llvm-svn: 22989

Use this information to avoid doing expensive interval intersections for
registers that could not possible be interesting.  This speeds up linscan
on ia64 compiling kc++ in release mode from taking 7.82s to 4.8s(!), total
itanium llc time on this program is 27.3s now.  This marginally speeds up
PPC and X86, but they appear to be limited by other parts of linscan, not
this code.

On this program, on itanium, live intervals now takes 41% of llc time.

llvm-svn: 22986

either seteq X, 0 or srl (ctlz X), size(X-1), depending on what's legal
for the target.

llvm-svn: 22978

llvm-svn: 22977

number of regs (e.g. most riscs), many functions won't need to use callee
clobbered registers.  Do a speculative check to see if we can get a free
register without processing the fixed list (which has all of these).  This
saves a lot of time on machines with lots of callee clobbered regs (e.g.
ppc and itanium, also x86).

This reduces ppc llc compile time from 184s -> 172s on kc++.  This is probably
worth FAR FAR more on itanium though.

llvm-svn: 22972

we spill out of the fast path.  The scan of active_ and the calls to
updateSpillWeights don't need to happen unless a spill occurs.  This reduces
debug llc time of kc++ with ppc from 187.3s to 183.2s.

llvm-svn: 22971

promoted to the right type.  This fixes: IA64/2005-08-22-LegalizerCrash.ll

llvm-svn: 22969

add some comments.  This loop really needs to be reevaluated!

llvm-svn: 22966

allowing us to compile this:

float %test2(float* %P) {
        %Q = load float* %P
        %R = add float %Q, 10.1
        ret float %R
}

to this:

_test2:
        lfs r2, 0(r3)
        lis r3, ha16(.CPI_test2_0)
        lfs r3, lo16(.CPI_test2_0)(r3)
        fadds f1, r2, r3
        blr

llvm-svn: 22962

llvm-svn: 22957

llvm-svn: 22956

llvm-svn: 22955

llvm-svn: 22949

llvm-svn: 22948

the old condition to a one bit value.  The incoming value must have been
promoted, and the top bits are undefined.  This causes us to generate:

_test:
        rlwinm r2, r3, 0, 31, 31
        li r3, 17
        cmpwi cr0, r2, 0
        bne .LBB_test_2 ;
.LBB_test_1:    ;
        li r3, 1
.LBB_test_2:    ;
        blr

instead of:

_test:
        rlwinm r2, r3, 0, 31, 31
        li r2, 17
        cmpwi cr0, r3, 0
        bne .LBB_test_2 ;
.LBB_test_1:    ;
        li r2, 1
.LBB_test_2:    ;
        or r3, r2, r2
        blr

for:

int %test(bool %c) {
        %retval = select bool %c, int 17, int 1
        ret int %retval
}

llvm-svn: 22947

llvm-svn: 22943

llvm-svn: 22940

llvm-svn: 22938

us to compile stuff like this:

double %test(double %A, double %B, double %C, double %E) {
        %F = mul double %A, %A
        %G = add double %F, %B
        %H = sub double -0.0, %G
        %I = mul double %H, %C
        %J = add double %I, %E
        ret double %J
}

to:

_test:
        fnmadd f0, f1, f1, f2
        fmadd f1, f0, f3, f4
        blr

woot!

llvm-svn: 22937

llvm-svn: 22936

llvm-svn: 22934

This gets us this for the previous testcase:

_test:
        lis r2, 0
        ori r3, r2, 65535
        blr

Note that we actually write to r3 (the return reg) correctly now :)

llvm-svn: 22933

temporary registers for things that define a register.  This allows dag->dag
isel to compile this:

int %test() { ret int 65535 }

into:

_test:
        lis r2, 0
        ori r2, r2, 65535
        blr

Next up, getting CopyFromReg to work, allowing arguments and cross-bb values.

llvm-svn: 22932

llvm-svn: 22907

llvm-svn: 22902

llvm-svn: 22896

llvm-svn: 22878

codegen:

_empty:
.LBB_empty_0:   ;
        blr

but can't do anything more (yet). :)

llvm-svn: 22876

llvm-svn: 22868

llvm-svn: 22863

rlwinm.

llvm-svn: 22856

llvm-svn: 22853

Added some class dividers in SelectionDAG.cpp.

llvm-svn: 22841

llvm-svn: 22838

argument is not specified.

Implement ReplaceAllUsesWith.

llvm-svn: 22834

llvm-svn: 22831

llvm-svn: 22828

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

llvm-svn: 22822

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