This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PING][PATCH/RFT] Fix PR middle-end/PR28690, modify swap_commutative_operands_p


On Mon, Jun 04, 2007 at 02:40:05PM -0500, Peter Bergner wrote:
> On Sun, May 06, 2007 at 01:21:16PM -0700, H. J. Lu wrote:
> > Here are what I got on Core 2 Duo with -O2 -ffast-math:
> > 
> > 2. SPEC CPU 2000 cores
> [snip]
> > 168.wupwise                      -6.56276%
> 
> Well, we found a Core 2 Duo box here and we're not seeing as big
> a degradation as you are (-3.9%), but we seem to have narrowed
> down one slowdown and created a C testcase that seems to mimic the
> slowdown.  Can you confirm that the testcase below runs slower
> for you too.  Also, we don't know the x86/x86_64 arch that well,
> so can you tell us why the code is running slower so I can attempt
> to modify the patch so it doesn't?  Thanks.
> 

With revision 125027, I got the following on Core 2 Duo 64bit:

			(r125027 + patch - r125027)/125027

400.perlbench                    0%
401.bzip2                        0.613497%
403.gcc                          0%
429.mcf                          0%
445.gobmk                        0.581395%
456.hmmer                        0%
458.sjeng                        0.571429%
462.libquantum                   -1.0582%
464.h264ref                      0%
471.omnetpp                      -0.869565%
473.astar                        0.869565%
483.xalancbmk                    0.211416%
SPECint(R)_base2006                 0.666667%

410.bwaves                       0%
416.gamess                       -1.70455%
433.milc                         0%
434.zeusmp                       -0.653595%
435.gromacs                      0.866739%
436.cactusADM                    -2.83019%
437.leslie3d                     -0.757576%
444.namd                         -0.675676%
447.dealII                       -4.28016%
450.soplex                       0%
453.povray                       0%
454.calculix                     -5.28402%
459.GemsFDTD                     0.961538%
465.tonto                        0%
470.lbm                          0.70922%
481.wrf                          0.101937%
482.sphinx3                      0%
SPECfp(R)_base2006                       -0.757576%

164.gzip                         0%
175.vpr                          -0.21645%
176.gcc                          -2.14153%
181.mcf                          -0.43692%
186.crafty                       0.141343%
197.parser                       0.285919%
252.eon                          -0.481303%
253.perlbmk                      1.71658%
254.gap                          0.0880669%
255.vortex                       -1.04854%
256.bzip2                        -1.51237%
300.twolf                        -0.991853%
SPECint_base2000                         -0.366133%

168.wupwise                      0.24948%
171.swim                         -0.796312%
172.mgrid                        0.796813%
173.applu                        0.71582%
177.mesa                         0.365497%
178.galgel                       -1.30807%
179.art                          -5.57125%
183.equake                       -0.513479%
187.facerec                      -0.0365364%
188.ammp                         -2.66921%
189.lucas                        0.107991%
191.fma3d                        -2.39833%
200.sixtrack                     -2.21675%
301.apsi                         -0.929752%
SPECfp_base2000                          -1.01523%

I think we can ignoe 179.art since it changes from run to run. Does
anyone have numbers on Opteron?


H.J.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]