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This page is outdated!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 LLVM compiler flags (minimize execution time))

Scenario UID2aaed4c520956635 (experiment.tune.compiler.flags.llvm.e)
Data UID9cde58e04ab0abf3
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 2aaed4c520956635:9cde58e04ab0abf3
CompilerLLVM 3.8.0-2ubuntu4
CPUIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz
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 2768639eef545abb 5.43 1.49 -O3 -mno-implicit-float -O3 3 1 13591 13619 milepost-codelet-mibench-telecomm-gsm-src-rpe-codelet-4-1 default 3300.618, 3380.185, 3305.716, 3359.924 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S2 b41159e9a77afc82 3.23 0.99 -O3 -mrelax-all -mstackrealign -O3 2 5 13411 13445 milepost-codelet-mibench-security-pgp-e-src-mpilib-codelet-4-1 default 3224.932, 3322.576, 3205.647, 3297.663 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S3 2def555d04abeb45 1.53 1.00 -O3 -ffast-math -fslp-vectorize-aggressive -O3 4 5 13466 13499 milepost-codelet-mibench-consumer-lame-src-newmdct-codelet-10-1 default 3379.564, 3400.016, 3309.151, 3390.884 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S4 566540ae96202e85 1.42 0.99 -O3 -fno-unroll-loops -mstackrealign -O3 5 1 13464 13498 milepost-codelet-mibench-consumer-tiffdither-src-tif-fax3-codelet-8-1 default 3400.201, 3400.401, 3398.916, 3400.056 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S5 0f96676b4ca312e5 1.38 1.02 -O3 -fno-unroll-loops -O3 2 1 10974 11010 milepost-codelet-mibench-consumer-tiffmedian-src-tiffmedian-codelet-1-1 default 3400.364, 3405.783, 3398.335, 3400.16 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S6 72b4e8e818bb111c 1.38 1.02 -O3 -fslp-vectorize-aggressive -fno-unroll-loops -O3 2 2 12957 12994 milepost-codelet-mibench-consumer-tiffmedian-src-tiffmedian-codelet-1-1 default 3409.009, 3336.967, 3309.721, 3313.21 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S7 a35d03bca05d4b21 1.31 0.97 -O3 -fslp-vectorize-aggressive -mrelax-all -O3 1 3 13415 13448 milepost-codelet-mibench-security-pgp-e-src-mpilib-codelet-3-1 default 3283.581, 3394.49, 3258.331, 3314.284 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS
S8 4279ab52e89a2662 1.21 1.05 -O3 -fno-inline -fwrapv -O3 1 3 7319 7356 cbench-automotive-susan edges image-pgm-clean-gray-square-600-450-8 data.pgm 3231.702, 3269.746, 3257.279, 3335.698 4 Supermicro 0123456789 (Super Server) Ubuntu 16.04.1 LTS



[ 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