c++ - Confusing Memory Reordering Behavior -


i trying run simple task (obtaining x2apic id of current processor) on every available hardware thread. wrote following code this, works on machines tested on (see here complete mwe, compilable on linux c++11 code).

void print_x2apic_id() {         uint32_t r1, r2, r3, r4;         std::tie(r1, r2, r3, r4) = cpuid(11, 0);         std::cout << r4 << std::endl; }  int main() {         const auto _ = std::ignore;         auto nprocs = ::sysconf(_sc_nprocessors_onln);         auto set = ::cpu_set_t{};         std::cout << "processors online: " << nprocs << std::endl;          (auto = 0; != nprocs; ++i) {                 cpu_set(i, &set);                 check(::sched_setaffinity(0, sizeof(::cpu_set_t), &set));                 cpu_clr(i, &set);                 print_x2apic_id();         } }

output on 1 machine (when compiled g++, version 4.9.0):

0 2 4 6 32 34 36 38

each iteration printed different x2apic id, things working expected. problems start. replaced call print_x2apic_id following code:

uint32_t r4; std::tie(_, _, _, r4) = cpuid(11, 0); std::cout << r4 << std::endl;

this causes same id printed each iteration of loop:

36 36 36 36 36 36 36 36

my guess happened compiler noticed call cpuid not depend on loop iteration (even though does). compiler "optimized" code hoisting call cpuid outside loop. try fix this, converted r4 atomic:

std::atomic<uint32_t> r4; std::tie(_, _, _, r4) = cpuid(11, 0); std::cout << r4 << std::endl;

this failed fix problem. surprisingly, does fix problem:

std::atomic<uint32_t> r1; uint32_t r2, r3, r4; std::tie(r1, r2, r3, r4) = cpuid(11, 0); std::cout << r4 << std::endl;

... ok, i'm confused.

edit: replacing asm statement in cpuid function asm volatile fixes issue, don't see how should necessary.

my questions

  1. shouldn't inserting acquire fence before call cpuid , release fence after call cpuid sufficient prevent compiler performing memory reordering?
  2. why didn't converting r4 std::atomic<uint32_t> work? , why did storing first 3 outputs r1, r2, , r3 instead of ignoring them cause program work?
  3. how can correctly write loop, using least amount of synchronization necessary?

i've reproduced problem optimization enabled (-o). right suspecting compiler optimization. cpuid serves full memory barrier (for processor) itself; compiler generates code without calling cpuid function in loop since threats constant function. asm volatile prevents compiler such optimization saying has side-effects.

see answer details: https://stackoverflow.com/a/14449998/2527797


Comments

Post a Comment

Popular posts from this blog

javascript - Jquery show_hide, what to add in order to make the page scroll to the bottom of the hidden field once button is clicked -

i have button on website when clicked, reveals map. button can seen when page first loads up, when clicked, section holding map slides open , goes out of screen since page loads @ top (normal). want page scroll down bottom of div select when button pushed, if map out of screen. if page scrolled down, , clicks show map button, don't want page jump bottom of map. i tried figure out myself, no luck. seasoned jquery coders able give me guidance? many thanks! map = mapdiv.gmap3("get"); infobox = new infobox({ pixeloffset: new google.maps.size(-220, -310), closeboxurl: '', enableeventpropagation: true }); mapdiv.delegate('.infobox .close','click',function () { infobox.close(); }); jquery(".slidingdiv").hide(); jquery(".show_hide").show(); jquery('.show_hide').click(function(){ lastcenter=map.getcenter(); jquery(".slidingdiv...
Read more

python - Django-cities exits with "killed" -

i trying install django-cities on server 500mb ram. whenever run: manage.py cities the system exits saying killed. trying run: manage.py cities --import=country --force worked, guessing matter of running out of memory. to bypass, tried refer package local copy of cities' data file. still didn't work. any ideas on how can migrate data without having increase memory on server? based on suggestion comments, solved setting temporary swap file. if unfamiliar it, can follow these steps: set swap file touch /var/swap.img chmod 600 /var/swap.img set swap file size cd /var dd if=/dev/zero of=/var/swap.img bs=1024k count=1000 this create 1gb swap file. prepare disk image mkswap /var/swap.img activate swap memory swapon /var/swap.img once done, can turn off swap image: swapoff /var/swap.img more information on virtual memory , swap files can found here: https://www.digitalocean.com/community/tutorials/how-to-configure-virtual-me...
Read more

python - How to get a widget position inside it's layout in Kivy? -

i have gridlayout , added image widgets on after adding of images want draw rectangle in each image using canvas couldn't because don't know exact image widgets positions on gridlayout. code: http://paste.ofcode.org/3bdp9yhjrcrzmsztbu9hqp4 http://paste.ofcode.org/3az3gx4fxzr9dlhe2ami97c in last line of python code : rectangle(pos = (child.x - 2.4, child.y + 467), size = (70, 70)) how draw rectangle in child(my method not good^), also why gridlayout not coming in center after setting it's pos_hint = {"center_x" : .5}? if understand question right, try use such methods to_local() , to_parent() , to_widget() , to_window() . try substract position of gridlayout widgets' positions.
Read more