Skip to content
  1. Dec 23, 2006
    • Reid Spencer's avatar
      For PR950: · 266e42b3
      Reid Spencer authored
      This patch removes the SetCC instructions and replaces them with the ICmp
      and FCmp instructions. The SetCondInst instruction has been removed and
      been replaced with ICmpInst and FCmpInst.
      
      llvm-svn: 32751
      266e42b3
    • Chris Lattner's avatar
      add a simple fast-path for dead allocas · f171af97
      Chris Lattner authored
      llvm-svn: 32750
      f171af97
  2. Dec 20, 2006
  3. Dec 19, 2006
  4. Dec 18, 2006
  5. Dec 15, 2006
  6. Dec 13, 2006
  7. Dec 12, 2006
  8. Dec 11, 2006
    • Chris Lattner's avatar
      trunc to integer, not to FP. · e810140c
      Chris Lattner authored
      llvm-svn: 32426
      e810140c
    • Chris Lattner's avatar
      implement promotion of unions containing two packed types of the same width. · 23f4b68f
      Chris Lattner authored
      This implements Transforms/ScalarRepl/union-packed.ll
      
      llvm-svn: 32422
      23f4b68f
    • Chris Lattner's avatar
      * Eliminate calls to CastInst::createInferredCast. · 216c3028
      Chris Lattner authored
       * 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
      216c3028
  9. Dec 08, 2006
  10. Dec 07, 2006
  11. Dec 06, 2006
  12. Dec 05, 2006
  13. Dec 04, 2006
  14. Dec 02, 2006
  15. Dec 01, 2006
  16. Nov 29, 2006
Loading