| Commit message (Collapse) | Author | Age | Files | Lines |
| ... | |
| |
|
|
|
|
|
|
|
| |
the new zero extend, not the original operand. This fixes cast bool -> long
on ppc.
Add an unrelated fixme
llvm-svn: 21196
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
int a(short i) {
return i & 1;
}
as
_a:
andi. r3, r3, 1
blr
instead of:
_a:
rlwinm r2, r3, 0, 16, 31
andi. r3, r2, 1
blr
on ppc. It should also help the other risc targets.
llvm-svn: 21189
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
is deconstructed then reconstructed here. This catches 19 fabs's in 177.mesa
9 in 168.wupwise, 5 in 171.swim, 3 in 172.mgrid, and 14 in 173.applu out of
specfp2000.
This allows the X86 code generator to make MUCH better code than before for
each of these and saves one instr on ppc.
This depends on the previous CFE patch to expose these correctly.
llvm-svn: 21171
|
| |
|
|
| |
llvm-svn: 21165
|
| |
|
|
| |
llvm-svn: 21160
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
this into sign/zero extension instructions later.
On PPC, for example, this testcase:
%G = external global sbyte
implementation
void %test(int %X, int %Y) {
%C = setlt int %X, %Y
%D = cast bool %C to sbyte
store sbyte %D, sbyte* %G
ret void
}
Now codegens to:
cmpw cr0, r3, r4
li r3, 1
li r4, 0
blt .LBB_test_2 ;
.LBB_test_1: ;
or r3, r4, r4
.LBB_test_2: ;
addis r2, r2, ha16(L_G$non_lazy_ptr-"L00000$pb")
lwz r2, lo16(L_G$non_lazy_ptr-"L00000$pb")(r2)
stb r3, 0(r2)
instead of:
cmpw cr0, r3, r4
li r3, 1
li r4, 0
blt .LBB_test_2 ;
.LBB_test_1: ;
or r3, r4, r4
.LBB_test_2: ;
*** rlwinm r3, r3, 0, 31, 31
addis r2, r2, ha16(L_G$non_lazy_ptr-"L00000$pb")
lwz r2, lo16(L_G$non_lazy_ptr-"L00000$pb")(r2)
stb r3, 0(r2)
llvm-svn: 21148
|
| |
|
|
| |
llvm-svn: 21144
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(likewise for <= >=u >=u).
Second, it implements a special case hack to turn 'X gtu SINTMAX' -> 'X lt 0'
On powerpc, for example, this changes this:
lis r2, 32767
ori r2, r2, 65535
cmplw cr0, r3, r2
bgt .LBB_test_2
into:
cmpwi cr0, r3, 0
blt .LBB_test_2
llvm-svn: 21142
|
| |
|
|
|
|
| |
elements auto of the autoCSE maps.
llvm-svn: 21128
|
| |
|
|
|
|
| |
multiply.
llvm-svn: 21102
|
| |
|
|
| |
llvm-svn: 21008
|
| |
|
|
| |
llvm-svn: 21004
|
| |
|
|
| |
llvm-svn: 21001
|
| |
|
|
|
|
|
|
|
| |
Teach the SelectionDAG code how to expand and promote it
Have PPC32 LowerCallTo generate ISD::UNDEF for int arg regs used up by fp
arguments, but not shadowing their value. This allows us to do the right
thing with both fixed and vararg floating point arguments.
llvm-svn: 20988
|
| |
|
|
| |
llvm-svn: 20965
|
| |
|
|
|
|
|
| |
because we were checking the wrong thing. Thanks to andrew for pointing
this out!
llvm-svn: 20554
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This allows the alpha backend to compile:
bool %test(uint %P) {
%c = seteq uint %P, 0
ret bool %c
}
into:
test:
ldgp $29, 0($27)
ZAP $16,240,$0
CMPEQ $0,0,$0
AND $0,1,$0
ret $31,($26),1
instead of:
test:
ldgp $29, 0($27)
ZAP $16,240,$0
ldiq $1,0
ZAP $1,240,$1
CMPEQ $0,$1,$0
AND $0,1,$0
ret $31,($26),1
... and fixes PR534.
llvm-svn: 20534
|
| |
|
|
|
|
| |
for 0.0 and -0.0.
llvm-svn: 20230
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
the new TLI that is available.
Implement support for handling out of range shifts. This allows us to
compile this code (a 64-bit rotate):
unsigned long long f3(unsigned long long x) {
return (x << 32) | (x >> (64-32));
}
into this:
f3:
mov %EDX, DWORD PTR [%ESP + 4]
mov %EAX, DWORD PTR [%ESP + 8]
ret
GCC produces this:
$ gcc t.c -masm=intel -O3 -S -o - -fomit-frame-pointer
..
f3:
push %ebx
mov %ebx, DWORD PTR [%esp+12]
mov %ecx, DWORD PTR [%esp+8]
mov %eax, %ebx
mov %edx, %ecx
pop %ebx
ret
The Simple ISEL produces (eww gross):
f3:
sub %ESP, 4
mov DWORD PTR [%ESP], %ESI
mov %EDX, DWORD PTR [%ESP + 8]
mov %ECX, DWORD PTR [%ESP + 12]
mov %EAX, 0
mov %ESI, 0
or %EAX, %ECX
or %EDX, %ESI
mov %ESI, DWORD PTR [%ESP]
add %ESP, 4
ret
llvm-svn: 19780
|
| |
|
|
| |
llvm-svn: 19739
|
| |
|
|
| |
llvm-svn: 19737
|
| |
|
|
| |
llvm-svn: 19736
|
| |
|
|
| |
llvm-svn: 19735
|
| |
|
|
| |
llvm-svn: 19727
|
| |
|
|
| |
llvm-svn: 19714
|
| |
|
|
| |
llvm-svn: 19699
|
| |
|
|
| |
llvm-svn: 19698
|
| |
|
|
| |
llvm-svn: 19670
|
| |
|
|
| |
llvm-svn: 19656
|
| |
|
|
| |
llvm-svn: 19651
|
| |
|
|
| |
llvm-svn: 19635
|
| |
|
|
| |
llvm-svn: 19596
|
| |
|
|
| |
llvm-svn: 19577
|
| |
|
|
| |
llvm-svn: 19575
|
| |
|
|
| |
llvm-svn: 19572
|
| |
|
|
| |
llvm-svn: 19568
|
| |
|
|
|
|
| |
stores/loads.
llvm-svn: 19562
|
| |
|
|
| |
llvm-svn: 19559
|
| |
|
|
| |
llvm-svn: 19535
|
| |
|
|
| |
llvm-svn: 19526
|
| |
|
|
|
|
| |
This fixes llvm-test/SingleSource/Regression/C/casts.c
llvm-svn: 19519
|
| |
|
|
| |
llvm-svn: 19517
|
| |
|
|
| |
llvm-svn: 19464
|
| |
|
|
| |
llvm-svn: 19453
|
| |
|
|
| |
llvm-svn: 19443
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
int test2(int * P, int* Q, int A, int B) {
return P+A == P;
}
into:
test2:
movl 4(%esp), %eax
movl 12(%esp), %eax
shll $2, %eax
cmpl $0, %eax
sete %al
movzbl %al, %eax
ret
instead of:
test2:
movl 4(%esp), %eax
movl 12(%esp), %ecx
leal (%eax,%ecx,4), %ecx
cmpl %eax, %ecx
sete %al
movzbl %al, %eax
ret
ICC is producing worse code:
test2:
movl 4(%esp), %eax #8.5
movl 12(%esp), %edx #8.5
lea (%edx,%edx), %ecx #9.9
addl %ecx, %ecx #9.9
addl %eax, %ecx #9.9
cmpl %eax, %ecx #9.16
movl $0, %eax #9.16
sete %al #9.16
ret #9.16
as is GCC (looks like our old code):
test2:
movl 4(%esp), %edx
movl 12(%esp), %eax
leal (%edx,%eax,4), %ecx
cmpl %edx, %ecx
sete %al
movzbl %al, %eax
ret
llvm-svn: 19430
|
| |
|
|
| |
llvm-svn: 19429
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
.LBB_Z5test0PdS__3: # no_exit.1
fldl data(,%eax,8)
fldl 24(%esp)
faddp %st(1)
fstl 24(%esp)
incl %eax
movl $16000, %ecx
sarl $3, %ecx
cmpl %eax, %ecx
fstpl 16(%esp)
#FP_REG_KILL
jg .LBB_Z5test0PdS__3 # no_exit.1
into:
.LBB_Z5test0PdS__3: # no_exit.1
fldl data(,%eax,8)
fldl 24(%esp)
faddp %st(1)
fstl 24(%esp)
incl %eax
cmpl $2000, %eax
fstpl 16(%esp)
#FP_REG_KILL
jl .LBB_Z5test0PdS__3 # no_exit.1
llvm-svn: 19427
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
codegen this loop in stepanov:
no_exit.i: ; preds = %entry, %no_exit.i, %then.i, %_Z5checkd.exit
%i.0.0 = phi int [ 0, %entry ], [ %i.0.0, %no_exit.i ], [ %inc.0, %_Z5checkd.exit ], [ %inc.012, %then.i ] ; <int> [#uses=3]
%indvar = phi uint [ %indvar.next, %no_exit.i ], [ 0, %entry ], [ 0, %then.i ], [ 0, %_Z5checkd.exit ] ; <uint> [#uses=3]
%result_addr.i.0 = phi double [ %tmp.4.i.i, %no_exit.i ], [ 0.000000e+00, %entry ], [ 0.000000e+00, %then.i ], [ 0.000000e+00, %_Z5checkd.exit ] ; <double> [#uses=1]
%first_addr.0.i.2.rec = cast uint %indvar to int ; <int> [#uses=1]
%first_addr.0.i.2 = getelementptr [2000 x double]* %data, int 0, uint %indvar ; <double*> [#uses=1]
%inc.i.rec = add int %first_addr.0.i.2.rec, 1 ; <int> [#uses=1]
%inc.i = getelementptr [2000 x double]* %data, int 0, int %inc.i.rec ; <double*> [#uses=1]
%tmp.3.i.i = load double* %first_addr.0.i.2 ; <double> [#uses=1]
%tmp.4.i.i = add double %result_addr.i.0, %tmp.3.i.i ; <double> [#uses=2]
%tmp.2.i = seteq double* %inc.i, getelementptr ([2000 x double]* %data, int 0, int 2000) ; <bool> [#uses=1]
%indvar.next = add uint %indvar, 1 ; <uint> [#uses=1]
br bool %tmp.2.i, label %_Z10accumulateIPddET0_T_S2_S1_.exit, label %no_exit.i
To this:
.LBB_Z4testIPddEvT_S1_T0__1: # no_exit.i
fldl data(,%eax,8)
fldl 16(%esp)
faddp %st(1)
fstpl 16(%esp)
incl %eax
movl %eax, %ecx
shll $3, %ecx
cmpl $16000, %ecx
#FP_REG_KILL
jne .LBB_Z4testIPddEvT_S1_T0__1 # no_exit.i
instead of this:
.LBB_Z4testIPddEvT_S1_T0__1: # no_exit.i
fldl data(,%eax,8)
fldl 16(%esp)
faddp %st(1)
fstpl 16(%esp)
incl %eax
leal data(,%eax,8), %ecx
leal data+16000, %edx
cmpl %edx, %ecx
#FP_REG_KILL
jne .LBB_Z4testIPddEvT_S1_T0__1 # no_exit.i
llvm-svn: 19425
|
| |
|
|
| |
llvm-svn: 19423
|