, , , ,

Pollara 400

The Ultra Ethernet Consortium (UEC) has delayed release of the version 1.0 of specification from Q3 2024 to Q1 2025, but it looks like AMD is ready to announce an actual network interface card for AI datacenters that is ready to be deployed into Ultra Ethernet datacenters. The new unit is the AMD Pensando Pollara 400, which promises an up to six times performance boost for AI workloads. In edge deployments, running a firewall directly on the NIC allows for more efficient security enforcement, where system resources may be limited. Using the NIC for firewall tasks frees up CPU cores, allowing your system to scale more efficiently without degrading performance as traffic volumes increase.

The AMD Pensando Pollara 400 is a 400 GbE Ultra Ethernet card based on a processor designed by the company’s Pensando unit. The network processor features a processor with a programmable hardware pipeline, programmable RDMA transport, programmable congestion control, and communication library acceleration. The NIC will sample in the fourth quarter and will be commercially available in the first half of 2025, just after the Ultra Ethernet Consortium formally publishes the UEC 1.0 specification. Businesses can implement NIC-based firewalling to manage traffic across VLANs or isolated network segments, enhancing network security without the need for dedicated firewall hardware.

Pollara 400

The AMD Pensando Pollara 400 AI NIC is designed to optimize AI and HPC networking through several advanced capabilities. One of its key features is intelligent multipathing, which dynamically distributes data packets across optimal routes, preventing network congestion and improving overall efficiency. The NIC also includes path-aware congestion control, which reroutes data away from temporarily congested paths to ensure continuous high-speed data flow.

The AMD Pensando Pollara 400 AI NIC supports advanced programmability and can be integrated with a development kit that is available for free. The AMD Pensando Software-in-Silicon Development Kit (SSDK) provides a robust environment for building and deploying applications directly on the NIC, allowing you to offload networking, firewall, encryption, and even AI inference tasks from the CPU.

The SSDK supports programming in P416 for fast path operations, as well as C and C++ for more traditional processing tasks. It provides full support for network and security functions like firewalling, IPsec, and NAT, allowing these to be handled directly by the NIC rather than the host CPU. Developers can use the provided reference pipelines and code samples to quickly get started with firewall implementations or other network services.

The SDK and related tools are open and accessible via GitHub and AMD’s official developer portals, enabling developers to experiment with and integrate Pensando’s NICs into their systems without licensing fees. Some repositories and tools are available directly on GitHub under AMD Pensando’s.

The delay in the release of the Ultra Ethernet Consortium’s (UEC) version 1.0 specification, initially expected in the third quarter of 2024 and now pushed to the first quarter of 2025, does little to shake the confidence of those observing AMD’s bold march forward. While others may have stumbled, AMD stands ready to unveil a fully realized network interface card (NIC) for AI datacenters—the AMD Pensando Pollara 400—an innovation poised to redefine the landscape of Ultra Ethernet data centers. This NIC, a formidable 400 GbE unit, embodies the very pinnacle of technological advancement. Designed by AMD’s Pensando unit, it promises no less than a sixfold increase in AI workload performance.

The Pollara 400’s impact goes beyond sheer processing power. At the edge, where resources are scarce and security paramount, the NIC performs firewall tasks directly, relieving the central processing unit from such burdensome duties. Herein lies its genius: by offloading these critical tasks, system scalability is enhanced, enabling traffic to flow unhindered and system performance to remain steady, even under mounting demands.

As we await the final specifications from the UEC, AMD has announced that the Pollara 400 will be available for sampling by the fourth quarter of 2024, with commercial deployment anticipated in early 2025. It is no mere stopgap solution—it is a harbinger of a new era in AI networking, built upon a programmable hardware pipeline capable of handling RDMA transport, congestion control, and advanced communication library acceleration.

Furthermore, the NIC’s intelligent multipathing is a feat of engineering brilliance. With its path-aware congestion control, this marvel dynamically directs data around congested network routes, ensuring that AI workloads are never hampered by the bottlenecks that so often plague high-performance computing.

The Pollara 400 is more than just hardware; it is an ecosystem supported by the AMD Pensando Software-in-Silicon Development Kit (SSDK), a free and versatile tool that allows developers to fully leverage its capabilities. Whether programming in P416 for high-speed operations or using C and C++ for more traditional tasks, developers can easily deploy firewalls, IPsec, and NAT directly onto the NIC itself, bypassing the need for traditional CPU involvement.

The SSDK provides not only the means but also the guidance to streamline development. From pre-built reference pipelines to comprehensive code samples, it invites developers to embrace the future of network security and AI processing, all while maintaining openness and accessibility via AMD’s repositories on GitHub. This is no longer just the work of a single company—it is a shared endeavor, opening new frontiers for those bold enough to explore them.

Thus, as AMD prepares to thrust the Pollara 400 into the spotlight, one thing becomes abundantly clear: the future of AI networking will not be forged in the server rooms of yesterday but at the cutting edge of what is possible, where firewalls, encryption, and AI tasks are handled in stride by a NIC that rewrites the rules.

Story By

Skeeter Wesinger

October 11, 2024

 

https://www.linkedin.com/pulse/amd-pensando-pollara-400-skeeter-wesinger-yulwe

/by
, , , , ,

Living off the Land (LotL)

If it sounds like a spy novel, then it might just be true. Living off the Land (LotL) has become the first weapon in the new Cold War, this time between the United States and the People’s Republic of China. This modern battlefield is fought not with tanks or missiles but through the subtle, insidious operations of cyber espionage. It is a war where the battlefield is the internet, and the combatants are not soldiers but bots—small, autonomous programs acting as the foot soldiers of nation-state-sponsored operations.

These bots infiltrate corporate networks with surgical precision, using disguised communications to siphon off critical data and metadata. Unlike overt attacks that trigger alarms and demand immediate responses, these bots slip under the radar, blending seamlessly into the everyday digital traffic of a company. Their presence is not felt, their actions not seen, often for long stretches of time—weeks, months, or even years—until the damage is done.

And the damage, when it finally becomes clear, is catastrophic. Intellectual property is stolen, financial systems are compromised, and sensitive data leaks into the hands of foreign adversaries. The consequences of these attacks stretch far beyond individual companies, threatening the security and economic stability of nations. This new cold war is not fought on the ground but in the unseen spaces of cyberspace, where vigilance is the only defense.

A bot, once embedded within a company’s systems, begins its covert mission. It is a malicious program, programmed with a singular purpose: to relay the company’s most guarded secrets to its unseen master. But its greatest weapon is not brute force or direct confrontation; it is stealth. These bots conceal their communication within the very lifeblood of corporate networks—normal, everyday traffic. Disguised as benign emails, mundane web traffic, or encrypted transmissions that mimic legitimate corporate exchanges, they send stolen information back to their creators without raising suspicion. What appears to be routine data passing through the system is, in fact, a betrayal unfolding in real time.

Their quarry is not just the obvious treasures—financial records, intellectual property, or proprietary designs. The bots are after something less tangible but no less valuable: metadata. The seemingly trivial details about the data—who sent it, when, from where—might appear inconsequential at first glance. But in the hands of a skilled adversary, metadata becomes a road map to the company’s inner workings. It reveals patterns, weaknesses, and, critically, the pathways to deeper infiltration.

For the corporation targeted by such an attack, the consequences are manifold. There is, of course, the potential loss of intellectual property—the crown jewels of any enterprise. Plans, designs, and trade secrets—each a piece of the company’s competitive edge—can be stolen and replicated by rivals. Financial information, once in the wrong hands, can result in fraud, a hemorrhage of funds that can cripple a company’s operations.

Perhaps the most dangerous aspect of these attacks is that compromised security extends beyond the initial theft. Once attackers have a firm grasp of a company’s systems through stolen metadata, they possess a detailed map of its vulnerabilities. They know where to strike next. And when they do, the company’s defenses, having already been breached once, may crumble further. What begins as a single act of theft quickly escalates into a full-scale infiltration.

And then, of course, there is the reputation damage. In the modern marketplace, trust is currency. When customers or clients discover their data has been stolen, they do not hesitate to seek alternatives. The collapse of faith in a company’s ability to safeguard its information can lead to long-term harm, far more difficult to recover from than the financial blow. The loss of reputation is a slow bleed, often fatal.

In short, these disguised communications are the perfect cover for botnet activities, allowing attackers to slip past defenses unnoticed. And when the theft is finally uncovered—if it is ever uncovered—it is often too late. The stolen data has already been transferred, the secrets already sold. The damage, irreversible.

I am reminded of a particular case, an incident that unfolded with a certain sense of inevitability. A seemingly reputable bank auditor, entrusted with sensitive client documents, calmly removed them from the premises one afternoon, claiming a simple lunch break. Upon returning, security, perhaps acting on an inkling of suspicion, inspected the bag. Inside, the documents—marked confidential—lay exposed. The auditor, caught red-handed, was promptly denied further access, and the documents seized. But, alas, the harm had already been done. Trust had been violated, and in that violation, the company learned a hard lesson: Never trust without verifying.

Such is the nature of modern-day espionage—not just a battle of information, but of vigilance. And in this game, those who are too trusting, too complacent, will find themselves outmatched, their vulnerabilities laid bare.

Story by Skeeter Wesinger

September 23, 2024

/by
, , , ,

Did you get hacked?

A Large corporation with a well-funded cyber security team recently found out they’d been hacked! Their opponents used the combination of Living off the Land (LotL) techniques, fileless malware, legitimate credentials, and disguised communication makes these types of botnet activities incredibly difficult to detect, even for their expert tiger teams. Without the right focus on behavioral analysis, memory forensics, and network monitoring, even highly skilled teams could miss the subtle signs of this advanced form of attack.

If your teams are looking for traditional malware or malicious executables, they might not have focused on monitoring the activities of legitimate tools. Attackers are now using these tools can camouflage their actions to blend in with normal system administration tasks, so even if your tiger teams were monitoring system processes, the malicious use of these tools could easily go unnoticed.

One of the core advantages of LotL is the use of fileless techniques, which means that the attackers often don’t drop detectable malware on the system’s disk. Instead, they execute code directly in memory or utilize scripting environments like PowerShell. This method leaves behind little to no trace that traditional malware-detection tools or endpoint security would recognize.

The teams may have been conducting disk-based or signature-based analysis, which would be ineffective against fileless malware. Without leaving artifacts on the disk, the attackers bypass traditional endpoint detection, which would have been a major focus of the teams.
Since most of the activity occurs in memory, it would require deep memory forensics to uncover these types of attacks. If the tiger teams didn’t perform real-time memory analysis or use sophisticated memory forensics tools, they could miss the attack entirely.

Story By Skeeter Wesinger

September 19, 2024

/by
,

BitLocker

BitLocker, Microsoft’s encryption software for SSDs, has faced various challenges since its debut. The upcoming Windows 11 version 24H2 update, also known as the 2024 update, may introduce a new concern for users: BitLocker could be enabled by default during the installation process for all editions of Windows, including the Home edition. This information comes from a report by the German news outlet Deskmodder, which was subsequently covered by Neowin. Enabling BitLocker by default is seen as problematic for several reasons outlined below.

Firstly, enabling BitLocker, which encrypts and decrypts data continuously on your SSD, can significantly decrease your PC’s performance. Specifically, it could slow down system performance by up to 45% in Windows Pro, with similar impacts likely on other versions of the operating system.

Secondly, there is a risk for users who are not familiar with encryption. They might end up encrypting their data unintentionally during installation and could face difficulties decrypting it later if they misplace or fail to save the necessary decryption key. This could render both the CPU and the SSD inaccessible.

A third concern highlighted involves security vulnerabilities in BitLocker. According to YouTuber Stacksmashing, BitLocker’s encryption can be easily breached. They demonstrate that with a modest investment in a $10 Raspberry Pi Pico and physical access to the machine, encrypted data on a system with an external Trusted Platform Module (TPM) can be decrypted.

However, there is a straightforward remedy for this automatic encryption: users can disable Device Encryption in the Privacy & security section of the Settings menu. While this option exists, many Windows 11 users, particularly those with the Home version, may not be aware of it or know how to manage these settings.

If these reports are accurate, it would be prudent for Microsoft to reconsider the default auto-encryption feature before releasing the update. Such a feature seems to introduce more problems than it resolves.

/by

Intel 24-Core i9-14900 32GB RAM

Mini Desktop Intel 24-Core i9-14900, 32GB RAM, 1TB SSD, WiFi, Windows 11, Micro Workstation Computer
Great price; email us for a quote:

/by