Any other #manjaro users out there using https://nonfree.eu/ for #mesanonfree #hardwareacceleration?

Hardware Acceleration in Firefox not working after recent update #graphics #firefox #video #2304 #hardwareacceleration

https://askubuntu.com/q/1480436/612

Google Chrome-stable no hardware acceleration after 109 #kubuntu #2204 #googlechrome #chromium #hardwareacceleration

https://askubuntu.com/q/1474199/612

ubuntu chrome issues hardware acceleration #googlechrome #hardwareacceleration

https://askubuntu.com/q/1469631/612

Can hardware accelerated video decoding be enabled for Kodi on Raspberry Pi 4? #video #raspberrypi #2304 #hardwareacceleration #kodi

https://askubuntu.com/q/1469285/612

Poping up black rectangles in Chrome with Hardware Acceleration after drivers update #drivers #2204 #googlechrome #hardwareacceleration

https://askubuntu.com/q/1468574/612

@mergy we hit your segment squared away. Fiber cut, and backup core pathway was 2Gbps link, but we never tuned configs for over 1Gbps. Should of had mandatory stress tests. #Dobb-Frank
#HardwareAcceleration

RX.py (https://gitlab.com/pvmm/rx.py) is a Python script that prepares images for rendering them on the MSX2 blitter using this method described by Laurens Holst. It can be quite efficient compressing images rich in flat polygons, replacing the original image by a bunch of line segments (which are both easy to store and draw) and recreate the original image using the MSX2 hardware blitter (which is relatively fast). #msx2 #gamedev #retrogamedev #hardwareAcceleration #v9938

Say goodbye to slow video encoding and noisy fans with Intel QuickSync and AMD AMF's hardware-accelerated video encoding on Ubuntu 22.04! Enjoy faster and more energy-efficient video processing with these cutting-edge technologies. #HardwareAcceleration #VideoEncoding #Ubuntu22.04

https://nemozone.writeas.com/intel-quicksync-and-amd-amf-hardware-accelerated-video-encoding-on-ubuntu-22-04

Hardware-accelerated OpenMSX would not run on Wayland because GLEW expects GLX instead of EGL. So I wrote a tiny temporary fix until GLEW is fixed upstream and the major distros catch up. #glew #wayland #openMSX #emu #gnu #hardwareAcceleration #openGL https://github.com/openMSX/openMSX/pull/1492

Working on a blog post on a small free indie game. Played it a few times, it was fun! I figured I should get some #screenshots.

Played it a few more times, I enjoyed it. I tool screenshots using #Greenshot while playing. When done, I discover they're all of the title screen somehow. Argh.

So, I played it a few more times. It was a bit tiring. I took screenshots with #ShareX. When done, its screenshots, too, were unusable.

I recorded it using #OBS, which has a mode that's better at recording hardware acceleration, and got my screenshots out using #Shotcut. The game rasped against the inside walls of my brain while playing it.

#gamewriting #games #hardwareacceleration

N. Samardzic et al., "CraterLake: a hardware accelerator for efficient unbounded computation on encrypted data"¹

Fully Homomorphic Encryption (FHE) enables offloading computation to untrusted servers with cryptographic privacy. Despite its attractive security, FHE is not yet widely adopted due to its prohibitive overheads, about 10,000X over unencrypted computation. Recent FHE accelerators have made strides to bridge this performance gap. Unfortunately, prior accelerators only work well for simple programs, but become inefficient for complex programs, which bring additional costs and challenges.
We present CraterLake, the first FHE accelerator that enables FHE programs of unbounded size (i.e., unbounded multiplicative depth). Such computations require very large ciphertexts (tens of MBs each) and different algorithms that prior work does not support well. To tackle this challenge, CraterLake introduces a new hardware architecture that efficiently scales to very large cipher-texts, novel functional units to accelerate key kernels, and new algorithms and compiler techniques to reduce data movement.
We evaluate CraterLake on deep FHE programs, including deep neural networks like ResNet and LSTMs, where prior work takes minutes to hours per inference on a CPU. CraterLake outperforms a CPU by gmean 4,600X and the best prior FHE accelerator by 11.2X under similar area and power budgets. These speeds enable realtime performance on unbounded FHE programs for the first time.

#ResearchPapers #HomomorphicEncryption #HardwareAcceleration
__
¹ https://dl.acm.org/doi/10.1145/3470496.3527393

New post: Enabling Transparent Acceleration of Big Data Frameworks Using Heterogeneous Hardware based on our recent VLDB paper to be published in 2023.

Here we explain how #ApacheFlink is extended to run on GPUs and FPGAs with #TornadoVM.

https://jjfumero.github.io/posts/2022/11/enabling-transparent-acceleration-bigdata-heterogeneous-hardware/

#bigdataAnalytics #hardwareAcceleration #gpus #fpgas #java