Artificial intelligence chip developer, Habana Labs, just laid off over 10% of its workforce, just as Intel plans to layoff up to 20% of its employees.
Intel’s Habana Labs Cuts Over 10% Of Workforce!
Intel acquired artificial intelligence chip developer Habana Labs in 2019 for $2 billion. The acquisition allowed Habana Labs to rapidly increase its workforce from 180 people to over 900.
That breakneck expansion has not only come to a shuddering halt, it is being reversed – Habana Labs is laying off 100 of their employees. According to an Intel statement:
Habana Labs assesses and updates its technical and business focus from time to time in order to adapt to the current business reality and to continue and improve its competitiveness.
As part of these processes, it makes adjustments to its workforce and the balance between different disciplines from time to time. This is a normal process which occurs constantly and allows Habana to continue and develop attractive and competitive products and solutions.
Habana Labs was founded by David Dahan and Ran Halutz in San Jose in 2016, for the purpose of developing processors optimised for Artificial Intelligence (AI) applications.
Both Dahan and Halutz were former executives of PrimeSense Limited, which was acquired by Apple for $360 million in 2013. Its first investor and chairman was Israeli tech entrepreneur Avigdor Willenz.
Gartner recently announced that worldwide PC shipments only totalled 68 million units in the third quarter of 2022 – a 19.5% drop from a year ago. This was the steepest market decline it recorded since it started tracking the market in the mid-1990s.
Please Support My Work!
Support my work through a bank transfer / PayPal / credit card!
Did China successfully fabricate 7nm chips, despite US sanctions on advanced chip manufacturing technology?
Well, yes, but not quite. Here is what you need to know about China’s mysterious 7nm chips!
China Made 7nm Chips In Spite Of US Sanctions!
A TechInsights report recently concluded that China has successfully created 7nm chips since last year.
This caused quite a ruckus, because it essentially meant that China jumped two generations ahead in chip manufacturing technology!
The TechInsights team bought a MinerVa mining ASIC which used a custom chip that has been manufactured by China’s SMIC since July 2021.
When they examined the chip, they discovered that it was fabricated on a 7nm process that appears to be a “close copy” of a 7nm process used by TSMC – the Taiwanese foundry giant.
The MinerVa chip is small – at just 19.3 mm², with 120 chips populating the MinerVa board. Each mining ASIC has 3 of these boards, for a total of 360 chips and a total power consumption of 3300 watts.
This discovery is deeply concerning to many people, because it meant that China has more advanced chip manufacturing technology than is even available in the United States or EU.
After all, US sanctioned the sale of advanced chip manufacturing technology to China – which was meant to crippled China’s ability to manufacture such chips.
US Senate Majority Leader Chuck Schumer used this report to stress the danger of delaying the $50 billion subsidy package for semiconductor manufacturing in the United States.
Members of both sides know that America’s chips crisis is sending shock waves across the economy.
It is endangering our national security. […] China’s top chips maker has now likely advanced its tech by two generations, threatening U.S. competitiveness.
But the situation really isn’t as dire as many people make it out to be…
SMIC / China Barely Made Those 7nm Chips
After the report was released, the Internet fell into two main camps – American politicians and China hawks bemoaning the “loss” of Western chip making advantage, and pro-CCP netizens celebrating it.
First, let me start by congratulating China / SMIC on achieving this feat despite being hobbled by US sanctions on crucial chipmaking technology.
Whether China / SMIC “copied / stole / bought” the technology knowhow from TSMC whose 7nm process it closely resembles, it is still a remarkable achievement.
That said, SMIC / China barely made those 7nm chips, and here are the reasons why…
SMIC manufactured these 7nm chips using older Deep Ultraviolet Lithography (DUV) machines, instead of the state-of-art Extreme Ultraviolet Light (EUV) lithography machines made by Dutch company ASML.
This isn’t extraordinary in itself – TSMC and Samsung had much earlier developed 7nm process nodes using the older DUV machines. However, this comes at the cost of “increased process complexity and design rule restrictions“.
That is likely why the MinerVa chip is not only very small, it actually lacks SRAM (Static Random Access Memory) that is critical in processors that run our computers and smartphones.
The simpler design and small size allow SMIC to obtain sufficient workable chips, even with a poor yield. However, the cost of chip would be much higher than if it was manufactured on a higher-quality process.
So for all intents and purposes – this should be considered as a niche / prototype 7nm process, and not a true 7nm process node.
On top of that, SMIC apparently isn’t capable of producing large quantities of these 7nm chips, suggesting either a yield problem, or difficulty in scaling up.
MinerVa has not been able to deliver the mining ASICs based on these SMIC 7nm chips in large numbers. A Bitcoin mining company – Stronghold Digital Mining, for example, said that it ordered 15,000 miners from MinerVa but only received about 3,200 units as of March 2022.
For China / SMIC to present a true “threat” as far as chipmaking is concerned, it would have to be capable of manufacturing MILLIONS of chips, not thousands.
Regardless of whether the Americans are howling in despair, or the pro-CCP netizens are howling in delight, China really does not have true 7nm chipmaking capability for mass production yet.
And even if they somehow manage to improve and scale up this 7nm DUV process, they cannot make more advanced chips without EUV machines made by ASML.
As long as the Dutch government holds firm on blocking sale of ASML’s EUV machines to China, this is likely as far as they can go… unless they invade Taiwan, which is where TSMC is based and has the world’s most advanced chip manufacturing facilities.
Please Support My Work!
Support my work through a bank transfer / PayPal / credit card!
IBM just introduced the z16 system, powered by their new Telum processor with an integrated AI accelerator!
Take a look at the z16, and find out why it is the industry’s first quantum-safe system!
IBM z16 : Industry’s First Quantum-Safe System!
On 25 April 2022, IBM officially unveiled their new z16 system in Malaysia – the industry’s first quantum-safe system.
IBM Vice President for Worldwide Sales of IBM Z and LinuxONE, Jose Castano, flew to Kuala Lumpur, to give us an exclusive briefing on the new z16 system, and tell us why it is the industry’s first quantum-safe system.
IBM Z and LinuxONE Security CTO Michael Jordan also briefed us on why quantum-safe computing will be critical for enterprises, as quantum computing improves.
Thanks to its Telum processor, the IBM z16 system delivers low and consistent latency for embedding AI into response time-sensitive transactions. This can enable customers to leverage AI inference to better control the outcome of transactions before they complete.
For example, they can leverage AI inference to mitigate risk in Clearing & Settlement applications, to predict which transactions have high risk exposure, and highlight questionable transactions, to prevent costly consequences.
In a use-case example, one international bank uses AI on IBM Z as part of their credit card authorization process instead of using an off-platform inference solution. As a result, the bank can detect fraud during its credit card transaction authorisation processing.
The IBM z16 will offer better AI inference capacity, thanks to its integrated AI accelerator offering up to 1 ms of latency, expanding use cases that include :
tax fraud and organised retail theft detection
real-time payments and alternative payment methods, including cryptocurrencies
speed up business or consumer loan approvals
As the industry’s first quantum-safe system, the IBM z16 is protected by lattice-based crypto graphs – an approach for constructing security primitives that help protect data and systems against current and future threats.
IBM z16 : Powered By The New Telum Processor!
The IBM z16 is built around the new IBM Telum processor, which is specifically designed for secure processing, and real-time AI inference.
Here are the key features of the IBM Telum processor that powers the new IBM z16 system :
Fabricated on the 7 nm process technology
Has 8 processor cores, clocked at over 5 GHz
Each processor core has a dedicated 32 MB private L2 cache
The eight 32 MB L2 cache can form a virtual 256 MB L3 cache, and a 2 GB L4 cache.
Transparent encryption of main memory, with 8-channel fault tolerant memory interface
Integrated AI accelerator with 6 TFLOPS compute capacity
Centralised AI accelerator architecture, with direct connection to the cache infrastructure
The Telum processor is designed to enable extremely low latency inference for response-time sensitive workloads. With planned system support for up to 200 TFLOPs, the AI acceleration is also designed to scale up to the requirements of the most demanding workloads.
Thanks to the Telum processor, the IBM z16 can process 300 billion inference requests per day, with just one millisecond of latency.
Please Support My Work!
Support my work through a bank transfer / PayPal / credit card!
Intel joined over 600 other companies in condemning and leaving Russia over its invasion of Ukraine!
Here is what you need to know…
Intel Condemned Russia Over Invasion Of Ukraine!
A week after Russia invaded Ukraine, Intel issued a press release condemning the invasion, and announcing a stop to all shipments to both Russia and Belarus.
While Belarus did not directly participate in the Russian invasion of Ukraine, it continues to be a willing partner in the invasion, allowing Russian troops, tanks and aircraft to attack Ukraine from their territory.
This announcement on 3 March 2022 effectively cut off supply of Intel chips to both countries.
Intel condemns the invasion of Ukraine by Russia and we have suspended all shipments to customers in both Russia and Belarus. Our thoughts are with everyone who has been impacted by this war, including the people of Ukraine and the surrounding countries and all those around the world with family, friends and loved ones in the region.
We are working to support all of our employees through this difficult situation, especially those with close ties to this region. We have launched an employee donation and matching campaign through the Intel Foundation that has already raised over $1.2 million for relief efforts, and we are proud of the work our teams in surrounding areas including Poland, Germany and Romania are doing to aid refugees. We will continue to stand with the people of Ukraine and the global community in calling for an immediate end to this war and a swift return to peace.
Intel Leaves Russia Over Invasion Of Ukraine!
After Russia’s initial attempt to seize Kyiv and topple the Ukrainian government failed spectacularly, Russian forces began a wholesale bombardment of Ukrainian cities.
Even worse, it was recently discovered that Russian forces raped and massacred Ukrainian civilians in the town of Bucha.
All those atrocities may have made it untenable for companies like Intel to even maintain a local presence while waiting out the war.
On 5 April 2022, Intel announced that they immediately suspended all business operations in Russia.
It is unknown what will happen to their 1,200 employees in Russia, but Intel says that it is now working to support those employees.
Intel continues to join the global community in condemning Russia’s war against Ukraine and calling for a swift return to peace. Effective immediately, we have suspended all business operations in Russia. This follows our earlier decision to suspend all shipments to customers in Russia and Belarus.
Our thoughts are with everyone who has been impacted by this war, particularly the people of Ukraine and the surrounding countries and all those around the world with family, friends and loved ones in the region.
We are working to support all of our employees through this difficult situation, including our 1,200 employees in Russia. We have also implemented business continuity measures to minimize disruption to our global operations.
The new mobile processors also uses a single, monolithic die, which eliminates the I/O latency between dies.
Placeholder : AMD Ryzen PRO 5000 tech briefing video coming soon!
In addition to its improved performance, the AMD Ryzen PRO 5000 mobile processors also come with these AMD PRO technologies :
AMD PRO security provides a multi-layered approach to security features by embedding defenses at every level, from silicon through operating system.
– AMD Memory Guard, automatically enabled on Microsoft Secured-Core PCs, helps enable data and identity protection, while
– AMD Shadow Stack helps provide hardware enabled protection against malware attacks.
AMD PRO manageability enables a full manageability feature set for simplified deployment, imaging and management that is compatible with modern IT infrastructures.
AMD Ryzen PRO processors offer full support for Microsoft Endpoint Manager to deliver a flexible and integrated cloud management solution.
AMD PRO business ready technologies bring enterprise-grade computing solutions designed for quality and reliability, in addition to platform longevity.
AMD Ryzen PRO processors feature 18-months of planned software stability and 24-months of planned availability.
AMD Ryzen PRO 5000 : Models + Specifications
AMD announced three Ryzen PRO 5000 models to replace the three Ryzen PRO 4000 models from last year.
Ryzen 7 PRO 5850U : 8C/16T | 15W | 1.9 to 4.4 GHz | 20 MB cache
Ryzen 5 PRO 5650U : 6C/12T | 15W | 2.3 to 4.2 GHz | 19 MB cache
Ryzen 3 PRO 5450U : 4C/8T | 15W | 2.6 to 4.0 GHz | 10 MB cache
For easier comparison, here is a table comparing their key specifications :
Cores / Threads
8 / 16
6 / 12
4 / 8
AMD Ryzen PRO 5000 : Availability
According to AMD, enterprise customers will be able to purchase the new Ryzen PRO 5000 laptops from top PC vendors like HP and Lenovo starting in Q2, 2021.
On the other hand, AMD reused the chiplet design, with one or two CCDs (fabricated on 7 nm) paired with a 12 nm IOD (I/O Die).
Reads from CCD to IO are still 2X write, to conserve die area and transistor budget. And it uses the same IOD from Matisse (Zen 2).
AMD Zen 3 Transistor Count + Die Size
The new Zen 3 CCD has 4.15 billion transistors, with a die size of 80.7 mm². That’s up from the 3.8 billion transistors and a die size of 74 mm² for the Zen 2 CCD.
The Matisse-era IOD remains the same – 2.09 billion transistors, with a die size of 125 mm².
They will both be manufactured using the same 7 nm TSMC process for CCD, and 12 nm Global Foundries process for IOD.
7 nm TSMC
12 nm GoFlo
AMD Zen 3 Precision Boost : No Change
Precision Boost 2 in Zen 3 remains the same as that of Zen 2, just with higher frequencies to “play with”.
It is an opportunistic boost algorithm that drives the loaded cores to the highest possible frequency, until it hits any one of these limits :
VRM thermal limit
VRM current limit
maximum clock speed
Precision Boost 2 will dynamically analyse and boost or dither the core clock speeds every 1 ms using the Infinity Fabric command and control functions.
In this example of the new Ryzen 9 5900X with a base clock of 3.7 GHz and a boost clock of 4.8 GHz, Precision Boost 2 will typically result in frequencies of 4.4 GHz to 4.6 GHz, even with 24 threads running at the same time.
AMD Zen 3 Voltage Range : No Change
Despite the changes in the microarchitecture and SoC design, Zen 3 processors will continue to be engineered with the same voltage range as Zen- and Zen 2-based processors.
The typical voltage range will vary according to usage, but basically, Zen 3 processors, like the Ryzen 5000 series, will support 0.2 V to 1.5 V.
AMD Zen 3 Temperature Range : No Change
AMD Zen 3-based processors will also have the same temperature ranges as Zen- and Zen 2-based processors.
Note : The temperature range below assumes an enclosed chassis, and an air-conditioned room.
Even at 4K, CPU performance mattered in Ashes of the Singularity. The Ryzen 9 5950X delivered just 2% higher frame rates than the Ryzen 7 5800X, and 14% higher frame rates than both the Core i7-8700K and the Ryzen 7 3700X.
AMD just introduced the Ryzen 7 3700C, Ryzen 5 3500C and Ryzen 3 3250C mobile processors with Radeon Graphics!
Here is what you need to know about the new AMD Ryzen 3000 C-Series mobile APUs!
Ryzen 7 3700C | Ryzen 5 3500C | Ryzen 3 3250C : Chromebooks Get A Boost!
The three new AMD Ryzen 3000 C-Series mobile processors come with integrated Radeon Graphics cores. That makes them APUs, instead of pure processors.
Built on the older Zen+ or Zen architecture and fabricated on the 12 nm or 14 nm process technology, they are designed as premium APUs for Chromebooks.
At launch, AMD is introducing three Ryzen 3000 C-Series processors, with a 15 W TDP :
AMD Ryzen 7 3700C : 4C/8T | up to 4.0 GHz | 6 MB cache | 10 graphics cores
AMD Ryzen 5 3500C : 4C/8T | up to 3.7 GHz | 6 MB cache | 8 graphics cores
AMD Ryzen 3 3250C : 2C/4T | up to 3.5 GHz | 5 MB cache | 3 graphics cores
These Ryzen 3000 C-Series processors will be used in premium Chromebook laptops, offering significantly better performance than the old AMD A-Series APUs, and better performance than the AMD Ryzen 3000 C-Series processors.
Although they are not part of these processors, Chromebooks based on the AMD Ryzen 3000 C-Series will feature Wi-Fi 6 and Bluetooth 5 connectivity.
The AMD A-Series APUs, with a 6 W TDP, will continue to ship in entry-level Chromebooks.
AMD Ryzen Threadripper PRO : Official Tech Briefing!
AMD Ryzen Threadripper PRO : Available Models
As of today’s launch, AMD is launching only these four processor models :
AMD Ryzen Threadripper PRO 3995WX
This is the flagship, with 64 cores capable of processing up to 128 threads simultaneously. It comes with 288 MB of L2 and L3 caches, a 2.7 GHz base clock and a 4.2 GHz boost clock, with a 280 W TDP.
AMD Ryzen Threadripper PRO 3975WX
This processor has 32 cores with the ability to process up to 64 threads simultaneously. It comes with 144 MB of L2 and L3 caches, a 3.5 GHz base clock and a 4.2 GHz boost clock, with a 280 W TDP.
AMD Ryzen Threadripper PRO 3955WX
This processor has 16 cores with the ability to process up to 32 threads simultaneously. It comes with 72 MB of L2 and L3 caches, a 3.9 GHz base clock and a 4.3 GHz boost clock, with a 280 W TDP.
AMD Ryzen Threadripper PRO 3945WX
This processor has 12 cores with the ability to process up to 24 threads simultaneously. It comes with 70 MB of L2 and L3 caches, a 4.0 GHz base clock and a 4.3 GHz boost clock, with a 280 W TDP.
There Is No Threadripper PRO 3965WX
Although earlier rumoured, this 24-core, 48-thread processor will not be released, at least not on 14 July 2020.
AMD Ryzen Threadripper PRO : Specifications
In this table, we compare the key specifications of the four processor models :
7 nm (CPU) + 12 nm (I/O)
Cores / Threads
64 / 128
32 / 64
16 / 32
12 / 24
8 x DDR4-3200 channels 2 TB maximum
128 x PCIe Gen 4 lanes
AMD Ryzen Threadripper PRO : Performance
Threadripper PRO 3945WX
According to AMD, the “baby” of the family will offer 12% better single-threaded performance in CINEBENCH R20, and 28% better multi-threaded performance than a competing 12-core Intel Xeon processor.
They say that this is targeted at those whose software is licensed on a per-core basis. Its high performance per core will allow for better performance, without resorting to more cores and corresponding licence fees.
Threadripper PRO 3955WX
AMD also showed how the 16-core 3955WX can render 14% faster than an 18-core Intel Xeon processor.
Threadripper PRO 3995WX
AMD compared the flagship Threadripper PRO 3995WX with its 64 cores against two Intel Xeon Platinum 8280 processors, with 56 cores.
In the SPECviewperf13 benchmark, that 8-core, 16-thread advantage gave the 3995WX a performance advantage between 4% and 37%.
Assassin’s Creed Valhalla – the upcoming AAA game from Ubisoft – will be FREE with the purchase of selected AMD Ryzen CPUs! Here are the details!
Assassin’s Creed Valhalla : A Quick Primer!
Assassin’s Creed Valhalla is an upcoming action role-playing video game by Ubisoft, the twelfth major installment and the successor to the 2018 game Assassin’s Creed Odyssey.
Become Eivor, a Viking raider raised to be a fearless warrior, and lead your clan from icy desolation in Norway to a new home amid the lush farmlands of ninth-century England. Find your settlement and conquer this hostile land by any means to earn a place in Valhalla.
England in the age of the Vikings is a fractured nation of petty lords and warring kingdoms. Beneath the chaos lies a rich and untamed land waiting for a new conqueror. Will it be you?
Write Your Viking Saga
Blaze your own path across England with advanced RPG mechanics. Fight brutal battles, lead fiery raids or use strategy and alliances with other leaders to bring victory. Every choice you make in combat and conversation is another step on the path to greatness.
Lead Epic Raids
Lead a crew of raiders and launch lightning-fast surprise attacks against Saxon armies and fortresses. Claim the riches of your enemies’ lands for your clan and expand your influence far beyond your growing settlement.
Engage In Visceral Combat
Unleash the ruthless fighting style of a Viking warrior as you dual-wield axes, swords, or even shields against relentless foes. Decapitate opponents in close-quarters combat, riddle them with arrows, or assassinate them with your Hidden Blade.
Grow Your Settlement
Your clan’s new home grows with your legend. Customise your settlement by building upgradable structures. Unlock new features and quests by constructing a barracks, a blacksmith, a tattoo parlour, and much more.
Share Your Custom Raider
Recruit mercenary Vikings designed by other players or create and customise your own to share online. Sit back and reap the rewards when they fight alongside your friends in their game worlds.
Assassin’s Creed Valhalla : FREE With Selected AMD Ryzen CPUs
From 7 July until 3 October 2020, you will receive a FREE copy of Assassin’s Creed Valhalla with the purchase of these AMD Ryzen processors :
The AMD Ryzen 5 3600XT (US | UK | AU | SG | MY) is a slightly faster variant of the Ryzen 5 3600X, with a better CPU cooler.
Find out how it fares against the other processors, and why it left us quite perplexed…
AMD Ryzen 3000XT : Turbocharged? Not Quite…
The Ryzen 9 3900XT, Ryzen 7 3800XT and Ryzen 5 3600XT are higher-speed variants existing 3rd Gen Ryzen processors. These XT variants are slightly different in their performance and the cooler they come with.
While the XT postfix implied these are turbocharged processors, that depends on the model :
3900XT vs 3900X : 100 MHz faster boost clock + $50 higher price tag, no Wraith Prism RGB cooler
3800XT vs 3800X : 200 MHz faster boost clocks, no Wraith Prism RGB cooler.
3600XT vs 3600X : 100 MHz faster boost clock, Wraith Spire instead of Wraith Stealth
AMD Ryzen 5 3600XT Specifications Compared!
In this table, we compare the Ryzen 5 3600XT against the Ryzen 5 3600X and Ryzen 5 3600.
7 nm (CPU) + 12 nm (I/O)
Cores / Threads
6 / 12
PCIe Gen 4 (24 lanes)
AMD Ryzen 5 3600XT : Price + Availability
Here are the official prices for the AMD Ryzen 5 3600XT (US | UK | AU | SG | MY) processor, which will be available for purchase starting 7 July 2020.
The AMD Ryzen 5 3600XT (US | UK | AU | SG | MY) comes in a large retail box, bundled with an AMD Wraith Spire cooler inside.
When you fully unbox it, this is what you will find inside :
AMD Ryzen 5 3600XT processor
AMD Wraith Spire CPU cooler
AMD Ryzen 5 case badge
AMD desktop CPU installation sheet
AMD Ryzen 5 3600XT Hands-On Experience!
The AMD Ryzen 5 3600XT (US | UK | AU | SG | MY) has six Ryzen processor cores, with a 3.8 GHz base clock, and a 4.5 GHz boost clock.
It supports SMT (simultaneous multi-threading), and can therefore handle 12 threads simultaneously. It also has a 95W TDP.
Like the previous generations, it has 512 KB L2 cache per core, with a total L2 cache size of 3 MB. But thanks to a larger transistor budget, it has a very large 32 MB L3 cache – twice that of the last-generation 2nd Gen Ryzen processors!
You can just swap out your existing 3rd Gen Ryzen processor and drop in this processor without a BIOS update. If you are upgrading an older motherboard, make sure first update its BIOS to support the 3rd Gen Ryzen processor.
Built around the Zen 2 microarchitecture, the AMD Ryzen 5 3600XT (US | UK | AU | SG | MY) uses a chiplet design which combines 7 nm and 12 nm parts to deliver a more powerful, and power-efficient processor at a great price point.
The end result is significantly better single-core and multi-core performance over previous generation Ryzen processors.
There is no doubt that this 6-core, 12-thread processor offers great performance at a great price point, with a better Wraith Spire cooler to boot.