[Mono-bugs] [Bug 533079] New: Mono.Simd problems in SSE1 processor. op_Multiply returns wrong results.

bugzilla_noreply at novell.com bugzilla_noreply at novell.com
Thu Aug 20 17:36:03 EDT 2009


http://bugzilla.novell.com/show_bug.cgi?id=533079


           Summary: Mono.Simd problems in SSE1 processor. op_Multiply
                    returns wrong results.
    Classification: Mono
           Product: Mono: Runtime
           Version: 2.4.x
          Platform: x86
        OS/Version: Other
            Status: NEW
          Severity: Normal
          Priority: P5 - None
         Component: JIT
        AssignedTo: lupus at novell.com
        ReportedBy: tony_hild at yahoo.com
         QAContact: mono-bugs at lists.ximian.com
          Found By: ---


Created an attachment (id=314398)
 --> (http://bugzilla.novell.com/attachment.cgi?id=314398)
Simd vector multiplication

User-Agent:       Mozilla/5.0 (Windows; U; Windows NT 5.1; pt-BR; rv:1.9.1.1)
Gecko/20090715 Firefox/3.5.1 (.NET CLR 3.5.30729)

When SIMD optimization is enabled, the multiplication result of two vectors is
wrong.


Reproducible: Always

Steps to Reproduce:
1. Compile the attached code
2. Run with mono -O=simd
3. Run with mono -O=-simd
4. See the console output differences
Actual Results:  
<0, 0,01161598, 0, 0>
<5, 12, ?², ?
[x:9, y:9, z:9]
[x:4, y:10, z:18]

Expected Results:  
<9, 9, 9, 9>
<5, 12, 21, 32>
[x:9, y:9, z:9]
[x:4, y:10, z:18]

My processor is a Semprom 2800 + with MMX Technology, Fast FP Save/Restore (IA
MMX-2) Present and Streaming SIMD Extensions.

SimdRuntime.IsMethodAccelerated(typeof(Vector4f), "op_Addition") returns true.
SimdRuntime.IsMethodAccelerated(typeof(Vector4f), "op_Multiply") returns true.
SimdRuntime.IsMethodAccelerated(typeof(Vector4f), "Shuffle") returns false.

I run this test in Windows XP SP3 and openSUSE 11.1 on Mono 2.4.2.3.

-- 
Configure bugmail: http://bugzilla.novell.com/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the QA contact for the bug.


More information about the mono-bugs mailing list