Difference between revisions of "Fall 2015 SPO600 Compiler Options Presentation"
Nitish Bajaj (talk | contribs) (→Topics) |
Jlaso-barros (talk | contribs) (→Topics: Added resource links) |
||
| (28 intermediate revisions by 14 users not shown) | |||
| Line 9: | Line 9: | ||
== Deadlines == | == Deadlines == | ||
| − | * Topic selection: ''' | + | * Topic selection: '''1:30 pm, Tuesday, September 22''' (End of the scheduled Tuesday class in Week 3) |
* Presentation ready: '''11:40 am, Tuesday, September 29''' (You must be prepared to present before the scheduled Tuesday class in Week 4) | * Presentation ready: '''11:40 am, Tuesday, September 29''' (You must be prepared to present before the scheduled Tuesday class in Week 4) | ||
| Line 67: | Line 67: | ||
| -fcse-follow-jumps|| || || || | | -fcse-follow-jumps|| || || || | ||
|- | |- | ||
| − | | -fcse-skip-blocks|| || || || | + | | -fcse-skip-blocks|| Joseph Jaku || || ||[http://jjakuseneca.blogspot.ca/2015/10/compiler-optimization-options.html Blog Post] |
|- | |- | ||
| − | | -fdce|| || || || | + | | -fdce|| Joseph Jaku || || ||[http://jjakuseneca.blogspot.ca/2015/10/compiler-optimization-options.html Blog Post] |
|- | |- | ||
| -fdelayed-branch|| || || || | | -fdelayed-branch|| || || || | ||
|- | |- | ||
| − | | -fdelete-null-pointer-checks|| Joel Aro || || || | + | | -fdelete-null-pointer-checks|| Joel Aro || || [https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html GCC Optimize Options] || |
|- | |- | ||
| − | | -fdevirtualize|| || || || | + | | -fdevirtualize|| Suk-Joong Han || || https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html || |
|- | |- | ||
| -fdevirtualize-speculatively|| || || || | | -fdevirtualize-speculatively|| || || || | ||
| Line 87: | Line 87: | ||
| -ffat-lto-objects|| || || || | | -ffat-lto-objects|| || || || | ||
|- | |- | ||
| − | | -ffast-math|| Miguel Dizon || || || | + | | -ffast-math|| Miguel Dizon || || https://gcc.gnu.org/wiki/FloatingPointMath || |
|- | |- | ||
| -ffinite-math-only|| || || || | | -ffinite-math-only|| || || || | ||
| Line 115: | Line 115: | ||
| -fhoist-adjacent-loads|| || || || | | -fhoist-adjacent-loads|| || || || | ||
|- | |- | ||
| − | | -fif-conversion|| | + | | -fif-conversion|| || || || |
|- | |- | ||
| -fif-conversion2|| || || || | | -fif-conversion2|| || || || | ||
| Line 121: | Line 121: | ||
| -findirect-inlining|| || || || | | -findirect-inlining|| || || || | ||
|- | |- | ||
| − | | -finline-functions|| || || || | + | | -finline-functions||Kirill Lepetinskiy|| || [https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html GCC Docs] || [http://klepetinskiy.blogspot.ca/2015/09/finline-functions.html Blog Post] |
|- | |- | ||
| -finline-functions-called-once|| || || || | | -finline-functions-called-once|| || || || | ||
| Line 127: | Line 127: | ||
| -finline-limit=n|| || || || | | -finline-limit=n|| || || || | ||
|- | |- | ||
| − | | -finline-small-functions|| || || || | + | | -finline-small-functions|| Yehoshua Ghitis|| || || |
|- | |- | ||
| -fipa-cp|| || || || | | -fipa-cp|| || || || | ||
| Line 167: | Line 167: | ||
| -flive-range-shrinkage|| || || || | | -flive-range-shrinkage|| || || || | ||
|- | |- | ||
| − | | -floop-block|| || || || | + | | -floop-block|| Dmytro Yegorov || ||[http://www.cc.gatech.edu/~bader/COURSES/UNM/ece637-Fall2003/papers/KW03.pdf -floop-block]|| [https://dyegorov.wordpress.com/2015/10/02/gcc-floop-block-and-floop-interchange/ Blog Post] |
|- | |- | ||
| − | | -floop-interchange|| || || || | + | | -floop-interchange|| Dmytro Yegorov || || [https://en.wikipedia.org/wiki/Loop_interchange -floop-interchange]|| [https://dyegorov.wordpress.com/2015/10/02/gcc-floop-block-and-floop-interchange/ Blog Post] |
|- | |- | ||
| -floop-strip-mine|| || || || | | -floop-strip-mine|| || || || | ||
| Line 195: | Line 195: | ||
| -fmodulo-sched-allow-regmoves|| || || || | | -fmodulo-sched-allow-regmoves|| || || || | ||
|- | |- | ||
| − | | -fmove-loop-invariants||Gaurav Patel || || || | + | | -fmove-loop-invariants||Gaurav Patel || ||https://en.wikipedia.org/wiki/Loop-invariant_code_motion || |
|- | |- | ||
| -fno-branch-count-reg|| || || || | | -fno-branch-count-reg|| || || || | ||
|- | |- | ||
| − | | -fno-defer-pop|| || || || | + | | -fno-defer-pop|| Andy Cooc || || || |
|- | |- | ||
| − | | -fno-function-cse|| || || || | + | | -fno-function-cse|| Andy Cooc || || || |
|- | |- | ||
| -fno-guess-branch-probability|| || || || | | -fno-guess-branch-probability|| || || || | ||
| Line 213: | Line 213: | ||
| -fno-sched-spec|| || || || | | -fno-sched-spec|| || || || | ||
|- | |- | ||
| − | | -fno-signed-zeros|| || || || | + | | -fno-signed-zeros|| Suk-Joong Han || || https://en.wikipedia.org/wiki/Signed_zero || |
|- | |- | ||
| -fno-toplevel-reorder|| || || || | | -fno-toplevel-reorder|| || || || | ||
| Line 227: | Line 227: | ||
| -fpartial-inlining|| || || || | | -fpartial-inlining|| || || || | ||
|- | |- | ||
| − | | -fpeel-loops|| || || || | + | | -fpeel-loops|| James Shin|| || || |
|- | |- | ||
| -fpredictive-commoning|| || || || | | -fpredictive-commoning|| || || || | ||
|- | |- | ||
| − | | -fprefetch-loop-arrays|| || || || | + | | -fprefetch-loop-arrays||Jayme Laso-Barros|| ||[https://gcc.gnu.org/onlinedocs/gcc-5.2.0/gcc/Optimize-Options.html GCC 5.2 Manual: Section 3.10]|| |
|- | |- | ||
| -fprofile-report|| || || || | | -fprofile-report|| || || || | ||
| Line 243: | Line 243: | ||
| -fprofile-generate=path|| || || || | | -fprofile-generate=path|| || || || | ||
|- | |- | ||
| − | | -fprofile-use|| || || || | + | | -fprofile-use||Ramanan Manokaran || || || |
|- | |- | ||
| -fprofile-use=path|| || || || | | -fprofile-use=path|| || || || | ||
| Line 257: | Line 257: | ||
| -frename-registers|| || || || | | -frename-registers|| || || || | ||
|- | |- | ||
| − | | -freorder-blocks|| || || || | + | | -freorder-blocks|| Ramanan Manokaran|| || || |
|- | |- | ||
| -freorder-blocks-and-partition|| || || || | | -freorder-blocks-and-partition|| || || || | ||
|- | |- | ||
| − | | -freorder-functions|| || || || | + | | -freorder-functions||Jayme Laso-Barros|| ||[https://gcc.gnu.org/onlinedocs/gcc-5.2.0/gcc/Optimize-Options.html GCC 5.2 Manual: Section 3.10]|| |
|- | |- | ||
| -frerun-cse-after-loop|| || || || | | -frerun-cse-after-loop|| || || || | ||
| Line 311: | Line 311: | ||
| -fsplit-ivs-in-unroller|| || || || | | -fsplit-ivs-in-unroller|| || || || | ||
|- | |- | ||
| − | | -fsplit-wide-types|| || || || | + | | -fsplit-wide-types|| Shirwa Egal || || || |
|- | |- | ||
| -fstack-protector / -fstack-protector-all / -fstack-protector-strong|| || || || | | -fstack-protector / -fstack-protector-all / -fstack-protector-strong|| || || || | ||
| Line 339: | Line 339: | ||
| -ftree-copyrename|| || || || | | -ftree-copyrename|| || || || | ||
|- | |- | ||
| − | | -ftree-dce|| Gaurav Patel || || || | + | | -ftree-dce|| Gaurav Patel || ||https://en.wikipedia.org/wiki/Dead_code_elimination|| |
|- | |- | ||
| -ftree-dominator-opts|| || || || | | -ftree-dominator-opts|| || || || | ||
|- | |- | ||
| − | | -ftree-dse|| || || || | + | | -ftree-dse|| Shirwa Egal|| || || |
|- | |- | ||
| -ftree-forwprop|| || || || | | -ftree-forwprop|| || || || | ||
| Line 351: | Line 351: | ||
| -ftree-loop-if-convert|| Donald Nguyen || || || | | -ftree-loop-if-convert|| Donald Nguyen || || || | ||
|- | |- | ||
| − | | -ftree-loop-if-convert-stores|| || || || | + | | -ftree-loop-if-convert-stores||Kirill Lepetinskiy|| || [https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html GCC Docs] [http://www.rcollins.org/p6/opcodes/CMOV.html On CMOV] ||[http://klepetinskiy.blogspot.ca/2015/09/ftree-loop-if-convert-stores.html Blog Post] |
|- | |- | ||
| -ftree-loop-im|| || || || | | -ftree-loop-im|| || || || | ||
| Line 397: | Line 397: | ||
| -funit-at-a-time|| || || || | | -funit-at-a-time|| || || || | ||
|- | |- | ||
| − | | -funroll-all-loops|| | + | | -funroll-all-loops|| Yehoshua Ghitis|| || || |
|- | |- | ||
| − | | -funroll-loops|| || || || | + | | -funroll-loops|| Joel Aro || || [https://en.wikipedia.org/wiki/Loop_unrolling Loop Unrolling] || |
|- | |- | ||
| -funsafe-loop-optimizations|| || || || | | -funsafe-loop-optimizations|| || || || | ||
|- | |- | ||
| − | | -funsafe-math-optimizations|| || || || | + | | -funsafe-math-optimizations||James Shin || || || |
|- | |- | ||
| − | | -funswitch-loops|| || || || | + | | -funswitch-loops|| Miguel Dizon || || || |
|- | |- | ||
| -fvariable-expansion-in-unroller|| || || || | | -fvariable-expansion-in-unroller|| || || || | ||
Latest revision as of 18:42, 6 October 2015
Contents
Assignment
- Select two unrelated compiler options, below, by placing your name in the "Student" column (first come, first served - one student per topic).
- During week 3, research the topics and prepare a 3- to 5-minute presentation to teach the class.
- Be prepared to teach this presentation during week 4. You may want to draw whiteboard diagrams, use presentation slides, or have a 1-page handout. Please avoid taking more than 5 minutes in total for your presentation.
Deadlines
- Topic selection: 1:30 pm, Tuesday, September 22 (End of the scheduled Tuesday class in Week 3)
- Presentation ready: 11:40 am, Tuesday, September 29 (You must be prepared to present before the scheduled Tuesday class in Week 4)
FAQ
- Q: How much detail should the presentation include?
- A: Each of these topics is pretty small and straightforward. Provide some type of resource for future reference -- a link to an existing web resource, a 1-page handout, or a blog post or wiki page about the topic. Your presentation should include:
- The Option: The compiler option as described in the gcc documentation - What it is and why it is provided.
- The Impact: Write and compile code that is impacted by this particular compiler option. Identify the characteristics that must be present in the source code in order to benefit from this compiler option (for example: double-precision math, use of arrays, pointer math). Describe the effect of the option on performance, code size, and code readability. If there are any problems or dangers with this option, identify them.
- Recommendation: Make a recommendation on when this compiler option should be used and when it should not be used.
- A: Each of these topics is pretty small and straightforward. Provide some type of resource for future reference -- a link to an existing web resource, a 1-page handout, or a blog post or wiki page about the topic. Your presentation should include:
- Q: How will this be marked?
- A: In week 4, I will ask you to write a short blog post summarizing your presentation.
- Q: Can we work with others preparing our topic?
- A: Yes. In many cases, one topic is complimentary to another topic, and it would be great if you coordinated on your presentations.
- Q: What resources should I use?
- A: Use the gcc documentation. Also, there are resources on the web as well as on this wiki (for example, see the Assembly Language category on this wiki).
- Q: Are there any classes scheduled during Week 3?
- A: No. Your professor will be at Linaro Connect. However, the classroom is reserved for our use, and you're welcome to use it to discuss your presentation ideas with classmates.
Topics
| Compiler Option | Presenter Name | (Leave blank) | Links to resources (Wiki page, handout, web resources) | Link to blog post on this topic |
|---|---|---|---|---|
| -faggressive-loop-optimizations | ||||
| -fassociative-math | Kevin Paiva | |||
| -fauto-inc-dec | ||||
| -fbranch-probabilities | ||||
| -fbranch-target-load-optimize | ||||
| -fbranch-target-load-optimize2 | ||||
| -fbtr-bb-exclusive | ||||
| -fcaller-saves | ||||
| -fcheck-data-deps | ||||
| -fcombine-stack-adjustments | ||||
| -fconserve-stack | ||||
| -fcompare-elim | Kevin Paiva | |||
| -fcprop-registers | ||||
| -fcrossjumping | ||||
| -fcse-follow-jumps | ||||
| -fcse-skip-blocks | Joseph Jaku | Blog Post | ||
| -fdce | Joseph Jaku | Blog Post | ||
| -fdelayed-branch | ||||
| -fdelete-null-pointer-checks | Joel Aro | GCC Optimize Options | ||
| -fdevirtualize | Suk-Joong Han | https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html | ||
| -fdevirtualize-speculatively | ||||
| -fdse | ||||
| -fearly-inlining | ||||
| -fipa-sra | ||||
| -ffat-lto-objects | ||||
| -ffast-math | Miguel Dizon | https://gcc.gnu.org/wiki/FloatingPointMath | ||
| -ffinite-math-only | ||||
| -ffloat-store | ||||
| -fexcess-precision=style | ||||
| -fforward-propagate | ||||
| -ffp-contract=style | ||||
| -ffunction-sections | ||||
| -fgcse | ||||
| -fgcse-after-reload | ||||
| -fgcse-las | ||||
| -fgcse-lm | ||||
| -fgraphite-identity | ||||
| -fgcse-sm | ||||
| -fhoist-adjacent-loads | ||||
| -fif-conversion | ||||
| -fif-conversion2 | ||||
| -findirect-inlining | ||||
| -finline-functions | Kirill Lepetinskiy | GCC Docs | Blog Post | |
| -finline-functions-called-once | ||||
| -finline-limit=n | ||||
| -finline-small-functions | Yehoshua Ghitis | |||
| -fipa-cp | ||||
| -fipa-cp-clone | ||||
| -fipa-pta | ||||
| -fipa-profile | ||||
| -fipa-pure-const | ||||
| -fipa-reference | ||||
| -fira-algorithm=algorithm | ||||
| -fira-region=region | ||||
| -fira-hoist-pressure | ||||
| -fira-loop-pressure | ||||
| -fno-ira-share-save-slots | ||||
| -fno-ira-share-spill-slots | ||||
| -fira-verbose=n | ||||
| -fisolate-erroneous-paths-dereference | ||||
| -fisolate-erroneous-paths-attribute | ||||
| -fivopts | ||||
| -fkeep-inline-functions | ||||
| -fkeep-static-consts | ||||
| -flive-range-shrinkage | ||||
| -floop-block | Dmytro Yegorov | -floop-block | Blog Post | |
| -floop-interchange | Dmytro Yegorov | -floop-interchange | Blog Post | |
| -floop-strip-mine | ||||
| -floop-nest-optimize | ||||
| -floop-parallelize-all | ||||
| -flto | ||||
| -flto-compression-level | ||||
| -flto-partition=alg | ||||
| -flto-report | ||||
| -flto-report-wpa | ||||
| -fmerge-all-constants | ||||
| -fmerge-constants | ||||
| -fmodulo-sched | ||||
| -fmodulo-sched-allow-regmoves | ||||
| -fmove-loop-invariants | Gaurav Patel | https://en.wikipedia.org/wiki/Loop-invariant_code_motion | ||
| -fno-branch-count-reg | ||||
| -fno-defer-pop | Andy Cooc | |||
| -fno-function-cse | Andy Cooc | |||
| -fno-guess-branch-probability | ||||
| -fno-inline | Donald Nguyen | |||
| -fno-math-errno | ||||
| -fno-sched-interblock | ||||
| -fno-sched-spec | ||||
| -fno-signed-zeros | Suk-Joong Han | https://en.wikipedia.org/wiki/Signed_zero | ||
| -fno-toplevel-reorder | ||||
| -fno-trapping-math | ||||
| -fno-zero-initialized-in-bss | ||||
| -fomit-frame-pointer | ||||
| -foptimize-sibling-calls | ||||
| -fpartial-inlining | ||||
| -fpeel-loops | James Shin | |||
| -fpredictive-commoning | ||||
| -fprefetch-loop-arrays | Jayme Laso-Barros | GCC 5.2 Manual: Section 3.10 | ||
| -fprofile-report | ||||
| -fprofile-correction | ||||
| -fprofile-dir=path | ||||
| -fprofile-generate | ||||
| -fprofile-generate=path | ||||
| -fprofile-use | Ramanan Manokaran | |||
| -fprofile-use=path | ||||
| -fprofile-values | ||||
| -fprofile-reorder-functions | ||||
| -freciprocal-math | ||||
| -free | ||||
| -frename-registers | ||||
| -freorder-blocks | Ramanan Manokaran | |||
| -freorder-blocks-and-partition | ||||
| -freorder-functions | Jayme Laso-Barros | GCC 5.2 Manual: Section 3.10 | ||
| -frerun-cse-after-loop | ||||
| -freschedule-modulo-scheduled-loops | ||||
| -frounding-math | ||||
| -fsched2-use-superblocks | ||||
| -fsched-pressure | ||||
| -fsched-spec-load | ||||
| -fsched-spec-load-dangerous | ||||
| -fsched-stalled-insns-dep[=n] | ||||
| -fsched-stalled-insns[=n] | ||||
| -fsched-group-heuristic | ||||
| -fsched-critical-path-heuristic | ||||
| -fsched-spec-insn-heuristic | ||||
| -fsched-rank-heuristic | ||||
| -fsched-last-insn-heuristic | ||||
| -fsched-dep-count-heuristic | ||||
| -fschedule-insns | ||||
| -fschedule-insns2 | ||||
| -fsection-anchors | ||||
| -fselective-scheduling / -fselective-scheduling-2 | ||||
| -fsel-sched-pipelining / -fsel-sched-pipelining-outer-loops | ||||
| -fshrink-wrap | ||||
| -fsignaling-nans | ||||
| -fsingle-precision-constant | ||||
| -fsplit-ivs-in-unroller | ||||
| -fsplit-wide-types | Shirwa Egal | |||
| -fstack-protector / -fstack-protector-all / -fstack-protector-strong | ||||
| -fstrict-aliasing | ||||
| -fstrict-overflow | ||||
| -fthread-jumps | ||||
| -ftracer | ||||
| -ftree-bit-ccp | ||||
| -ftree-builtin-call-dce | ||||
| -ftree-ccp | ||||
| -ftree-ch | ||||
| -ftree-coalesce-inline-vars | ||||
| -ftree-coalesce-vars | ||||
| -ftree-copy-prop | ||||
| -ftree-copyrename | ||||
| -ftree-dce | Gaurav Patel | https://en.wikipedia.org/wiki/Dead_code_elimination | ||
| -ftree-dominator-opts | ||||
| -ftree-dse | Shirwa Egal | |||
| -ftree-forwprop | ||||
| -ftree-fre | ||||
| -ftree-loop-if-convert | Donald Nguyen | |||
| -ftree-loop-if-convert-stores | Kirill Lepetinskiy | GCC Docs On CMOV | Blog Post | |
| -ftree-loop-im | ||||
| -ftree-phiprop | ||||
| -ftree-loop-distribution | Nitish Bajaj | |||
| -ftree-loop-distribute-patterns | ||||
| -ftree-loop-ivcanon | ||||
| -ftree-loop-linear | ||||
| -ftree-loop-optimize | ||||
| -ftree-loop-vectorize | ||||
| -ftree-parallelize-loops=n | ||||
| -ftree-pre | ||||
| -ftree-partial-pre | ||||
| -ftree-pta | ||||
| -ftree-reassoc | ||||
| -ftree-sink | ||||
| -ftree-slsr | ||||
| -ftree-sra | ||||
| -ftree-switch-conversion | ||||
| -ftree-tail-merge | ||||
| -ftree-ter | ||||
| -ftree-vectorize | ||||
| -ftree-vrp | Nitish Bajaj | |||
| -funit-at-a-time | ||||
| -funroll-all-loops | Yehoshua Ghitis | |||
| -funroll-loops | Joel Aro | Loop Unrolling | ||
| -funsafe-loop-optimizations | ||||
| -funsafe-math-optimizations | James Shin | |||
| -funswitch-loops | Miguel Dizon | |||
| -fvariable-expansion-in-unroller | ||||
| -fvect-cost-model | ||||
| -fvpt | ||||
| -fweb | ||||
| -fwhole-program |
