diff --git a/CMakeLists.txt b/CMakeLists.txt index 5f3e9f8..0c80bce 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1,4 +1,4 @@ -cmake_minimum_required(VERSION 3.0) +cmake_minimum_required(VERSION 3.1) project(cis565_getting_started) diff --git a/INSTRUCTION.md b/INSTRUCTION.md index 5f31bdb..1ce02b9 100644 --- a/INSTRUCTION.md +++ b/INSTRUCTION.md @@ -1,7 +1,7 @@ Project 0 CUDA Getting Started: Instructions ======================== -This is due **Friday, September 1 2017**. (See [late policy](#late-policy) at the bottom) +This is due **Friday, August 31st 2018**. (See [late policy](#late-policy) at the bottom) **Summary:** In this project, you will set up your CUDA development tools and verify that you can build, run, and do performance analysis. @@ -26,6 +26,11 @@ machine with these specs, you may use computers in the Moore or SIG Labs. Skip this part if you are developing on a lab computer. +#### Notes +- Before you get started: if you have multiple VS code and/or CMake versions, you will probably run into trouble. Either uninstall extra versions (if possible) or ensure that the correct VSCode (or XCode) and CMake versions are being chosen. +- If you are running into a lot of trouble, a clean installation of VS Code (or XCode), CMake, and CUDA can help fix any problems if other methods don't work. +- If you have driver issues or random crashing: uninstalling and reinstalling drivers usually works + ### Windows 1. Make sure you are running Windows 7/8/10 and that your NVIDIA drivers are @@ -73,7 +78,7 @@ Capability 5.0. * CUDA 8 is recommended. However, if you have any reason that you have to use CUDA 7.5, please clarify you're using CUDA 7.5 in your report. Also you need to change `find_package(CUDA 8.0 REQUIRED)` in `CMakeLists.txt` to `find_package(CUDA REQUIRED)` before you build your project. - For more Linux installation info, check out [CUDA_Linux Installation Guide](http://developer2.download.nvidia.com/compute/cuda/8.0/secure/Prod2/docs/sidebar/CUDA_Installation_Guide_Linux.pdf?weyH9mwDHKcyP4LBe1idPT47TTMqM6s3HKNrW1hOYPlw0om73Jx7isV6gG6L3O7p6pJm1JNcY4sp_4LDlBVE7dG7mGyjDeKq5O_T7eRdBDlb1I-ZhvperJ5VfM8dT_R6RuRj5hTUEijr5vY8_KFfZAQ1dvq2CQOW5O2gLBtMc3UISE-o11fzsUTBYQ). + For more Linux installation info, check out [CUDA_Linux Installation Guide](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html). * Make sure you select Nsight. 2. Install Git (`apt-get install git` on Debian/Ubuntu). 3. Install CMake (`apt-get install cmake` on Debian/Ubuntu). diff --git a/README.md b/README.md index fd52a04..ad1d7dc 100644 --- a/README.md +++ b/README.md @@ -3,11 +3,13 @@ Project 0 CUDA Getting Started **University of Pennsylvania, CIS 565: GPU Programming and Architecture, Project 0** -* (TODO) YOUR NAME HERE -* Tested on: (TODO) Windows 22, i7-2222 @ 2.22GHz 22GB, GTX 222 222MB (Moore 2222 Lab) +* Salaar Kohari + * [LinkedIn](https://www.linkedin.com/in/salaarkohari), [personal website](http://salaar.kohari.com) +* Tested on: Windows 10, Intel Xeon @ 3.1GHz 32GB, GTX 980 4GB (SIG Lab) -### (TODO: Your README) +### Screenshots/Analysis -Include screenshots, analysis, etc. (Remember, this is public, so don't put -anything here that you don't want to share with the world.) +Implemented analysis as described in instructions. The debug breakpoint could not be hit due to a gpu debugging setting that I could not access. Tried reinstalling everything to no avail. +![](images/run.png) +![](images/analysis.png) diff --git a/images/analysis.png b/images/analysis.png new file mode 100644 index 0000000..45dc4bd Binary files /dev/null and b/images/analysis.png differ diff --git a/images/run.png b/images/run.png new file mode 100644 index 0000000..84087a7 Binary files /dev/null and b/images/run.png differ diff --git a/src/main.cpp b/src/main.cpp index 886fd4c..dff46c3 100644 --- a/src/main.cpp +++ b/src/main.cpp @@ -10,8 +10,7 @@ * C main function. */ int main(int argc, char* argv[]) { - // TODO: Change this line to use your name! - m_yourName = "TODO: YOUR NAME HERE"; + m_yourName = "Salaar Kohari"; if (init(argc, argv)) { mainLoop();