llvm-svn: 32468

llvm-svn: 32426

This implements Transforms/ScalarRepl/union-packed.ll

llvm-svn: 32422

 * Add support for promoting unions with fp values in them.  This produces
   our new int<->fp bitcast instructions, implementing
   Transforms/ScalarRepl/union-fp-int.ll

As an example, this allows us to compile this:

union intfloat { int i; float f; };
float invsqrt(const float arg_x) {
    union intfloat x = { .f = arg_x };
    const float xhalf = arg_x * 0.5f;
    x.i = 0x5f3759df - (x.i >> 1);
    return x.f * (1.5f - xhalf * x.f * x.f);
}

into:

_invsqrt:
        movss 4(%esp), %xmm0
        movd %xmm0, %eax
        sarl %eax
        movl $1597463007, %ecx
        subl %eax, %ecx
        movd %ecx, %xmm1
        mulss LCPI1_0, %xmm0
        mulss %xmm1, %xmm0
        movss LCPI1_1, %xmm2
        mulss %xmm1, %xmm0
        subss %xmm0, %xmm2
        movl 8(%esp), %eax
        mulss %xmm2, %xmm1
        movss %xmm1, (%eax)
        ret

instead of:

_invsqrt:
        subl $4, %esp
        movss 8(%esp), %xmm0
        movss %xmm0, (%esp)
        movl (%esp), %eax
        movl $1597463007, %ecx
        sarl %eax
        subl %eax, %ecx
        movl %ecx, (%esp)
        mulss LCPI1_0, %xmm0
        movss (%esp), %xmm1
        mulss %xmm1, %xmm0
        mulss %xmm1, %xmm0
        movss LCPI1_1, %xmm2
        subss %xmm0, %xmm2
        mulss %xmm2, %xmm1
        movl 12(%esp), %eax
        movss %xmm1, (%eax)
        addl $4, %esp
        ret

llvm-svn: 32418

MarkAliveBlocks.

llvm-svn: 32375

llvm-svn: 32333

llvm-svn: 32320

now cerr, cout, and NullStream resp.

llvm-svn: 32298

llvm-svn: 32288

llvm-svn: 32280

is 'unsigned'.

llvm-svn: 32279

passing false would make the asmprinter fail anyway.

llvm-svn: 32264

llvm-svn: 32252

7.48s.  This regression is due to unforseen consequences of the cast patch.

llvm-svn: 32209

for now.

llvm-svn: 32208

llvm-svn: 32166

llvm-svn: 32113

Transforms/InstCombine/2006-12-01-BadFPVectorXform.ll

llvm-svn: 32112

llvm-svn: 32051

llvm-svn: 32044

llvm-svn: 32043

llvm-svn: 32042

unsigned short swp(unsigned short a) {
       return ((a & 0xff00) >> 8 | (a & 0x00ff) << 8);
}

as an idiom for bswap.

llvm-svn: 32011

This implements InstCombine/cast.ll:test34.  It fires hundreds of times on
176.gcc.

llvm-svn: 32009

folding   seteq (bswap(x)), c -> seteq(x,bswap(c))

llvm-svn: 32006

llvm-svn: 31996

llvm-svn: 31977

producing code for "trunc to bool". This passes all tests on Linux.

llvm-svn: 31963

llvm-svn: 31941

The long awaited CAST patch. This introduces 12 new instructions into LLVM
to replace the cast instruction. Corresponding changes throughout LLVM are
provided. This passes llvm-test, llvm/test, and SPEC CPUINT2000 with the
exception of 175.vpr which fails only on a slight floating point output
difference.

llvm-svn: 31931

llvm-svn: 31925

llvm-svn: 31924

llvm-svn: 31923

llvm-svn: 31922

Remove predicate simplifier from default gcc3 pipeline. New design is too
slow to enable by default.
Add new testcases for problems encountered in development.

llvm-svn: 31895

llvm-svn: 31889

only do these transformations if there are a small number of phi's.
This speeds up Ptrdist/ks from 2.35s to 2.19s on my mac pro.

llvm-svn: 31853

and handle it like constant stride vars.  This fixes some bad codegen in
variable stride cases.  For example, it compiles this:

void foo(int k, int i) {
  for (k=i+i; k <= 8192; k+=i)
    flags2[k] = 0;
}

to:

LBB1_1: #bb.preheader
        movl %eax, %ecx
        addl %ecx, %ecx
        movl L_flags2$non_lazy_ptr, %edx
LBB1_2: #bb
        movb $0, (%edx,%ecx)
        addl %eax, %ecx
        cmpl $8192, %ecx
        jle LBB1_2      #bb
LBB1_5: #return
        ret

or (if the array is local and we are in dynamic-nonpic or static mode):

LBB3_2: #bb
        movb $0, _flags2(%ecx)
        addl %eax, %ecx
        cmpl $8192, %ecx
        jle LBB3_2      #bb

and:

        lis r2, ha16(L_flags2$non_lazy_ptr)
        lwz r2, lo16(L_flags2$non_lazy_ptr)(r2)
        slwi r3, r4, 1
LBB1_2: ;bb
        li r5, 0
        add r6, r4, r3
        stbx r5, r2, r3
        cmpwi cr0, r6, 8192
        bgt cr0, LBB1_5 ;return

instead of:

        leal (%eax,%eax,2), %ecx
        movl %eax, %edx
        addl %edx, %edx
        addl L_flags2$non_lazy_ptr, %edx
        xorl %esi, %esi
LBB1_2: #bb
        movb $0, (%edx,%esi)
        movl %eax, %edi
        addl %esi, %edi
        addl %ecx, %esi
        cmpl $8192, %esi
        jg LBB1_5       #return

and:

        lis r2, ha16(L_flags2$non_lazy_ptr)
        lwz r2, lo16(L_flags2$non_lazy_ptr)(r2)
        mulli r3, r4, 3
        slwi r5, r4, 1
        li r6, 0
        add r2, r2, r5
LBB1_2: ;bb
        li r5, 0
        add r7, r3, r6
        stbx r5, r2, r6
        add r6, r4, r6
        cmpwi cr0, r7, 8192
        ble cr0, LBB1_2 ;bb

This speeds up Benchmarks/Shootout/sieve from 8.533s to 6.464s and
implements LoopStrengthReduce/var_stride_used_by_compare.ll

llvm-svn: 31809

llvm-svn: 31751

(X >> Z) op (Y >> Z)  -> (X op Y) >> Z

for all shifts and all ops={and/or/xor}.

llvm-svn: 31729