performance - Why does CUDA code run so much faster in NVIDIA Visual Profiler? -


a piece of code takes well on 1 minute on command line done in matter of seconds in nvidia visual profiler (running same .exe). natural question why? there wrong command line, or visual profiler different , not execute on command line?

i'm using cublas, thrust , curand.

incidentally, there's been noticeable slowdown in compiled code on machine recently, old code ran quickly, hence i'm getting suspicious.

update:

  • i have checked calculated output on command line , visual profiler identical - i.e. required code has been run in both cases.
  • gpu-shark indicated performance state unchanged @ p0 when switched command line visual profiler.
  • however, gpu usage reported @ 0.0% when run visual profiler, went high 98% when run off command line.
  • moreover, far less memory used visual profiler. when run off command line, task manager indicates usage of 650-700mb of memory (spikes @ first cudafree(0) call). in visual profiler figure goes down ~100mb.

this old question, i've finished chasing same issue (though cause may not same).

namely: app achieved between 900 , 1100 frames (synchronous launches) per second when running under nvvp, around 100-120 when running outside of profiler.

the cause appears status message printing console via cout. had intended happen once every 100-200 frames. instead, printing status message every frame, , console io became bottleneck.

by printing status message every 100 frames (though optimal number here depend on application), frame rate jumped match seeing in nvvp. of course, handled in separate cpu thread if sort of overhead unacceptable in circumstances.

nvvp has redirect stdout own internal buffer in order capture application's output (which shows in console tab). appears nvvp's mechanism buffering or processing output has less overhead allowing operating system handle directly. looks nvvp buffering everything, , displaying in separate thread, or saving bunch of output until threshold reached, when adds buffer own console tab.

so, advice disable console io, , see if or how affects things.

(it didn't vs2012 refused profile cuda app. have been nice see 80% of execution time spent on console io.)

hope helps!


Comments

Post a Comment

Popular posts from this blog

jquery - How can I dynamically add a browser tab? -

since using iframes house external pages are, accounts "not preferred method" , disallowed sites (flickr, one), want dynamically generate browser tabs. e.g., when user submits form, want dynamically generate tab on browser in response submitted. e.g., might want add new tab url like: http://www.bigsurgarrapata.com/contact how in jquery? you want form target attribute action attribute. http://www.w3schools.com/tags/att_form_target.asp browsers have ultimate control on result of target attribute open new tab value of _blank. <form action="contact_submit.php" target="_blank" method="post">
Read more

node.js - Getting the socket id,user id pair of a logged in user(s) -

i have web application done using node js , in it,i have authentication system requires users log in before can access pages. have 2 pages,the homepage , updates page. from read docs,a new socket id issued when user opens tab in browser. me being admin,i know socket id of logged in user , more so,the socket id,logged in user id pair logged in users. what method can use socket id,logged in user id pair make sure broadcast realtime info users online?.
Read more

keyboard - C++ GetAsyncKeyState alternative -

i using windows.h library's getasynckeystate function define key pushed on keyboard . here program returns int value of pushed key example. #include <iostream> #include <windows.h> using namespace std; int main (){ char i; for(i=8;i<190;i++){ if(getasynckeystate(i)== -32767){ cout<<int (i)<<endl; } } return 0; } but trying make opengl simple game , function appeared slow . there function not need cycle 180 times , if statement . thanks you're trying make opengl game, you're going use glfw. if that's case can away using glfwgetkey() such: if (glfwgetkey(glfw_key_up) == glfw_press) {...} if (glfwgetkey(glfw_key_down) == glfw_press) {...} that method nicely explained in tutorial 6 opengl-tutorial.org . should start first tutorial of beginners tutorials , later intermediate tutorials . if you're going make win32 window can listen wm_keydown or wm_keyup messages , virtua
Read more