2a4d7b845b
remove cases handled elsewhere
...
llvm-svn: 28150
2006-05-06 22:43:44 +00:00
1ecb2a2dac
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
llvm-svn: 28146
2006-05-06 09:30:03 +00:00
907e392dba
Fold trunc(any_ext). This gives stuff like:
...
27,28c27
< movzwl %di, %edi
< movl %edi, %ebx
---
> movw %di, %bx
llvm-svn: 28137
2006-05-05 22:56:26 +00:00
57f8c5a387
Shrink shifts when possible.
...
llvm-svn: 28136
2006-05-05 22:53:17 +00:00
3d26577396
Fold (fpext (load x)) -> (extload x)
...
llvm-svn: 28130
2006-05-05 21:34:35 +00:00
25a5283a86
Fold some common code.
...
llvm-svn: 28124
2006-05-05 06:32:04 +00:00
002ee91457
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))
llvm-svn: 28123
2006-05-05 06:31:05 +00:00
5ac4293606
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
llvm-svn: 28122
2006-05-05 06:10:43 +00:00
812646aa0c
Implement a variety of simplifications for ANY_EXTEND.
...
llvm-svn: 28121
2006-05-05 05:58:59 +00:00
8d6fc20181
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))
llvm-svn: 28120
2006-05-05 05:51:50 +00:00
2b48a94413
Remove a bogus transformation. This fixes SingleSource/UnitTests/2006-01-23-InitializedBitField.c
...
with some changes I have to the new CFE.
llvm-svn: 28022
2006-04-28 23:33:20 +00:00
662e940f73
Fix a couple more memory issues
...
llvm-svn: 27930
2006-04-21 15:32:26 +00:00
cc47ab3305
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).
llvm-svn: 27922
2006-04-20 23:55:59 +00:00
a320abc494
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.
llvm-svn: 27874
2006-04-20 08:56:16 +00:00
e1401e3610
Canonicalize vvector_shuffle(x,x) -> vvector_shuffle(x,undef) to enable patterns
...
to match again :)
llvm-svn: 27533
2006-04-08 05:34:25 +00:00
098c01e94e
Codegen shufflevector as VVECTOR_SHUFFLE
...
llvm-svn: 27529
2006-04-08 04:15:24 +00:00
613996c55e
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.
llvm-svn: 27472
2006-04-06 23:20:43 +00:00
4ea52cac01
Do not create ZEXTLOAD's unless we are before legalize or the operation is
...
legal.
llvm-svn: 27402
2006-04-04 17:39:18 +00:00
e1e3adf802
Add a missing check, this fixes UnitTests/Vector/sumarray.c
...
llvm-svn: 27375
2006-04-03 17:29:28 +00:00
04c00fc844
Add a missing check, which broke a bunch of vector tests.
...
llvm-svn: 27374
2006-04-03 17:21:50 +00:00
94f012f606
back this out
...
llvm-svn: 27367
2006-04-03 03:16:50 +00:00
015eaf5f33
This should be a win of every arch
...
llvm-svn: 27364
2006-04-02 21:42:45 +00:00
4993249a04
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
llvm-svn: 27356
2006-04-02 06:11:11 +00:00
0442a18758
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
llvm-svn: 27343
2006-04-02 03:25:57 +00:00
e4e64b6b85
Implement constant folding of bit_convert of arbitrary constant vbuild_vector nodes.
...
llvm-svn: 27341
2006-04-02 02:53:43 +00:00
39dcf1a9e2
Delete identity shuffles, implementing CodeGen/Generic/vector-identity-shuffle.ll
...
llvm-svn: 27317
2006-03-31 22:16:43 +00:00
7e30af3887
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
llvm-svn: 27297
2006-03-31 18:10:41 +00:00
2d8551c85b
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
llvm-svn: 27296
2006-03-31 18:06:18 +00:00
20e619fba3
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
llvm-svn: 27236
2006-03-28 22:19:47 +00:00
a46dfe80c8
Canonicalize VECTOR_SHUFFLE(X, X, Y) -> VECTOR_SHUFFLE(X,undef,Y')
...
llvm-svn: 27235
2006-03-28 22:11:53 +00:00
c9992548fc
Turn a series of extract_element's feeding a build_vector into a
...
vector_shuffle node. For this:
void test(__m128 *res, __m128 *A, __m128 *B) {
*res = _mm_unpacklo_ps(*A, *B);
}
we now produce this code:
_test:
movl 8(%esp), %eax
movaps (%eax), %xmm0
movl 12(%esp), %eax
unpcklps (%eax), %xmm0
movl 4(%esp), %eax
movaps %xmm0, (%eax)
ret
instead of this:
_test:
subl $76, %esp
movl 88(%esp), %eax
movaps (%eax), %xmm0
movaps %xmm0, (%esp)
movaps %xmm0, 32(%esp)
movss 4(%esp), %xmm0
movss 32(%esp), %xmm1
unpcklps %xmm0, %xmm1
movl 84(%esp), %eax
movaps (%eax), %xmm0
movaps %xmm0, 16(%esp)
movaps %xmm0, 48(%esp)
movss 20(%esp), %xmm0
movss 48(%esp), %xmm2
unpcklps %xmm0, %xmm2
unpcklps %xmm1, %xmm2
movl 80(%esp), %eax
movaps %xmm2, (%eax)
addl $76, %esp
ret
GCC produces this (with -fomit-frame-pointer):
_test:
subl $12, %esp
movl 20(%esp), %eax
movaps (%eax), %xmm0
movl 24(%esp), %eax
unpcklps (%eax), %xmm0
movl 16(%esp), %eax
movaps %xmm0, (%eax)
addl $12, %esp
ret
llvm-svn: 27233
2006-03-28 20:28:38 +00:00
b7163598f9
Don't crash on X^X if X is a vector. Instead, produce a vector of zeros.
...
llvm-svn: 27229
2006-03-28 19:11:05 +00:00
dc1eab5886
Don't call SimplifyDemandedBits on vectors
...
llvm-svn: 27128
2006-03-25 22:19:00 +00:00
5336a59e4b
fold insertelement(buildvector) -> buildvector if the inserted element # is
...
a constant. This implements test_constant_insert in CodeGen/Generic/vector.ll
llvm-svn: 26851
2006-03-19 01:27:56 +00:00
bb01d4f272
Remove BRTWOWAY*
...
Make the PPC backend not dependent on BRTWOWAY_CC and make the branch
selector smarter about the code it generates, fixing a case in the
readme.
llvm-svn: 26814
2006-03-17 01:40:33 +00:00
68ac09d5cb
make sure dead token factor nodes are removed by the dag combiner.
...
llvm-svn: 26731
2006-03-13 18:37:30 +00:00
d8c2a48d58
Fold X+Y -> X|Y when safe. This implements:
...
Regression/CodeGen/PowerPC/and_add.ll
a case that occurs with dynamic allocas of constant size.
llvm-svn: 26727
2006-03-13 06:51:27 +00:00
8bb6cb7d7b
add a couple of missing folds
...
llvm-svn: 26724
2006-03-13 06:26:26 +00:00
bdaf4f38b5
Reinstate this now that the offending opposite xform has been removed.
...
llvm-svn: 26548
2006-03-05 19:53:55 +00:00
d428e22c07
Back out fold (shl (add x, c1), c2) -> (add (shl x, c2), c1<<c2) for now.
...
It's causing an infinite loop compiling ldecod on x86 / Darwin.
llvm-svn: 26544
2006-03-05 07:30:16 +00:00
3bc4050217
Add some simple copysign folds
...
llvm-svn: 26543
2006-03-05 05:30:57 +00:00
f29f5204cc
fold (mul (add x, c1), c2) -> (add (mul x, c2), c1*c2)
...
fold (shl (add x, c1), c2) -> (add (shl x, c2), c1<<c2)
This allows us to compile CodeGen/PowerPC/addi-reassoc.ll into:
_test1:
slwi r2, r4, 4
add r2, r2, r3
lwz r3, 36(r2)
blr
_test2:
mulli r2, r4, 5
add r2, r2, r3
lbz r2, 11(r2)
extsb r3, r2
blr
instead of:
_test1:
addi r2, r4, 2
slwi r2, r2, 4
add r2, r3, r2
lwz r3, 4(r2)
blr
_test2:
addi r2, r4, 2
mulli r2, r2, 5
add r2, r3, r2
lbz r2, 1(r2)
extsb r3, r2
blr
llvm-svn: 26535
2006-03-04 23:33:26 +00:00
0db2f2c689
Fix CodeGen/Generic/2006-03-01-dagcombineinfloop.ll, an infinite loop
...
in the dag combiner on 176.gcc on x86.
llvm-svn: 26459
2006-03-01 21:47:21 +00:00
232024edb8
Fix a typo evan noticed
...
llvm-svn: 26454
2006-03-01 19:55:35 +00:00
bc1c85beea
Add support for target-specific dag combines
...
llvm-svn: 26443
2006-03-01 04:53:38 +00:00
fbcd62d3bb
Add a new AddToWorkList method, start using it
...
llvm-svn: 26441
2006-03-01 04:03:14 +00:00
324871ef1a
Pull shifts by a constant through multiplies (a form of reassociation),
...
implementing Regression/CodeGen/X86/mul-shift-reassoc.ll
llvm-svn: 26440
2006-03-01 03:44:24 +00:00
b97aab4371
Vector ops lowering.
...
llvm-svn: 26436
2006-03-01 01:09:54 +00:00
f0032b350c
Compile:
...
unsigned foo4(unsigned short *P) { return *P & 255; }
unsigned foo5(short *P) { return *P & 255; }
to:
_foo4:
lbz r3,1(r3)
blr
_foo5:
lbz r3,1(r3)
blr
not:
_foo4:
lhz r2, 0(r3)
rlwinm r3, r2, 0, 24, 31
blr
_foo5:
lhz r2, 0(r3)
rlwinm r3, r2, 0, 24, 31
blr
llvm-svn: 26419
2006-02-28 06:49:37 +00:00
bdbc4476d9
Fold "and (LOAD P), 255" -> zextload. This allows us to compile:
...
unsigned foo3(unsigned *P) { return *P & 255; }
as:
_foo3:
lbz r3, 3(r3)
blr
instead of:
_foo3:
lwz r2, 0(r3)
rlwinm r3, r2, 0, 24, 31
blr
and:
unsigned short foo2(float a) { return a; }
as:
_foo2:
fctiwz f0, f1
stfd f0, -8(r1)
lhz r3, -2(r1)
blr
instead of:
_foo2:
fctiwz f0, f1
stfd f0, -8(r1)
lwz r2, -4(r1)
rlwinm r3, r2, 0, 16, 31
blr
llvm-svn: 26417
2006-02-28 06:35:35 +00:00
Chris Lattner