llvm-svn: 21275

Olden/mst, Ptrdist/bc, Obsequi, etc.

llvm-svn: 21274

llvm-svn: 21273

llvm-svn: 21272

llvm-svn: 21271

like this:

        ldah $1,1($31)
        lda $1,-1($1)
        and $0,$1,$24

instead of this:

        zap $0,252,$24

To get this back, the selector should recognize the ISD::AND case where this
happens and emit the appropriate ZAP instruction.

llvm-svn: 21270

things like this:

       mov r9 = 65535;;
       and r8 = r8, r9;;

To be emitted instead of:

        zxt2 r8 = r8;;

To get this back, the selector for ISD::AND should recognize this case.

llvm-svn: 21269

andi instructions instead of rlwinm instructions for zero extend, but they
seem like they would take the same time.

llvm-svn: 21268

llvm-svn: 21267

SelectionDAG to do the job with AND.  Don't legalize Z_E_I anymore as
it is gone

llvm-svn: 21266

instead.  OVerall, this increases the amount of folding we can do.

llvm-svn: 21265

ZERO_EXTEND_INREG was.

llvm-svn: 21264

llvm-svn: 21263

llvm-svn: 21262

Make llvm undef values generate ISD::UNDEF nodes

llvm-svn: 21261

Remove dead setcc op, 0 sequences
Coming later: generalization of op, imm

llvm-svn: 21260

llvm-svn: 21258

llvm-svn: 21255

llvm-svn: 21254

llvm-svn: 21253

to avoid redundant mov out3=r44 type instructions, we need to
tell the register allocator the truth about out? registers.

FIXME: unfortunately, since the list of allocatable registers is immutable,
we can't simply 'delete r127' from the allocation order, say, if 'out0' is
used. The only correct thing we can do is have a linear order of regs:

out7, out6 ... out2, out1, out0, r32, r33, r34 ... r126, r127

and slide a 'window' of 96 registers along this line, depending on how many
of the out? regs a function actually uses. The only downside of this is
that the out? registers will be allocated _first_, which makes the
resulting assembly ugly. :( Note this in the README. Hope this gets fixed
soon. :) (note the 3rd person speech there)

llvm-svn: 21252

llvm-svn: 21251

llvm-svn: 21250

coallesce moves into outgoing args.

llvm-svn: 21249

llvm-svn: 21248

llvm-svn: 21247

llvm-svn: 21246

llvm-svn: 21245

compile this:

int foo (unsigned long a, unsigned long long g) {
  return a >= g;
}

To:

foo:
        movl 8(%esp), %eax
        cmpl %eax, 4(%esp)
        setae %al
        cmpl $0, 12(%esp)
        sete %cl
        andb %al, %cl
        movzbl %cl, %eax
        ret

instead of:

foo:
        movl 8(%esp), %eax
        cmpl %eax, 4(%esp)
        setae %al
        movzbw %al, %cx
        movl 12(%esp), %edx
        cmpl $0, %edx
        sete %al
        movzbw %al, %ax
        cmpl $0, %edx
        cmove %cx, %ax
        movzbl %al, %eax
        ret

llvm-svn: 21244

bool %test1(long %X) {
        %A = setlt long %X, 0
        ret bool %A
}

like this:

test1:
        cmpl $0, 8(%esp)
        setl %al
        movzbl %al, %eax
        ret

instead of:

test1:
        movl 8(%esp), %ecx
        cmpl $0, %ecx
        setl %al
        movzbw %al, %ax
        cmpl $0, 4(%esp)
        setb %dl
        movzbw %dl, %dx
        cmpl $0, %ecx
        cmove %dx, %ax
        movzbl %al, %eax
        ret

llvm-svn: 21243

test2:
        movl 8(%esp), %eax
        notl %eax
        movl 4(%esp), %ecx
        notl %ecx
        orl %eax, %ecx
        cmpl $0, %ecx
        sete %al
        movzbl %al, %eax
        ret

or this (PPC):

_test2:
        nor r2, r4, r4
        nor r3, r3, r3
        or r2, r2, r3
        cntlzw r2, r2
        srwi r3, r2, 5
        blr

Emit this:

test2:
        movl 8(%esp), %eax
        andl 4(%esp), %eax
        cmpl $-1, %eax
        sete %al
        movzbl %al, %eax
        ret

or this:

_test2:
.LBB_test2_0:   ;
        and r2, r4, r3
        cmpwi cr0, r2, -1
        li r3, 1
        li r2, 0
        beq .LBB_test2_2        ;
.LBB_test2_1:   ;
        or r3, r2, r2
.LBB_test2_2:   ;
        blr

it seems like the PPC isel could do better for R32 == -1 case.

llvm-svn: 21242

unsigned long long g;
unsigned long foo (unsigned long a) {
  return (a >= g) ? 1 : 0;
}

It changes the ppc code from:

_foo:
.LBB_foo_0:     ; entry
        mflr r11
        stw r11, 8(r1)
        bl "L00000$pb"
"L00000$pb":
        mflr r2
        addis r2, r2, ha16(L_g$non_lazy_ptr-"L00000$pb")
        lwz r2, lo16(L_g$non_lazy_ptr-"L00000$pb")(r2)
        lwz r4, 0(r2)
        lwz r2, 4(r2)
        cmplw cr0, r3, r2
        li r2, 1
        li r3, 0
        bge .LBB_foo_2  ; entry
.LBB_foo_1:     ; entry
        or r2, r3, r3
.LBB_foo_2:     ; entry
        cmplwi cr0, r4, 1
        li r3, 1
        li r5, 0
        blt .LBB_foo_4  ; entry
.LBB_foo_3:     ; entry
        or r3, r5, r5
.LBB_foo_4:     ; entry
        cmpwi cr0, r4, 0
        beq .LBB_foo_6  ; entry
.LBB_foo_5:     ; entry
        or r2, r3, r3
.LBB_foo_6:     ; entry
        rlwinm r3, r2, 0, 31, 31
        lwz r11, 8(r1)
        mtlr r11
        blr


to:

_foo:
.LBB_foo_0:     ; entry
        mflr r11
        stw r11, 8(r1)
        bl "L00000$pb"
"L00000$pb":
        mflr r2
        addis r2, r2, ha16(L_g$non_lazy_ptr-"L00000$pb")
        lwz r2, lo16(L_g$non_lazy_ptr-"L00000$pb")(r2)
        lwz r4, 0(r2)
        lwz r2, 4(r2)
        cmplw cr0, r3, r2
        li r2, 1
        li r3, 0
        bge .LBB_foo_2  ; entry
.LBB_foo_1:     ; entry
        or r2, r3, r3
.LBB_foo_2:     ; entry
        cntlzw r3, r4
        srwi r3, r3, 5
        cmpwi cr0, r4, 0
        beq .LBB_foo_4  ; entry
.LBB_foo_3:     ; entry
        or r2, r3, r3
.LBB_foo_4:     ; entry
        rlwinm r3, r2, 0, 31, 31
        lwz r11, 8(r1)
        mtlr r11
        blr

llvm-svn: 21241

Implement divide by negative power of two

llvm-svn: 21240

llvm-svn: 21232

long long test2(unsigned A, unsigned B) {
        return ((unsigned long long)A << 32) + B;
}

is equivalent to this:

long long test1(unsigned A, unsigned B) {
        return ((unsigned long long)A << 32) | B;
}

Now they are both codegen'd to this on ppc:

_test2:
        blr

or this on x86:

test2:
        movl 4(%esp), %edx
        movl 8(%esp), %eax
        ret

llvm-svn: 21231

masking shifts.

This fixes the miscompilation of this:

long long test1(unsigned A, unsigned B) {
        return ((unsigned long long)A << 32) | B;
}

into this:

test1:
        movl 4(%esp), %edx
        movl %edx, %eax
        orl 8(%esp), %eax
        ret

allowing us to generate this instead:

test1:
        movl 4(%esp), %edx
        movl 8(%esp), %eax
        ret

llvm-svn: 21230

llvm-svn: 21228

llvm-svn: 21227

llvm-svn: 21226

Refactor how . instructions are handled.  In particular, instead of passing
the RC flag all the way up the inheritance hierarchy, just make a new tblgen
class 'DOT' which can be added to an instruction definition.

For example, instead of this:

-def AND  : XForm_6<31,  28, 0, 0, 0, (ops GPRC:$rA, GPRC:$rS, GPRC:$rB),
-let Defs = [CR0] in
-def ANDo : XForm_6<31,  28, 1, 0, 0, (ops GPRC:$rA, GPRC:$rS, GPRC:$rB),
-                   "and. $rA, $rS, $rB">;

We now have this:

+def AND  : XForm_6<31,  28, 0, 0, (ops GPRC:$rA, GPRC:$rS, GPRC:$rB),
                    "and $rA, $rS, $rB">;

llvm-svn: 21225