289 91177308-0d34-0410-b5e6-96231b3b80d8
2008-04-25 19:11:04 +00:00
Evan Cheng
80f5404e18 Fix MMX_MOVQ2DQrr pattern. It's illegal to do a bitconvert from a smaller type to a larger one.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50278 91177308-0d34-0410-b5e6-96231b3b80d8
2008-04-25 18:19:54 +00:00
Dan Gohman
0416b0a26d Fix the encoding of the MMX movd that moves from MMX to 64-bit GPR.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@50053 91177308-0d34-0410-b5e6-96231b3b80d8
2008-04-21 19:52:29 +00:00
Dan Gohman
a630f4ed91 Add movd instructions to move from MMX registers
to 64-bit GPR registers on x86-64.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49757 91177308-0d34-0410-b5e6-96231b3b80d8
2008-04-15 23:55:07 +00:00
Evan Cheng
fa5a91a71e Undo 48570. Correctly match mmx shift instructions with an immediate operand.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48627 91177308-0d34-0410-b5e6-96231b3b80d8
2008-03-21 00:40:09 +00:00
Evan Cheng
dff1dcac6c Add intrinsics to match mmx shift builtin's with immediate operand.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48569 91177308-0d34-0410-b5e6-96231b3b80d8
2008-03-19 23:38:52 +00:00
Evan Cheng
da47e6e0d0 Replace all target specific implicit def instructions with a target independent one: TargetInstrInfo::IMPLICIT_DEF.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48380 91177308-0d34-0410-b5e6-96231b3b80d8
2008-03-15 00:03:38 +00:00
Evan Cheng
c8e3b147ee Clean up my own mess.
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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48279 91177308-0d34-0410-b5e6-96231b3b80d8
2008-03-12 07:02:50 +00:00
Anders Carlsson
b26947e967 Use the correct instruction encodings for the 64-bit MMX movd.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@47740 91177308-0d34-0410-b5e6-96231b3b80d8
2008-02-29 01:35:12 +00:00
Evan Cheng
efec751a1b - 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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@47290 91177308-0d34-0410-b5e6-96231b3b80d8
2008-02-18 23:04:32 +00:00
Chris Lattner
ba7e756c22 Start inferring side effect information more aggressively, and fix many bugs in the
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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45829 91177308-0d34-0410-b5e6-96231b3b80d8
2008-01-10 07:59:24 +00:00
Chris Lattner
dd41527a7d remove explicit sets of 'neverHasSideEffects' that can now be
inferred from the instr patterns.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45824 91177308-0d34-0410-b5e6-96231b3b80d8
2008-01-10 05:45:39 +00:00
Chris Lattner
834f1ce031 rename isLoad -> isSimpleLoad due to evan's desire to have such a predicate.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45667 91177308-0d34-0410-b5e6-96231b3b80d8
2008-01-06 23:38:27 +00:00
Chris Lattner
4ee451de36 Remove attribution from file headers, per discussion on llvmdev.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45418 91177308-0d34-0410-b5e6-96231b3b80d8
2007-12-29 20:36:04 +00:00
Bill Wendling
627c00b663 Add "mayHaveSideEffects" and "neverHasSideEffects" flags to some instructions. I
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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45132 91177308-0d34-0410-b5e6-96231b3b80d8
2007-12-17 23:07:56 +00:00
Evan Cheng
6e141fd048 Implicit def instructions, e.g. X86::IMPLICIT_DEF_GR32, are always re-materializable and they should not be spilled.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@44960 91177308-0d34-0410-b5e6-96231b3b80d8
2007-12-12 23:12:09 +00:00
Chris Lattner
8a594489bf Fix a long standing deficiency in the X86 backend: we would
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.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@44310 91177308-0d34-0410-b5e6-96231b3b80d8
2007-11-25 00:24:49 +00:00
Evan Cheng
071a279e94 Remove (somewhat confusing) Imp<> helper, use let Defs = [], Uses = [] instead.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@41863 91177308-0d34-0410-b5e6-96231b3b80d8
2007-09-11 19:55:27 +00:00
Evan Cheng
2f39426ec9 Mark load instructions with isLoad = 1.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@41595 91177308-0d34-0410-b5e6-96231b3b80d8
2007-08-30 05:49:43 +00:00
Dan Gohman
73a902b228 Mark the SSE and MMX load instructions that
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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@40736 91177308-0d34-0410-b5e6-96231b3b80d8
2007-08-02 14:27:55 +00:00
Dan Gohman
b1576f56c8 Change the x86 assembly output to use tab characters to separate the
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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@40648 91177308-0d34-0410-b5e6-96231b3b80d8
2007-07-31 20:11:57 +00:00
Evan Cheng
c64a1a921c Redo and generalize previously removed opt for pinsrw: (vextract (v4i32 bc (v4f32 s2v (f32 load ))), 0) -> (i32 load )
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@40628 91177308-0d34-0410-b5e6-96231b3b80d8
2007-07-31 08:04:03 +00:00
Evan Cheng
64d80e3387 Change instruction description to split OperandList into OutOperandList and
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))]>;


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@40033 91177308-0d34-0410-b5e6-96231b3b80d8
2007-07-19 01:14:50 +00:00
Bill Wendling
10404c47d1 Support generation of GR64 to MMX code in the JIT.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@37866 91177308-0d34-0410-b5e6-96231b3b80d8
2007-07-04 01:29:22 +00:00
Bill Wendling
93888428d4 Allow a GR64 to be moved into an MMX register via the "movd" instruction.
Still need to have JIT generate this code.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@37863 91177308-0d34-0410-b5e6-96231b3b80d8
2007-07-04 00:19:54 +00:00
Dan Gohman
d45eddd214 Revert the earlier change that removed the M_REMATERIALIZABLE machine
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).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@37728 91177308-0d34-0410-b5e6-96231b3b80d8
2007-06-26 00:48:07 +00:00
Dan Gohman
82a87a0172 Replace M_REMATERIALIZIBLE and the newly-added isOtherReMaterializableLoad
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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@37644 91177308-0d34-0410-b5e6-96231b3b80d8
2007-06-19 01:48:05 +00:00
Chris Lattner
738a6ec0ae implement the missing maskmovq mmx intrinsic that akor hit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@37100 91177308-0d34-0410-b5e6-96231b3b80d8
2007-05-16 06:08:17 +00:00
Bill Wendling
69dc5332de Add the final MMX instructions. Correct a few wrong patterns.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@36405 91177308-0d34-0410-b5e6-96231b3b80d8
2007-04-24 21:18:37 +00:00
Bill Wendling
71bfd11c67 Adding more MMX instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35638 91177308-0d34-0410-b5e6-96231b3b80d8
2007-04-03 23:48:32 +00:00
Bill Wendling
823efee633 Add FEMMS and ADDQ. Renamed MMX recipes to prepend the MMX_ to them.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35616 91177308-0d34-0410-b5e6-96231b3b80d8
2007-04-03 06:00:37 +00:00
Bill Wendling
826f36ff80 Unbreak mmx arithmetic. It was barfing trying to do v8i8 arithmetic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35392 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-28 00:57:11 +00:00
Bill Wendling
6dc29ece6e Add the "unpack low packed data" instructions. This should be the last of
the MMX instructions that are needed...


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35389 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-27 21:20:36 +00:00
Bill Wendling
ccc44add81 Fix so that pandn is emitted instead of an xor/and combo. Add integer
comparison operators.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35385 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-27 20:22:40 +00:00
Bill Wendling
eebc8a1bc5 Add support for the v1i64 type. This makes better code for this:
#include <mmintrin.h>

extern __m64 C;

void baz(__v2si *A, __v2si *B)
{
  *A = C;
  _mm_empty();
}

We get this:

_baz:
        call "L1$pb"
"L1$pb":
        popl %eax
        movl L_C$non_lazy_ptr-"L1$pb"(%eax), %eax
        movq (%eax), %mm0
        movl 4(%esp), %eax
        movq %mm0, (%eax)
        emms
        ret

GCC gives us this:

_baz:
        pushl   %ebx
        call    L3
"L00000000001$pb":
L3:
        popl    %ebx
        subl    $8, %esp
        movl    L_C$non_lazy_ptr-"L00000000001$pb"(%ebx), %eax
        movl    (%eax), %edx
        movl    4(%eax), %ecx
        movl    16(%esp), %eax
        movl    %edx, (%eax)
        movl    %ecx, 4(%eax)
        emms
        addl    $8, %esp
        popl    %ebx
        ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35351 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-26 07:53:08 +00:00
Bill Wendling
b8440a0c39 PR1260:
Add final support to get the QT example to compile.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35290 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-23 22:35:46 +00:00
Bill Wendling
02ced83ce7 We generate a shufflevector instruction, so we don't need the builtin
intrinsic.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35269 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-22 20:29:26 +00:00
Bill Wendling
a348c56fde Support added for shifts and unpacking MMX instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35266 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-22 18:42:45 +00:00
Bill Wendling
1b7a81d3ae And now support for MMX logical operations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35125 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-16 09:44:46 +00:00
Bill Wendling
74027e98f1 Multiplication support for MMX.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35118 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-15 21:24:36 +00:00
Bill Wendling
c1fb0473ed Adding more arithmetic operators to MMX. This is an almost exact copy of
the addition. Please let me know if you have suggestions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35055 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-10 09:57:05 +00:00
Bill Wendling
2f88dcdfb3 Added "padd*" support for MMX. Added MMX move stuff to X86InstrInfo so that
moves, loads, etc. are recognized.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35031 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-08 22:09:11 +00:00
Bill Wendling
c32a7f98ab Remove useless pattern fragments.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35009 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-07 18:23:09 +00:00
Bill Wendling
bc9bffa27b Properly support v8i8 and v4i16 types. It now converts them to v2i32 for
load and stores.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35002 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-07 05:43:18 +00:00
Bill Wendling
a31bd27f12 Add LOAD/STORE support for MMX.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@34978 91177308-0d34-0410-b5e6-96231b3b80d8
2007-03-06 18:53:42 +00:00