Analysis After re-establishing itself in the datacenter over the past few years, AMD is now hoping to become a big player in the AI compute space with an expanded portfolio of chips that cover everything from the edge to the cloud.
It's quite an ambitious goal, given Nvidia's dominance in the space with its GPUs and the CUDA programming model, plus the increasing competition from Intel and several other companies.
But as executives laid out during AMD's Financial Analyst Day 2022 event last week, the resurgent chip designer believes it has the right silicon and software coming into place to pursue the wider AI space.
"Our vision here is to provide a broad technology roadmap across training and inference that touches cloud, edge and endpoint, and we can do that because we have exposure to all of those markets and all of those products," AMD CEO Lisa Su said in her opening remarks at the end.
Su admitted that it will take "a lot of work" for AMD to catch up in the AI space, but she said the market represents the company's "single highest growth opportunity."
At last week's event, AMD executives said they have started to see some early traction in the AI compute market with the company's Epyc server chips being used for inference applications and its Instinct datacenter GPUs being deployed for AI model training.
For instance, multiple cloud service providers are already using AMD's software optimizations via its ZenDNN library to provide a "very nice performance uplift" on recommendation engines using the company's Epyc CPUs, according to Dan McNamara, the head of AMD's Epyc business.
Short for Zen Deep Neural Network, ZenDNN is integrated with the popular TensorFlow and PyTorch frameworks as well as ONNXRT, and it's supported by the second and third generation of Epyc chips.
"I think it's really important to say that a large percentage of the inference is happening in CPUs, and we expect that to continue going forward," he said.
In the near future, AMD is looking to introduce more AI capabilities into CPUs at the hardware level.
This includes the AVX-512 VNNI instruction, which will be introduced to accelerate neural network processing in the next-generation Epyc chips, code-named Genoa, coming out later this year.
Since this capability is being implemented in Genoa's Zen 4 architecture, VNNI will also be present in the company's Ryzen 7000 desktop chips that are also due by the end of the year.
AMD plans to expand the AI capabilities of its CPUs future by making use of the AI engine technology from its $49 billion acquisition of FPGA designer Xilinx, which closed earlier this year.
These building blocks will appear in future chips across AMD's portfolio. Click to enlarge.
The AI engine, which falls under AMD's newly named XDNA banner of "adaptive architecture" building blocks, will be incorporated into several new products across the company's portfolio in the future.
After making its debut in Xilinx's Versal adaptive chip in 2018, the AI engine will be integrated in two future generations of Ryzen laptop chips. The first is code-named Phoenix Point and will arrive in 2023 while the second is code-named Strix Point and will arrive in 2024. The AI engine will also be used in a future generation of Epyc server chips, though AMD didn't say when that would happen.
In 2024, AMD expects to debut the first chips using its next-generation Zen 5 architecture, which will include new optimizations for AI and machine learning workloads.
As for GPUs, AMD has made some headway in the AI training space with its most recent generation of Instinct GPUs, the MI200 series, and it's hoping to make even more progress in the near future with new silicon and software improvements.
For instance, in the latest version of its ROCm GPU compute software, AMD has added optimizations for training and inference workloads running on frameworks like PyTorch and TensorFlow.
The company has also expanded ROCm support to its consumer-focused Radeon GPUs that use the RDNA architecture, according to David Wang, the head of AMD's GPU business.
"And lastly, we're developing SDKs with pre-optimized models to ease the development and deployment of AI applications," he said.
To drive adoption of its GPUs for AI purposes, Wang said AMD has developed "deep partnerships with some of the key leaders in the industry," including Microsoft and Facebook parent company Meta.
"We have optimized ROCm for PyTorch to deliver amazing, very, very competitive performance for their internal AI workloads as well as the jointly developed open-source benchmarks," he said.
Moving forward, AMD hopes to become even more competitive in the AI training space with the Instinct MI300, which it is calling the "world's first datacenter APU" as the chip combines a Zen 4-based Epyc CPU with a GPU that uses the company's new CDNA 3 architecture.
AMD is claiming that the Instinct MI300 is expected to deliver a greater than 8x boost in AI training performance over its Instinct MI250X chip that is currently in the market.
"The MI300 is a truly amazing part, and we believe it points the direction of the future of acceleration," said Forrest Norrod, head of AMD's Datacenter Solutions Business Group.
While AMD plans to use Xilinx's tech in future CPUs, the chip designer made it clear that the acquisition will also help the company cover a wider range of opportunities in the AI space and harden its software offerings. The latter is critical if AMD wants to better compete with Nvidia and others.
This was laid out by Victor Peng, Xilinx's former CEO who is now head of AMD's Adaptive and Embedded Group, which leads development for all the FPGA-based products from Xilinx's portfolio.
Before the Xilinx acquisition completed earlier this year, AMD's coverage in the AI compute space was mainly in cloud datacenters with its Epyc and Instinct chips, at enterprises with its Epyc and Ryzen pro chips, and at homes with its Ryzen and Radeon chips.
But with Xilinx's portfolio now under the AMD banner, the chip designer has much broader coverage in the AI market. This is because Xilinx's Zynq adaptive chips are used in a variety of industries, including health care and life sciences, transportation, smart retail, smart cities, and intelligent factories. Xilinx's Versal adaptive chips, on the other hand, are used by telecommunications providers. Xilinx also has Alveo accelerators and Kintex FPGAs that are used in cloud datacenters too.
With the Xilinx acquisition, AMD's products cover several industries in the AI compute space. Click to enlarge.
"We're actually in quite a bit of areas that are doing AI, mostly the inference, but, again, the heavy-duty training is happening in the cloud," Peng said.
AMD views the Xilinx products as "very complementary" with its portfolio of CPUs and GPUs. As such, the company is targeting its combined offerings for a wide spectrum of AI application needs:
"Once we start integrating AI into more of our products and we go to the next generation, we cover a tremendous more of the space across the models," Peng said.
How AMD sees CPUs, GPUs and adaptive chips covering different parts of the AI spectrum. Click to enlarge.
But if AMD wants broader industry adoption of its chips for AI purposes, the company will need to ensure that developers can easily program their applications across this menagerie of silicon.
That's why the chip designer plans to consolidate previously disparate software stacks for CPUs, GPUs and adaptive chips into one interface, which it's calling the AMD Unified AI Stack. The first version will bring together AMD's ROCm software for GPU programming, its CPU software and Xilinx's Vitis AI software to provide unified development and deployment tools for inference workloads.
Peng said the Unified AI Stack will be an ongoing development effort for AMD, which means the company plans to consolidate even more software components in the future, so that, for instance, developers only have to use one machine learning graph compiler for any chip type.
"Now people can, in the same development environment, hit any one of these target architectures. And in the next generation, we're going to unify even more of the middleware," he said.
While AMD has laid out a very ambitious strategy for AI compute, it will no doubt require a lot of heavy lifting and doing right by developers for such a strategy to work. ®
Aerospike, the value-key NoSQL database, has launched a collaboration with data connection vendor StarBurst to offer SQL access to its datastores.
Dubbed Aerospike SQL Powered by Starburst, the system hopes to offer data analysts and data scientists a single point of access to federated data in Aerospike using existing SQL analytic tools such as Tableau, Qlik, and Power BI. It is the first time Aerospike has offered an off-the-shelf tool to analyze its database using SQL, the ubiquitous database language.
Aerospike was purpose-built with a highly parallelized architecture to support real-time, data-driven applications that cost-effectively scale up and out. It claims to offer predictable sub-millisecond performance up to petabyte-scale with five-nines uptime with globally distributed, strongly consistent data.
A letter has been filed with America's communications watchdog confirming that SpaceX and OneWeb, which are building mega-constellations of broadband satellites, are content to play nicely.
The letter sweeps all the unpleasantness between the two neatly under the rug "after extensive good-faith coordination discussions." Despite what could charitably be described as snarky remarks about each other to the FCC over the years, the duo have agreed that their first-generation broadband satellite services can, after all, co-exist.
"Their respective second-round systems can also efficiently coexist with each other while protecting their respective first-round systems," the memo, dated June 13 and shared by Reuters' journo Joey Roulette today, reads.
Big Tech in America has had enough of Congress' inability to pass pending legislation that includes tens of billions of dollars in subsidies to boost semiconductor manufacturing and R&D in the country.
In a letter [PDF] sent to Senate and House leaders Wednesday, the CEOs of Alphabet, Amazon, Dell, IBM, Microsoft, Salesforce, VMware, and dozens of other tech and tech-adjacent companies urged the two chambers of Congress to reach consensus on a long-stalled bill they believe will make the US more competitive against China and other countries.
"The rest of the world is not waiting for the US to act. Our global competitors are investing in their industry, their workers, and their economies, and it is imperative that Congress act to enhance US competitiveness," said the letter.
DataStax, the database company based on the open-source Cassandra system, has secured $115 million in funding for a $1.6 billion valuation.
Led by the Growth Equity business within Goldman Sachs and backed by RCM Private Markets and EDB Investments, the latest round follows a strong first quarter based on the popularity of DataStax's Cassandra DBaaS Astra DB. Existing investors include Crosslink Capital, Meritech Capital Partners, OnePrime Capital, and others.
Cassandra is a distributed, wide-column store database suited to real-time use cases such as e-commerce and inventory management, personalization and recommendations, Internet of Things-related applications, and fraud detection. It is freely available on the Apache Version 2 license, although DataStax offers managed service Astra on a subscription model.
First-of-its-kind research on advanced driver assist systems (ADAS) involved in accidents found that one company dominated with nearly 70 percent of reported incidents: Tesla.
The data was presented by the US National Highway Traffic Safety Association (NHTSA), the conclusion of the first round of data it began gathering last year of vehicle crashes involving level 2 ADAS technology such as Tesla Autopilot. Of the 394 accidents analyzed, 270 involved Teslas with Autopilot engaged.
"New vehicle technologies have the potential to help prevent crashes, reduce crash severity and save lives, and the Department is interested in fostering technologies that are proven to do so," said NHTSA administrator Dr Steven Cliff.
Microsoft has opened its wallet once more to pick up New York-based cyber-threat analyst Miburo.
Founded by Clint Watts in 2011, Miburo is all about the detection of and response to foreign (in the context of the US) information operations. The team is to be folded into Microsoft's Customer Security and Trust organization and the work of its analysts is to be fed into the Windows giants' threat detection and analysis capabilities.
"Miburo," said Microsoft, "has become a leading expert in identification of foreign information operations." Its research teams have hunted out some nasty influence campaigns over 16 languages.
The Floppotron computer hardware orchestra has reached version 3.0. The question is, where do you even find 512 floppy disk drives? Its creator, Paweł Zadrożniak, tells all.
The Floppotron is a marvellous bit of engineering. Its tones frequent many a YouTube video (this writer was rather taken by the rendition of "Take On Me" performed by the device's second iteration) and as a repurposing of obsolete hardware, it would be hard to come up with a more imaginative approach.
The first version made its debut in 2011 and consisted of a pair of floppy drives. The device's performance of the Imperial March has clocked up 6.7 million views at time of writing.
Hewlett Packard Enterprise must pay Oracle $30 million for copyright infringement after a jury found it guilty of providing customers with Solaris software updates without Big Red's permission.
The decision, which HPE may contest, is the culmination of a three-week trial in Oakland, California. However, the case was first raised years back when Oracle claimed HPE had offered illegal updates under a scheme devised by software support provider Terix, which settled its case in 2015 for almost $58 million.
In proceedings at the start of this week, Oracle’s lawyer, Christopher Yeates of Latham & Watkins LLP, pressed the eight-person jury to award his client $72 million for HPE using software not covered by a support contract, and for pinching clients, including Comcast.
Cloud data warehouse specialist Snowflake is broadening its toolset to allow devs to build applications inside its platform, while providing a new row-based storage engine to support analytics on transactional data.
Launched at its annual conference this week, the features are part of a plan to encourage users – and investors – to no longer see it as a mere cloud data warehouse and to view it more as a platform for sharing data and data-analytics applications.
Snowflake is supporting new transactional workloads in something it calls Unistore, which is based on Hybrid Tables supported by a new row-based storage engine to better handle transactional data.
The European Commission's competition enforcer is being handed another defeat, with the EU General Court nullifying a $1.04 billion (€997 million) antitrust fine against Qualcomm.
The decision to reverse the fine is directed at the body's competition team, headed by Danish politico Margrethe Vestager, which the General Court said made "a number of procedural irregularities [which] affected Qualcomm's rights of defense and invalidate the Commission's analysis" of Qualcomm's conduct.
At issue in the original case was a series of payments Qualcomm made to Apple between 2011 and 2016, which the competition enforcer had claimed were made in order to guarantee the iPhone maker exclusively used Qualcomm chips.
Concern is growing that a World Trade Organization (WTO) moratorium on cross-border tariffs covering data may not be extended, which would hit e-commerce if countries decide to introduce such tariffs.
Representatives of the WTO's 164 members are meeting in Geneva as part of a multi-day ministerial conference. June 15 was to be the final day but the trade organization today confirmed it is being extended until June 16, to facilitate outcomes on the main issues under discussion.
The current moratorium covering e-commerce tariffs was introduced in 1998, and so far the WTO has extended it at such meetings, which typically take place every two years.
The Register - Independent news and views for the tech community. Part of Situation Publishing
Biting the hand that feeds IT © 1998–2022