alphatensor

alphatensor copied to clipboard

How can I find more faster FFT algoritm using your alphatensor ?

1

Hi, @saran-t @google-admin @matejbalog @googlebot @AlisonBell This is great work! How can I find more faster FFT algoritm using your alphatensor ? FFT = Fast Fourier Transform. Please teach me...

bemoregt

Hi deepmind team, This is truly amazing work! Great job and thank you so much for publishing these findings. As a developer I'm keen to make use of these algorithmic...

drbh

Hello, I created this quick PR to benchmark the new algorithm also on other NVIDIA GPUs. The default behaviour will still be the same of the current script, but more...

vcarpani

How to apply it on GPU

1

That's an amazing work! We are university students from China.Our group projects are foucused on how to apply these algorithms on GPU to get it more efficient.But after learnt,we found...

1401163082

Clock Speed Set to 1530MHz when V100 has a max boost clock of 1380 MHz

2

In your GPU benchmark, you set the persistence mode to ON and then lock the GPU clocks to 1530,1530 as follows: ``` python3 process = subprocess.Popen( 'sudo nvidia-smi --lock-gpu-clocks=1530,1530'.split(' '),...

afzalxo

what are the differences between these directories like if I want to use faster matrix multiplication between two matrices which directory should I use?

Hesham-Aliy

Bumps [scipy](https://github.com/scipy/scipy) from 1.7.3 to 1.11.1. Release notes Sourced from scipy's releases. SciPy 1.11.1 Release Notes SciPy 1.11.1 is a bug-fix release with no new features compared to 1.11.0. In...

dependabot[bot]