Skip to content
  1. May 25, 2009
  3. Mar 12, 2009
    • Chris Lattner's avatar
      Move 3 "(add (select cc, 0, c), x) -> (select cc, x, (add, x, c))" · 4147f08e
      Chris Lattner authored 
      related transformations out of target-specific dag combine into the
ARM backend.  These were added by Evan in r37685 with no testcases
and only seems to help ARM (e.g. test/CodeGen/ARM/select_xform.ll).

Add some simple X86-specific (for now) DAG combines that turn things
like cond ? 8 : 0  -> (zext(cond) << 3).  This happens frequently
with the recently added cp constant select optimization, but is a
very general xform.  For example, we now compile the second example
in const-select.ll to:

_test:
        movsd   LCPI2_0, %xmm0
        ucomisd 8(%esp), %xmm0
        seta    %al
        movzbl  %al, %eax
        movl    4(%esp), %ecx
        movsbl  (%ecx,%eax,4), %eax
        ret

instead of:

_test:
        movl    4(%esp), %eax
        leal    4(%eax), %ecx
        movsd   LCPI2_0, %xmm0
        ucomisd 8(%esp), %xmm0
        cmovbe  %eax, %ecx
        movsbl  (%ecx), %eax
        ret

This passes multisource and dejagnu.

llvm-svn: 66779
      4147f08e
  5. Mar 10, 2009
  7. Mar 08, 2009
  9. Feb 17, 2009
  11. Feb 16, 2009
  13. Feb 08, 2009
  15. Dec 06, 2008
  17. Nov 30, 2008
  19. Nov 11, 2008
  21. Oct 24, 2008
  23. Oct 17, 2008
  25. Aug 26, 2008
  27. Jul 17, 2008
  29. Jun 24, 2008
  31. May 06, 2008
  33. Apr 21, 2008
  35. Mar 28, 2008
  37. Mar 23, 2008
  39. Mar 19, 2008
  41. Mar 14, 2008
  43. Mar 08, 2008
  45. Mar 06, 2008
  47. Mar 02, 2008
  49. Feb 28, 2008
  51. Feb 27, 2008
  53. Feb 21, 2008
  55. Feb 18, 2008
  57. Feb 17, 2008
  59. Feb 16, 2008
  61. Feb 14, 2008
  63. Jan 11, 2008
    • Chris Lattner's avatar
      add a note, remove a done deed. · ff5998e6
      Chris Lattner authored 
      llvm-svn: 45869
      ff5998e6
    • Arnold Schwaighofer's avatar
      Improve tail call optimized call's argument lowering. Before this · 6cf72fbb
      Arnold Schwaighofer authored 
      commit all arguments where moved to the stack slot where they would
reside on a normal function call before the lowering to the tail call
stack slot. This was done to prevent arguments overwriting each other.
Now only arguments sourcing from a FORMAL_ARGUMENTS node or a
CopyFromReg node with virtual register (could also be a caller's
argument) are lowered indirectly.

 --This line, and those below, will be ignored--

M    X86/X86ISelLowering.cpp
M    X86/README.txt

llvm-svn: 45867
      6cf72fbb
  65. Jan 09, 2008
  67. Jan 07, 2008
  69. Dec 29, 2007
    • Chris Lattner's avatar
      Fold comparisons against a constant nan, and optimize ORD/UNORD · 3b6a8211
      Chris Lattner authored 
      comparisons with a constant.  This allows us to compile isnan to:

_foo:
	fcmpu cr7, f1, f1
	mfcr r2
	rlwinm r3, r2, 0, 31, 31
	blr 

instead of:

LCPI1_0:					;  float
	.space	4
_foo:
	lis r2, ha16(LCPI1_0)
	lfs f0, lo16(LCPI1_0)(r2)
	fcmpu cr7, f1, f0
	mfcr r2
	rlwinm r3, r2, 0, 31, 31
	blr 

llvm-svn: 45405
      3b6a8211