Sign up for our newsletter and get the latest HPC news and analysis.

insideHPC Performance Guru Looks at Nvidia’s New NVLink

Bill D'Amico

“For NVLink to have its highest value it must function properly with unified memory. That means that the Memory Management Units in the CPUs have to be aware of NVLink DMA operations and update appropriate VM structures. The operating system needs to know when memory pages have been altered via NVLink DMA – and this can’t be solely the responsibility of the drivers. Tool developers also need to know details so that MPI or other communications protocols can make use of the new interconnect.”

High Performance Computing at CSCS

Schulthess

“With around 3.2 billion computer operations (3.2 gigaflops) per watt, the combination of GPUs CPUs makes “Piz Daint” one of the world’s most energy-­efficient supercomputers in the petaflop performance class.”

Negative Latency and Einstein Express

“I’ve been thinking for a while that our obsession with reduction of latency in computing and storage could be ameliorated by exploiting a negative latency design. A negative latency design would be one where a hypothetical message would arrive at a receiver before the sender completed sending it.”

InfiniBand Principles Every HPC Expert MUST Know

oded

In this video from the HPC Advisory Council Swiss Conference 2014, Oded Paz from Mellanox Global Education Services presents: InfiniBand Principles Every HPC Expert MUST Know.

Arista Networks Files for IPO

Andy Bechotolsheim

Arista Networks filed for an initial public offering today. Founded by Andy Bechtolsheim, Arista builds switches that handle traffic at large internet data centers for companies including Facebook Inc, Yahoo Inc, Comcast Corp and Citigroup Inc. The company said it would raise $200 million from the offering, but the final size of the IPO could vary.

HPC Advisory Council Announces Brazil Conference for May 26

hpcac

The HPC Advisory Council just announced the HPCAC Brazil Conference, which takes place on May 26, 2014, in São Paulo, Brazil.

Nvidia Develops NVLink Interconnect for Next-Gen “Pascal” GPUs

nvlink_quad-624x221

Today at GTC 2014, Nvidia announced new technologies that will ship with their next-generation “Pascal” GPUs. First up is a new interconnect called NVLink, a point-to-point interconnect that offers advantages over PCI-E.

OpenFabrics Developer Workshop Coming Up March 30 – April 2

The 10th annual OpenFabrics Alliance International Developer Workshop takes place March 30–April 2 at the Monterey Marriott in Monterey, CA. “This isn’t the usual industry conference with one-way presentations. It’s a workshop featuring discussions on the development and improvement of OpenFabrics Software (OFS), the open-source software foundation of all RDMA enabled fabrics, and the strategic opportunities and advancements within the OFA. “

10th Annual OpenFabrics Workshop Brings Together HPC Interconnect Community

imgres

“Over the years the OpenFabrics Alliance has developed a record of technology leadership, and you only get that kind of leadership thinking through the sort of face-to-face collaboration that occurs at the annual workshops. These workshops are where I/O technologists from all branches of the computing world can gather in an environment that fosters creative solutions to problems such as those posed by emerging Exascale computing. The outcome of these workshops ends up being a key driver in focusing the OFA’s efforts in continuing to push I/O technology forward.”

Mellanox Rolls Out LinkX Cables and Transceivers

linkx-logo

Today Mellanox announced its new line of LinkX cables and transceivers supporting interconnect speeds of 10, 40 and 56 gigabit per second for both Ethernet and InfiniBand data center networks.