_foo2:
        extsw r2, r3
        std r2, -8(r1)
        lfd f0, -8(r1)
        fcfid f0, f0
        frsp f1, f0
        blr

instead of this:

_foo2:
        lis r2, ha16(LCPI2_0)
        lis r4, 17200
        xoris r3, r3, 32768
        stw r3, -4(r1)
        stw r4, -8(r1)
        lfs f0, lo16(LCPI2_0)(r2)
        lfd f1, -8(r1)
        fsub f0, f1, f0
        frsp f1, f0
        blr

This speeds up Misc/pi from 2.44s->2.09s with LLC and from 3.01->2.18s
with llcbeta (16.7% and 38.1% respectively).

llvm-svn: 26943

which is shifted left two bits before use.  Instructions like STD use this
addressing mode.

llvm-svn: 26942

llvm-svn: 26935

llvm-svn: 26930

llvm-svn: 26926

llvm-svn: 26924

       lwz r2, 8(0)
instead of this:
       lwz r2, 8(r0)

This fixes the llc/llc-beta failures on PPC last night.

llvm-svn: 26922

llvm-svn: 26917

llvm-svn: 26913

llvm-svn: 26912

disp field of the load/store if possible.  This compiles
CodeGen/PowerPC/load-constant-addr.ll to:

_test:
        lis r2, 2838
        lfs f1, 26848(r2)
        blr

instead of:

_test:
        lis r2, 2838
        ori r2, r2, 26848
        lfs f1, 0(r2)
        blr

llvm-svn: 26908

llvm-svn: 26907

figuring these out! :)

llvm-svn: 26904

llvm-svn: 26902

llvm-svn: 26901

llvm-svn: 26900

constant pool load.  This generates significantly nicer code for splats.

When tblgen gets bugfixed, we can remove the custom selection code.

llvm-svn: 26898

llvm-svn: 26897

llvm-svn: 26896

instructions

llvm-svn: 26894

llvm-svn: 26889

llvm-svn: 26888

TODO: leave specific ones as VECTOR_SHUFFLE's and turn them into specialized
operations like vsplt*

llvm-svn: 26887

llvm-svn: 26886

llvm-svn: 26883

llvm-svn: 26874

llvm-svn: 26868

llvm-svn: 26865

llvm-svn: 26863

llvm-svn: 26857

llvm-svn: 26856

llvm-svn: 26853

llvm-svn: 26848

cost-modeled as producing a flag.  This fixes the test I just added for neg

llvm-svn: 26835

Make the PPC backend not dependent on BRTWOWAY_CC and make the branch
selector smarter about the code it generates, fixing a case in the
readme.

llvm-svn: 26814

llvm-svn: 26813

more target independant, generate better code, and be less conservative.

llvm-svn: 26809

llvm-svn: 26808

llvm-svn: 26807

llvm-svn: 26806