#gpu programming

so because i am a crazy person i resently decided to try and learn how to use driver api's to use the GPU in python without any pipped libraires. in going down this rabbit hole i have disvored that these api's take some constants as specific hex values to indicate different meanings. and it feels so spooky to just use magic numbers pulled from the ether

This has all been in service of being able to run shit like openGL in vanilla with no added libraries ArcGIS Pro so that i could develop a toolbox that could be shared and it would run on anyone's project right out the gate.

so here is a rotating cube as an arcgis toolbox

Last weekend I tried to get my hand on GPU CUDA programming. I didn’t have access to a computer with a GPU. I thought AWS was the best possible way to go. I must say I wasn’t wrong. However, I faced an issue I wasn’t anticipating at the beginning — a Service Quota restriction. I’ve already explained that problem in my previous blog. You can also find its resolution there: How to Configure AWS…

As the weekend came to a close, I decided to finish it with a focused task — getting hands-on with CUDA programming on an NVIDIA GPU. I don’t have a machine at the moment that comes with an NVIDIA GPU, so AWS seemed like the perfect platform to explore GPU computing without any hardware constraints. After a bit of experimentation and setup, I finally managed to configure an AWS EC2 instance…

HPC Overview Important problems require powerful computers e.g if you want to predict climate, based on high volume data, so there may be many functions operating individually or simultaneously. Powerful computers must be parallel In this era, almost all computers have multi-core or multi-processor You must use all the cores/processors to yield maximum performance  Increasing importance of…

Why HPC (High Performance Computing) Multi-core and many-core era is here to stay Famous Moore’s Law Why? Technology Trends Many programmers will be developing parallel software But still not everyone is trained in parallel programming Learn how to put all these vast machine resources to the best use! Useful for Joining the work force Graduate school/research Our focus Teach core concepts Use…

PCI-Express 1.0 x16 vs. PCI-Express 2.0 x16 – have you oŝutimaâ difference?

We all know that the difference in the speed of transmission via pci-express doubled, but associated with a number of questions: 1) Do all possible bus used by modern video cards or visible difference will not, if you insert, for example, GeForce GTX460 in PCIe 1.0 and 2.0? 2) How to check the exact capacity? I found a PCIe Speed ​​Test v0.2, but it works only on graphics cards from ATi 3) Are…