llvm-svn: 22821

it.

llvm-svn: 22820

selector.  Also, there is no difference between addSImm and addImm, so just
use addImm, folding some branches.

llvm-svn: 22819

llvm-svn: 22818

llvm-svn: 22817

marked as legal.

llvm-svn: 22816

llvm-svn: 22815

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

llvm-svn: 22813

subjected to folding.

llvm-svn: 22812

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

llvm-svn: 22810

llvm-svn: 22809

llvm-svn: 22808

llvm-svn: 22807

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

fixme from the PowerPC backend.  Emit slightly better code for legalizing
select_cc.

llvm-svn: 22805

when printing a node, use it to render target operations with their
target instruction name instead of "<<unknown>>".

llvm-svn: 22804

llvm-svn: 22803

llvm-svn: 22802

Split RemoveNodeFromCSEMaps out of DeleteNodesIfDead to do it.

llvm-svn: 22801

llvm-svn: 22800

can be shared with the DAG->DAG selector.

llvm-svn: 22799

loop, because a IV-dependent value was used outside of the loop and didn't
have immediate-folding capability

llvm-svn: 22798

llvm-svn: 22797

llvm-svn: 22796

Only run createLowerConstantExpressionsPass for the simple isel.  The DAG
isel has no need for it.

llvm-svn: 22794

a < expression, e.g.: for (i = m; i < n; ++i)

llvm-svn: 22793

llvm-svn: 22792

Changed code gen for int to f32 to use rounding.  This makes FP results
consistent with gcc.

llvm-svn: 22791

llvm-svn: 22790

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

block.  nur.

llvm-svn: 22788

llvm-svn: 22787

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

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

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

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

.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

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