[LLVMbugs] [Bug 14866] New: AVX: Trunc of <8 x i32> to <8 x i32> is inefficient.

[bugzilla-daemon at llvm.org]

http://llvm.org/bugs/show_bug.cgi?id=14866

             Bug #: 14866
           Summary: AVX: Trunc of <8 x i32> to <8 x i32> is inefficient.
           Product: libraries
           Version: trunk
          Platform: PC
        OS/Version: All
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Backend: X86
        AssignedTo: unassignedbugs at nondot.org
        ReportedBy: nrotem at apple.com
                CC: llvmbugs at cs.uiuc.edu
    Classification: Unclassified


The following code is inefficient on corei7-avx. It should be done with two
shuffles and a blend. 

 %T0_39 = type <8 x i32>
 %T1_39 = type <8 x i16>
 define void @func39() {
   %v0 = load %T0_39* undef
   %r = trunc %T0_39 %v0 to %T1_39                                        
   store %T1_39 %r, %T1_39* undef                                         
   ret void                                                               
 }

-- 
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.