[LLVMbugs] [Bug 9169] New: inlined memcpy from/to global address inefficient

[bugzilla-daemon at llvm.org]

http://llvm.org/bugs/show_bug.cgi?id=9169

           Summary: inlined memcpy from/to global address inefficient
           Product: libraries
           Version: trunk
          Platform: PC
        OS/Version: Linux
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Backend: SystemZ
        AssignedTo: unassignedbugs at nondot.org
        ReportedBy: bagel99 at gmail.com
                CC: llvmbugs at cs.uiuc.edu


Created an attachment (id=6128)
 --> (http://llvm.org/bugs/attachment.cgi?id=6128)
test case

The code produced from the test case could be a lot better with
base+displacement:

ff:
    larl    %r1, aa+24
    lg    %r1, 0(%r1)
    larl    %r2, bb+24
    stg    %r1, 0(%r2)
    larl    %r1, aa+16
    lg    %r1, 0(%r1)
    larl    %r2, bb+16
    stg    %r1, 0(%r2)
    larl    %r1, aa+8
    lg    %r1, 0(%r1)
    larl    %r2, bb+8
    stg    %r1, 0(%r2)
    larl    %r1, aa
    lg    %r1, 0(%r1)
    larl    %r2, bb
    stg    %r1, 0(%r2)
    br    %r14

-- 
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.