New Enhancements Boost Chelsio’s 40Gbps T5 Adapter Capabilities

July 27, 2015

The release of three new software enhancements adds even more capabilities to Chelsio Communications’ powerful Terminator 5 (T5) ASIC.

The T5 is a fifth generation, high-performance 2x40Gbps/4x10Gbps server adapter engine with Unified Wire capability, enabling offloaded storage, compute and networking traffic to run simultaneously. T5 based adapters are high performance drop-in replacements for Fibre Channel storage adapters and InfiniBand RDMA adapters.

T5 is the only 40G Ethernet adapter with plug and play RDMA Ethernet support with no extra network configuration.

The enhancements include:

  • Linux 40GbE Data Plane Development Kit (DPDK) for high speed packet processing
  • GPUDirect over 40GbE iWARP RDMA for high performance CUDA clustering
  • NVMe over 40GbE iWARP RDMA for enhanced latency and throughput

Linux 40GbE DPDK

DPDK is a suite of packet processing libraries and NIC drivers optimized for running in user space to boost networking performance. DPDK provides a programming framework of open-source libraries to develop high speed data packet networking applications.

A recent report provides benchmark results that demonstrate the performance benefits of DPDK support for the T5 ASIC. The implementation allows networking applications to achieve unprecedented packet processing capacity and throughput unmatched by standard Linux kernel network stack or other DPDK implementations.

The benchmarks, which used Chelsio’s T580-CR Unified Wire Adapter at 40GbE, show record breaking performance, exceeding 47 MPPS in unidirectional tests, and 71 MPPS in bidirectional tests. In addition, a superior bandwidth curve showcases T5’s DPDK performance with line rate throughput at I/O size 256B for both unidirectional and bidirectional traffic.

These outstanding results make T5’s DPDK solution an ideal fit for networking applications striving for the best in packet processing performance.

TX Single Port
Fig 1. Single port unidirectional throughput and packet rate vs. I/O size using DPDK-Pktgen tool at different I/O sizes

GPUDirect over 40GbE iWARP RDMA

Remote DMA (RDMA) is a technology that achieves unprecedented levels of efficiency, thanks to direct system or application memory-to-memory communication, without CPU involvement or data copies. With RDMA enabled adapters, all packet and protocol processing required for communication is handled in hardware by the network adapter, resulting in high performance. iWARP RDMA uses a hardware TCP/IP stack that runs in the adapter, completely bypassing the host software stack, thus eliminating any inefficiencies due to software processing.

NVIDIA’s GPUDirect technology combined with iWARP RDMA takes full advantage of these advanced technologies. Network access to the GPU is achieved with high performance and efficiency. Since the host CPU and memory are completely bypassed, communication overheads and bottlenecks are eliminated, resulting in minimal impact on host resources, and translating to significantly higher overall cluster performance.

The use of Chelsio’s T580-CR iWARP RDMA adapter along with NVIDIA’s GPUDirect technology delivers dramatically lower latency and higher throughput for mission-critical scientific and HPC applications. The results also show that iWARP RDMA provides significantly higher bandwidth than competing RDMA over Ethernet protocols.

Fig. 2.  GDR enabled/disabled throughput vs. I/O size
Fig. 2. GDR enabled/disabled throughput vs. I/O size
Fig. 3  GDR enabled/disabled Latency vs. I/O size
Fig. 3 GDR enabled/disabled Latency vs. I/O size

 

NVMe over 40GbE iWARP RDMA

Developed by a consortium of storage and networking companies, NVM Express (NVMe) is an optimized interface for accessing PCI Express (PCIe) non-volatile memory (NVM) based storage solutions.

With an optimized stack, a streamlined register interface and command set designed for high performance solid state drives (SSD), NVMe is expected to provide significantly improved latency and throughput compared to SATA based solid state drives. The enhancement includes support for security and end-to-end data protection.

The benchmarks not only present superior throughput results, but also demonstrate the low remote storage access latency made possible with iWARP. Such latency numbers allow exploiting the full potential of ultra low latency SSD drives, and in combination with the efficient high throughput made possible by iWARP, provide the next generation, scalable storage network over standard, cost effective Ethernet.

iWARP is the only RDMA Ethernet that offers the performance and scalability needed by storage by using TCP/IP’s mature and proven design in hardware.

NVME iWARP Performance
Fig. 4 Using NVMe over RDMA, comparing throughput vs. I/O size
NVMe iWARP Latency
Fig 5. Using NVMe over RDMA, comparing Latency vs. I/O size

Related Links

 

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension around the potential changes that could affect or disrupt Lustre Read more…

By Carlos Aoki Thomaz

Inventor Claims to Have Solved Floating Point Error Problem

January 17, 2018

"The decades-old floating point error problem has been solved," proclaims a press release from inventor Alan Jorgensen. The computer scientist has filed for and received a patent for a "processor design, which allows rep Read more…

By Tiffany Trader

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitive computing, memory-centric computing, high-speed communicat Read more…

By John Russell

HPE Extreme Performance Solutions

HPE and NREL Take Steps to Create a Sustainable, Energy-Efficient Data Center with an H2 Fuel Cell

As enterprises attempt to manage rising volumes of data, unplanned data center outages are becoming more common and more expensive. As the cost of downtime rises, enterprises lose out on productivity and valuable competitive advantage without access to their critical data. Read more…

US Seeks to Automate Video Analysis

January 16, 2018

U.S. military and intelligence agencies continue to look for new ways to use artificial intelligence to sift through huge amounts of video imagery in hopes of freeing analysts to identify threats and otherwise put their Read more…

By George Leopold

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension aroun Read more…

By Carlos Aoki Thomaz

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitiv Read more…

By John Russell

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Momentum Builds for US Exascale

January 9, 2018

2018 looks to be a great year for the U.S. exascale program. The last several months of 2017 revealed a number of important developments that help put the U.S. Read more…

By Alex R. Larzelere

ANL’s Rick Stevens on CANDLE, ARM, Quantum, and More

January 8, 2018

Late last year HPCwire caught up with Rick Stevens, associate laboratory director for computing, environment and life Sciences at Argonne National Laboratory, f Read more…

By John Russell

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

The @hpcnotes Predictions for HPC in 2018

January 4, 2018

I’m not averse to making predictions about the world of High Performance Computing (and Supercomputing, Cloud, etc.) in person at conferences, meetings, causa Read more…

By Andrew Jones

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Leading Solution Providers

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Nvidia, Partners Announce Several V100 Servers

September 27, 2017

Here come the Volta 100-based servers. Nvidia today announced an impressive line-up of servers from major partners – Dell EMC, Hewlett Packard Enterprise, IBM Read more…

By John Russell

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

  • arrow
  • Click Here for More Headlines
  • arrow
Share This