abduld / webgpu Goto Github PK
View Code? Open in Web Editor NEWLicense: University of Illinois/NCSA Open Source License
License: University of Illinois/NCSA Open Source License
I am unable to use WebGPU. It pops the error "Please login first" even though i am already logged in. My coursera account is open and when I click on the Profile tab, it shows an option to logout. The "logout" doesn't work either.
Hi I followed the coursera course heterogeneous computing 2016 summer, and did assignment on webgpu website. But now I cannot see my code any more. How can I find my previous code back? Thank you!
I finished the first lab about adding vectors and they were correct for all the datasets. But I don't understand how the different labs uses the same datasets for different operations. Now I am working on the matrix multiplications and I can figure out where the correspondent datasets are. I downloaded it from the site and I validate all of them for the vector add but I still don't understand which dataset to use for the second exercise since they work for vector adding they shouldn't work for matrix multiplication, right?
I have submitted MP5.1. However, there is no record in the grade session for my submission of MP 5.1 as usual. Therefore, I don't know whether my submission has been recorded successfully or not.
I try to connect this account with my Coursera account, but when I click on the corresponding button I get a blank page instead of the form asking for my coursera user name and password.
The link is
https://class.coursera.org/hetero-004/courservice/lti/v1/973470/2
and I'm using google chrome.
Any advice?
WebGPU isn't running code correctly. When I try to "Compile and Run" a program, a busy spinner appears, and never goes away.
The code for Machine Problem 0 seems to be overwritten with code from other machine problems arbitrarily. Right now, the code for MP0 on my account is "MP Reduction", shortly before it was tiled matrix multiplication. I tried reverting the code (/mp/0/revert) which reports success, but still the Device Query code is no where to be found.
edit: Not just the code, the questions are also from another lab. The description though, is still Device Query.
I'm trying to compile & run but it doesn't work.
Is it because the course is over ?
Although the class has ended, I was wondering if you can open the sign up system for us, at least to just read the assignment instructions... Come on, I'd really like to attend this course and I can't wait till the next session... Appreciate it.
Dear Abdul,
I am attending the Heterogeneous Parallel Programming course on coursera. In the first lab assignment it is described that we should follow the instructions on webgpu. Unfortunately I cannot connect my coursera account to webgpu. Is there a possibility to do it?
Thank you in advance,
adrian
After scouring my notes and making sure my code is correct, it works perfectly on datasets 0, 2, 3, and 4. On sets 1 and 5 it gives me an error "Failed to run program..." with no additional info. I have checks for cuda errors after every cuda operation.
Hello,
I am enrolled in the Algorithmic Techniques class through a partner university to UIUC and am currently working through MP3 Basic Matrix Multiplication. When running dataset 1, I get the following error message: The solution did not match the expected results at column 0 and row 0. Expecting 312.04 but got 316.53.
I have tried calculating the result at column 0 and row 0 using serial C code and I get the same answer (316.53). Is it possible that the WebGPU platform does not have the correct answer? My code for serially calculating the output at (0, 0) is below.
float origin = 0;
for(int i = 0; i < numAColumns; i++)
{
origin += hostA[i] * hostB[i * numBRows];
}
A is the first vector and B is the second (Sorry for not formatting this too well; I haven't submitted an issue before).
Thanks
`
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.