CK Browser

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

Scenario UID	8289e0cf24346aa7 (experiment.tune.compiler.flags.gcc.e)
Data UID	dcafd9e0123ff9fe

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:dcafd9e0123ff9fe

Compiler	GCC 4.9
CPU	MT6750
Objective	min

Improvement key IK1	Main kernel execution time speedup [min]
Improvement key IK2	Code 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

Replay

d72db9147bcb5b9f

1.10

1.00

-O3 -fbranch-target-load-optimize2 -fno-compare-elim -fno-early-inlining -fno-ipa-sra -fno-gcse-sm -fno-isolate-erroneous-paths-dereference -fno-modulo-sched-allow-regmoves -fsched-interblock -ftrapping-math -fpredictive-commoning -freciprocal-math -fno-schedule-insns -fsel-sched-pipelining -fno-tree-dce -ftree-loop-im -fno-tree-loop-vectorize -ftree-partial-pre -fno-tree-slsr -fno-tree-tail-merge -fsched-stalled-insns-dep=0 --param max-inline-insns-single=363 --param max-inline-insns-recursive=0 --param max-inline-recursive-depth=15 --param max-inline-recursive-depth-auto=2 --param partial-inlining-entry-probability=119 --param max-delay-slot-insn-search=138 --param max-modulo-backtrack-attempts=18 --param early-inlining-insns=17 --param builtin-expect-probability=67 --param tracer-min-branch-probability-feedback=63 --param omega-max-keys=669 --param max-sched-extend-regions-iters=0 --param selsched-max-lookahead=69 --param simultaneous-prefetches=3 --param graphite-max-bbs-per-function=176 --param ipa-cp-loop-hint-bonus=14 --param max-stores-to-sink=2 --param asan-globals=0

-O3

milepost-codelet-mibench-consumer-tiffdither-src-tif-fax3-codelet-8-1

default

VIVO 1714

Android 7.0

[ 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