Intel® VMD and VROC

Intel® Volume Management Device (VMD)

The Intel® Xeon Scalable series processors based on Skylake-SP feature a new Volume Management Device (VMD) built-in. This feature will seem similar to VROC (Virtual RAID On CPU), which debuted with the Core X series and X299 chipset, but VMD is what actually enables VROC.

Each CPU has 3 VMD domains that manages 16 PCIe lanes (total 48 lanes per CPU). The Intel® VMD can be turned on and of in the BIOS per 4 lanes (x4 PCIe SSD)

The total number of PCIe lanes in a dual socket machine equals 96 (2×48) and can be devided in max. 24  NVMe drives that are directly attached to the CPU in the system.

 

Intel® Virtual RAID on CPU (VROC)

Intel® VROC is and Enterprise RAID solution specifically designed for NVMe SSD’s
RAID can be built within a Single VMD domain but also across domains, and even across CPU’s

A RAID array can be bootable when they remain within a single VMD domain. RAID arays that span across multiple VMD domains are not bootable.

Because the Intel® VROC creates RAID arrays without using a traditional RAID HBA the performance is much higher.

Intel® VROC is a hybrid RAID solution. It has attributes like hardware RAID because of the key silicon feature, Intel® Volume Management Device (Intel® VMD). Intel® VDM is offered with the new Intel® Xeon® Scalable Processors. Intel® VROC utilizes Intel® VMD to aggregate NVMe SSDs allowing bootable RAID. Intel® VROC also has attributes like software RAID. For instance, it uses some of the CPU cores to calculate the RAID logic. Because of this combination of software and silicon, Intel® VROC is called a hybrid RAID solution.

 

Intel® VROC replaces the NVMe RAID. Intel VROC uses Intel® Volume Management Device (Intel® VMD) to provide these new features that Intel® RSTe legacy NVMe RAID does not have:

  • Bootable RAID
  • Surprise hot-plug
  • LED management
  • RAID5 Double Fault Protection
  • Support for third-party SSDs

 

NVIDIA TESLA GPU FOR DATACENTERS

What are the differences with a desktop GPU?

HPC and Deep learning breakthroughs have sparked the artificial intelligence revolution. The scientific community is racing towards exascale computing. In both, the computational engine is the GPU. The NVIDIA GPU is the most pervasive high-performance computing (HPC) processor ever built. Whether your computing platform of choice is the PC or the cloud, there’s a GPU to accelerate your important work.The NVIDIA TITAN X or GeForce GTX consumer GPU is designed for the PC. The NVIDIA® Tesla® data center GPU is engineered for predictable behavior and uptime requirements of data centers.

DATACENTER GPU
Consumer GPU

 

TESLA GPU: BUILT FOR THE SERVER

Data centers are designed to optimize for throughput. Technologies ensuring 24/7 uptime, scalability, and manageability are just as important as raw performance for optimizing and reliably delivering data center throughput. The Tesla GPU powers some of the world’s largest data centers. It’s purpose-built for a server, and extensively qualified for the mechanical, physical, management, reliability, and availability needs of rack-scale deployments. The Tesla GPU features a longer warranty, enterprise support, and extended SKU life expected

TITAN X/GeForce GTX: BUILT FOR THE PC

Every developer should have access to the world’s most powerful computing platform. Powered by the new Pascal™ architecture, NVIDIA TITAN X / GeForce GTX is enabled to harness the power of GPU computing in a PC. A PC is very different than a server. Density, airflow, inlet temperature, uptime, and manageability are just a few design points to consider when building a GPU. A consumer GPU is engineered and tested for a PC design point.

 

BENEFIT TESLA GPU CONSUMER GPU
24/7 Uptime Guaranteed quality in a server Server-Grade Engineering

– Lower operating voltage for longer reliability

– Zero-error testing at aggressive clocks

– Error Correction Code (ECC) for data integrity

PC-Grade Engineering
Reduced thermal stress for uncompromised reliability Forced Air Cooling Design

– Designed for maximum airflow in a server

– Lower GPU temperature for reliability

– Lower power consumption

Active Fan Design

– Fan works against server airflow

– GPU runs up to 30-40% hotter, increasing failure rate

– Higher power consumption

Higher data center availability and serviceability Dynamic Page Retirement

– Monitors and removes bad memory with simple reboot

N/A: Need to physically remove GPU

with bad memory

Scalable Performance Application performance across nodes GPU Direct RDMA

– Direct transfers between GPUs

– 67% lower latency

– 5X higher GPU-to-GPU MPI bandwidth

N/A
Strong scaling performance in a node NVIDIA NVLink™

– 5X higher GPU-to-GPU bandwidth

– Linear strong scaling for lots of GPUs

N/A
Deploy large models – Up to 24 GB GDDR5 for Tesla M40

– Up to 16 GB HBM2 for Tesla P100

– Up to 32 GB HBM2 for Tesla V100

4 GB to 12 GB
Data Center Ready Simplified data center operations Data Center GPU Manager

– Device management

– System diagnostics

– Cluster management

– Integrated into leading HPC management tools

N/A
Extended product availability – 3-year product lifetime

– 3-year warranty

– 10-month end-of-life notice period

Short SKU lifetime and not sold in volume
Rapid issue resolution and continuity of operations Enteprise Support

– Long-term support and maintenance

– Direct support from tech experts

– On-site consultation

N/A

Ensuring the Highest Levels of Reliability and Service for Cable and Video Streaming

A leading nationwide provider of cable television has hundreds of local area data centers or Points of Presence (POP) to support regular programming and on-demand entertainment. Each POP is unmanned and all technical glitches must be investigated and resolved within a very short time frame to ensure the highest level of service for their paying customers. The POPs contain many different types of equipment including: routers for receiving data from the Central Network Control to HQ, routers for relaying data-rich video streams to paying customers, data storage, and servers.

Could Lantronix provide the cable provider with a cost-effective remote access and management solution that would allow 24/7 access to essential equipment in the POP network and help them to ensure reliable and consistent content delivery to millions of customers?

Read our solution in this document:

Data Center and Enterprise Storage Solutions

Meeting the Priorities and Challenges of the Data Center

Data needs to be stored, managed and transmitted across a broad range of IT infrastructures. The biggest dilemma is how to deliver greater performance, reliability, and manageability at an affordable price.

Efficiently Managing the Growth of Data

Data centers need to collect larger volumes and varieties of data. For data centers with outdated infrastructures harnessing the power of data is extremely challenging. HGST HelioSeal® Platform is ideal for enterprise and data center applications where capacity density and power efficiency are paramount. HGST SSDs provide ultra-high performance in the mission critical 24/7/365 transaction processing environments. The HGST object storage platform allows easy access and retrieval of deep-archived data. HGST solutions meet the needs of cloud service providers delivering scalability, capacity and performance.

 

 

 

 

 

 

 

 

 

HGST Data Center and Enterprise Storage Solutions

Protect against Spectre and Meltdown

Applies to multiple products

This article discusses the impact of the recently disclosed processor vulnerabilities, named “Spectre” and “Meltdown,” for Windows customers and provides resources to help keep your devices protected at home, at work, and across your enterprise.

Summary

Microsoft is aware of new vulnerabilities in hardware processors named “Spectre” and “Meltdown”. These are a newly discovered class of vulnerabilities based on a common chip architecture that, when originally designed, was created to speed up computers. The technical name is “speculative execution side-channel vulnerabilities”. You can learn more about these vulnerabilities at Google Project Zero.

Who is affected?

Affected chips include those manufactured by Intel, AMD, and ARM, which means all devices running Windows operating systems are potentially vulnerable (e.g., desktops, laptops, cloud servers, and smartphones). Devices running other operating systems such as Android, Chrome, iOS, and MacOS are also affected. We advise customers running these operating systems to seek guidance from those vendors.At this time of publication, we have not received any information to indicate that these vulnerabilities have been used to attack customers.

Protections Microsoft provided to date

As of January 3, 2018, Microsoft released several updates to help mitigate these vulnerabilities and help protect customers. We have also deployed updates to secure our cloud services and Internet Explorer and Microsoft Edge browsers. We are continuing to work closely with industry partners including chip makers, device manufacturers, and app vendors.

What steps should I take to protect my devices?

You will need to update both your hardware and your software to address this vulnerability. This includes firmware updates from device manufacturers and, in some cases, updates to your antivirus software as well.

To receive all available protections, follow these steps to get the latest updates for both software and hardware:

Note
Before your begin, make sure your antivirus (AV) software is up to date and compatible. Check your antivirus software manufacturer’s website for their latest compatibility information.

  1. Keep your Windows device up to date by turning on automatic updates.
  2. Check that you’ve installed the January 2018 Windows operating system security update from Microsoft. If automatic updates are turned on, the updates should be automatically delivered to you, but you should still confirm that they’re installed.
  3. Install available hardware (firmware) updates from your device manufacturer. All customers will need to check with their device manufacturer to download and install their device specific hardware update. If you have questions regarding the available firmware updates, contact Chip ICT Support, based on the serialnumber we can provide you with the needed information.

Note
Customers who only install the January 2018 Windows operating system security updates from Microsoft will not be fully protected against the vulnerabilities. Antivirus software updates should be installed first. Operating system and firmware updates should follow.

 

Intel® Optane™ Memory

Revolutionizing Memory and Storage

Intel® Optane™ technology provides an unparalleled combination of high throughput, low latency, high quality of service, and high endurance. Check out the video to see how new computer architectures are unleashing unprecedented possibilities from data center to desktop.

 

Intel® Optane™ Technology

This technology is a unique combination of 3D XPoint™ memory media, Intel Memory and Storage Controllers, Intel Interconnect IP and Intel® software. Together these building blocks deliver a revolutionary leap forward in decreasing latency and accelerating systems for workloads demanding large capacity and fast storage.

Flexible Capabilities

From system acceleration and fast caching to storage and memory expansion, new possibilities and insights are here.  We’re driving fundamental change in computer architecture for consumers, business, and data centers around the world.

Enterprise to Desktop

It’s technology that drives innovation and experiences. Retailers might more quickly identify fraud detection patterns. Financial institutions may speed trading. Healthcare researchers could work with even larger data sets in real-time. And at home, Intel® Optane™ technology can optimize PC experiences from interactive social media to immersive gaming.

 

BUSINESSline L3372 *Optane*

  •  Application: Home & Office-PC Education
  • Processor: Intel Core i3-7100
  • Chipset: Intel B250
  • Memory: 4 GB
  • Storage capacity: 1 TB
 

BUSINESSline S1731 *Optane*

  •  Application: Home & Office-PC Digital Signage Education
  • Processor: Intel Core i3-7100U
  • Chipset: integrated
  • Memory: 4 GB
  • Storage capacity: 1 TB
 

BUSINESSline S1771 *Optane*

  •  Application: Home & Office-PC Digital Signage Education
  • Processor: Intel Core i7-7567U
  • Chipset: integrated
  • Memory: 8 GB
  • Storage capacity: 2 TB
 

BUSINESSline S1751 *Optane*

  •  Application: Home & Office-PC Digital Signage Education
  • Processor: Intel Core i5-7260U
  • Chipset: integrated
  • Memory: 8 GB
  • Storage capacity: 1 TB

 

New in our Portfolio: HGST ActiveScale Systems

As official HGST Enterprise partner, Chip ICT has adopted the ActiveScale™ portfolio.

ActiveScale P100

ActiveScale Cloud Management

ActiveScale X100

Modular Object Storage System Scaling Up From 720TB To Over 19PB, So You Can Keep Up With Data Growth, Storage Management at Petabyte Scale, And Deliver On Business Objectives Monitoring And Storage Analytics For ActiveScale Systems Via A Cloud Interface Lets You Get Ahead of Events Before They Become Problems Integrated Object Storage System Scaling From 840TB To Over 52PB, Delivering Outstanding Data Consistency, Availability, And Durability For Building World-Class Cloud Infrastructure

NVMe-oF™ (NVM Express™ over Fabrics)

NVM Express (NVMe™) – Non-Volatile Memory Express is a communications interface/protocol developed specially for SSDs. Designed to take advantage of the unique properties of pipeline-rich, random access, memory-based storage, NVMe reduces latency and provide faster CPU to data storage device performance.

Itis a new and innovative method of accessing storage media and has been capturing the imagination of data center professionals worldwide. NVMe is an alternative to the Small Computer System Interface (SCSI) standard for connecting and transferring data between a host and a peripheral target storage device or system. SCSI became a standard in 1986, when hard disk drives (HDDs) and tape were the primary storage media. NVMe is designed for use with faster media, such as solid-state drives (SSDs) and post-flash memory-based technologies. NVMe provides a streamlined register interface and command set to reduce the I/O stack’s CPU overhead by directly accessing the PCIe bus. Benefits of NVMe-based storage drives include lower latency, deep parallelism and higher performance.

What is NVME over Fabrics (NVMe-oF™)?

NVMe over Fabrics (NVMe-oF™) enables the use of alternate transports to PCIe to extend the distance over which an NVMe host device and an NVMe storage drive or subsystem can connect. NVMe-oF™ defines a common architecture that supports a range of storage networking fabrics for NVMe block storage protocol over a storage networking fabric. This includes enabling a front-side interface into storage systems, scaling out to large numbers of NVMe devices and extending the distance within a datacenter over which NVMe devices and NVMe subsystems can be accessed.

NVMe-oF™ is designed to extend NVMe onto fabrics such as Ethernet, Fibre Channel, and InfiniBand.

New: Intel Xeon W Processor Family

After the succesfull launch of the Intel Scalable Processor Series earlier this year, Intel now has unveiled their latest Processor Family: Intel Xeon W.

This New CPU series is designed for Single Socket Professional Workstations.

The new Xeon W family is not based on the Xeon Scalable Processor design.

The Xeon W range’s flagship model is the Xeon W-2195 which includes 18 cores and 36 threads (18c/32t) running at a 2.3GHz base frequency and 4.3GHz turbo frequency, 24.75MB of unified cache, and a 140W thermal design profile (TDP).

The entry point, meanwhile, is the Xeon W-2123, which is a four-core eight-thread (4c/8t) part running at 3.6GHz base and 3.9GHz turbo with 8.25MB of cache in a 120W TDP.

From there the models go to 6c/12t, 8c/16t, and 10c/20t.

Each supports up to 512GB of DDR4 memory across four memory channels with ECC support, includes 48 PCI Express lanes

 

 

 

 

 

 

 

 

 

 

 

 

GPU Computing, the basics:

GPU-accelerated computing is the use of a Graphics Processing Unit (GPU) together with a CPU to accelerate deep learning, analytics, and engineering applications. Pioneered in 2007 by NVIDIA, GPU accelerators now power energy-efficient data centers in government labs, universities, enterprises, and small-and-medium businesses around the world. They play a huge role in accelerating applications in platforms ranging from artificial intelligence to cars, drones, and robots.

HOW GPU’s ACCELERATE SOFTWARE APPLICATIONS

GPU-accelerated computing offloads compute-intensive portions of the application to the GPU, while the remainder of the code still runs on the CPU. From a user’s perspective, applications simply run much faster.

How GPU Acceleration Works

GPU versus CPU Performance

A simple way to understand the difference between a GPU and a CPU is to compare how they process tasks. A CPU consists of a few cores optimized for sequential serial processing while a GPU has a massively parallel architecture consisting of thousands of smaller, more efficient cores designed for handling multiple tasks simultaneously.

 GPUs have thousands of cores to process parallel workloads efficiently
GPU versus GPU: Which is better?

Check out the video clip below for an entertaining GPU versus CPU comparisson


Video: Mythbusters Demo: GPU vs CPU (01:34)