[LLVMbugs] [Bug 3432] New: llvm-gcc is overly pessimistic of union alignment

[bugzilla-daemon at cs.uiuc.edu]

http://llvm.org/bugs/show_bug.cgi?id=3432

           Summary: llvm-gcc is overly pessimistic of union alignment
           Product: new-bugs
           Version: unspecified
          Platform: All
        OS/Version: All
            Status: NEW
          Severity: major
          Priority: P2
         Component: new bugs
        AssignedTo: unassignedbugs at nondot.org
        ReportedBy: evan.cheng at apple.com
                CC: llvmbugs at cs.uiuc.edu


#include <xmmintrin.h>

typedef union
{
  int i[4];
  float f[4];
  __m128 v;
} vector4_t;

__m128
swizzle (const void *a, vector4_t * b)
{
  return _mm_loadl_pi (b->v, (__m64 *) a);
}

On x86 / Mac OS X, this compiles to:

target triple = "i386-apple-darwin9.6"
        %struct.vector4_t = type { <4 x float> }

define <4 x float> @swizzle(i8* nocapture %a, %struct.vector4_t* nocapture %b)
nounwind readonly {
entry:
        %0 = getelementptr %struct.vector4_t* %b, i32 0, i32 0          ; <<4 x
float>*> [#uses=1]
        %1 = load <4 x float>* %0, align 4              ; <<4 x float>>
[#uses=1]
        %tmp.i = bitcast i8* %a to double*              ; <double*> [#uses=1]
        %tmp1.i = load double* %tmp.i           ; <double> [#uses=1]
        %2 = insertelement <2 x double> undef, double %tmp1.i, i32 0           
; <<2 x double>> [#uses=1]
        %tmp2.i = bitcast <2 x double> %2 to <4 x float>                ; <<4 x
float>> [#uses=1]
        %3 = shufflevector <4 x float> %1, <4 x float> %tmp2.i, <4 x i32> < i32
4, i32 5, i32 2, i32 3 >                ; <<4 x float>> [#uses=1]
        ret <4 x float> %3
}

Notice the alignment of the load instruction is 4. This is overly strict. We
ended up issuing a movups instead of a movaps.


-- 
Configure bugmail: http://llvm.org/bugs/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.