Results for: adreno gpu
Updating Deep Learning Models Right on the Mobile Device — Transfer Learning and Fine-Tuning
“It’s a good model,” you say, thinking about the model you’ve trained in the cloud for your machine learning application. “I just wish we could fine-tune it on the user’s device.”
Now you can do...
https://developer.qualcomm.com/blog/updating-deep-learning-models-right-mobile-device-transfer-learning-and-fine-tuningTags:
ML training at the edge: Training on mobile devices
You can get a lot of innovation out of running machine learning inference on mobile devices, but what if you could also train your models on mobile devices? What would you invent if you could fine-...
https://developer.qualcomm.com/blog/ml-training-edge-training-mobile-devicesTags:
Accelerate your models with our OpenCL ML SDK
Are you using OpenCL to run machine learning workloads on the Qualcomm® Adreno™ GPU? Want to optimize your application and improve performance? Download our OpenCL ML SDK and use our OpenCL extension...
https://developer.qualcomm.com/blog/accelerate-your-models-our-opencl-ml-sdkTags:
OpenCL Optimization: Accelerating the Epsilon Filter on the Adreno GPU
Co-written with Hongqiang Wang and Alex Bourd
Continuing our series on OpenCL optimization on the Qualcomm® Adreno™ GPU, we describe a multi-step optimization for apps that use the Epsilon filter....
https://developer.qualcomm.com/blog/opencl-optimization-accelerating-epsilon-filter-adreno-gpuTags:
OpenCL Optimization: Accelerating the Sobel Filter on Adreno GPU
Co-written with Hongqiang Wang and Alex Bourd
Our previous post about OpenCL optimization on the Qualcomm® Adreno™ GPU described several candidate use cases. In this post we’ll cover a two-step...
https://developer.qualcomm.com/blog/opencl-optimization-accelerating-sobel-filter-adreno-gpuTags:
OpenCL Optimization: Stop Leaving Compute Cycles on the Table
Co-written by Hongqiang Wang, Raga Ramachandra, and Alex Bourd
Have you started programming on the Qualcomm® Adreno™ GPU yet? For compute-intensive operations, you’ll find cycles in the GPU that you...
https://developer.qualcomm.com/blog/opencl-optimization-stop-leaving-compute-cycles-tableTags:
Start Cooking with Heterogeneous Computing Tools on QDN
How can I improve the performance of my application? How can I get more out of my hardware?
If limited processing power, energy management and thermal issues are important to your product’s...
https://developer.qualcomm.com/blog/start-cooking-heterogeneous-computing-tools-qdnTags:
Matrix Multiply on Adreno GPUs – Part 2: Host Code and Kernel
This is the second and final part of a guest post by Vladislav Shimanskiy, one of our Adreno™ engineers. His previous post explained the concepts behind an optimized implementation of device-side...
https://developer.qualcomm.com/blog/matrix-multiply-adreno-gpus-part-2-host-code-and-kernelTags:
Matrix Multiply on Adreno GPUs – Part 1: OpenCL Optimization
The matrix multiply (MM) operation has become very popular on GPUs thanks to recent interest in deep learning, which depends on convolutions. We’ve been hearing from developers who want to accelerate...
https://developer.qualcomm.com/blog/matrix-multiply-adreno-gpus-part-1-opencl-optimizationTags:
Better OpenCL Performance on Qualcomm Adreno GPU – Memory Optimization
When you want to accelerate an image processing or computer vision application using a graphics processing unit (GPU) like Adreno™, OpenCL™ offers a convenient way to write your program since it’s...
https://developer.qualcomm.com/blog/better-opencl-performance-qualcomm-adreno-gpu-memory-optimization