[LLVMbugs] [Bug 14513] New: Fast-math transform pass

bugzilla-daemon at llvm.org bugzilla-daemon at llvm.org
Tue Dec 4 17:02:45 PST 2012


             Bug #: 14513
           Summary: Fast-math transform pass
           Product: libraries
           Version: 3.1
          Platform: PC
        OS/Version: All
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Scalar Optimizations
        AssignedTo: unassignedbugs at nondot.org
        ReportedBy: josh.klontz at gmail.com
                CC: llvmbugs at cs.uiuc.edu
    Classification: Unclassified

It would be nice to have a the ability to apply fast-math optimizations at the
IR level to optimize out instructions like:
%accumulate = fadd double %6, 0.000000e+00

API support in IRBuilder and/or additions to InstCombine pass seem like good

See this email chain for reference:

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.

More information about the llvm-bugs mailing list