Looking for the company’s GPU-pioneers

Reading Time: 2 minutes

Getting from the technical advantages to the business advantages we have extensive experience.

Several projects were introduced to us via the company’s GPU-pioneer. These collaborations were very successful and pleasant to do, due to the internal support within the company. This is a reason we would like to do more of these – this text is dedicated to the GPU-pioneers out there.

Seeing the potential of GPUs is not easy, even when you’ve carefully read the 13 types of algorithms that OpenCL can speed up. So it’s even harder to convince your boss that GPUs are the way to go.

Here is where we come in. This is what you need to do.

Step 1: Discuss with us

Ofcourse GPUs are not always the way to go. Before you take all the effort, it is a good idea to just chat with us if GPUs are the solution. Also the advantages/disadvantages of OpenCL, CUDA, Metal, RenderScript and another APIs can be discussed, given the requirements for high-end server-GPUs, desktop-GPUs or embedded GPUs. This will help you to tell a stronger story.

Step 2: Bring GPUs to the attention

Depending on your company culture, discuss with your manager in a private meeting, with your colleagues at the cofee-machine or during a team-meeting. During step 1 we’ve prepared you what to say and what to present. Here you can introduce us.

Step 3: Let us call your boss

Your boss makes the decisions and can decide if GPUs are to be introduced. Besides showing a demo how much faster GPUs can be, we can also showcase the business advantages by example. After understanding the business and technical sides, we can calculate the return-on-investment and help your boss decide if GPUs are a good investment or not.

Step 4: Get GPU’ified code

We would like to work specifically with you to port the software to the GPU, or design software from scratch. This is because you know the company’s software and understand the power of GPUs.

We’ll explain you what we programmed, so you learn OpenCL from very experienced GPU-developers.

Step 5: Extend and further optimize the code

Congratulations! Your company now uses the GPU in their products and you are the first to pick to (technically) lead the effort!

As you’ve learnt from us during the project, we are confident you can extend and further optimize the code.

Step 0: Prepare and make contact

Read the 13 types of algorithms that OpenCL can speed up, and see if it applies to your company’s software. Then contact us.

 

Related Posts

nvidia logo

Academic hackatons for Nvidia GPUs

Are you working with Nvidia GPUs in your research and wish Nvidia would support you as they used to 5 years ago? This is now done with hackatons, wher ...

IWOCL-logo

IWOCL 2019

On Monday May 13, 2019 at 09:30 the latest edition of IWOCL starts, not taking into account any pre-events that might be spontaneously organized. This ...

cuda

Question: do we work with CUDA?

Answer: Yes, actually a lot!The company was built on OpenCL and we are still work with the language a lot - from embedded GPUs and FPGAs to high-end ...

screenshot-twitter

The 12 latest Twitter Poll Results of 2018

Via our Twitter channel we have various polls. Not always have we shared the full background of these polls, so we've taken the polls of the past half ...