8ad8f71447
Move code dependency for MathExtras.h out of Constants.h.
...
llvm-svn: 22840
2005-08-17 20:06:22 +00:00
17e7599ecb
Promote dependency for MathExtras.h out of Constants.h.
...
llvm-svn: 22839
2005-08-17 20:04:34 +00:00
b74c666186
Culling out use of unions for converting FP to bits and vice versa.
...
llvm-svn: 22838
2005-08-17 19:34:49 +00:00
c6aa80668e
add a beta option for turning on dag->dag isel
...
llvm-svn: 22837
2005-08-17 19:33:30 +00:00
43ff01e2e6
initial hack at a dag->dag instruction selector. This is obviously woefully
...
incomplete, but it is a start. It handles basic argument/retval stuff, immediates,
add and sub.
llvm-svn: 22836
2005-08-17 19:33:03 +00:00
f61cce952b
add prototype, remove dead proto
...
llvm-svn: 22835
2005-08-17 19:32:03 +00:00
ab0de9d7fc
Fix a bug in RemoveDeadNodes where it would crash when its "optional"
...
argument is not specified.
Implement ReplaceAllUsesWith.
llvm-svn: 22834
2005-08-17 19:00:20 +00:00
686d6a1cb2
Switched to using BitsToDouble for int_to_float to avoid aliasing problem.
...
llvm-svn: 22831
2005-08-17 17:42:52 +00:00
33900811ee
Fix some bugs in the alpha backend, some of which I introduced yesterday,
...
and some that were preexisting. All alpha regtests pass now.
llvm-svn: 22829
2005-08-17 17:08:24 +00:00
898ba557d0
Change hex float constants for the sake of VC++.
...
llvm-svn: 22828
2005-08-17 09:44:59 +00:00
c9950c11a9
Add a new beta option for critical edge splitting, to avoid a problem that
...
Nate noticed in yacr2 (and I know occurs in other places as well).
This is still rough, as the critical edge blocks are not intelligently placed
but is added to get some idea to see if this improves performance.
llvm-svn: 22825
2005-08-17 06:37:43 +00:00
2bf7cb5213
Use a new helper to split critical edges, making the code simpler.
...
Do not claim to not change the CFG. We do change the cfg to split critical
edges. This isn't causing us a problem now, but could likely do so in the
future.
llvm-svn: 22824
2005-08-17 06:35:16 +00:00
ba28c2733f
Fix a regression on X86, where FP values can be promoted too.
...
llvm-svn: 22822
2005-08-17 06:06:25 +00:00
63f774ec6e
Fix a few small typos I noticed when converting this over to the DAG->DAG
...
selector. Also, there is no difference between addSImm and addImm, so just
use addImm, folding some branches.
llvm-svn: 22819
2005-08-17 01:25:14 +00:00
9828f26cf1
Removed UINT_TO_FP and SINT_TO_FP from ISel outright.
...
llvm-svn: 22818
2005-08-17 01:14:38 +00:00
73370ba5fd
thinko. Should fix s4addl.ll regression
...
llvm-svn: 22817
2005-08-17 00:47:24 +00:00
5909c8b10a
Remove ISel code generation for UINT_TO_FP and SINT_TO_FP. Now asserts if
...
marked as legal.
llvm-svn: 22816
2005-08-17 00:41:40 +00:00
6267b2c97c
Make UINT_TO_FP and SINT_TO_FP use generic expansion.
...
llvm-svn: 22815
2005-08-17 00:40:22 +00:00
f2516a9180
Added generic code expansion for [signed|unsigned] i32 to [f32|f64] casts in the
...
legalizer. PowerPC now uses this expansion instead of ISel version.
Example:
// signed integer to double conversion
double f1(signed x) {
return (double)x;
}
// unsigned integer to double conversion
double f2(unsigned x) {
return (double)x;
}
// signed integer to float conversion
float f3(signed x) {
return (float)x;
}
// unsigned integer to float conversion
float f4(unsigned x) {
return (float)x;
}
Byte Code:
internal fastcc double %_Z2f1i(int %x) {
entry:
%tmp.1 = cast int %x to double ; <double> [#uses=1]
ret double %tmp.1
}
internal fastcc double %_Z2f2j(uint %x) {
entry:
%tmp.1 = cast uint %x to double ; <double> [#uses=1]
ret double %tmp.1
}
internal fastcc float %_Z2f3i(int %x) {
entry:
%tmp.1 = cast int %x to float ; <float> [#uses=1]
ret float %tmp.1
}
internal fastcc float %_Z2f4j(uint %x) {
entry:
%tmp.1 = cast uint %x to float ; <float> [#uses=1]
ret float %tmp.1
}
internal fastcc double %_Z2g1i(int %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.2 = cast int %x to uint ; <uint> [#uses=1]
%tmp.3 = xor uint %tmp.2, 2147483648 ; <uint> [#uses=1]
%tmp.5 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %tmp.3, uint* %tmp.5
%tmp.9 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.10 = load double* %tmp.9 ; <double> [#uses=1]
%tmp.13 = load double* cast (long* %signed_bias to double*) ; <double> [#uses=1]
%tmp.14 = sub double %tmp.10, %tmp.13 ; <double> [#uses=1]
ret double %tmp.14
}
internal fastcc double %_Z2g2j(uint %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.1 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %x, uint* %tmp.1
%tmp.4 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.5 = load double* %tmp.4 ; <double> [#uses=1]
%tmp.8 = load double* cast (long* %unsigned_bias to double*) ; <double> [#uses=1]
%tmp.9 = sub double %tmp.5, %tmp.8 ; <double> [#uses=1]
ret double %tmp.9
}
internal fastcc float %_Z2g3i(int %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.2 = cast int %x to uint ; <uint> [#uses=1]
%tmp.3 = xor uint %tmp.2, 2147483648 ; <uint> [#uses=1]
%tmp.5 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %tmp.3, uint* %tmp.5
%tmp.9 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.10 = load double* %tmp.9 ; <double> [#uses=1]
%tmp.13 = load double* cast (long* %signed_bias to double*) ; <double> [#uses=1]
%tmp.14 = sub double %tmp.10, %tmp.13 ; <double> [#uses=1]
%tmp.16 = cast double %tmp.14 to float ; <float> [#uses=1]
ret float %tmp.16
}
internal fastcc float %_Z2g4j(uint %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.1 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %x, uint* %tmp.1
%tmp.4 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.5 = load double* %tmp.4 ; <double> [#uses=1]
%tmp.8 = load double* cast (long* %unsigned_bias to double*) ; <double> [#uses=1]
%tmp.9 = sub double %tmp.5, %tmp.8 ; <double> [#uses=1]
%tmp.11 = cast double %tmp.9 to float ; <float> [#uses=1]
ret float %tmp.11
}
PowerPC Code:
.machine ppc970
.const
.align 2
.CPIl1__Z2f1i_0: ; float 0x4330000080000000
.long 1501560836 ; float 4.5036e+15
.text
.align 2
.globl l1__Z2f1i
l1__Z2f1i:
.LBBl1__Z2f1i_0: ; entry
xoris r2, r3, 32768
stw r2, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl1__Z2f1i_0)
lfs f1, lo16(.CPIl1__Z2f1i_0)(r2)
fsub f1, f0, f1
blr
.const
.align 2
.CPIl2__Z2f2j_0: ; float 0x4330000000000000
.long 1501560832 ; float 4.5036e+15
.text
.align 2
.globl l2__Z2f2j
l2__Z2f2j:
.LBBl2__Z2f2j_0: ; entry
stw r3, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl2__Z2f2j_0)
lfs f1, lo16(.CPIl2__Z2f2j_0)(r2)
fsub f1, f0, f1
blr
.const
.align 2
.CPIl3__Z2f3i_0: ; float 0x4330000080000000
.long 1501560836 ; float 4.5036e+15
.text
.align 2
.globl l3__Z2f3i
l3__Z2f3i:
.LBBl3__Z2f3i_0: ; entry
xoris r2, r3, 32768
stw r2, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl3__Z2f3i_0)
lfs f1, lo16(.CPIl3__Z2f3i_0)(r2)
fsub f0, f0, f1
frsp f1, f0
blr
.const
.align 2
.CPIl4__Z2f4j_0: ; float 0x4330000000000000
.long 1501560832 ; float 4.5036e+15
.text
.align 2
.globl l4__Z2f4j
l4__Z2f4j:
.LBBl4__Z2f4j_0: ; entry
stw r3, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl4__Z2f4j_0)
lfs f1, lo16(.CPIl4__Z2f4j_0)(r2)
fsub f0, f0, f1
frsp f1, f0
blr
llvm-svn: 22814
2005-08-17 00:39:29 +00:00
0d2456e1f0
add a new TargetConstant node
...
llvm-svn: 22813
2005-08-17 00:34:06 +00:00
784c8068a7
Implement a couple improvements:
...
Remove dead code in ISD::Constant handling
Add support for add long, imm16
We now codegen 'long long foo(long long a) { return ++a; }'
as:
addic r4, r4, 1
addze r3, r3
blr
instead of:
li r2, 1
li r5, 0
addc r2, r4, r2
adde r3, r3, r5
blr
llvm-svn: 22811
2005-08-17 00:20:08 +00:00
5a1d5e30e2
This is a dummy, it doesn't matter what the ValueType is
...
llvm-svn: 22809
2005-08-16 21:59:52 +00:00
79f5ebc7b9
updates for changes in nodes
...
llvm-svn: 22808
2005-08-16 21:58:15 +00:00
7c76278242
update the backends to work with the new CopyFromReg/CopyToReg/ImplicitDef nodes
...
llvm-svn: 22807
2005-08-16 21:56:37 +00:00
33182325f5
Eliminate the RegSDNode class, which 3 nodes (CopyFromReg/CopyToReg/ImplicitDef)
...
used to tack a register number onto the node.
Instead of doing this, make a new node, RegisterSDNode, which is a leaf
containing a register number. These three operations just become normal
DAG nodes now, instead of requiring special handling.
Note that with this change, it is no longer correct to make illegal
CopyFromReg/CopyToReg nodes. The legalizer will not touch them, and this
is bad, so don't do it. :)
llvm-svn: 22806
2005-08-16 21:55:35 +00:00
371e49515d
Implement BR_CC and BRTWOWAY_CC. This allows the removal of a rather nasty
...
fixme from the PowerPC backend. Emit slightly better code for legalizing
select_cc.
llvm-svn: 22805
2005-08-16 19:49:35 +00:00
bc89226527
Allow passing a dag into dump and getOperationName. If one is available
...
when printing a node, use it to render target operations with their
target instruction name instead of "<<unknown>>".
llvm-svn: 22804
2005-08-16 18:33:07 +00:00
7e57d18b79
Use a extant helper to do this.
...
llvm-svn: 22802
2005-08-16 18:31:23 +00:00
1973278b38
Add some methods for dag->dag isel.
...
Split RemoveNodeFromCSEMaps out of DeleteNodesIfDead to do it.
llvm-svn: 22801
2005-08-16 18:17:10 +00:00
f22556d3ad
Pull the LLVM -> DAG lowering code out of the pattern selector so that it
...
can be shared with the DAG->DAG selector.
llvm-svn: 22799
2005-08-16 17:14:42 +00:00
5cf983ee0f
Fix a bad case in gzip where we put lots of things in registers across the
...
loop, because a IV-dependent value was used outside of the loop and didn't
have immediate-folding capability
llvm-svn: 22798
2005-08-16 00:38:11 +00:00
e515416396
Fix Transforms/LoopStrengthReduce/2005-08-15-AddRecIV.ll
...
llvm-svn: 22797
2005-08-16 00:37:01 +00:00
73785d2ef2
Turn loop strength reduction on by default.
...
Only run createLowerConstantExpressionsPass for the simple isel. The DAG
isel has no need for it.
llvm-svn: 22794
2005-08-15 23:47:04 +00:00
587a75b6e0
Teach LLVM to know how many times a loop executes when constructed with
...
a < expression, e.g.: for (i = m; i < n; ++i)
llvm-svn: 22793
2005-08-15 23:33:51 +00:00
24b84072ea
Broke 80 column rule.
...
llvm-svn: 22792
2005-08-15 17:35:26 +00:00
42623a9539
Changed code gen for int to f32 to use rounding. This makes FP results
...
consistent with gcc.
llvm-svn: 22791
2005-08-15 17:14:19 +00:00
b65b1568ae
isIntImmediate is a good Idea. Add a flavor that checks bounds while it is at it
...
llvm-svn: 22790
2005-08-15 14:31:37 +00:00
d5e739dcc2
Fix last night's PPC32 regressions by
...
1. Not selecting the false value of a select_cc in the false arm, which
isn't legal for nested selects.
2. Actually returning the node we created and Legalized in the FP_TO_UINT
Expander.
llvm-svn: 22789
2005-08-14 18:38:32 +00:00
e5394d453d
Fix last night's X86 regressions by putting code for SSE in the if(SSE)
...
block. nur.
llvm-svn: 22788
2005-08-14 18:37:02 +00:00
ed07233868
only build .a on alpha
...
llvm-svn: 22787
2005-08-14 15:14:34 +00:00
4d959f6627
Fix FP_TO_UINT with Scalar SSE2 now that the legalizer can handle it. We
...
now generate the relatively good code sequences:
unsigned short foo(float a) { return a; }
_foo:
movss 4(%esp), %xmm0
cvttss2si %xmm0, %eax
movzwl %ax, %eax
ret
and
unsigned bar(float a) { return a; }
_bar:
movss .CPI_bar_0, %xmm0
movss 4(%esp), %xmm1
movapd %xmm1, %xmm2
subss %xmm0, %xmm2
cvttss2si %xmm2, %eax
xorl $-2147483648, %eax
cvttss2si %xmm1, %ecx
ucomiss %xmm0, %xmm1
cmovb %ecx, %eax
ret
llvm-svn: 22786
2005-08-14 04:36:51 +00:00
36853ee1fd
Teach the legalizer how to legalize FP_TO_UINT.
...
Teach the legalizer to promote FP_TO_UINT to FP_TO_SINT if the wider
FP_TO_UINT is also illegal. This allows us on PPC to codegen
unsigned short foo(float a) { return a; }
as:
_foo:
.LBB_foo_0: ; entry
fctiwz f0, f1
stfd f0, -8(r1)
lwz r2, -4(r1)
rlwinm r3, r2, 0, 16, 31
blr
instead of:
_foo:
.LBB_foo_0: ; entry
fctiwz f0, f1
stfd f0, -8(r1)
lwz r2, -4(r1)
lis r3, ha16(.CPI_foo_0)
lfs f0, lo16(.CPI_foo_0)(r3)
fcmpu cr0, f1, f0
blt .LBB_foo_2 ; entry
.LBB_foo_1: ; entry
fsubs f0, f1, f0
fctiwz f0, f0
stfd f0, -16(r1)
lwz r2, -12(r1)
xoris r2, r2, 32768
.LBB_foo_2: ; entry
rlwinm r3, r2, 0, 16, 31
blr
llvm-svn: 22785
2005-08-14 01:20:53 +00:00
83f6b98c42
Make FP_TO_UINT Illegal. This allows us to generate significantly better
...
codegen for FP_TO_UINT by using the legalizer's SELECT variant.
Implement a codegen improvement for SELECT_CC, selecting the false node in
the MBB that feeds the phi node. This allows us to codegen:
void foo(int *a, int b, int c) { int d = (a < b) ? 5 : 9; *a = d; }
as:
_foo:
li r2, 5
cmpw cr0, r4, r3
bgt .LBB_foo_2 ; entry
.LBB_foo_1: ; entry
li r2, 9
.LBB_foo_2: ; entry
stw r2, 0(r3)
blr
insted of:
_foo:
li r2, 5
li r5, 9
cmpw cr0, r4, r3
bgt .LBB_foo_2 ; entry
.LBB_foo_1: ; entry
or r2, r5, r5
.LBB_foo_2: ; entry
stw r2, 0(r3)
blr
llvm-svn: 22784
2005-08-14 01:17:16 +00:00
107a0a7690
Testing a variable before it is defined doesn't work so well. It is a fairly small thing, so just let everyone build the .a file
...
llvm-svn: 22783
2005-08-13 14:58:23 +00:00
47d3ec3525
Ooops, don't forget to clear this. The real inner loop is now:
...
.LBB_foo_3: ; no_exit.1
lfd f2, 0(r9)
lfd f3, 8(r9)
fmul f4, f1, f2
fmadd f4, f0, f3, f4
stfd f4, 8(r9)
fmul f3, f1, f3
fmsub f2, f0, f2, f3
stfd f2, 0(r9)
addi r9, r9, 16
addi r8, r8, 1
cmpw cr0, r8, r4
ble .LBB_foo_3 ; no_exit.1
llvm-svn: 22782
2005-08-13 07:42:01 +00:00
5949d49032
Recursively scan scev expressions for common subexpressions. This allows us
...
to handle nested loops much better, for example, by being able to tell that
these two expressions:
{( 8 + ( 16 * ( 1 + %Tmp11 + %Tmp12)) + %c_),+,( 16 * %Tmp 12)}<loopentry.1>
{(( 16 * ( 1 + %Tmp11 + %Tmp12)) + %c_),+,( 16 * %Tmp12)}<loopentry.1>
Have the following common part that can be shared:
{(( 16 * ( 1 + %Tmp11 + %Tmp12)) + %c_),+,( 16 * %Tmp12)}<loopentry.1>
This allows us to codegen an important inner loop in 168.wupwise as:
.LBB_foo_4: ; no_exit.1
lfd f2, 16(r9)
fmul f3, f0, f2
fmul f2, f1, f2
fadd f4, f3, f2
stfd f4, 8(r9)
fsub f2, f3, f2
stfd f2, 16(r9)
addi r8, r8, 1
addi r9, r9, 16
cmpw cr0, r8, r4
ble .LBB_foo_4 ; no_exit.1
instead of:
.LBB_foo_3: ; no_exit.1
lfdx f2, r6, r9
add r10, r6, r9
lfd f3, 8(r10)
fmul f4, f1, f2
fmadd f4, f0, f3, f4
stfd f4, 8(r10)
fmul f3, f1, f3
fmsub f2, f0, f2, f3
stfdx f2, r6, r9
addi r9, r9, 16
addi r8, r8, 1
cmpw cr0, r8, r4
ble .LBB_foo_3 ; no_exit.1
llvm-svn: 22781
2005-08-13 07:27:18 +00:00
dc3154ec66
Remove an unncessary argument to SimplifySelectCC and add an additional
...
assert when creating a select_cc node.
llvm-svn: 22780
2005-08-13 06:14:17 +00:00
b6651e81a0
Fix the fabs regression on x86 by abstracting the select_cc optimization
...
out into SimplifySelectCC. This allows both ISD::SELECT and ISD::SELECT_CC
to use the same set of simplifying folds.
llvm-svn: 22779
2005-08-13 06:00:21 +00:00
a22bf778c9
Remove support for 64b PPC, it's been broken for a long time. It'll be
...
back once a DAG->DAG ISel exists.
llvm-svn: 22778
2005-08-13 05:59:16 +00:00
6b62b479fa
Fix oversized GOT problem with gcc-4 on alpha
...
llvm-svn: 22777
2005-08-13 05:09:50 +00:00
89c1dfc733
Teach SplitCriticalEdge to update LoopInfo if it is alive. This fixes
...
a problem in LoopStrengthReduction, where it would split critical edges
then confused itself with outdated loop information.
llvm-svn: 22776
2005-08-13 01:38:43 +00:00
79396539d3
remove dead code. The exit block list is computed on demand, thus does not
...
need to be updated. This code is a relic from when it did.
llvm-svn: 22775
2005-08-13 01:30:36 +00:00
21381e8424
implement a couple of simple shift foldings.
...
e.g. (X & 7) >> 3 -> 0
llvm-svn: 22774
2005-08-12 23:54:58 +00:00
35960708b7
Fix for 2005-08-12-rlwimi-crash.ll. Make allowance for masks being shifted to
...
zero.
llvm-svn: 22773
2005-08-12 23:52:46 +00:00
a568700618
1. This changes handles the cases of (~x)&y and x&(~y) yielding ANDC, and
...
(~x)|y and x|(~y) yielding ORC.
llvm-svn: 22771
2005-08-12 23:38:02 +00:00
8447b49526
When splitting critical edges, make sure not to leave the new block in the
...
middle of the loop. This turns a critical loop in gzip into this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
bne .LBB_test_8 ; loopentry.loopexit_crit_edge
.LBB_test_2: ; shortcirc_next.0
add r28, r3, r27
lhz r28, 5(r28)
add r26, r4, r27
lhz r26, 5(r26)
cmpw cr0, r28, r26
bne .LBB_test_7 ; shortcirc_next.0.loopexit_crit_edge
.LBB_test_3: ; shortcirc_next.1
add r28, r3, r27
lhz r28, 7(r28)
add r26, r4, r27
lhz r26, 7(r26)
cmpw cr0, r28, r26
bne .LBB_test_6 ; shortcirc_next.1.loopexit_crit_edge
.LBB_test_4: ; shortcirc_next.2
add r28, r3, r27
lhz r26, 9(r28)
add r28, r4, r27
lhz r25, 9(r28)
addi r28, r27, 8
cmpw cr7, r26, r25
mfcr r26, 1
rlwinm r26, r26, 31, 31, 31
add r25, r8, r27
cmpw cr7, r25, r7
mfcr r25, 1
rlwinm r25, r25, 29, 31, 31
and. r26, r26, r25
bne .LBB_test_1 ; loopentry
instead of this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2: ; loopentry.loopexit_crit_edge
add r2, r30, r27
add r8, r29, r27
b .LBB_test_9 ; loopexit
.LBB_test_3: ; shortcirc_next.0
add r28, r3, r27
lhz r28, 5(r28)
add r26, r4, r27
lhz r26, 5(r26)
cmpw cr0, r28, r26
beq .LBB_test_5 ; shortcirc_next.1
.LBB_test_4: ; shortcirc_next.0.loopexit_crit_edge
add r2, r11, r27
add r8, r12, r27
b .LBB_test_9 ; loopexit
.LBB_test_5: ; shortcirc_next.1
add r28, r3, r27
lhz r28, 7(r28)
add r26, r4, r27
lhz r26, 7(r26)
cmpw cr0, r28, r26
beq .LBB_test_7 ; shortcirc_next.2
.LBB_test_6: ; shortcirc_next.1.loopexit_crit_edge
add r2, r9, r27
add r8, r10, r27
b .LBB_test_9 ; loopexit
.LBB_test_7: ; shortcirc_next.2
add r28, r3, r27
lhz r26, 9(r28)
add r28, r4, r27
lhz r25, 9(r28)
addi r28, r27, 8
cmpw cr7, r26, r25
mfcr r26, 1
rlwinm r26, r26, 31, 31, 31
add r25, r8, r27
cmpw cr7, r25, r7
mfcr r25, 1
rlwinm r25, r25, 29, 31, 31
and. r26, r26, r25
bne .LBB_test_1 ; loopentry
Next up, improve the code for the loop.
llvm-svn: 22769
2005-08-12 22:22:17 +00:00
e09bbc800c
Add a helper method
...
llvm-svn: 22768
2005-08-12 22:14:06 +00:00
4fec86d348
Fix a FIXME: if we are inserting code for a PHI argument, split the critical
...
edge so that the code is not always executed for both operands. This
prevents LSR from inserting code into loops whose exit blocks contain
PHI uses of IV expressions (which are outside of loops). On gzip, for
example, we turn this ugly code:
.LBB_test_1: ; loopentry
add r27, r3, r28
lhz r27, 3(r27)
add r26, r4, r28
lhz r26, 3(r26)
add r25, r30, r28 ;; Only live if exiting the loop
add r24, r29, r28 ;; Only live if exiting the loop
cmpw cr0, r27, r26
bne .LBB_test_5 ; loopexit
into this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2: ; loopentry.loopexit_crit_edge
add r2, r30, r27
add r8, r29, r27
b .LBB_test_9 ; loopexit
.LBB_test_2: ; shortcirc_next.0
...
blt .LBB_test_1
into this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2: ; loopentry.loopexit_crit_edge
add r2, r30, r27
add r8, r29, r27
b .LBB_t_3: ; shortcirc_next.0
.LBB_test_3: ; shortcirc_next.0
...
blt .LBB_test_1
Next step: get the block out of the loop so that the loop is all
fall-throughs again.
llvm-svn: 22766
2005-08-12 22:06:11 +00:00
b7ebe65c56
Change break critical edges to not remove, then insert, PHI node entries.
...
Instead, just update the BB in-place. This is both faster, and it prevents
split-critical-edges from shuffling the PHI argument list unneccesarily.
llvm-svn: 22765
2005-08-12 21:58:07 +00:00
8c6701be6e
match gcc's use of tabs, makes diffs easier
...
llvm-svn: 22764
2005-08-12 16:14:08 +00:00
ca94102d3e
.section cleanup, patch from Nicholas Riley
...
llvm-svn: 22763
2005-08-12 16:13:43 +00:00
a50f770a2c
1. Added the function isOpcWithIntImmediate to simplify testing of operand with
...
specified opcode and an integer constant right operand.
2. Modified ISD::SHL, ISD::SRL, ISD::SRA to use rlwinm when applied after a mask.
llvm-svn: 22761
2005-08-11 21:59:23 +00:00
d418d752f4
Tidied up the use of dyn_cast<ConstantSDNode> by using isIntImmediate more.
...
Patch by Jim Laskey.
llvm-svn: 22760
2005-08-11 17:56:50 +00:00
c5e1312baa
Use a more efficient method of creating integer and float virtual registers
...
(avoids an extra level of indirection in MakeReg).
defined MakeIntReg using RegMap->createVirtualRegister(PPC32::GPRCRegisterClass)
defined MakeFPReg using RegMap->createVirtualRegister(PPC32::FPRCRegisterClass)
s/MakeReg(MVT::i32)/MakeIntReg/
s/MakeReg(MVT::f64)/MakeFPReg/
Patch by Jim Laskey!
llvm-svn: 22759
2005-08-11 17:15:31 +00:00
5c7656fd53
Add a select_cc optimization for recognizing abs(int). This speeds up an
...
integer MPEG encoding loop by a factor of two.
llvm-svn: 22758
2005-08-11 02:18:13 +00:00
180b08897f
Some SELECT_CC cleanups:
...
1. move assertions for node creation to getNode()
2. legalize the values returned in ExpandOp immediately
3. Move select_cc optimizations from SELECT's getNode() to SELECT_CC's,
allowing them to be cleaned up significantly.
This paves the way to pick up additional optimizations on SELECT_CC, such
as sum-of-absolute-differences.
llvm-svn: 22757
2005-08-11 01:12:20 +00:00
5646b181e8
Make SELECT illegal on PPC32, switch to using SELECT_CC, which more closely
...
reflects what the hardware is capable of. This significantly simplifies
the CC handling logic throughout the ISel.
llvm-svn: 22756
2005-08-10 20:52:09 +00:00
e5b86d7442
Add new node, SELECT_CC. This node is for targets that don't natively
...
implement SELECT.
llvm-svn: 22755
2005-08-10 20:51:12 +00:00
3428b95634
Changes for PPC32ISelPattern.cpp
...
1. Clean up how SelectIntImmediateExpr handles use counts.
2. "Subtract from" was not clearing hi 16 bits.
Patch by Jim Laskey
llvm-svn: 22754
2005-08-10 18:11:33 +00:00
21c0fd9e8f
Fix an oversight that may be causing PR617.
...
llvm-svn: 22753
2005-08-10 17:37:53 +00:00
62df798919
remove some trickiness that broke yacr2 and some other programs last night
...
llvm-svn: 22751
2005-08-10 17:15:20 +00:00
aeedcc7fc2
Changed the XOR case to use the isOprNot predicate.
...
Patch by Jim Laskey!
llvm-svn: 22750
2005-08-10 16:35:46 +00:00
67d0753773
1. Refactored handling of integer immediate values for add, or, xor and sub.
...
New routine: ISel::SelectIntImmediateExpr
2. Now checking use counts of large constants. If use count is > 2 then drop
thru so that the constant gets loaded into a register.
Source:
int %test1(int %a) {
entry:
%tmp.1 = add int %a, 123456789 ; <int> [#uses=1]
%tmp.2 = or int %tmp.1, 123456789 ; <int> [#uses=1]
%tmp.3 = xor int %tmp.2, 123456789 ; <int> [#uses=1]
%tmp.4 = sub int %tmp.3, -123456789 ; <int> [#uses=1]
ret int %tmp.4
}
Did Emit:
.machine ppc970
.text
.align 2
.globl _test1
_test1:
.LBB_test1_0: ; entry
addi r2, r3, -13035
addis r2, r2, 1884
ori r2, r2, 52501
oris r2, r2, 1883
xori r2, r2, 52501
xoris r2, r2, 1883
addi r2, r2, 52501
addis r3, r2, 1883
blr
Now Emits:
.machine ppc970
.text
.align 2
.globl _test1
_test1:
.LBB_test1_0: ; entry
lis r2, 1883
ori r2, r2, 52501
add r3, r3, r2
or r3, r3, r2
xor r3, r3, r2
add r3, r3, r2
blr
Patch by Jim Laskey!
llvm-svn: 22749
2005-08-10 16:34:52 +00:00
1c2f9fdf71
sorry!! this is temporary; for some reason the nasty constmul code seems to
...
be an infinite loop when using g++-4.0.1*, this kills the ia64 nightly
tester. A proper fix shall be forthcoming!!! thanks for not killing me. :)
llvm-svn: 22748
2005-08-10 12:38:57 +00:00
5f56d71cd7
Fix a bug compiling: select (i32 < i32), f32, f32
...
llvm-svn: 22747
2005-08-10 03:40:09 +00:00
f83ce5faee
Make loop-simplify produce better loops by turning PHI nodes like X = phi [X, Y]
...
into just Y. This often occurs when it seperates loops that have collapsed loop
headers. This implements LoopSimplify/phi-node-simplify.ll
llvm-svn: 22746
2005-08-10 02:07:32 +00:00
677d85784a
Allow indvar simplify to canonicalize ANY affine IV, not just affine IVs with
...
constant stride. This implements Transforms/IndVarsSimplify/variable-stride-ivs.ll
llvm-svn: 22744
2005-08-10 01:12:06 +00:00
35c0e2ee33
Fix an obvious oops
...
llvm-svn: 22742
2005-08-10 00:59:40 +00:00
edff91a49a
Teach LSR to strength reduce IVs that have a loop-invariant but non-constant stride.
...
For code like this:
void foo(float *a, float *b, int n, int stride_a, int stride_b) {
int i;
for (i=0; i<n; i++)
a[i*stride_a] = b[i*stride_b];
}
we now emit:
.LBB_foo2_2: ; no_exit
lfs f0, 0(r4)
stfs f0, 0(r3)
addi r7, r7, 1
add r4, r2, r4
add r3, r6, r3
cmpw cr0, r7, r5
blt .LBB_foo2_2 ; no_exit
instead of:
.LBB_foo_2: ; no_exit
mullw r8, r2, r7 ;; multiply!
slwi r8, r8, 2
lfsx f0, r4, r8
mullw r8, r2, r6 ;; multiply!
slwi r8, r8, 2
stfsx f0, r3, r8
addi r2, r2, 1
cmpw cr0, r2, r5
blt .LBB_foo_2 ; no_exit
loops with variable strides occur pretty often. For example, in SPECFP2K
there are 317 variable strides in 177.mesa, 3 in 179.art, 14 in 188.ammp,
56 in 168.wupwise, 36 in 172.mgrid.
Now we can allow indvars to turn functions written like this:
void foo2(float *a, float *b, int n, int stride_a, int stride_b) {
int i, ai = 0, bi = 0;
for (i=0; i<n; i++)
{
a[ai] = b[bi];
ai += stride_a;
bi += stride_b;
}
}
into code like the above for better analysis. With this patch, they generate
identical code.
llvm-svn: 22740
2005-08-10 00:45:21 +00:00
dde7dc525e
Fix Regression/Transforms/LoopStrengthReduce/phi_node_update_multiple_preds.ll
...
by being more careful about updating PHI nodes
llvm-svn: 22739
2005-08-10 00:35:32 +00:00
c6c4d99a21
Fix some 80 column violations.
...
Once we compute the evolution for a GEP, tell SE about it. This allows users
of the GEP to know it, if the users are not direct. This allows us to compile
this testcase:
void fbSolidFillmmx(int w, unsigned char *d) {
while (w >= 64) {
*(unsigned long long *) (d + 0) = 0;
*(unsigned long long *) (d + 8) = 0;
*(unsigned long long *) (d + 16) = 0;
*(unsigned long long *) (d + 24) = 0;
*(unsigned long long *) (d + 32) = 0;
*(unsigned long long *) (d + 40) = 0;
*(unsigned long long *) (d + 48) = 0;
*(unsigned long long *) (d + 56) = 0;
w -= 64;
d += 64;
}
}
into:
.LBB_fbSolidFillmmx_2: ; no_exit
li r2, 0
stw r2, 0(r4)
stw r2, 4(r4)
stw r2, 8(r4)
stw r2, 12(r4)
stw r2, 16(r4)
stw r2, 20(r4)
stw r2, 24(r4)
stw r2, 28(r4)
stw r2, 32(r4)
stw r2, 36(r4)
stw r2, 40(r4)
stw r2, 44(r4)
stw r2, 48(r4)
stw r2, 52(r4)
stw r2, 56(r4)
stw r2, 60(r4)
addi r4, r4, 64
addi r3, r3, -64
cmpwi cr0, r3, 63
bgt .LBB_fbSolidFillmmx_2 ; no_exit
instead of:
.LBB_fbSolidFillmmx_2: ; no_exit
li r11, 0
stw r11, 0(r4)
stw r11, 4(r4)
stwx r11, r10, r4
add r12, r10, r4
stw r11, 4(r12)
stwx r11, r9, r4
add r12, r9, r4
stw r11, 4(r12)
stwx r11, r8, r4
add r12, r8, r4
stw r11, 4(r12)
stwx r11, r7, r4
add r12, r7, r4
stw r11, 4(r12)
stwx r11, r6, r4
add r12, r6, r4
stw r11, 4(r12)
stwx r11, r5, r4
add r12, r5, r4
stw r11, 4(r12)
stwx r11, r2, r4
add r12, r2, r4
stw r11, 4(r12)
addi r4, r4, 64
addi r3, r3, -64
cmpwi cr0, r3, 63
bgt .LBB_fbSolidFillmmx_2 ; no_exit
llvm-svn: 22737
2005-08-09 23:39:36 +00:00
b310ac4a86
implement two helper methods
...
llvm-svn: 22736
2005-08-09 23:36:33 +00:00
679f5b0b40
Fix spelling, fix some broken canonicalizations by my last patch
...
llvm-svn: 22734
2005-08-09 23:09:05 +00:00
54ee86aca7
add a optimization note
...
llvm-svn: 22732
2005-08-09 22:30:57 +00:00
14e060f743
add cc nodes to the AllNodes list so they show up in Graphviz output
...
llvm-svn: 22731
2005-08-09 20:40:02 +00:00
6ec7745e80
Update the targets to the new SETCC/CondCodeSDNode interfaces.
...
llvm-svn: 22729
2005-08-09 20:21:10 +00:00
d47675ed24
Eliminate the SetCCSDNode in favor of a CondCodeSDNode class. This pulls the
...
CC out of the SetCC operation, making SETCC a standard ternary operation and
CC's a standard DAG leaf. This will make it possible for other node to use
CC's as operands in the future...
llvm-svn: 22728
2005-08-09 20:20:18 +00:00
2035c4f7f8
Minor cleanup patch, no functionality changes. Written by Jim Laskey.
...
llvm-svn: 22727
2005-08-09 18:29:55 +00:00
4c62c647c2
Fix CodeGen/Generic/div-neg-power-2.ll, a regression from last night.
...
llvm-svn: 22726
2005-08-09 18:08:41 +00:00
02742710f3
SCEVAddExpr::get() of an empty list is invalid.
...
llvm-svn: 22724
2005-08-09 01:13:47 +00:00
a091ff1764
Implement: LoopStrengthReduce/share_ivs.ll
...
Two changes:
* Only insert one PHI node for each stride. Other values are live in
values. This cannot introduce higher register pressure than the
previous approach, and can take advantage of reg+reg addressing modes.
* Factor common base values out of uses before moving values from the
base to the immediate fields. This improves codegen by starting the
stride-specific PHI node out at a common place for each IV use.
As an example, we used to generate this for a loop in swim:
.LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_2: ; no_exit.7.i
lfd f0, 0(r8)
stfd f0, 0(r3)
lfd f0, 0(r6)
stfd f0, 0(r7)
lfd f0, 0(r2)
stfd f0, 0(r5)
addi r9, r9, 1
addi r2, r2, 8
addi r5, r5, 8
addi r6, r6, 8
addi r7, r7, 8
addi r8, r8, 8
addi r3, r3, 8
cmpw cr0, r9, r4
bgt .LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_1
now we emit:
.LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_2: ; no_exit.7.i
lfdx f0, r8, r2
stfdx f0, r9, r2
lfdx f0, r5, r2
stfdx f0, r7, r2
lfdx f0, r3, r2
stfdx f0, r6, r2
addi r10, r10, 1
addi r2, r2, 8
cmpw cr0, r10, r4
bgt .LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_1
As another more dramatic example, we used to emit this:
.LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_2: ; no_exit.1.i19
lfd f0, 8(r21)
lfd f4, 8(r3)
lfd f5, 8(r27)
lfd f6, 8(r22)
lfd f7, 8(r5)
lfd f8, 8(r6)
lfd f9, 8(r30)
lfd f10, 8(r11)
lfd f11, 8(r12)
fsub f10, f10, f11
fadd f5, f4, f5
fmul f5, f5, f1
fadd f6, f6, f7
fadd f6, f6, f8
fadd f6, f6, f9
fmadd f0, f5, f6, f0
fnmsub f0, f10, f2, f0
stfd f0, 8(r4)
lfd f0, 8(r25)
lfd f5, 8(r26)
lfd f6, 8(r23)
lfd f9, 8(r28)
lfd f10, 8(r10)
lfd f12, 8(r9)
lfd f13, 8(r29)
fsub f11, f13, f11
fadd f4, f4, f5
fmul f4, f4, f1
fadd f5, f6, f9
fadd f5, f5, f10
fadd f5, f5, f12
fnmsub f0, f4, f5, f0
fnmsub f0, f11, f3, f0
stfd f0, 8(r24)
lfd f0, 8(r8)
fsub f4, f7, f8
fsub f5, f12, f10
fnmsub f0, f5, f2, f0
fnmsub f0, f4, f3, f0
stfd f0, 8(r2)
addi r20, r20, 1
addi r2, r2, 8
addi r8, r8, 8
addi r10, r10, 8
addi r12, r12, 8
addi r6, r6, 8
addi r29, r29, 8
addi r28, r28, 8
addi r26, r26, 8
addi r25, r25, 8
addi r24, r24, 8
addi r5, r5, 8
addi r23, r23, 8
addi r22, r22, 8
addi r3, r3, 8
addi r9, r9, 8
addi r11, r11, 8
addi r30, r30, 8
addi r27, r27, 8
addi r21, r21, 8
addi r4, r4, 8
cmpw cr0, r20, r7
bgt .LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_1
we now emit:
.LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_2: ; no_exit.1.i19
lfdx f0, r21, r20
lfdx f4, r3, r20
lfdx f5, r27, r20
lfdx f6, r22, r20
lfdx f7, r5, r20
lfdx f8, r6, r20
lfdx f9, r30, r20
lfdx f10, r11, r20
lfdx f11, r12, r20
fsub f10, f10, f11
fadd f5, f4, f5
fmul f5, f5, f1
fadd f6, f6, f7
fadd f6, f6, f8
fadd f6, f6, f9
fmadd f0, f5, f6, f0
fnmsub f0, f10, f2, f0
stfdx f0, r4, r20
lfdx f0, r25, r20
lfdx f5, r26, r20
lfdx f6, r23, r20
lfdx f9, r28, r20
lfdx f10, r10, r20
lfdx f12, r9, r20
lfdx f13, r29, r20
fsub f11, f13, f11
fadd f4, f4, f5
fmul f4, f4, f1
fadd f5, f6, f9
fadd f5, f5, f10
fadd f5, f5, f12
fnmsub f0, f4, f5, f0
fnmsub f0, f11, f3, f0
stfdx f0, r24, r20
lfdx f0, r8, r20
fsub f4, f7, f8
fsub f5, f12, f10
fnmsub f0, f5, f2, f0
fnmsub f0, f4, f3, f0
stfdx f0, r2, r20
addi r19, r19, 1
addi r20, r20, 8
cmpw cr0, r19, r7
bgt .LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_1
llvm-svn: 22722
2005-08-09 00:18:09 +00:00
37c24cc98c
Suck the base value out of the UsersToProcess vector into the BasedUser
...
class to simplify the code. Fuse two loops.
llvm-svn: 22721
2005-08-08 22:56:21 +00:00
37ed895bf1
Split MoveLoopVariantsToImediateField out from MoveImmediateValues. The
...
first is a correctness thing, and the later is an optzn thing. This also
is needed to support a future change.
llvm-svn: 22720
2005-08-08 22:32:34 +00:00
c92787e1f5
Factor out some common code, and be smarter about when to emit load hi/lo
...
code sequences.
llvm-svn: 22719
2005-08-08 22:22:56 +00:00
d09a9a788b
Allow tools with "consume after" options (like lli) to take more positional
...
opts than they take directly. Thanks to John C for pointing this problem
out to me!
llvm-svn: 22717
2005-08-08 21:57:27 +00:00
64068eb7da
Remove getImmediateForOpcode, which is now dead.
...
Patch by Jim Laskey.
llvm-svn: 22716
2005-08-08 21:34:13 +00:00
25388199a2
Add new immediate handling support for mul/div.
...
Patch by Jim Laskey!
llvm-svn: 22715
2005-08-08 21:33:23 +00:00
8e9dc31928
Add support for OR/XOR/SUB immediates that are handled with the new immediate
...
way. This allows ORI/ORIS pairs, for example.
llvm-svn: 22714
2005-08-08 21:30:29 +00:00
fd0fe76ba6
Modify the ISD::AND opcode case to use new immediate constant predicates.
...
Includes wider support for rotate and mask cases.
Patch by Jim Laskey.
I've requested that Jim add new regression tests the newly handled cases.
llvm-svn: 22712
2005-08-08 21:24:57 +00:00
81e0e3e933
Modify the ISD::ADD opcode case to use new immediate constant predicates.
...
Includes support for 32-bit constants using addi/addis.
Patch by Jim Laskey.
llvm-svn: 22711
2005-08-08 21:21:03 +00:00
4c54dae243
Modify existing support functions to use new immediate constant predicates.
...
Patch by Jim Laskey
llvm-svn: 22710
2005-08-08 21:12:35 +00:00
3cc070cc36
Add support predicates for future immediate constant changes.
...
Patch by Jim Laskey
llvm-svn: 22709
2005-08-08 21:10:27 +00:00
f2267ed5c5
Move IsRunOfOnes to a more logical place and rename to a proper predicate form
...
(lowercase isXXX).
Patch by Jim Laskey.
llvm-svn: 22708
2005-08-08 21:08:09 +00:00
9a838678b0
Fix JIT encoding of ppc mfocrf instruction; the operands were reversed
...
llvm-svn: 22707
2005-08-08 20:04:52 +00:00
9f269e40c9
Use the new 'moveBefore' method to simplify some code. Really, which is
...
easier to understand? :)
llvm-svn: 22706
2005-08-08 19:11:57 +00:00
d380d8412d
Reject command lines that have too many positional arguments passed (e.g.,
...
'opt x y'). This fixes PR493.
Patch contributed by Owen Anderson!
llvm-svn: 22705
2005-08-08 17:25:38 +00:00
14203e85b2
Not all constants are legal immediates in load/store instructions.
...
llvm-svn: 22704
2005-08-08 06:25:50 +00:00
c70bbc0c41
Implement LoopStrengthReduce/share_code_in_preheader.ll by having one
...
rewriter for all code inserted into the preheader, which is never flushed.
llvm-svn: 22702
2005-08-08 05:47:49 +00:00
9bfa6f8784
Implement a simple optimization for the termination condition of the loop.
...
The termination condition actually wants to use the post-incremented value
of the loop, not a new indvar with an unusual base.
On PPC, for example, this allows us to compile
LoopStrengthReduce/exit_compare_live_range.ll to:
_foo:
li r2, 0
.LBB_foo_1: ; no_exit
li r5, 0
stw r5, 0(r3)
addi r2, r2, 1
cmpw cr0, r2, r4
bne .LBB_foo_1 ; no_exit
blr
instead of:
_foo:
li r2, 1 ;; IV starts at 1, not 0
.LBB_foo_1: ; no_exit
li r5, 0
stw r5, 0(r3)
addi r5, r2, 1
cmpw cr0, r2, r4
or r2, r5, r5 ;; Reg-reg copy, extra live range
bne .LBB_foo_1 ; no_exit
blr
This implements LoopStrengthReduce/exit_compare_live_range.ll
llvm-svn: 22699
2005-08-08 05:28:22 +00:00
24a0a43cb0
add new helper function
...
llvm-svn: 22698
2005-08-08 05:21:50 +00:00
88e2d2ee6b
Handle 64-bit constant exprs on 64-bit targets.
...
llvm-svn: 22696
2005-08-08 04:26:32 +00:00
579b20b747
All stats are "Number of ..."
...
llvm-svn: 22694
2005-08-07 20:02:04 +00:00
2c14cf7b74
Add some simple folds that occur in bitfield cases. Fix a minor bug in
...
isHighOnes, where it would consider 0 to have high ones.
llvm-svn: 22693
2005-08-07 07:03:10 +00:00
134ebd0801
Fix typoCVS: ----------------------------------------------------------------------
...
llvm-svn: 22692
2005-08-07 07:00:52 +00:00
0c26a0b902
add a small simplification that can be exposed after promotion/expansion
...
llvm-svn: 22691
2005-08-07 05:00:44 +00:00
f4dd8c445c
* Use the new PHINode::hasConstantValue method to simplify some code
...
* Teach this code to move allocas out of the loop when tail call eliminating
a call marked 'tail'. This implements TailCallElim/move_alloca_for_tail_call.ll
* Do not perform this transformation if a call is marked 'tail' and if there
are allocas that we cannot move out of the loop in #2 . Doing so would increase
the stack usage of the function. This implements fixes
PR615 and TailCallElim/dont-tce-tail-marked-call.ll.
llvm-svn: 22690
2005-08-07 04:27:41 +00:00
983a415b6a
Consolidate the GPOpt stuff to all use the Subtarget, instead of still
...
depending on the command line option. Now the command line option just
sets the subtarget as appropriate. G5 opts will now default to on on
G5-enabled nightly testers among other machines.
llvm-svn: 22688
2005-08-05 22:05:03 +00:00
158acab986
adjust to change in getSubtarget() api
...
llvm-svn: 22687
2005-08-05 21:54:27 +00:00
431b8d80bd
Enable gp optimizations by default when available, even when a target triple
...
is available, since the target triple doesn't specify whether to use gpopts
or not.
llvm-svn: 22685
2005-08-05 21:25:13 +00:00
11fc319b5d
add a note
...
llvm-svn: 22681
2005-08-05 19:18:32 +00:00
96ad31321a
Change FindEarliestCallSeqEnd (used by libcall insertion) to use a set to
...
avoid revisiting nodes more than once. This eliminates a source of
potentially exponential behavior. For a small function in 191.fma3d
(hexah_stress_divergence_), this speeds up isel from taking > 20mins to
taking 0.07s.
llvm-svn: 22680
2005-08-05 18:10:27 +00:00
1095dc94a9
Fix a use-of-dangling-pointer bug, from the introduction of SrcValue's.
...
llvm-svn: 22679
2005-08-05 16:55:31 +00:00
cabdc34563
Fix a latent bug in the libcall inserter that was exposed by Nate's patch
...
yesterday. This fixes whetstone and a bunch of programs in the External tests.
llvm-svn: 22678
2005-08-05 16:23:57 +00:00
8c636bf8b2
don't crash when running the PPC backend on non-ppc hosts without specifying
...
a subtarget.
llvm-svn: 22677
2005-08-05 16:17:22 +00:00
6e709c1318
PHINode::hasConstantValue should never return the PHI itself, even if the
...
PHI is its only operand.
llvm-svn: 22676
2005-08-05 15:37:31 +00:00
1749aaa5e6
Fix an iterator invalidation problem when we decide a phi has a constant value
...
llvm-svn: 22675
2005-08-05 15:34:10 +00:00
11e7a5eda7
Make sure to clean CastedPointers after casts are potentially deleted.
...
This fixes LSR crashes on 301.apsi, 191.fma3d, and 189.lucas
llvm-svn: 22673
2005-08-05 01:30:11 +00:00
9f9c260b8c
now that hasConstantValue defaults to only returning values that dominate
...
the PHI node, this ugly code can vanish.
llvm-svn: 22672
2005-08-05 01:04:30 +00:00
37774affb1
Invoke instructions do not dominate all successors
...
llvm-svn: 22671
2005-08-05 01:03:27 +00:00
6f58350daf
Now that hasConstantValue is more careful w.r.t. returning values that only
...
dominate the PHI node, this code can go away. This also makes passes more
aggressive, e.g. implementing Transforms/CondProp/phisimplify2.ll
llvm-svn: 22670
2005-08-05 01:02:04 +00:00
bcd8d2c6e5
Use the bool argument to hasConstantValue to decide whether the client is
...
prepared to deal with return values that do not dominate the PHI. If we
cannot prove that the result dominates the PHI node, do not return it if
the client can't cope.
llvm-svn: 22669
2005-08-05 01:00:58 +00:00
257efb2ad3
This code can handle non-dominating instructions
...
llvm-svn: 22667
2005-08-05 00:57:45 +00:00
1d8b24878f
Mark hasConstantValue as a const method
...
llvm-svn: 22666
2005-08-05 00:49:06 +00:00
0a94dec78a
Add an extra parameter that Chris requested
...
llvm-svn: 22665
2005-08-04 23:50:43 +00:00
b392321cae
Fix a fixme in CondPropagate.cpp by moving a PhiNode optimization into
...
BasicBlock's removePredecessor routine. This requires shuffling around
the definition and implementation of hasContantValue from Utils.h,cpp into
Instructions.h,cpp
llvm-svn: 22664
2005-08-04 23:24:19 +00:00
45f8b6e7aa
Modify how immediates are removed from base expressions to deal with the fact
...
that the symbolic evaluator is not always able to use subtraction to remove
expressions. This makes the code faster, and fixes the last crash on 178.galgel.
Finally, add a statistic to see how many phi nodes are inserted.
On 178.galgel, we get the follow stats:
2562 loop-reduce - Number of PHIs inserted
3927 loop-reduce - Number of GEPs strength reduced
llvm-svn: 22662
2005-08-04 22:34:05 +00:00
77558da546
Fix a fixme in LegalizeDAG
...
llvm-svn: 22661
2005-08-04 21:43:28 +00:00
e3cbe1027d
Hack to naturally align doubles in the constant pool. Remove this once we
...
know what The Right Thing To Do is.
llvm-svn: 22660
2005-08-04 21:04:09 +00:00
295ea90634
Use the new subtarget support to automatically choose the correct ABI
...
and asm printer for PowerPC if one is not specified.
llvm-svn: 22659
2005-08-04 20:49:48 +00:00
a6d7c355bc
* Refactor some code into a new BasedUser::RewriteInstructionToUseNewBase
...
method.
* Fix a crash on 178.galgel, where we would insert expressions before PHI
nodes instead of into the PHI node predecessor blocks.
llvm-svn: 22657
2005-08-04 20:03:32 +00:00
0f7c0fa2a7
Fix a case that caused this to crash on 178.galgel
...
llvm-svn: 22653
2005-08-04 19:26:19 +00:00
acc42c4df1
Teach LSR about loop-variant expressions, such as loops like this:
...
for (i = 0; i < N; ++i)
A[i][foo()] = 0;
here we still want to strength reduce the A[i] part, even though foo() is
l-v.
This also simplifies some of the 'CanReduce' logic.
This implements Transforms/LoopStrengthReduce/ops_after_indvar.ll
llvm-svn: 22652
2005-08-04 19:08:16 +00:00
456044b724
Remove some more dead code.
...
llvm-svn: 22650
2005-08-04 18:13:56 +00:00
eaf24725b2
Refactor this code substantially with the following improvements:
...
1. We only analyze instructions once, guaranteed
2. AnalyzeGetElementPtrUsers has been ripped apart and replaced with
something much simpler.
The next step is to handle expressions that are not all indvar+loop-invariant
values (e.g. handling indvar+loopvariant).
llvm-svn: 22649
2005-08-04 17:40:30 +00:00
5adb830b30
No, IDEFs shouldn't be JITed
...
llvm-svn: 22648
2005-08-04 15:32:36 +00:00
a54e201edf
* Unbreak release build
...
* Add comments to #endif pragmas for readability
llvm-svn: 22647
2005-08-04 14:22:41 +00:00
41acd5e08d
* Unbreak optimized build (noticed by Eric van Riet Paap)
...
* Comment #endif clauses for readability
llvm-svn: 22646
2005-08-04 14:16:48 +00:00
3bcfcd9474
Add Subtarget support to PowerPC. Next up, using it.
...
llvm-svn: 22644
2005-08-04 07:12:09 +00:00
6f286b760f
refactor some code
...
llvm-svn: 22643
2005-08-04 01:19:13 +00:00
6510749050
invert to if's to make the logic simpler
...
llvm-svn: 22641
2005-08-04 00:40:47 +00:00
a0102fbc4f
When processing outer loops and we find uses of an IV in inner loops, make
...
sure to handle the use, just don't recurse into it.
This permits us to generate this code for a simple nested loop case:
.LBB_foo_0: ; entry
stwu r1, -48(r1)
stw r29, 44(r1)
stw r30, 40(r1)
mflr r11
stw r11, 56(r1)
lis r2, ha16(L_A$non_lazy_ptr)
lwz r30, lo16(L_A$non_lazy_ptr)(r2)
li r29, 1
.LBB_foo_1: ; no_exit.0
bl L_bar$stub
li r2, 1
or r3, r30, r30
.LBB_foo_2: ; no_exit.1
lfd f0, 8(r3)
stfd f0, 0(r3)
addi r4, r2, 1
addi r3, r3, 8
cmpwi cr0, r2, 100
or r2, r4, r4
bne .LBB_foo_2 ; no_exit.1
.LBB_foo_3: ; loopexit.1
addi r30, r30, 800
addi r2, r29, 1
cmpwi cr0, r29, 100
or r29, r2, r2
bne .LBB_foo_1 ; no_exit.0
.LBB_foo_4: ; return
lwz r11, 56(r1)
mtlr r11
lwz r30, 40(r1)
lwz r29, 44(r1)
lwz r1, 0(r1)
blr
instead of this:
_foo:
.LBB_foo_0: ; entry
stwu r1, -48(r1)
stw r28, 44(r1) ;; uses an extra register.
stw r29, 40(r1)
stw r30, 36(r1)
mflr r11
stw r11, 56(r1)
li r30, 1
li r29, 0
or r28, r29, r29
.LBB_foo_1: ; no_exit.0
bl L_bar$stub
mulli r2, r28, 800 ;; unstrength-reduced multiply
lis r3, ha16(L_A$non_lazy_ptr) ;; loop invariant address computation
lwz r3, lo16(L_A$non_lazy_ptr)(r3)
add r2, r2, r3
mulli r4, r29, 800 ;; unstrength-reduced multiply
addi r3, r3, 8
add r3, r4, r3
li r4, 1
.LBB_foo_2: ; no_exit.1
lfd f0, 0(r3)
stfd f0, 0(r2)
addi r5, r4, 1
addi r2, r2, 8 ;; multiple stride 8 IV's
addi r3, r3, 8
cmpwi cr0, r4, 100
or r4, r5, r5
bne .LBB_foo_2 ; no_exit.1
.LBB_foo_3: ; loopexit.1
addi r28, r28, 1 ;;; Many IV's with stride 1
addi r29, r29, 1
addi r2, r30, 1
cmpwi cr0, r30, 100
or r30, r2, r2
bne .LBB_foo_1 ; no_exit.0
.LBB_foo_4: ; return
lwz r11, 56(r1)
mtlr r11
lwz r30, 36(r1)
lwz r29, 40(r1)
lwz r28, 44(r1)
lwz r1, 0(r1)
blr
llvm-svn: 22640
2005-08-04 00:14:11 +00:00
fc62470466
Teach loop-reduce to see into nested loops, to pull out immediate values
...
pushed down by SCEV.
In a nested loop case, this allows us to emit this:
lis r3, ha16(L_A$non_lazy_ptr)
lwz r3, lo16(L_A$non_lazy_ptr)(r3)
add r2, r2, r3
li r3, 1
.LBB_foo_2: ; no_exit.1
lfd f0, 8(r2) ;; Uses offset of 8 instead of 0
stfd f0, 0(r2)
addi r4, r3, 1
addi r2, r2, 8
cmpwi cr0, r3, 100
or r3, r4, r4
bne .LBB_foo_2 ; no_exit.1
instead of this:
lis r3, ha16(L_A$non_lazy_ptr)
lwz r3, lo16(L_A$non_lazy_ptr)(r3)
add r2, r2, r3
addi r3, r3, 8
li r4, 1
.LBB_foo_2: ; no_exit.1
lfd f0, 0(r3)
stfd f0, 0(r2)
addi r5, r4, 1
addi r2, r2, 8
addi r3, r3, 8
cmpwi cr0, r4, 100
or r4, r5, r5
bne .LBB_foo_2 ; no_exit.1
llvm-svn: 22639
2005-08-03 23:44:42 +00:00
bb78c97e24
improve debug output
...
llvm-svn: 22638
2005-08-03 23:30:08 +00:00
8d394eb703
Scalar SSE: load +0.0 -> xorps/xorpd
...
Scalar SSE: a < b ? c : 0.0 -> cmpss, andps
Scalar SSE: float -> i16 needs to be promoted
llvm-svn: 22637
2005-08-03 23:26:28 +00:00
db23c74e5e
Move from Stage 0 to Stage 1.
...
Only emit one PHI node for IV uses with identical bases and strides (after
moving foldable immediates to the load/store instruction).
This implements LoopStrengthReduce/dont_insert_redundant_ops.ll, allowing
us to generate this PPC code for test1:
or r30, r3, r3
.LBB_test1_1: ; Loop
li r2, 0
stw r2, 0(r30)
stw r2, 4(r30)
bl L_pred$stub
addi r30, r30, 8
cmplwi cr0, r3, 0
bne .LBB_test1_1 ; Loop
instead of this code:
or r30, r3, r3
or r29, r3, r3
.LBB_test1_1: ; Loop
li r2, 0
stw r2, 0(r29)
stw r2, 4(r30)
bl L_pred$stub
addi r30, r30, 8 ;; Two iv's with step of 8
addi r29, r29, 8
cmplwi cr0, r3, 0
bne .LBB_test1_1 ; Loop
llvm-svn: 22635
2005-08-03 22:51:21 +00:00
3a18a39587
Alpha ABI specifies stack is always 16 byte alligned, and gcc does it, so I will too
...
llvm-svn: 22634
2005-08-03 22:33:21 +00:00
430d0022df
Rename IVUse to IVUsersOfOneStride, use a struct instead of a pair to
...
unify some parallel vectors and get field names more descriptive than
"first" and "second". This isn't lisp afterall :)
llvm-svn: 22633
2005-08-03 22:21:05 +00:00
84e9baa925
Fix a nasty dangling pointer issue. The ScalarEvolution pass would keep a
...
map from instruction* to SCEVHandles. When we delete instructions, we have
to tell it about it. We would run into nasty cases where new instructions
were reallocated at old instruction addresses and get the old map values.
Bad bad bad :(
llvm-svn: 22632
2005-08-03 21:36:09 +00:00
8191442548
Fix PR611, codegen'ing SREM of FP operands to fmod or fmodf instead of
...
the sequence used for integer ops
llvm-svn: 22629
2005-08-03 20:31:37 +00:00
3de05cc930
The correct fix for PR612, which also fixes
...
Transforms/LowerInvoke/2005-08-03-InvokeWithPHIUse.ll
llvm-svn: 22628
2005-08-03 18:51:44 +00:00
f8a81a9886
When inserting code, make sure not to insert it before PHI nodes. This
...
fixes PR612 and Transforms/LowerInvoke/2005-08-03-InvokeWithPHI.ll
llvm-svn: 22626
2005-08-03 18:34:29 +00:00
d683bdd0f8
Fix Transforms/SimplifyCFG/2005-08-03-PHIFactorCrash.ll, a problem that
...
occurred while bugpointing another testcase
llvm-svn: 22621
2005-08-03 17:59:45 +00:00
590642eb91
add support for Graphviz when viewing CFGs
...
llvm-svn: 22620
2005-08-03 17:55:05 +00:00
fce3285891
Fix grammar: apostrophe-s ('s) is possessive, not plural; also iff vs. if.
...
llvm-svn: 22619
2005-08-03 17:29:52 +00:00
8dc82b7909
minor capitalization thing, patch by Jim Laskey
...
llvm-svn: 22617
2005-08-03 16:52:22 +00:00
2dbf1960ff
Finally, add the required constraint checks to fix Transforms/SimplifyCFG/2005-08-01-PHIUpdateFail.ll
...
the right way
llvm-svn: 22615
2005-08-03 00:59:12 +00:00
908036942c
Simplify some code, add the correct pred checks
...
llvm-svn: 22613
2005-08-03 00:38:27 +00:00
982b75c061
Refactor code out of PropagatePredecessorsForPHIs, turning it into a pure function with no side-effects
...
llvm-svn: 22612
2005-08-03 00:29:26 +00:00
1f047fd513
use splice instead of remove/insert to avoid some symtab operations
...
llvm-svn: 22611
2005-08-03 00:23:42 +00:00
76dc204488
move two functions up in the file, use SafeToMergeTerminators to eliminate
...
some duplicated code
llvm-svn: 22610
2005-08-03 00:19:45 +00:00
733d6704ce
Rip some code out of the main SimplifyCFG function into a subfunction and
...
call it from the only place it is live. No functionality changes.
llvm-svn: 22609
2005-08-03 00:11:16 +00:00
ac594de8dc
Disable this patch:
...
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20050801/027345.html
This breaks real programs and only fixes an obscure regression testcase. A
real fix is in development.
llvm-svn: 22606
2005-08-02 23:31:38 +00:00
eee90f7eb4
Change a place to use an arbitrary value instead of null, when possible
...
llvm-svn: 22605
2005-08-02 23:29:23 +00:00
80e038c148
one more hunk that got dropped
...
llvm-svn: 22596
2005-08-02 19:35:29 +00:00
989d8bbda9
This hunk accidentally got dropped. Patch by Jim Laskey
...
llvm-svn: 22595
2005-08-02 19:30:55 +00:00
6667bdbaca
Update to use the new MathExtras.h support for log2 computation.
...
Patch contributed by Jim Laskey!
llvm-svn: 22594
2005-08-02 19:26:06 +00:00
22d00a8e90
Update to use the new MathExtras.h support for log2 computation.
...
Patch contributed by Jim Laskey!
llvm-svn: 22592
2005-08-02 19:16:58 +00:00
c98d48fabe
add a pass name to make debugging dumps nicer
...
llvm-svn: 22588
2005-08-02 19:07:49 +00:00
c9076e0acf
Fix grammar: it's == "it is".
...
llvm-svn: 22587
2005-08-02 16:04:59 +00:00
351b891cbc
Like the comment says, do not insert cast instructions before phi nodes
...
llvm-svn: 22586
2005-08-02 03:31:14 +00:00
9aafa06bef
It's dangerous coding on Mondays.
...
llvm-svn: 22585
2005-08-02 03:26:32 +00:00
4fd3e16cbd
This code was very close, but not quite right. It did not take into
...
consideration the case where a reference in an unreachable block could
occur. This fixes Transforms/SimplifyCFG/2005-08-01-PHIUpdateFail.ll,
something I ran into while bugpoint'ing another pass.
llvm-svn: 22584
2005-08-02 03:24:05 +00:00
ba7cc68594
Implement SetInterruptFunction for Windows.
...
llvm-svn: 22582
2005-08-02 03:04:47 +00:00
75a44e154e
add a comment, make a check more lenient
...
llvm-svn: 22581
2005-08-02 02:52:02 +00:00
dcce49e006
Simplify for loop, clear a per-loop map after processing each loop
...
llvm-svn: 22580
2005-08-02 02:44:31 +00:00
6a5d6ecd09
Implement sys::SetInterruptFunction on Unix, stub it on win32 so that the
...
build will not fail
llvm-svn: 22578
2005-08-02 02:14:22 +00:00
9ef1294210
Add a comment
...
Make LSR ignore GEP's that have loop variant base values, as we currently
cannot codegen them
llvm-svn: 22576
2005-08-02 01:32:29 +00:00
564900e5e5
Fix an iterator invalidation problem
...
llvm-svn: 22575
2005-08-02 00:41:11 +00:00
fca31aee4f
200.sixtrack prints FP numbers with a very strange notation that uses D
...
instead of E for exponentials (e.g. 1.234D-43). Add support for this
notation.
llvm-svn: 22574
2005-08-02 00:11:53 +00:00
ae97fff758
update function codes to reflect /su flags that have been added since this was written
...
llvm-svn: 22571
2005-08-01 20:06:01 +00:00
4398daf069
Fix casts from long to sbyte on ppc
...
llvm-svn: 22570
2005-08-01 18:16:37 +00:00
33bbf15147
use llabs not abs
...
llvm-svn: 22569
2005-08-01 17:47:28 +00:00
27f1e26db7
one cannot allocate a global, until one is done initializing the global pointers
...
llvm-svn: 22568
2005-08-01 17:35:40 +00:00
e17c5d0e59
ConstantInt::get only works for arguments < 128.
...
SimplifyLibCalls probably has to be audited to make sure it does not make
this mistake elsewhere. Also, if this code knows that the type will be
unsigned, obviously one arm of this is dead.
Reid, can you take a look into this further?
llvm-svn: 22566
2005-08-01 16:52:50 +00:00
546fd5944e
Keep tabs and trailing spaces out.
...
llvm-svn: 22565
2005-07-30 18:33:25 +00:00
c500991055
Fix VC++ build problems.
...
llvm-svn: 22564
2005-07-30 18:22:27 +00:00
941d84a34d
fix float->long conversions on x86
...
llvm-svn: 22563
2005-07-30 01:40:57 +00:00
4913457573
fix a typeo
...
llvm-svn: 22561
2005-07-30 00:43:00 +00:00
17a0e2afea
Ack, typo
...
llvm-svn: 22560
2005-07-30 00:21:31 +00:00
aeef51b6b7
Change the fp to integer code to not perform 2-byte stores followed by
...
1 byte loads and other operations. This is bad for store-forwarding on
common CPUs. We now do this:
fnstcw WORD PTR [%ESP]
mov %AX, WORD PTR [%ESP]
instead of:
fnstcw WORD PTR [%ESP]
mov %AL, BYTE PTR [%ESP + 1]
llvm-svn: 22559
2005-07-30 00:17:52 +00:00
Jim Laskey