[llvm-testresults] pollyperf-O3-polly-detect__clang_DEV__x86_64 test results

llvm-testresults at cs.uiuc.edu llvm-testresults at cs.uiuc.edu
Tue Feb 18 11:17:44 PST 2014


http://llvm.org/perf/db_default/v4/nts/22407?compare_to=22396&baseline=19899
Nickname: pollyperf-O3-polly-detect__clang_DEV__x86_64:35

Comparing:
     Run: 22407, Order: 201573, Start Time: 2014-02-18 14:35:12, End Time: 2014-02-18 19:23:09
      To: 22396, Order: 201555, Start Time: 2014-02-18 09:44:07, End Time: 2014-02-18 14:31:33
Baseline: 19899, Order: 198654, Start Time: 2014-01-07 01:22:04, End Time: 2014-01-07 06:18:02

===============
Tests Summary
===============

Performance Regressions: 19 (69 on baseline)
Performance Improvements: 0 (17 on baseline)
Unchanged Tests: 1091 (1024 on baseline)
Total Tests: 1110

===========================
Run-Over-Run Changes Detail
===========================

Performance Regressions - Compile Time
--------------------------------------
  SingleSource/Regression/C/2003-10-12-GlobalVarInitializers: 300.00% (0.0040 => 0.0160, std.dev.: 0.0039)
  SingleSource/Regression/C/badidx: 133.33% (0.0120 => 0.0280, std.dev.: 0.0045)
  SingleSource/Regression/C/sumarray: 60.00% (0.0200 => 0.0320, std.dev.: 0.0045)
  MultiSource/Benchmarks/MiBench/automotive-basicmath/automotive-basicmath: 17.50% (0.1600 => 0.1880, std.dev.: 0.0078)
  SingleSource/Benchmarks/Polybench/linear-algebra/kernels/bicg/bicg: 15.00% (0.0800 => 0.0920, std.dev.: 0.0033)
  SingleSource/Benchmarks/Polybench/linear-algebra/kernels/syrk/syrk: 15.00% (0.0800 => 0.0920, std.dev.: 0.0037)
  MultiSource/Benchmarks/Olden/health/health: 11.90% (0.1680 => 0.1880, std.dev.: 0.0060)
  SingleSource/Benchmarks/Shootout-C++/hello: 10.20% (0.1960 => 0.2160, std.dev.: 0.0041)
  SingleSource/Benchmarks/Polybench/medley/reg_detect/reg_detect: 8.33% (0.1440 => 0.1560, std.dev.: 0.0026)
  SingleSource/Benchmarks/Misc-C++/oopack_v1p8: 8.11% (0.1480 => 0.1600, std.dev.: 0.0037)
  SingleSource/Benchmarks/Shootout-C++/strcat: 5.17% (0.2320 => 0.2440, std.dev.: 0.0044)
  MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt: 3.24% (1.2361 => 1.2761, std.dev.: 0.0057)
  MultiSource/Applications/hexxagon/hexxagon: 3.20% (1.1240 => 1.1600, std.dev.: 0.0115)
  MultiSource/Benchmarks/TSVC/Reductions-dbl/Reductions-dbl: 2.41% (1.3281 => 1.3601, std.dev.: 0.0057)
  MultiSource/Benchmarks/TSVC/Equivalencing-dbl/Equivalencing-dbl: 1.61% (1.2441 => 1.2641, std.dev.: 0.0076)
  MultiSource/Applications/d/make_dparser: 1.60% (4.0001 => 4.0641, std.dev.: 0.0216)
  MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl: 1.56% (1.2801 => 1.3001, std.dev.: 0.0072)
  MultiSource/Benchmarks/TSVC/GlobalDataFlow-flt/GlobalDataFlow-flt: 1.54% (1.3001 => 1.3201, std.dev.: 0.0073)
  SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding: 1.33% (3.0002 => 3.0402, std.dev.: 0.0078)

================================
Run-Over-Baseline Changes Detail
================================

Performance Regressions - Compile Time
--------------------------------------
  SingleSource/Regression/C/ConstructorDestructorAttributes: 300.00% (0.0040 => 0.0160, std.dev.: 0.0040)
  SingleSource/UnitTests/2003-07-10-SignConversions: 300.00% (0.0040 => 0.0160, std.dev.: 0.0033)
  SingleSource/Benchmarks/Polybench/linear-algebra/kernels/bicg/bicg: 21.05% (0.0760 => 0.0920, std.dev.: 0.0033)
  SingleSource/Benchmarks/Polybench/linear-algebra/kernels/syrk/syrk: 21.05% (0.0760 => 0.0920, std.dev.: 0.0037)
  SingleSource/Benchmarks/McGill/chomp: 18.75% (0.1920 => 0.2280, std.dev.: 0.0075)
  SingleSource/Benchmarks/Polybench/stencils/fdtd-2d/fdtd-2d: 14.81% (0.1080 => 0.1240, std.dev.: 0.0033)
  SingleSource/Benchmarks/Polybench/linear-algebra/kernels/gemver/gemver: 12.50% (0.0960 => 0.1080, std.dev.: 0.0041)
  MultiSource/Benchmarks/TSVC/NodeSplitting-flt/NodeSplitting-flt: 8.50% (1.1761 => 1.2761, std.dev.: 0.0057)
  SingleSource/Benchmarks/Polybench/medley/reg_detect/reg_detect: 8.33% (0.1440 => 0.1560, std.dev.: 0.0026)
  MultiSource/Benchmarks/TSVC/LoopRerolling-dbl/LoopRerolling-dbl: 8.30% (1.1561 => 1.2521, std.dev.: 0.0095)
  MultiSource/Benchmarks/TSVC/Packing-dbl/Packing-dbl: 8.13% (1.1321 => 1.2241, std.dev.: 0.0085)
  MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt: 7.48% (1.1761 => 1.2641, std.dev.: 0.0108)
  MultiSource/Benchmarks/TSVC/GlobalDataFlow-flt/GlobalDataFlow-flt: 7.14% (1.2321 => 1.3201, std.dev.: 0.0073)
  MultiSource/Benchmarks/TSVC/Expansion-flt/Expansion-flt: 7.05% (1.2481 => 1.3361, std.dev.: 0.0070)
  MultiSource/Benchmarks/TSVC/Recurrences-flt/Recurrences-flt: 6.94% (1.1521 => 1.2321, std.dev.: 0.0078)
  MultiSource/Benchmarks/TSVC/IndirectAddressing-dbl/IndirectAddressing-dbl: 6.83% (1.1721 => 1.2521, std.dev.: 0.0130)
  MultiSource/Benchmarks/TSVC/LoopRerolling-flt/LoopRerolling-flt: 6.83% (1.1721 => 1.2521, std.dev.: 0.0097)
  MultiSource/Benchmarks/TSVC/Equivalencing-dbl/Equivalencing-dbl: 6.76% (1.1841 => 1.2641, std.dev.: 0.0076)
  MultiSource/Benchmarks/TSVC/Expansion-dbl/Expansion-dbl: 6.41% (1.2481 => 1.3281, std.dev.: 0.0073)
  MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt: 6.34% (1.1361 => 1.2081, std.dev.: 0.0131)
  MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl: 6.29% (1.1441 => 1.2161, std.dev.: 0.0123)
  MultiSource/Benchmarks/TSVC/ControlFlow-flt/ControlFlow-flt: 6.14% (1.3681 => 1.4521, std.dev.: 0.0095)
  MultiSource/Benchmarks/TSVC/Symbolics-dbl/Symbolics-dbl: 6.12% (1.1761 => 1.2481, std.dev.: 0.0115)
  MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl: 6.08% (1.1841 => 1.2561, std.dev.: 0.0151)
  MultiSource/Benchmarks/TSVC/IndirectAddressing-flt/IndirectAddressing-flt: 6.06% (1.1881 => 1.2601, std.dev.: 0.0115)
  MultiSource/Benchmarks/TSVC/Searching-dbl/Searching-dbl: 5.99% (1.1361 => 1.2041, std.dev.: 0.0075)
  MultiSource/Benchmarks/TSVC/StatementReordering-dbl/StatementReordering-dbl: 5.96% (1.1401 => 1.2081, std.dev.: 0.0131)
  MultiSource/Benchmarks/TSVC/Packing-flt/Packing-flt: 5.94% (1.1441 => 1.2121, std.dev.: 0.0123)
  MultiSource/Benchmarks/TSVC/Reductions-dbl/Reductions-dbl: 5.92% (1.2841 => 1.3601, std.dev.: 0.0057)
  MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl: 5.86% (1.2281 => 1.3001, std.dev.: 0.0072)
  MultiSource/Benchmarks/TSVC/GlobalDataFlow-dbl/GlobalDataFlow-dbl: 5.84% (1.2321 => 1.3041, std.dev.: 0.0125)
  MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt: 5.75% (1.2521 => 1.3241, std.dev.: 0.0067)
  MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt: 5.67% (1.2001 => 1.2681, std.dev.: 0.0145)
  MultiSource/Benchmarks/TSVC/LinearDependence-flt/LinearDependence-flt: 5.57% (1.2921 => 1.3641, std.dev.: 0.0091)
  MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt: 5.52% (1.2321 => 1.3001, std.dev.: 0.0109)
  MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl: 4.93% (1.2161 => 1.2761, std.dev.: 0.0139)
  MultiSource/Benchmarks/TSVC/LinearDependence-dbl/LinearDependence-dbl: 4.92% (1.3001 => 1.3641, std.dev.: 0.0128)
  MultiSource/Benchmarks/TSVC/StatementReordering-flt/StatementReordering-flt: 4.83% (1.1601 => 1.2161, std.dev.: 0.0136)
  MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl: 4.79% (1.2521 => 1.3121, std.dev.: 0.0138)
  MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt: 4.66% (1.2881 => 1.3481, std.dev.: 0.0125)
  MultiSource/Benchmarks/TSVC/Equivalencing-flt/Equivalencing-flt: 4.33% (1.2001 => 1.2521, std.dev.: 0.0107)
  MultiSource/Benchmarks/TSVC/LoopRestructuring-dbl/LoopRestructuring-dbl: 4.22% (1.2321 => 1.2841, std.dev.: 0.0173)
  MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael: 4.12% (0.6800 => 0.7080, std.dev.: 0.0105)
  MultiSource/Benchmarks/TSVC/LoopRestructuring-flt/LoopRestructuring-flt: 3.87% (1.2401 => 1.2881, std.dev.: 0.0137)
  SingleSource/Benchmarks/Linpack/linpack-pc: 3.85% (0.3120 => 0.3240, std.dev.: 0.0036)
  MultiSource/Benchmarks/TSVC/ControlFlow-dbl/ControlFlow-dbl: 3.47% (1.3841 => 1.4321, std.dev.: 0.0122)
  MultiSource/Applications/sqlite3/sqlite3: 1.73% (24.7575 => 25.1855, std.dev.: 0.0334)
  MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000: 1.59% (9.5802 => 9.7322, std.dev.: 0.0532)
  MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4: 1.36% (29.3298 => 29.7299, std.dev.: 0.0481)
  MultiSource/Benchmarks/PAQ8p/paq8p: 1.32% (2.7282 => 2.7642, std.dev.: 0.0120)

Performance Regressions - Execution Time
----------------------------------------
  SingleSource/Benchmarks/Shootout/sieve: 157.80% (6.6644 => 17.1811, std.dev.: 0.0028)
  MultiSource/Benchmarks/McCat/01-qbsort/qbsort: 25.00% (0.0640 => 0.0800, std.dev.: 0.0012)
  MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000: 8.64% (3.9842 => 4.3283, std.dev.: 0.0144)
  MultiSource/Benchmarks/Olden/perimeter/perimeter: 8.00% (0.3000 => 0.3240, std.dev.: 0.0066)
  MultiSource/Benchmarks/Ptrdist/bc/bc: 5.41% (0.5920 => 0.6240, std.dev.: 0.0085)
  MultiSource/Benchmarks/Ptrdist/yacr2/yacr2: 5.31% (0.8281 => 0.8721, std.dev.: 0.0043)
  MultiSource/Applications/sqlite3/sqlite3: 4.34% (4.0563 => 4.2323, std.dev.: 0.0265)
  SingleSource/Benchmarks/Dhrystone/fldry: 4.00% (0.6000 => 0.6240, std.dev.: 0.0036)
  MultiSource/Benchmarks/MallocBench/cfrac/cfrac: 3.25% (1.3521 => 1.3961, std.dev.: 0.0050)
  SingleSource/Benchmarks/BenchmarkGame/Large/fasta: 3.24% (0.9881 => 1.0201, std.dev.: 0.0069)
  MultiSource/Benchmarks/Olden/bisort/bisort: 2.75% (0.7280 => 0.7480, std.dev.: 0.0045)
  SingleSource/Benchmarks/BenchmarkGame/fannkuch: 2.60% (3.2362 => 3.3202, std.dev.: 0.0025)
  MultiSource/Benchmarks/Olden/power/power: 2.35% (1.3601 => 1.3921, std.dev.: 0.0041)
  MultiSource/Benchmarks/Ptrdist/ft/ft: 1.50% (1.0681 => 1.0841, std.dev.: 0.0031)
  SingleSource/Benchmarks/Misc/oourafft: 1.46% (7.3965 => 7.5045, std.dev.: 0.0122)
  MultiSource/Applications/JM/lencod/lencod: 1.38% (8.1245 => 8.2365, std.dev.: 0.0146)
  MultiSource/Applications/aha/aha: 1.25% (2.8802 => 2.9162, std.dev.: 0.0097)
  MultiSource/Applications/SIBsim4/SIBsim4: 1.23% (4.2403 => 4.2923, std.dev.: 0.0078)
  MultiSource/Benchmarks/TSVC/ControlFlow-dbl/ControlFlow-dbl: 1.05% (4.5563 => 4.6043, std.dev.: 0.0040)

Performance Improvements - Compile Time
---------------------------------------
  SingleSource/UnitTests/2009-12-07-StructReturn: -80.00% (0.0200 => 0.0040, std.dev.: 0.0051)
  MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2: -8.54% (0.3280 => 0.3000, std.dev.: 0.0102)
  MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm: -3.93% (1.5280 => 1.4680, std.dev.: 0.0193)
  MultiSource/Benchmarks/nbench/nbench: -2.67% (1.3521 => 1.3160, std.dev.: 0.0114)
  MultiSource/Applications/ClamAV/clamscan: -1.91% (19.2243 => 18.8563, std.dev.: 0.0644)
  MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset: -1.80% (16.7083 => 16.4083, std.dev.: 0.0505)
  MultiSource/Applications/SPASS/SPASS: -1.30% (18.7966 => 18.5524, std.dev.: 0.0643)
  MultiSource/Benchmarks/Bullet/bullet: -1.12% (39.0726 => 38.6366, std.dev.: 0.0624)

Performance Improvements - Execution Time
-----------------------------------------
  SingleSource/Benchmarks/Linpack/linpack-pc: -15.06% (7.8605 => 6.6764, std.dev.: 0.0070)
  MultiSource/Applications/sgefa/sgefa: -13.25% (0.6040 => 0.5240, std.dev.: 0.0032)
  SingleSource/UnitTests/Vectorizer/gcc-loops: -6.75% (5.2763 => 4.9203, std.dev.: 0.0624)
  MultiSource/Applications/siod/siod: -4.69% (2.9842 => 2.8442, std.dev.: 0.0170)
  MultiSource/Benchmarks/TSVC/Equivalencing-flt/Equivalencing-flt: -4.08% (2.0601 => 1.9761, std.dev.: 0.0030)
  MultiSource/Benchmarks/TSVC/LinearDependence-flt/LinearDependence-flt: -1.95% (4.5123 => 4.4243, std.dev.: 0.0022)
  MultiSource/Benchmarks/BitBench/five11/five11: -1.37% (2.3401 => 2.3081, std.dev.: 0.0032)
  MultiSource/Applications/lambda-0_1_3/lambda: -1.26% (5.0963 => 5.0323, std.dev.: 0.0146)
  MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl: -1.04% (3.8562 => 3.8162, std.dev.: 0.0137)

Report Time: 1.88s
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-testresults/attachments/20140218/14e39153/attachment.html>


More information about the llvm-testresults mailing list