| Commit message (Collapse) | Author | Age | Files | Lines |
| ... | |
| |
|
|
| |
llvm-svn: 26006
|
| |
|
|
| |
llvm-svn: 26005
|
| |
|
|
| |
llvm-svn: 26001
|
| |
|
|
| |
llvm-svn: 26000
|
| |
|
|
| |
llvm-svn: 25945
|
| |
|
|
| |
llvm-svn: 25934
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
and instruction. This allows us to compile stuff like this:
bool %X(int %X) {
%Y = add int %X, 14
%Z = setne int %Y, 12345
ret bool %Z
}
to this:
_X:
cmpl $12331, 4(%esp)
setne %al
movzbl %al, %eax
ret
instead of this:
_X:
cmpl $12331, 4(%esp)
setne %al
movzbl %al, %eax
andl $1, %eax
ret
This occurs quite a bit with the X86 backend. For example, 25 times in
lambda, 30 times in 177.mesa, 14 times in galgel, 70 times in fma3d,
25 times in vpr, several hundred times in gcc, ~45 times in crafty,
~60 times in parser, ~140 times in eon, 110 times in perlbmk, 55 on gap,
16 times on bzip2, 14 times on twolf, and 1-2 times in many other SPEC2K
programs.
llvm-svn: 25901
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(C1-X) == C2 --> X == C1-C2
(X+C1) == C2 --> X == C2-C1
This allows us to compile this:
bool %X(int %X) {
%Y = add int %X, 14
%Z = setne int %Y, 12345
ret bool %Z
}
into this:
_X:
cmpl $12331, 4(%esp)
setne %al
movzbl %al, %eax
andl $1, %eax
ret
not this:
_X:
movl $14, %eax
addl 4(%esp), %eax
cmpl $12345, %eax
setne %al
movzbl %al, %eax
andl $1, %eax
ret
Testcase here: Regression/CodeGen/X86/compare-add.ll
nukage of the and coming up next.
llvm-svn: 25898
|
| |
|
|
|
|
| |
of the SELECT_CC, BR_CC, and BRTWOWAY_CC nodes.
llvm-svn: 25875
|
| |
|
|
|
|
| |
interface,making isMaskedValueZeroForTargetNode simpler, and useable from other partsof the compiler.
llvm-svn: 25803
|
| |
|
|
|
|
| |
to permit recursion
llvm-svn: 25799
|
| |
|
|
| |
llvm-svn: 25767
|
| |
|
|
| |
llvm-svn: 25723
|
| |
|
|
| |
llvm-svn: 25515
|
| |
|
|
|
|
| |
Now all constant folding in the code generator is in one place.
llvm-svn: 25426
|
| |
|
|
|
|
| |
fixes: test/Regression/CodeGen/Generic/2005-01-18-SetUO-InfLoop.ll
llvm-svn: 25419
|
| |
|
|
| |
llvm-svn: 25339
|
| |
|
|
|
|
|
|
|
|
|
| |
subfic r3, r2, 33
instead of this:
subfic r2, r2, 32
addi r3, r2, 1
llvm-svn: 25255
|
| |
|
|
|
|
| |
promote/expand code yet. This fixes the 177.mesa failure on PPC.
llvm-svn: 25250
|
| |
|
|
|
|
|
|
|
| |
Add dag combiner code to recognize rotl, rotr
Add ppc code to match rotl
Targets should add rotl/rotr patterns if they have them
llvm-svn: 25222
|
| |
|
|
| |
llvm-svn: 25121
|
| |
|
|
| |
llvm-svn: 25120
|
| |
|
|
|
|
| |
inserted in the code.
llvm-svn: 25104
|
| |
|
|
| |
llvm-svn: 25096
|
| |
|
|
| |
llvm-svn: 24995
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
void bar(double Y, double *X) {
*X = Y;
}
to this:
bar:
save -96, %o6, %o6
st %i1, [%i2+4]
st %i0, [%i2]
restore %g0, %g0, %g0
retl
nop
instead of this:
bar:
save -104, %o6, %o6
st %i1, [%i6+-4]
st %i0, [%i6+-8]
ldd [%i6+-8], %f0
std %f0, [%i2]
restore %g0, %g0, %g0
retl
nop
on sparcv8.
llvm-svn: 24983
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This allows us to compile this:
void foo(double);
void bar(double *X) { foo(*X); }
To this:
bar:
save -96, %o6, %o6
ld [%i0+4], %o1
ld [%i0], %o0
call foo
nop
restore %g0, %g0, %g0
retl
nop
instead of this:
bar:
save -104, %o6, %o6
ldd [%i0], %f0
std %f0, [%i6+-8]
ld [%i6+-4], %o1
ld [%i6+-8], %o0
call foo
nop
restore %g0, %g0, %g0
retl
nop
on SparcV8.
llvm-svn: 24982
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
void foo(double);
void bar(double X) { foo(X); }
to this:
bar:
save -96, %o6, %o6
or %g0, %i0, %o0
or %g0, %i1, %o1
call foo
nop
restore %g0, %g0, %g0
retl
nop
instead of this:
bar:
save -112, %o6, %o6
st %i1, [%i6+-4]
st %i0, [%i6+-8]
ldd [%i6+-8], %f0
std %f0, [%i6+-16]
ld [%i6+-12], %o1
ld [%i6+-16], %o0
call foo
nop
restore %g0, %g0, %g0
retl
nop
on V8.
llvm-svn: 24981
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
conversions. This allows V8 to compiles this:
void %test() {
call float %test2( float 1.000000e+00, float 2.000000e+00, double 3.000000e+00, double* null )
ret void
}
into:
test:
save -96, %o6, %o6
sethi 0, %o3
sethi 1049088, %o2
sethi 1048576, %o1
sethi 1040384, %o0
or %g0, %o3, %o4
call test2
nop
restore %g0, %g0, %g0
retl
nop
instead of:
test:
save -112, %o6, %o6
sethi 0, %o4
sethi 1049088, %l0
st %o4, [%i6+-12]
st %l0, [%i6+-16]
ld [%i6+-12], %o3
ld [%i6+-16], %o2
sethi 1048576, %o1
sethi 1040384, %o0
call test2
nop
restore %g0, %g0, %g0
retl
nop
llvm-svn: 24980
|
| |
|
|
|
|
| |
* Teach DAG combiner about X86ISD::SETCC by adding a TargetLowering hook.
llvm-svn: 24921
|
| |
|
|
|
|
| |
if after legalize. This fixes IA64 failures.
llvm-svn: 24725
|
| |
|
|
|
|
|
|
|
| |
load. This reduces number of worklist iterations and avoid missing optimizations
depending on folding of things into sext_inreg nodes (which aren't supported by
all targets).
Tested by Regression/CodeGen/X86/extend.ll:test2
llvm-svn: 24712
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Allow (zext (truncate)) to apply after legalize if the target supports
AND (which all do).
This compiles
short %foo() {
%tmp.0 = load ubyte* %X ; <ubyte> [#uses=1]
%tmp.3 = cast ubyte %tmp.0 to short ; <short> [#uses=1]
ret short %tmp.3
}
to:
_foo:
movzbl _X, %eax
ret
instead of:
_foo:
movzbl _X, %eax
movzbl %al, %eax
ret
thanks to Evan for pointing this out.
llvm-svn: 24709
|
| |
|
|
| |
llvm-svn: 24706
|
| |
|
|
| |
llvm-svn: 24702
|
| |
|
|
|
|
| |
if the target supports the resultant sextinreg
llvm-svn: 24632
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
when the types match up. This allows the X86 backend to compile:
sbyte %toggle_value(sbyte* %tmp.1) {
%tmp.2 = load sbyte* %tmp.1
ret sbyte %tmp.2
}
to this:
_toggle_value:
mov %EAX, DWORD PTR [%ESP + 4]
movsx %EAX, BYTE PTR [%EAX]
ret
instead of this:
_toggle_value:
mov %EAX, DWORD PTR [%ESP + 4]
movsx %EAX, BYTE PTR [%EAX]
movsx %EAX, %AL
ret
noticed in Shootout/objinst.
-Chris
llvm-svn: 24630
|
| |
|
|
| |
llvm-svn: 24318
|
| |
|
|
|
|
|
|
| |
eliminates the vector, allows constant time removal of a node froma graph, and makes iteration over the all nodes list stable when adding
nodes to the graph.
llvm-svn: 24263
|
| |
|
|
|
|
| |
XCode's indenting.
llvm-svn: 24159
|
| |
|
|
|
|
| |
may fix PR652. Thanks to Andrew for tracking down the problem.
llvm-svn: 24145
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This implements test/Regression/CodeGen/PowerPC/mul-neg-power-2.ll,
producing:
_foo:
slwi r2, r3, 1
subfic r3, r2, 63
blr
instead of:
_foo:
mulli r2, r3, -2
addi r3, r2, 63
blr
llvm-svn: 24106
|
| |
|
|
|
|
| |
VT as the killing one. Fix fixes PR491
llvm-svn: 24034
|
| |
|
|
| |
llvm-svn: 24029
|
| |
|
|
| |
llvm-svn: 23980
|
| |
|
|
|
|
|
|
| |
the input is that type, this caused a failure on gs on X86 last night.
Move the hard checks into Build[US]Div since that is where decisions like
this should be made.
llvm-svn: 23881
|
| |
|
|
|
|
| |
2005-10-21-longlonggtu.ll.
llvm-svn: 23875
|
| |
|
|
| |
llvm-svn: 23856
|
| |
|
|
|
|
|
|
|
|
| |
Add a new flag to TargetLowering indicating if the target has really cheap
signed division by powers of two, make ppc use it. This will probably go
away in the future.
Implement some more ISD::SDIV folds in the dag combiner
Remove now dead code in the x86 backend.
llvm-svn: 23853
|
| |
|
|
|
|
|
| |
for types that aren't legal, and fail a divisor is less than zero
comparison, which would cause us to drop a subtract.
llvm-svn: 23846
|