[llvm-testresults] Geryon-X86-64 nightly tester results

[Daniel Dunbar]

On Dec 15, 2009, at 6:01 PM, Chris Lattner wrote:

>
> On Dec 15, 2009, at 2:48 PM, Evan Cheng wrote:
>
>> This is a significant optimizer regression. Any ideas?
>
> I upgraded the machine to 10.5.8 yesterday.  So this is what the  
> future looks like!

That's strange, did the uname not change?

And uh, I'm dubious. Upgrading to 10.5.8 made some proper subset of  
the tests slower? Either way, seems like a bug somewhere. It would be  
interesting to have some idea which tests end up actually using the OS  
much (for example, pumping out lots of output).

  - Daniel

> -Chris
>
>>
>> Evan
>>
>> On Dec 15, 2009, at 2:11 AM, daniel_dunbar at apple.com wrote:
>>
>>> http://smooshlab.apple.com/perf.cgi/db_nt_internal/nightlytest/3790/
>>> Name:  clattner2.apple.com
>>> Nickname: Geryon-X86-64:4
>>>
>>> Run: 3790, Start Time: 2009-12-14 23:10:32, End Time: 2009-12-15  
>>> 02:10:49
>>> Comparing To: 3774, Start Time: 2009-12-13 23:10:33, End Time:  
>>> 2009-12-14 02:09:38
>>>
>>>
>>> Significant Changes in Test Results:
>>> CBE:
>>> Externals/SPEC/CINT2000/181_mcf/181_mcf: 7.13% (5.7500 => 6.1600)
>>> Externals/SPEC/CINT2006/429_mcf/429_mcf: 7.02% (3.5600 => 3.8100)
>>> MultiSource/Applications/spiff/spiff: 15.89% (3.8400 => 4.4500)
>>> MultiSource/Benchmarks/VersaBench/bmm/bmm: 5.53% (2.3500 => 2.4800)
>>> SingleSource/Benchmarks/CoyoteBench/fftbench: 5.24% (2.1000 =>  
>>> 2.2100)
>>> SingleSource/Benchmarks/McGill/chomp: 12.05% (0.8300 => 0.9300)
>>> SingleSource/Benchmarks/Misc-C++/bigfib: 5.45% (0.5500 => 0.5800)
>>> SingleSource/Benchmarks/Misc/ffbench: 6.52% (0.9200 => 0.9800)
>>> SingleSource/Benchmarks/Misc/himenobmtxpa: 13.59% (3.9000 => 4.4300)
>>> SingleSource/Benchmarks/Shootout-C++/sieve: 8.70% (2.0700 => 2.2500)
>>>
>>
>>> LLC:
>>> Externals/SPEC/CINT2000/181_mcf/181_mcf: 6.23% (5.7800 => 6.1400)
>>> Externals/SPEC/CINT2006/429_mcf/429_mcf: 6.46% (3.5600 => 3.7900)
>>> MultiSource/Benchmarks/Ptrdist/ft/ft: 7.07% (0.9900 => 1.0600)
>>> MultiSource/Benchmarks/VersaBench/bmm/bmm: 7.18% (2.0900 => 2.2400)
>>> MultiSource/Benchmarks/llubenchmark/llu: 5.75% (3.4800 => 3.6800)
>>> SingleSource/Benchmarks/CoyoteBench/fftbench: 5.77% (2.0800 =>  
>>> 2.2000)
>>> SingleSource/Benchmarks/McGill/chomp: 12.94% (0.8500 => 0.9600)
>>> SingleSource/Benchmarks/Misc/ffbench: 6.74% (0.8900 => 0.9500)
>>> SingleSource/Benchmarks/Misc/himenobmtxpa: 10.59% (2.5500 => 2.8200)
>>> SingleSource/Benchmarks/Shootout-C++/ary3: 5.93% (3.5400 => 3.7500)
>>> SingleSource/Benchmarks/Shootout-C++/sieve: 11.06% (2.3500 =>  
>>> 2.6100)
>>> SingleSource/Benchmarks/Shootout/ary3: -5.35% (3.7400 => 3.5400)
>>> LLC-BETA compile:
>>> Externals/SPEC/CINT2006/458_sjeng/458_sjeng: 7.11% (3.4755 =>  
>>> 3.7226)
>>> MultiSource/Benchmarks/Prolangs-C/cdecl/cdecl: 5.65% (0.6483 =>  
>>> 0.6849)
>>> _______________________________________________
>>> llvm-testresults mailing list
>>> llvm-testresults at cs.uiuc.edu
>>> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-testresults
>>
>