Collective Knowledge Aggregator proof-of-concept
Crowd results Raw CK browser Graphs Reports Datasets Models Home

This page is outdated! New version is available here.


Distinct solutions after online classification (auto/crowd-tune GCC compiler flags (minimize execution time))

Scenario UID8289e0cf24346aa7 (experiment.tune.compiler.flags.gcc.e)
Data UIDe0d4443cc82efef5
Discuss (optimizations to improve compilers,
semantic/data set/hardware features
to improve predictions, etc):		GitHub wiki, Google group
Download:[ All solutions in JSON ], [ Solutions' classification in JSON ]
Reproduce all (with reactions):ck replay 8289e0cf24346aa7:e0d4443cc82efef5
CompilerGCC 6.1.0
CPUIntel(R) Xeon(R) CPU X5570 @ 2.93GHz
Objectivemin
Improvement key IK1Main kernel execution time speedup [min]
Improvement key IK2Code size improvement

Improvements (<4% variation) Distinct workload for highest improvement
# Solution UID IK1 IK2 New distinct optimization choices Ref Best species Worst species Touched Iters Program CMD Dataset Dataset file CPU freq (MHz) Cores Platform OS Replay
S1 796e526dd95424cb 2.22 0.84 -O3 -fno-tree-loop-optimize -funroll-all-loops -O3 3 2 24 61 milepost-codelet-mibench-automotive-basicmath-isqrt-codelet-1-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S2 fb36b6be51a91232 2.09 0.48 -O3 -flto -O3 4 0 54 82 milepost-codelet-mibench-automotive-qsort1-src-qsort-codelet-1-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S3 4a4a58b8ed7741b3 1.55 0.37 -O3 -flto -fsched2-use-superblocks -O3 1 1 14 53 milepost-codelet-mibench-consumer-tiffmedian-src-tiffmedian-codelet-5-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S4 4b780078e4cd79cb 1.54 1.01 -O3 -fno-tree-loop-vectorize -O3 1 0 35 71 milepost-codelet-mibench-automotive-basicmath-isqrt-codelet-1-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S5 9e287364ec784cf9 1.41 1.03 -O3 -fno-merge-constants -fno-ssa-phiopt -fno-tree-pre -O3 2 3 43 75 milepost-codelet-mibench-consumer-tiffmedian-src-tiffmedian-codelet-5-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S6 a6d7f08d240f0ba7 1.41 1.00 -O3 -fno-tree-pre -O3 1 0 53 81 milepost-codelet-mibench-consumer-tiffmedian-src-tiffmedian-codelet-5-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S7 4dd28b08b502cdd6 1.41 0.98 -O3 -ftracer -O3 1 1 10 50 milepost-codelet-mibench-consumer-tiffmedian-src-tiffmedian-codelet-4-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S8 ffc38fc414fc58a0 1.40 0.79 -O3 -funroll-all-loops -O3 2 1 39 74 milepost-codelet-mibench-security-pgp-e-src-mpilib-codelet-4-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S9 4d08a2594a17bd39 1.40 0.80 -O3 -fno-tree-ch -funroll-loops -O3 2 2 52 81 milepost-codelet-mibench-security-pgp-e-src-mpilib-codelet-4-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S10 7c4e2645c47a481b 1.36 0.80 -O3 -funroll-loops --param max-unroll-times=7 -O3 1 0 19 57 milepost-codelet-mibench-consumer-tiff2rgba-src-tif-predict-codelet-4-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S11 4c9e8b1a09643972 1.17 1 -O3 -fno-ssa-phiopt -fno-tree-forwprop -O3 1 1 41 74 milepost-codelet-mibench-consumer-tiffdither-src-tiffdither-codelet-1-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2
S12 877e262ba8b64cc5 1.15 1 -O3 -fselective-scheduling2 -O3 1 2 45 76 milepost-codelet-mibench-security-pgp-e-src-mpilib-codelet-3-1 default 2933, 2933, 2933, 2933, 2933, 2933, 2933, 2933 8 Sun Microsystems REV 50 (SUN FIRE X2270) Debian 8.2



[ Participated users, platforms, OS, CPU, GPU, GPGPU, NN, NPU ] [ How to participate ] [ Motivation (PPT) (PDF) ] [ Papers 1 , 2 , 3] [ Android app ] [ Collective training set ] [ Unified AI ]
View entry in raw format

Developed by Grigori Fursin           
Implemented as a CK workflow 		                         
   
                      Hosted at