1. Computers
  2. Display Drivers
  3. Graphics Cards
  4. Memory
  5. Motherboards
  6. Processors
  7. Software
  8. Storage
  9. Operating Systems


Facebook RSS Twitter Twitter Google Plus


Phoronix Test Suite

OpenBenchmarking.org

HPL-GPU 1.0 Released For GPU Super Computing

Hardware

Published on 11 December 2010 08:25 AM EST
Written by Michael Larabel in Hardware
13 Comments

Matthias Bach, a researcher and developer on high-performance computing with the Goethe Universitaet Frankfurt am Main, has written in to inform us of this German university's release of HPL-GPU 1.0. The HPL-GPU software package is a rewritten version of the LINPACK library that is re-engineered to run atop CALDGEMM, which is a DGEMM implementation developed at this university designed to run atop the latest AMD graphics processors.

The HPL-GPU 1.0 package is the code that's running atop LOEWE-CSC, which is a 832-node CPU/GPU cluster at Frankfurt University's Center for Scientific Computing. This LOEWE-CSC cluster HPL performance was measured at 285 TeraFLOPS this year making it one of the fastest super-computers in the world. LOEWE-CSC was ranked 22nd on this year's top 500 super-computer list and took the 8th spot on the green 500 list for the most energy efficient super-computers. This Frankfurt super-computer put outs out a massive 741 MFlops per Watt.

This open-source HPL-GPU code is designed to run on ATI/AMD Radeon graphics hardware under Linux when using the proprietary Catalyst driver (namely Catalyst 10.9 or newer) and using the latest ATI Stream SDK for its CAL support. The code is also engineered for the Radeon HD 5000 "Evergreen" series of graphics cards.

The release announcement (and download links/instructions) for this high-performance LINPACK library for the GPU can be found at uni-frankfurt.de.

Matthias Bach also mentioned to us in his email, "The really interesting thing however is, that this code can run AMD GPUs (Cypress Type, we use AMD 5870) at 100% load for hours, a load that except of our Linpack/DGEMM only Furmark can cause...The code also stomps NVIDIA, reaching 497 flops DGEMM on the HD5870 where NVIDIA only reaches around 300 on the much more expensive Tesla systems."

Latest Linux Hardware Reviews
  1. Mini-Box M350: A Simple, Affordable Mini-ITX Case
  2. Overclocking The AMD AM1 Athlon & Sempron APUs
  3. AMD Athlon 5350 / 5150 & Sempron 3850 / 2650
  4. Upgraded Kernel & Mesa Yield A Big Boost For Athlon R3 Graphics
Latest Linux Articles
  1. A Quick Look At GCC 4.9 vs. LLVM Clang 3.5
  2. Are AMD Athlon/Sempron APUs Fast Enough For Steam On Linux?
  3. AMD Athlon's R3 Graphics: RadeonSI Gallium3D vs. Catalyst
  4. GCC 4.9 Compiler Optimization Benchmarks For Faster Binaries
Latest Linux News
  1. Fedora 21 Gets GNOME 3.12, PHP 5.6, Mono 3.4
  2. Fedora Workstation Is Making Me Quite Excited
  3. Maynard: A Lightweight Wayland Desktop
  4. Chromium Browser Going Through Growing Pains In Ubuntu 14.04
  5. KDE 4.13 Is Being Released Today With New Features
  6. Trying Out Radeon R9 290 Graphics On Open-Source
  7. Intel Broadwell GT3 Graphics Have Dual BSD Rings
  8. Early Linux 3.15 Benchmarks Of Intel Core i7 + Radeon
  9. Red Hat Releases Its RHEL 7 Release Candidate
  10. New Features Coming To Xubuntu 14.04 LTS
  11. NVIDIA Officially Releases CUDA 6
  12. Google Releases An AutoFDO Converter For Perf In LLVM
Latest Forum Discussions
  1. The GNOME Foundation Is Running Short On Money
  2. Linux Kernel Developers Fed Up With Ridiculous Bugs In Systemd
  3. Change installation destination from home directory
  4. After Jack Keane, RuseSoft will briing Ankh 3 to Linux through Desura
  5. Bye bye BSD, Hello Linux: A Sys Admin's Story
  6. New tool for undervolt/overclock AMD K8L and K10 processors
  7. How to enable opengl 3.3 on r9 270?
  8. R290x sound problems