Commit Graph

182 Commits

Author SHA1 Message Date
Chris Lattner
3577e38c2b change internal impl of dag combiner so that calls to CombineTo never have to
make a temporary vector.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29618 91177308-0d34-0410-b5e6-96231b3b80d8
2006-08-11 17:56:38 +00:00
Chris Lattner
b9ea4a39b8 Change one ReplaceAllUsesWith method to take an array of operands to replace
instead of a vector of operands.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29616 91177308-0d34-0410-b5e6-96231b3b80d8
2006-08-11 17:46:28 +00:00
Chris Lattner
bd564bfc63 Start eliminating temporary vectors used to create DAG nodes. Instead, pass
in the start of an array and a count of operands where applicable.  In many
cases, the number of operands is known, so this static array can be allocated
on the stack, avoiding the heap.  In many other cases, a SmallVector can be
used, which has the same benefit in the common cases.

I updated a lot of code calling getNode that takes a vector, but ran out of
time.  The rest of the code should be updated, and these methods should be
removed.

We should also do the same thing to eliminate the methods that take a
vector of MVT::ValueTypes.

It would be extra nice to convert the dagiselemitter to avoid creating vectors
for operands when calling getTargetNode.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29566 91177308-0d34-0410-b5e6-96231b3b80d8
2006-08-08 02:23:42 +00:00
Reid Spencer
9160a6a18f Initialize some variables the compiler warns about.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29277 91177308-0d34-0410-b5e6-96231b3b80d8
2006-07-25 20:44:41 +00:00
Evan Cheng
917ec983df If a shuffle is a splat, check if the argument is a build_vector with all elements being the same. If so, return the argument.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29242 91177308-0d34-0410-b5e6-96231b3b80d8
2006-07-21 08:25:53 +00:00
Evan Cheng
e7bec0dbb5 If a shuffle is unary, i.e. one of the vector argument is not needed, turn the
operand into a undef and adjust mask accordingly.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29232 91177308-0d34-0410-b5e6-96231b3b80d8
2006-07-20 22:44:41 +00:00
Andrew Lenharth
ae6153f943 80 cols
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29221 91177308-0d34-0410-b5e6-96231b3b80d8
2006-07-20 17:43:27 +00:00
Andrew Lenharth
ed41f1bb19 Reduce number of exported symbols
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29220 91177308-0d34-0410-b5e6-96231b3b80d8
2006-07-20 17:28:38 +00:00
Chris Lattner
360e8200ec Mark these two classes as hidden, shrinking libllbmgcc.dylib by 25K
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28970 91177308-0d34-0410-b5e6-96231b3b80d8
2006-06-28 21:58:30 +00:00
Andrew Lenharth
232c910b8a Start on my todo list
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28752 91177308-0d34-0410-b5e6-96231b3b80d8
2006-06-12 16:07:18 +00:00
Evan Cheng
7b336a8746 visitVBinOp: Can't fold divide by zero!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28584 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-31 06:08:35 +00:00
Chris Lattner
729c6d1da8 Fix a nasty dag combiner bug that caused nondeterminstic crashes (MY FAVORITE!):
SimplifySelectOps would eliminate a Select, delete it, then return true.

The clients would see that it did something and return null.

The top level would see a null return, and decide that nothing happened,
proceeding to process the node in other ways: boom.

The fix is simple: clients of SimplifySelectOps should return the select
node itself.

In order to catch really obnoxious boogs like this in the future, add an
assert that nodes are not deleted.  We do this by checking for a sentry node
type that the SDNode dtor sets when a node is destroyed.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28514 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-27 00:43:02 +00:00
Andrew Lenharth
dae9cbe8d4 Move this code to a common place
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28329 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-16 17:42:15 +00:00
Chris Lattner
5eed34d208 Comment out dead variables
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28252 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-12 17:57:54 +00:00
Chris Lattner
21a57dc751 Two simplifications for token factor nodes: simplify tf(x,x) -> x.
simplify tf(x,y,y,z) -> tf(x,y,z).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28233 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-12 05:01:37 +00:00
Evan Cheng
60e8c71c9f Debugging info
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28200 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-09 06:55:15 +00:00
Chris Lattner
4b37e87ab9 Make the case I just checked in stronger. Now we compile this:
short test2(short X, short x) {
  int Y = (short)(X+x);
  return Y >> 1;
}

to:

_test2:
        add r2, r3, r4
        extsh r2, r2
        srawi r3, r2, 1
        blr

instead of:

_test2:
        add r2, r3, r4
        extsh r2, r2
        srwi r2, r2, 1
        extsh r3, r2
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28175 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08 21:18:59 +00:00
Chris Lattner
eaeda56649 Implement and_sext.ll:test3, generating:
_test4:
        srawi r3, r3, 16
        blr

instead of:

_test4:
        srwi r2, r3, 16
        extsh r3, r2
        blr

for:

short test4(unsigned X) {
  return (X >> 16);
}


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28174 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08 20:59:41 +00:00
Chris Lattner
a850446a0b Compile this:
short test4(unsigned X) {
  return (X >> 16);
}

to:

_test4:
        movl 4(%esp), %eax
        sarl $16, %eax
        ret

instead of:

_test4:
        movl $-65536, %eax
        andl 4(%esp), %eax
        sarl $16, %eax
        ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28171 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08 20:51:54 +00:00
Nate Begeman
5c742681ed Fix PR772
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28161 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08 01:35:01 +00:00
Chris Lattner
310b578023 Simplify some code, add a couple minor missed folds
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28152 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-06 23:06:26 +00:00
Chris Lattner
541a24f7af remove cases handled elsewhere
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28150 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-06 22:43:44 +00:00
Chris Lattner
ee4ea92358 Use the new TargetLowering::ComputeNumSignBits method to eliminate
sign_extend_inreg operations.  Though ComputeNumSignBits is still rudimentary,
this is enough to compile this:

short test(short X, short x) {
  int Y = X+x;
  return (Y >> 1);
}
short test2(short X, short x) {
  int Y = (short)(X+x);
  return Y >> 1;
}

into:

_test:
        add r2, r3, r4
        srawi r3, r2, 1
        blr
_test2:
        add r2, r3, r4
        extsh r2, r2
        srawi r3, r2, 1
        blr

instead of:

_test:
        add r2, r3, r4
        srawi r2, r2, 1
        extsh r3, r2
        blr
_test2:
        add r2, r3, r4
        extsh r2, r2
        srawi r2, r2, 1
        extsh r3, r2
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28146 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-06 09:30:03 +00:00
Chris Lattner
b72773bb88 Fold trunc(any_ext). This gives stuff like:
27,28c27
<       movzwl %di, %edi
<       movl %edi, %ebx
---
>       movw %di, %bx


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28137 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 22:56:26 +00:00
Chris Lattner
06afe07037 Shrink shifts when possible.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28136 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 22:53:17 +00:00
Chris Lattner
e564dbb51c Fold (fpext (load x)) -> (extload x)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28130 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 21:34:35 +00:00
Chris Lattner
0d8dae749c Fold some common code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28124 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 06:32:04 +00:00
Chris Lattner
540121f1ec Implement:
// fold (and (sext x), (sext y)) -> (sext (and x, y))
  // fold (or  (sext x), (sext y)) -> (sext (or  x, y))
  // fold (xor (sext x), (sext y)) -> (sext (xor x, y))
  // fold (and (aext x), (aext y)) -> (aext (and x, y))
  // fold (or  (aext x), (aext y)) -> (aext (or  x, y))
  // fold (xor (aext x), (aext y)) -> (aext (xor x, y))


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28123 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 06:31:05 +00:00
Chris Lattner
a3dc3f692c Pull and through and/or/xor. This compiles some bitfield code to:
mov EAX, DWORD PTR [ESP + 4]
        mov ECX, DWORD PTR [EAX]
        mov EDX, ECX
        add EDX, EDX
        or EDX, ECX
        and EDX, -2147483648
        and ECX, 2147483647
        or EDX, ECX
        mov DWORD PTR [EAX], EDX
        ret

instead of:

        sub ESP, 4
        mov DWORD PTR [ESP], ESI
        mov EAX, DWORD PTR [ESP + 8]
        mov ECX, DWORD PTR [EAX]
        mov EDX, ECX
        add EDX, EDX
        mov ESI, ECX
        and ESI, -2147483648
        and EDX, -2147483648
        or EDX, ESI
        and ECX, 2147483647
        or EDX, ECX
        mov DWORD PTR [EAX], EDX
        mov ESI, DWORD PTR [ESP]
        add ESP, 4
        ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28122 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 06:10:43 +00:00
Chris Lattner
5ffc066912 Implement a variety of simplifications for ANY_EXTEND.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28121 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 05:58:59 +00:00
Chris Lattner
35e5c14b80 Factor some code, add these transformations:
// fold (and (trunc x), (trunc y)) -> (trunc (and x, y))
  // fold (or  (trunc x), (trunc y)) -> (trunc (or  x, y))
  // fold (xor (trunc x), (trunc y)) -> (trunc (xor x, y))


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28120 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05 05:51:50 +00:00
Chris Lattner
25c344a758 Remove a bogus transformation. This fixes SingleSource/UnitTests/2006-01-23-InitializedBitField.c
with some changes I have to the new CFE.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28022 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-28 23:33:20 +00:00
Chris Lattner
ef027f940c Fix a couple more memory issues
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27930 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-21 15:32:26 +00:00
Chris Lattner
fedced7bc3 Fix a really subtle and obnoxious memory bug that caused issues with an
llvm-gcc4 boostrap.  Whenever a node is deleted by the dag combiner, it
*must* be returned by the visit function, or the dag combiner will not
know that the node has been processed (and will, e.g., send it to the
target dag combine xforms).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27922 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-20 23:55:59 +00:00
Evan Cheng
44f1f09b4e Turn a VAND into a VECTOR_SHUFFLE is applicable.
DAG combiner can turn a VAND V, <-1, 0, -1, -1>, i.e. vector clear elements,
into a vector shuffle with a zero vector. It only does so when TLI tells it
the xform is profitable.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27874 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-20 08:56:16 +00:00
Chris Lattner
17614ea63d Canonicalize vvector_shuffle(x,x) -> vvector_shuffle(x,undef) to enable patterns
to match again :)


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27533 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-08 05:34:25 +00:00
Chris Lattner
3e104b1116 Codegen shufflevector as VVECTOR_SHUFFLE
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27529 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-08 04:15:24 +00:00
Evan Cheng
c04766a228 1. If both vector operands of a vector_shuffle are undef, turn it into an undef.
2. A shuffle mask element can also be an undef.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27472 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-06 23:20:43 +00:00
Chris Lattner
e44be60ee9 Do not create ZEXTLOAD's unless we are before legalize or the operation is
legal.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27402 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-04 17:39:18 +00:00
Chris Lattner
97c2073270 Add a missing check, this fixes UnitTests/Vector/sumarray.c
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27375 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-03 17:29:28 +00:00
Chris Lattner
a4c5d8c6b4 Add a missing check, which broke a bunch of vector tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27374 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-03 17:21:50 +00:00
Andrew Lenharth
cf4fb61f6c back this out
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27367 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-03 03:16:50 +00:00
Andrew Lenharth
50a0d426e8 This should be a win of every arch
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27364 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-02 21:42:45 +00:00
Chris Lattner
350bec0fb9 Add a little dag combine to compile this:
int %AreSecondAndThirdElementsBothNegative(<4 x float>* %in) {
entry:
        %tmp1 = load <4 x float>* %in           ; <<4 x float>> [#uses=1]
        %tmp = tail call int %llvm.ppc.altivec.vcmpgefp.p( int 1, <4 x float> < float 0x7FF8000000000000, float 0.000000e+00, float 0.000000e+00, float 0x7FF8000000000000 >, <4 x float> %tmp1 )           ; <int> [#uses=1]
        %tmp = seteq int %tmp, 0                ; <bool> [#uses=1]
        %tmp3 = cast bool %tmp to int           ; <int> [#uses=1]
        ret int %tmp3
}

into this:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        lvx v0, 0, r3
        lvx v1, r5, r4
        vcmpgefp. v0, v1, v0
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        mtspr 256, r2
        blr

instead of this:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        lvx v0, 0, r3
        lvx v1, r5, r4
        vcmpgefp. v0, v1, v0
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        xori r3, r3, 1
        cntlzw r3, r3
        srwi r3, r3, 5
        mtspr 256, r2
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27356 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-02 06:11:11 +00:00
Chris Lattner
edab1b9133 Constant fold all of the vector binops. This allows us to compile this:
"vector unsigned char mergeLowHigh = (vector unsigned char)
( 8, 9, 10, 11, 16, 17, 18, 19, 12, 13, 14, 15, 20, 21, 22, 23 );
vector unsigned char mergeHighLow = vec_xor( mergeLowHigh, vec_splat_u8(8));"

aka:

void %test2(<16 x sbyte>* %P) {
  store <16 x sbyte> cast (<4 x int> xor (<4 x int> cast (<16 x ubyte> < ubyte 8, ubyte 9, ubyte 10, ubyte 11, ubyte 16, ubyte 17, ubyte 18, ubyte 19, ubyte 12, ubyte 13, ubyte 14, ubyte 15, ubyte 20, ubyte 21, ubyte 22, ubyte 23 > to <4 x int>), <4 x int> cast (<16 x sbyte> < sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8 > to <4 x int>)) to <16 x sbyte>), <16 x sbyte> * %P
  ret void
}

into this:

_test2:
        mfspr r2, 256
        oris r4, r2, 32768
        mtspr 256, r4
        li r4, lo16(LCPI2_0)
        lis r5, ha16(LCPI2_0)
        lvx v0, r5, r4
        stvx v0, 0, r3
        mtspr 256, r2
        blr

instead of this:

_test2:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI2_0)
        lis r5, ha16(LCPI2_0)
        vspltisb v0, 8
        lvx v1, r5, r4
        vxor v0, v1, v0
        stvx v0, 0, r3
        mtspr 256, r2
        blr

... which occurs here:
http://developer.apple.com/hardware/ve/calcspeed.html


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27343 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-02 03:25:57 +00:00
Chris Lattner
6258fb2592 Implement constant folding of bit_convert of arbitrary constant vbuild_vector nodes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27341 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-02 02:53:43 +00:00
Chris Lattner
f1d0c623c6 Delete identity shuffles, implementing CodeGen/Generic/vector-identity-shuffle.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27317 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-31 22:16:43 +00:00
Chris Lattner
29cd7db310 Remove dead *extloads. This allows us to codegen vector.ll:test_extract_elt
to:

test_extract_elt:
        alloc r3 = ar.pfs,0,1,0,0
        adds r8 = 12, r32
        ;;
        ldfs f8 = [r8]
        mov ar.pfs = r3
        br.ret.sptk.many rp

instead of:

test_extract_elt:
        alloc r3 = ar.pfs,0,1,0,0
        adds r8 = 28, r32
        adds r9 = 24, r32
        adds r10 = 20, r32
        adds r11 = 16, r32
        ;;
        ldfs f6 = [r8]
        ;;
        ldfs f6 = [r9]
        adds r8 = 12, r32
        adds r9 = 8, r32
        adds r14 = 4, r32
        ;;
        ldfs f6 = [r10]
        ;;
        ldfs f6 = [r11]
        ldfs f8 = [r8]
        ;;
        ldfs f6 = [r9]
        ;;
        ldfs f6 = [r14]
        ;;
        ldfs f6 = [r32]
        mov ar.pfs = r3
        br.ret.sptk.many rp


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27297 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-31 18:10:41 +00:00
Chris Lattner
e4b953939c Delete dead loads in the dag. This allows us to compile
vector.ll:test_extract_elt2 into:

_test_extract_elt2:
        lfd f1, 32(r3)
        blr

instead of:

_test_extract_elt2:
        lfd f0, 56(r3)
        lfd f0, 48(r3)
        lfd f0, 40(r3)
        lfd f1, 32(r3)
        lfd f0, 24(r3)
        lfd f0, 16(r3)
        lfd f0, 8(r3)
        lfd f0, 0(r3)
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27296 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-31 18:06:18 +00:00
Chris Lattner
cef896e50c When building a VVECTOR_SHUFFLE node from extract_element operations, make
sure to build it as SHUFFLE(X, undef, mask), not SHUFFLE(X, X, mask).

The later is not canonical form, and prevents the PPC splat pattern from
matching.  For a particular splat, we go from generating this:

	li r10, lo16(LCPI1_0)
	lis r11, ha16(LCPI1_0)
	lvx v3, r11, r10
	vperm v3, v2, v2, v3

to generating:

	vspltw v3, v2, 3


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27236 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-28 22:19:47 +00:00