x86 and ppc for 100% dense switch statements when relocations are non-PIC.
This support will be extended and enhanced in the coming days to support
PIC, and less dense forms of jump tables.

llvm-svn: 27947

Don't do all the lowering stuff for 2-wide build_vector's. Also, minor optimization for shuffle of undef.

llvm-svn: 27946

Fix a performance regression. Use {p}shuf* when there are only two distinct elements in a build_vector.

llvm-svn: 27945

llvm-svn: 27944

llvm-svn: 27943

llvm-svn: 27942

This allows Prolangs-C++/city and probably a bunch of other stuff to work
well with the new front-end

llvm-svn: 27941

movd always clear the top 96 bits and movss does so when it's loading the
value from memory.
The net result is codegen for 4-wide shuffles is much improved. It is near
optimal if one or more elements is a zero. e.g.

__m128i test(int a, int b) {
  return _mm_set_epi32(0, 0, b, a);
}

compiles to

_test:
	movd 8(%esp), %xmm1
	movd 4(%esp), %xmm0
	punpckldq %xmm1, %xmm0
	ret

compare to gcc:

_test:
	subl	$12, %esp
	movd	20(%esp), %xmm0
	movd	16(%esp), %xmm1
	punpckldq	%xmm0, %xmm1
	movq	%xmm1, %xmm0
	movhps	LC0, %xmm0
	addl	$12, %esp
	ret

or icc:

_test:
        movd      4(%esp), %xmm0                                #5.10
        movd      8(%esp), %xmm3                                #5.10
        xorl      %eax, %eax                                    #5.10
        movd      %eax, %xmm1                                   #5.10
        punpckldq %xmm1, %xmm0                                  #5.10
        movd      %eax, %xmm2                                   #5.10
        punpckldq %xmm2, %xmm3                                  #5.10
        punpckldq %xmm3, %xmm0                                  #5.10
        ret                                                     #5.10

There are still room for improvement, for example the FP variant of the above example:

__m128 test(float a, float b) {
  return _mm_set_ps(0.0, 0.0, b, a);
}

_test:
	movss 8(%esp), %xmm1
	movss 4(%esp), %xmm0
	unpcklps %xmm1, %xmm0
	xorps %xmm1, %xmm1
	movlhps %xmm1, %xmm0
	ret

The xorps and movlhps are unnecessary. This will require post legalizer optimization to handle.

llvm-svn: 27939

llvm-svn: 27938

llvm-svn: 27937

llvm-svn: 27936

llvm-svn: 27935

llvm-svn: 27934

miscompares).  Switch RISC targets to use the list-td scheduler, which isn't.

llvm-svn: 27933

llvm-svn: 27932

llvm-svn: 27931

llvm-svn: 27930

some versions of nm don't recognize it (its a gnu option).

llvm-svn: 27928

llvm-svn: 27927

llvm-svn: 27926

llvm-svn: 27925

llvm-svn: 27924

scalar value.

e.g.
        _mm_set_epi32(0, a, 0, 0);
==>
	movd 4(%esp), %xmm0
	pshufd $69, %xmm0, %xmm0

        _mm_set_epi8(0, 0, 0, 0, 0, a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
==>
	movzbw 4(%esp), %ax
	movzwl %ax, %eax
	pxor %xmm0, %xmm0
	pinsrw $5, %eax, %xmm0

llvm-svn: 27923

llvm-gcc4 boostrap.  Whenever a node is deleted by the dag combiner, it
*must* be returned by the visit function, or the dag combiner will not
know that the node has been processed (and will, e.g., send it to the
target dag combine xforms).

llvm-svn: 27922

any of the fancy graphs or other output. Just produce the flat, makefile
style output on stdout.

llvm-svn: 27921

llvm-svn: 27920

llvm-svn: 27919

llvm-svn: 27918

llvm-svn: 27917

llvm-svn: 27916

1. If Perl is not available, don't run Perl dependent targets.
2. Check in FinalLibDeps.txt for build environments that can't build it
   because there's no Perl processor.
3. Ensure that FinalLibDeps.txt depends on LibDeps.txt so it is
   automatically regenerated.
4. Support objdir != srcdir building.

llvm-svn: 27915

llvm-svn: 27914

llvm-svn: 27913

llvm-svn: 27912

llvm-svn: 27911

llvm-svn: 27910

llvm-svn: 27909

llvm-svn: 27908

llvm-svn: 27907

llvm-svn: 27906