This issue tracker has been migrated to GitHub, and is currently read-only.
For more information, see the GitHub FAQs in the Python's Developer Guide.

Author ajaksu2
Recipients ajaksu2, alexandre.vassalotti, bboissin, blaisorblade, christian.heimes, djc, lemburg, pitrou, rhettinger, skip.montanaro, theatrus
Date 2009-01-04.02:00:49
SpamBayes Score 0.0001569462
Marked as misclassified No
Message-id <1231034451.72.0.0523187640754.issue4753@psf.upfronthosting.co.za>
In-reply-to
Content
IIUC, this is what gcc 4.2.4 generates on a Celeron M for the code
Alexandre posted:
        movl    -272(%ebp), %eax
        movl    8(%ebp), %edx
        subl    -228(%ebp), %eax
        movl    %eax, 60(%edx)
        movl    -272(%ebp), %ecx
        movzbl  (%ecx), %eax
-
        addl    $1, %ecx
        movl    %ecx, -272(%ebp)
        movl    opcode_targets.9311(,%eax,4), %ecx
        movl    %eax, %ebx
-
        jmp     *%ecx


And this is what ICC 11.0 generates for (what I think is) the same bit:
        movl      360(%esp), %ecx
        movl      %esi, %edi
        subl      304(%esp), %edi
        movl      %edi, 60(%ecx)
        movzbl    (%esi), %ecx 
-
        movl      opcode_targets.2239.0.34(,%ecx,4), %eax
        incl      %esi
-
        jmp       ..B12.137     # Prob 100%
        # ..B12.137: jmp       *%eax  


Does this mean that icc handles register starvation better here?

FWIW, on this CPU, compiling with icc gives a 20% speed boost in pybench
regardless of this patch.
History
Date User Action Args
2009-01-04 02:00:52ajaksu2setrecipients: + ajaksu2, lemburg, skip.montanaro, rhettinger, pitrou, christian.heimes, alexandre.vassalotti, djc, bboissin, blaisorblade, theatrus
2009-01-04 02:00:51ajaksu2setmessageid: <1231034451.72.0.0523187640754.issue4753@psf.upfronthosting.co.za>
2009-01-04 02:00:50ajaksu2linkissue4753 messages
2009-01-04 02:00:49ajaksu2create