[Openmp-dev] Phoronix numbers for clang-omp compiler
Alexey Bataev
a.bataev at hotmail.com
Thu Jun 5 05:43:40 PDT 2014
Jack,
Yes, this is true, but I don't think that it is a good idea to compare
performance between code compiled with -O2 and compiled with -O0.
Best regards,
Alexey Bataev
=============
Software Engineer
Intel Compiler Team
5 Июнь 2014 г. 16:06:32, Jack Howarth писал:
> Alexey,
> This wouldn't be the first time that Phoronix has gotten sloppy
> with using a common set of optimization flags in their gcc vs clang
> benchmarks. Although, it is getting harder to make direct comparisons.
> Clang now autovectorizes at -O2 while, as you can see from the
> my prior posting of the assembly from-fverbose-asm -O2, FSF gcc 4.9.0
> doesn't.
> Jack
>
>
>
> On Wed, Jun 4, 2014 at 10:32 PM, Alexey Bataev <a.bataev at hotmail.com
> <mailto:a.bataev at hotmail.com>> wrote:
>
> Jack,
> Actually everything is quite simple. Config files for Phoronix
> test suites are using gcc by default and -O2 is provided by
> default in this config files. I think they just compiled these
> tests by gcc with the default config (which already includes -O2)
> while for clang they had to specify some custom options (like
> "-fopenmp -lgomp", though the second one is not needed), but
> forget to add any optimization options.
>
> Best regards,
> Alexey Bataev
> =============
>
> Software Engineer
> Intel Compiler Team
>
> 04.06.2014 22:19, openmp-dev-request at cs.uiuc.edu
> <mailto:openmp-dev-request at cs.uiuc.edu> пишет:
>
> Message: 4
> Date: Wed, 4 Jun 2014 14:19:49 -0400
> From: Jack Howarth<howarth.mailing.lists at __gmail.com
> <mailto:howarth.mailing.lists at gmail.com>>
> To: Andrey Bokhanko<andreybokhanko at gmail.__com
> <mailto:andreybokhanko at gmail.com>>
> Cc:"openmp-dev at dcs-maillist2.__engr.illinois.edu
> <mailto:openmp-dev at dcs-maillist2.engr.illinois.edu>"
> <openmp-dev at dcs-maillist2.__engr.illinois.edu
> <mailto:openmp-dev at dcs-maillist2.engr.illinois.edu>>
> Subject: Re: [Openmp-dev] Phoronix numbers for clang-omp compiler
> Message-ID:
>
> <CADtEn-__2YdnYNjg3bOcbGxJCJB87fdPyq1oAo__k4ZFoBTD33Y8Ag at mail.gmail.com
> <mailto:CADtEn-2YdnYNjg3bOcbGxJCJB87fdPyq1oAok4ZFoBTD33Y8Ag at mail.gmail.com>>
> Content-Type: text/plain; charset="utf-8"
>
>
> Andrey,
> FSF gcc is not exactly defaulting to -O2 but certainly
> is higher than
> the default optimizations on clang?.
>
>
> % touch t.cc
> % g++-fsf-4.9 -fverbose-asm t.cc -S
> % more t.s
> # GNU C++ (GCC) version 4.9.0 (x86_64-apple-darwin11.4.2)
> # compiled by GNU C version 4.9.0, GMP version 6.0.0,
> MPFR version
> 3.1.2, MPC version 1.0.2
> # GGC heuristics: --param ggc-min-expand=100 --param
> ggc-min-heapsize=131072
> # options passed: -D__DYNAMIC__ t.cc -fPIC
> -mmacosx-version-min=10.7.4
> # -mtune=core2 -fverbose-asm
> # options enabled: -Wnonportable-cfstrings -fPIC
> # -faggressive-loop-__optimizations -fasynchronous-unwind-tables
> # -fauto-inc-dec -fcommon -fdelete-null-pointer-checks
> -fearly-inlining
> # -feliminate-unused-debug-types -fexceptions -ffunction-cse
> -fgcse-lm
> # -fgnu-unique -fident -finline-atomics -fira-hoist-pressure
> # -fira-share-save-slots -fira-share-spill-slots -fivopts
> # -fkeep-static-consts -fleading-underscore -fmath-errno
> # -fmerge-debug-strings -fnext-runtime -fobjc-abi-version=
> -fpeephole
> # -fprefetch-loop-arrays -freg-struct-return
> # -fsched-critical-path-__heuristic -fsched-dep-count-heuristic
> # -fsched-group-heuristic -fsched-interblock
> -fsched-last-insn-heuristic
> # -fsched-rank-heuristic -fsched-spec -fsched-spec-insn-heuristic
> # -fsched-stalled-insns-dep -fshow-column -fsigned-zeros
> # -fsplit-ivs-in-unroller -fstrict-volatile-bitfields
> -fsync-libcalls
> # -ftrapping-math -ftree-coalesce-vars -ftree-cselim
> -ftree-forwprop
> # -ftree-loop-if-convert -ftree-loop-im -ftree-loop-ivcanon
> # -ftree-loop-optimize -ftree-parallelize-loops= -ftree-phiprop
> # -ftree-reassoc -ftree-scev-cprop -funit-at-a-time
> -funwind-tables
> # -fverbose-asm -fzero-initialized-in-bss -gstrict-dwarf
> # -m128bit-long-double -m64 -m80387 -malign-stringops -matt-stubs
> # -mconstant-cfstrings -mfancy-math-387 -mfp-ret-in-387 -mfxsr
> -mieee-fp
> # -mlong-double-80 -mmmx -mno-sse4 -mpush-args -mred-zone
> -msse -msse2
> # -msse3
>
> .constructor
> .destructor
> .align 1
> .subsections_via_symbols
>
> % g++-fsf-4.9 -fverbose-asm -O2 t.cc -S
> % more t.s
> # GNU C++ (GCC) version 4.9.0 (x86_64-apple-darwin11.4.2)
> # compiled by GNU C version 4.9.0, GMP version 6.0.0,
> MPFR version
> 3.1.2, MPC version 1.0.2
> # GGC heuristics: --param ggc-min-expand=100 --param
> ggc-min-heapsize=131072
> # options passed: -D__DYNAMIC__ t.cc -fPIC
> -mmacosx-version-min=10.7.4
> # -mtune=core2 -O2 -fverbose-asm
> # options enabled: -Wnonportable-cfstrings -fPIC
> # -faggressive-loop-__optimizations -fasynchronous-unwind-tables
> # -fauto-inc-dec -fbranch-count-reg -fcaller-saves
> # -fcombine-stack-adjustments -fcommon -fcompare-elim
> -fcprop-registers
> # -fcrossjumping -fcse-follow-jumps -fdefer-pop
> # -fdelete-null-pointer-checks -fdevirtualize
> -fdevirtualize-speculatively
> # -fearly-inlining -feliminate-unused-debug-types -fexceptions
> # -fexpensive-optimizations -fforward-propagate -ffunction-cse
> -fgcse
> # -fgcse-lm -fgnu-unique -fguess-branch-probability
> -fhoist-adjacent-loads
> # -fident -fif-conversion -fif-conversion2 -findirect-inlining
> -finline
> # -finline-atomics -finline-functions-called-once
> -finline-small-functions
> # -fipa-cp -fipa-profile -fipa-pure-const -fipa-reference
> -fipa-sra
> # -fira-hoist-pressure -fira-share-save-slots
> -fira-share-spill-slots
> # -fisolate-erroneous-paths-__dereference -fivopts
> -fkeep-static-consts
> # -fleading-underscore -fmath-errno -fmerge-constants
> -fmerge-debug-strings
> # -fmove-loop-invariants -fnext-runtime -fobjc-abi-version=
> # -fomit-frame-pointer -foptimize-sibling-calls -foptimize-strlen
> # -fpartial-inlining -fpeephole -fpeephole2
> -fprefetch-loop-arrays -free
> # -freg-struct-return -freorder-blocks
> -freorder-blocks-and-partition
> # -freorder-functions -frerun-cse-after-loop
> # -fsched-critical-path-__heuristic -fsched-dep-count-heuristic
> # -fsched-group-heuristic -fsched-interblock
> -fsched-last-insn-heuristic
> # -fsched-rank-heuristic -fsched-spec -fsched-spec-insn-heuristic
> # -fsched-stalled-insns-dep -fschedule-insns2 -fshow-column
> -fshrink-wrap
> # -fsigned-zeros -fsplit-ivs-in-unroller -fsplit-wide-types
> # -fstrict-aliasing -fstrict-overflow -fstrict-volatile-bitfields
> # -fsync-libcalls -fthread-jumps -ftoplevel-reorder
> -ftrapping-math
> # -ftree-bit-ccp -ftree-builtin-call-dce -ftree-ccp -ftree-ch
> # -ftree-coalesce-vars -ftree-copy-prop -ftree-copyrename
> -ftree-cselim
> # -ftree-dce -ftree-dominator-opts -ftree-dse -ftree-forwprop
> -ftree-fre
> # -ftree-loop-if-convert -ftree-loop-im -ftree-loop-ivcanon
> # -ftree-loop-optimize -ftree-parallelize-loops=
> -ftree-phiprop -ftree-pre
> # -ftree-pta -ftree-reassoc -ftree-scev-cprop -ftree-sink
> -ftree-slsr
> # -ftree-sra -ftree-switch-conversion -ftree-tail-merge -ftree-ter
> # -ftree-vrp -funit-at-a-time -funwind-tables -fverbose-asm
> # -fzero-initialized-in-bss -gstrict-dwarf
> -m128bit-long-double -m64
> # -m80387 -malign-stringops -matt-stubs -mconstant-cfstrings
> # -mfancy-math-387 -mfp-ret-in-387 -mfxsr -mieee-fp
> -mlong-double-80 -mmmx
> # -mno-sse4 -mpush-args -mred-zone -msse -msse2 -msse3
> -mvzeroupper
>
> .constructor
> .destructor
> .align 1
> .subsections_via_symbols
>
> You might consider filing an enhancement request for clang 3.5
> to have the
> default behavior without optimization flags bumped up to -O1.
> Jack
>
>
>
More information about the Openmp-dev
mailing list