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

llvm-svn: 22970

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

llvm-svn: 22963

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

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

By returning the right result.

llvm-svn: 22961

Make sure expressions only have one use before emitting them into a place that is conditionally executed

llvm-svn: 22960

llvm-svn: 22959

llvm-svn: 22957

llvm-svn: 22956

llvm-svn: 22955

llvm-svn: 22953

simplifies BRTWOWAY into BR if one of the results is a fall-through.
Unless I'm missing something, there is no reason to duplicate this
in the target-specific code.

llvm-svn: 22952

llvm-svn: 22951

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

it in the block.  This codegens:

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

as:

_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

instead of:

_test:
        rlwinm r2, r3, 0, 31, 31
        li r2, 17
        li r4, 1
        cmpwi cr0, r3, 0
        bne .LBB_test_2 ;
.LBB_test_1:    ;
        or r2, r4, r4
.LBB_test_2:    ;
        or r3, r2, r2
        blr

... which is one fewer instruction.  The savings are more significant for
global address and constantfp nodes.

llvm-svn: 22946

llvm-svn: 22944

llvm-svn: 22943

llvm-svn: 22942

This REALLY should be lowered by the legalizer!

llvm-svn: 22941

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: 22935

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: 22929

llvm-svn: 22927

llvm-svn: 22926

llvm-svn: 22925

llvm-svn: 22924

namespace instead of the reg class namespace.  Update getRegClassForType()
to use modified names due to tblgen change.

llvm-svn: 22923

llvm-svn: 22922

llvm-svn: 22921

llvm-svn: 22917