d07be232ba
Core antialiasing for load and store.
...
llvm-svn: 30597
2006-09-25 16:29:54 +00:00
5e2bacd6be
Fix jump tables to match gcc (and the ABI and whatnot)
...
llvm-svn: 30594
2006-09-24 19:46:56 +00:00
783a4a9d86
Add support for other relocation bases to jump tables, as well as custom asm directives
...
llvm-svn: 30593
2006-09-24 19:45:58 +00:00
68324f8f85
jump table note
...
llvm-svn: 30591
2006-09-24 13:13:10 +00:00
77c0757f8b
PIC jump table entries are always 32-bit. This fixes PIC jump table support on X86-64.
...
llvm-svn: 30590
2006-09-24 05:22:38 +00:00
059c79264f
Style changes only. Remove dead code, fix a comment.
...
llvm-svn: 30588
2006-09-23 15:13:08 +00:00
6bd6da4097
Be far more careful when splitting a loop header, either to form a preheader
...
or when splitting loops with a common header into multiple loops. In particular
the old code would always insert the preheader before the old loop header. This
is disasterous in cases where the loop hasn't been rotated. For example, it can
produce code like:
.. outside the loop...
jmp LBB1_2 #bb13.outer
LBB1_1: #bb1
movsd 8(%esp,%esi,8), %xmm1
mulsd (%edi), %xmm1
addsd %xmm0, %xmm1
addl $24, %edi
incl %esi
jmp LBB1_3 #bb13
LBB1_2: #bb13.outer
leal (%edx,%eax,8), %edi
pxor %xmm1, %xmm1
xorl %esi, %esi
LBB1_3: #bb13
movapd %xmm1, %xmm0
cmpl $4, %esi
jl LBB1_1 #bb1
Note that the loop body is actually LBB1_1 + LBB1_3, which means that the
loop now contains an uncond branch WITHIN it to jump around the inserted
loop header (LBB1_2). Doh.
This patch changes the preheader insertion code to insert it in the right
spot, producing this code:
... outside the loop, fall into the header ...
LBB1_1: #bb13.outer
leal (%edx,%eax,8), %esi
pxor %xmm0, %xmm0
xorl %edi, %edi
jmp LBB1_3 #bb13
LBB1_2: #bb1
movsd 8(%esp,%edi,8), %xmm0
mulsd (%esi), %xmm0
addsd %xmm1, %xmm0
addl $24, %esi
incl %edi
LBB1_3: #bb13
movapd %xmm0, %xmm1
cmpl $4, %edi
jl LBB1_2 #bb1
Totally crazy, no branch in the loop! :)
llvm-svn: 30587
2006-09-23 08:19:21 +00:00
608cd05e3f
Teach UpdateDomInfoForRevectoredPreds to handle revectored preds that are not
...
reachable, making it general purpose enough for use by InsertPreheaderForLoop.
Eliminate custom dominfo updating code in InsertPreheaderForLoop, using
UpdateDomInfoForRevectoredPreds instead.
llvm-svn: 30586
2006-09-23 07:40:52 +00:00
4091f4690a
add method, correct comment
...
llvm-svn: 30584
2006-09-23 04:03:45 +00:00
1da0ab2f58
Delete dead code; fix 80 col violations.
...
llvm-svn: 30583
2006-09-22 21:43:59 +00:00
72d4c070c0
add a note
...
llvm-svn: 30581
2006-09-22 11:36:17 +00:00
d31efd190f
Fold AND and ROTL more often
...
llvm-svn: 30577
2006-09-22 05:01:56 +00:00
81c9e42bea
remove extra white spaces.
...
llvm-svn: 30576
2006-09-22 01:07:57 +00:00
0c4e730c9c
Use iterative algorith to assign DFS number. This reduces
...
call stack depth.
llvm-svn: 30575
2006-09-22 01:05:33 +00:00
449a0c7e33
Make it work for DAG combine of multi-value nodes.
...
llvm-svn: 30573
2006-09-21 19:04:05 +00:00
35f7eebb49
core corrections
...
llvm-svn: 30570
2006-09-21 17:35:47 +00:00
5d19d59017
Basic "in frame" alias analysis.
...
llvm-svn: 30568
2006-09-21 16:28:59 +00:00
7b700e517a
more condition codes
...
llvm-svn: 30567
2006-09-21 13:06:26 +00:00
0c71a5adc8
if a constant can't be an immediate, add it to the constant pool
...
llvm-svn: 30566
2006-09-21 11:29:52 +00:00
082db3f9aa
fold (aext (and (trunc x), cst)) -> (and x, cst).
...
llvm-svn: 30561
2006-09-21 06:40:43 +00:00
fa9f92cf65
Check the right value type. This fixes 186.crafty on x86
...
llvm-svn: 30560
2006-09-21 06:17:39 +00:00
08a8ccaaf1
implemented
...
llvm-svn: 30559
2006-09-21 06:14:54 +00:00
8d8a3bf9c9
Compile:
...
int %test(ulong *%tmp) {
%tmp = load ulong* %tmp ; <ulong> [#uses=1]
%tmp.mask = shr ulong %tmp, ubyte 50 ; <ulong> [#uses=1]
%tmp.mask = cast ulong %tmp.mask to ubyte
%tmp2 = and ubyte %tmp.mask, 3 ; <ubyte> [#uses=1]
%tmp2 = cast ubyte %tmp2 to int ; <int> [#uses=1]
ret int %tmp2
}
to:
_test:
movl 4(%esp), %eax
movl 4(%eax), %eax
shrl $18, %eax
andl $3, %eax
ret
instead of:
_test:
movl 4(%esp), %eax
movl 4(%eax), %eax
shrl $18, %eax
# TRUNCATE movb %al, %al
andb $3, %al
movzbl %al, %eax
ret
llvm-svn: 30558
2006-09-21 06:14:31 +00:00
a31f0a622b
Generalize (zext (truncate x)) and (sext (truncate x)) folding to work when
...
the src/dst are not the same size. This catches things like "truncate
32-bit X to 8 bits, then zext to 16", which happens a bit on X86.
llvm-svn: 30557
2006-09-21 06:00:20 +00:00
1c18c0db79
Fit in 80-cols
...
llvm-svn: 30556
2006-09-21 05:46:00 +00:00
51c95cdd82
Fix Transforms/IndVarsSimplify/2006-09-20-LFTR-Crash.ll
...
llvm-svn: 30555
2006-09-21 05:12:20 +00:00
c68bbef874
Fix compile error.
...
llvm-svn: 30553
2006-09-21 02:08:31 +00:00
fde9c308b2
Don't rewrite ConstantExpr::get.
...
llvm-svn: 30552
2006-09-21 01:05:35 +00:00
d74c55f483
Once we're down to "setcc type constant1, constant2", at least come up
...
with the right answer.
llvm-svn: 30550
2006-09-20 23:02:24 +00:00
3c5b3df6a0
Adding codegeneration for StdCall & FastCall calling conventions
...
llvm-svn: 30549
2006-09-20 22:03:51 +00:00
ccdaecc448
Account for pseudo-ops correctly
...
llvm-svn: 30548
2006-09-20 20:08:52 +00:00
a81a75c390
The DarwinAsmPrinter need not check for isDarwin. createPPCAsmPrinterPass
...
should create the right asmprinter subclass.
llvm-svn: 30542
2006-09-20 17:12:19 +00:00
8597a2fc4e
Wrap some darwin'isms with isDarwin checks.
...
llvm-svn: 30541
2006-09-20 17:07:15 +00:00
cfff1c3f86
Use a total ordering to compare instructions.
...
Fixes infinite loop in resolve().
llvm-svn: 30540
2006-09-20 17:04:01 +00:00
44cb67af5c
simplify
...
llvm-svn: 30535
2006-09-20 15:37:57 +00:00
f007f21c8a
catch constants more often
...
llvm-svn: 30534
2006-09-20 15:05:49 +00:00
97a4e99aff
clarify with test case
...
llvm-svn: 30531
2006-09-20 14:48:00 +00:00
e2d138a462
Add Note
...
llvm-svn: 30530
2006-09-20 14:40:01 +00:00
fba9e8f422
item done
...
llvm-svn: 30518
2006-09-20 06:41:56 +00:00
c8cd62d381
Compile:
...
int test3(int a, int b) { return (a < 0) ? a : 0; }
to:
_test3:
srawi r2, r3, 31
and r3, r2, r3
blr
instead of:
_test3:
cmpwi cr0, r3, 1
li r2, 0
blt cr0, LBB2_2 ;entry
LBB2_1: ;entry
mr r3, r2
LBB2_2: ;entry
blr
This implements: PowerPC/select_lt0.ll:seli32_a_a
llvm-svn: 30517
2006-09-20 06:41:35 +00:00
27d8985a71
add a note
...
llvm-svn: 30515
2006-09-20 06:32:10 +00:00
8746e2cd57
Fold the full generality of (any_extend (truncate x))
...
llvm-svn: 30514
2006-09-20 06:29:17 +00:00
8b68decb27
Two things:
...
1. teach SimplifySetCC that '(srl (ctlz x), 5) == 0' is really x != 0.
2. Teach visitSELECT_CC to use SimplifySetCC instead of calling it and
ignoring the result. This allows us to compile:
bool %test(ulong %x) {
%tmp = setlt ulong %x, 4294967296
ret bool %tmp
}
to:
_test:
cntlzw r2, r3
cmplwi cr0, r3, 1
srwi r2, r2, 5
li r3, 0
beq cr0, LBB1_2 ;
LBB1_1: ;
mr r3, r2
LBB1_2: ;
blr
instead of:
_test:
addi r2, r3, -1
cntlzw r2, r2
cntlzw r3, r3
srwi r2, r2, 5
cmplwi cr0, r2, 0
srwi r2, r3, 5
li r3, 0
bne cr0, LBB1_2 ;
LBB1_1: ;
mr r3, r2
LBB1_2: ;
blr
This isn't wonderful, but it's an improvement.
llvm-svn: 30513
2006-09-20 06:19:26 +00:00
f62f090ea1
This is already done
...
llvm-svn: 30512
2006-09-20 04:59:33 +00:00
380c7e9a59
We went through all that trouble to compute whether it was safe to transform
...
this comparison, but never checked it. Whoops, no wonder we miscompiled
177.mesa!
llvm-svn: 30511
2006-09-20 04:44:59 +00:00
da9b1a9322
Improve PPC64 equality comparisons like PPC32 comparisons.
...
llvm-svn: 30510
2006-09-20 04:33:27 +00:00
aa3926b7ea
Two improvements:
...
1. Codegen this comparison:
if (X == 0x8000)
as:
cmplwi cr0, r3, 32768
bne cr0, LBB1_2 ;cond_next
instead of:
lis r2, 0
ori r2, r2, 32768
cmpw cr0, r3, r2
bne cr0, LBB1_2 ;cond_next
2. Codegen this comparison:
if (X == 0x12345678)
as:
xoris r2, r3, 4660
cmplwi cr0, r2, 22136
bne cr0, LBB1_2 ;cond_next
instead of:
lis r2, 4660
ori r2, r2, 22136
cmpw cr0, r3, r2
bne cr0, LBB1_2 ;cond_next
llvm-svn: 30509
2006-09-20 04:25:47 +00:00
ab33d350a7
Add a note that we should match rlwnm better
...
llvm-svn: 30508
2006-09-20 03:59:25 +00:00
601b86513d
Legalize is no longer limited to cleverness with just constant shift amounts.
...
Allow it to be clever when possible and fall back to the gross code when needed.
This allows us to compile:
long long foo1(long long X, int C) {
return X << (C|32);
}
long long foo2(long long X, int C) {
return X << (C&~32);
}
to:
_foo1:
rlwinm r2, r5, 0, 27, 31
slw r3, r4, r2
li r4, 0
blr
.globl _foo2
.align 4
_foo2:
rlwinm r2, r5, 0, 27, 25
subfic r5, r2, 32
slw r3, r3, r2
srw r5, r4, r5
or r3, r3, r5
slw r4, r4, r2
blr
instead of:
_foo1:
ori r2, r5, 32
subfic r5, r2, 32
addi r6, r2, -32
srw r5, r4, r5
slw r3, r3, r2
slw r6, r4, r6
or r3, r3, r5
slw r4, r4, r2
or r3, r3, r6
blr
.globl _foo2
.align 4
_foo2:
rlwinm r2, r5, 0, 27, 25
subfic r5, r2, 32
addi r6, r2, -32
srw r5, r4, r5
slw r3, r3, r2
slw r6, r4, r6
or r3, r3, r5
slw r4, r4, r2
or r3, r3, r6
blr
llvm-svn: 30507
2006-09-20 03:47:40 +00:00
875ea0cdbd
Expand 64-bit shifts more optimally if we know that the high bit of the
...
shift amount is one or zero. For example, for:
long long foo1(long long X, int C) {
return X << (C|32);
}
long long foo2(long long X, int C) {
return X << (C&~32);
}
we get:
_foo1:
movb $31, %cl
movl 4(%esp), %edx
andb 12(%esp), %cl
shll %cl, %edx
xorl %eax, %eax
ret
_foo2:
movb $223, %cl
movl 4(%esp), %eax
movl 8(%esp), %edx
andb 12(%esp), %cl
shldl %cl, %eax, %edx
shll %cl, %eax
ret
instead of:
_foo1:
subl $4, %esp
movl %ebx, (%esp)
movb $32, %bl
movl 8(%esp), %eax
movl 12(%esp), %edx
movb %bl, %cl
orb 16(%esp), %cl
shldl %cl, %eax, %edx
shll %cl, %eax
xorl %ecx, %ecx
testb %bl, %bl
cmovne %eax, %edx
cmovne %ecx, %eax
movl (%esp), %ebx
addl $4, %esp
ret
_foo2:
subl $4, %esp
movl %ebx, (%esp)
movb $223, %cl
movl 8(%esp), %eax
movl 12(%esp), %edx
andb 16(%esp), %cl
shldl %cl, %eax, %edx
shll %cl, %eax
xorl %ecx, %ecx
xorb %bl, %bl
testb %bl, %bl
cmovne %eax, %edx
cmovne %ecx, %eax
movl (%esp), %ebx
addl $4, %esp
ret
llvm-svn: 30506
2006-09-20 03:38:48 +00:00
Jim Laskey