David Patterson Kicks Off AI Hardware Summit Championing Domain Specific Chips

By John Russell

September 30, 2020

The 2020 AI Hardware Summit kicked off yesterday with long-time computer luminary David Patterson digging into all things TPU and extolling on how they outrun GPUs for AI needs. After presenting data in which the TPUv3 bested Nvidia’s V100, he was asked about Google’s forthcoming TPUv4 versus Nvidia A100. Expect the same kind of advantage for TPUv4, he suggested.

With that the AI Hardware Summit was off and running.

It’s a virtual conference this year with two days this week and two more next week (link to conference). Other highlights on opening day included seasoned AI watcher Karl Freund’s (senior analyst, Moor Insights and Strategy) spotlight on 2019 and 2020 accelerator trends; startups SambaNova and Groq providing glimpses into their systems; and a pair of fascinating panels – one on AI use for chip design and another on AI compiler development. There was actually a good deal more going on and it’s best to check out the agenda.

Patterson, of course, is a familiar name in computing. He’s a UC Berkeley professor, a Google distinguished engineer, and the RISC-V Foundation Vice-Chair. His work at Google on TPU development is well-known.

David Patterson

As he recalled, “Google was one of the first people to get excited about both deep neural networks, and then domain specific architectures. In 2013, they calculated that if 100 million users started doing deep neural networks, three minutes a day on CPUs, they would have to double the size of the data center. Not only would that be very expensive, that would take forever to build twice as many data centers in the cloud. So they set an emergency project whose goal was to make a factor of 10 improvement over existing CPUs and GPUs.”

To some extent the rest is history as Google developed its tensor processor unit focusing on the AI needs of Google’s workload.

“Why was it successful? First of all, it an amazing number of arithmetic units. It has 256 by 256, arithmetic units, 64,000 multiply accumulators. Secondly, that they were doing work on eight-bit integer data rather than 32-bit floating data so it can be more energy efficient and take less memory capacity and be faster. And because it was domain specific, it dropped a lot of the general-purpose features that dominate CPUs and GPUs like caches and branch predictors. This saves area and energy in lets the transistors get reused. The legacy of TPU v1 is not only its technical excellence, but the impact it made,” said Patterson.

Lots of interesting choices were made along the way, for example how many cores should the new device have. “Where we went to [for] advice is Seymour Cray…and when we asked him, he said, “If you’re plowing a field, what would you rather use to strong oxen or 1024 chickens? So we went with two strong oxen so the TPUv2 has two cores per chip so it wouldn’t have a slower clock cycle.”

In addition to presenting more detail around the TPUv1-though-TPUv3 architecture, Patterson’s talk reinforced the idea designing domain specific chips (and tools) for AI comprise an increasingly formidable approach, likening the TPU’s success to  a galvanizing proof point that’s now launching “1000 chips”.

“Let me conclude the slowing of Moore’s law means AI needs to tailor machines to be able to continue to make improvements in training and efforts. [A]ll the decisions you want to make are easier when it’s just for one domain rather than for general purpose. Despite using older technology and smaller chips, Google’s TPU v2 and v3 demonstrated a 50x performance improvement per watt versus general purpose supercomputers. I think the 2020s is a Cambrian era with all kinds of innovation, and exotic species, but which ones are going to flourish?”

Two such companies hoping to flourish are SambaNova and Groq.

SambaNova cofounder and CTO Kunle Olukotun walked briefly through its reconfigurable data flow architecture. Here’s brief excerpt from Olukotun’s remarks:

“We define a reconfigurable data flow architecture that’s optimized for data flow problems. So it takes these hierarchical pal (parallel) patterns and maps them to an architecture so they can be executed very efficiently. This is a reconfigurable architecture composed of reconfigurable compute, reconfigurable memory, and communication primitives that makes it very efficient to execute these sorts of data flow problems.

“The first incarnation of this reconfigurable Dataflow architecture is the Cardinal SN10 reconfigurable data flow unit (RDU). This is implemented in TSMC seven nanometer technology and 40 billion transistors. Over 50 kilometers of wire provide all the interconnect between the different components on the chip. It provides hundreds of teraflops of compute capability, and hundreds of megabytes of memory on chip. Just as importantly, it has different direct interfaces to terabytes of memory off chip. Architecture We’ve combined these RDU chips into systems that provide scalable performance for both training and inference. We call them data scale systems,” said Olukotun.

“When mapping data flow applications to the data scale system, a critical thing is to delicately balance computation and communication. If you look at conventional architectures, they allow you to program the computation, but they don’t allow you to program the communication and this is critical for getting efficient data flow. However, with reconfigurable dataflow, we are able to program the communication and the data flow, so that we can get a 10x improvement in performance on some applications. And we can enable applications that are not possible with current accelerator technology available in the form of GPUs.”

“We don’t expect the programmer to do this manually, we have a set of software called SambaFlow, which provides the capability to map these models very efficiently to our architecture. The idea is that the programmer can start either in one of the frameworks, PyTorch or TensorFlow, or they can provide their own graph of custom operations. If you start in one of the frameworks, then you’ll use a standard set of ML operations, and here we want to optimize the graph so that we can take advantage of both model parallelism and data parallelism. Then given a graph of operators, either custom operators or standard ML operators, we want to optimize the data flow in the graph. And this is done by number of different optimizations, such as tiling to improve the memory performance, exploiting parallelism within the operators, and then some very specific optimizations that that are specific to our architecture, such as streaming and nested pipelining.”

Groq cofounder and CEO Jonathan Ross gave a somewhat less technical presentation, noting recent key funding milestones, the company’s expanding portfolio, and use cases. It’s Tensor Streaming processor is another AI chip that seeks to reduce some of the overhead (instructions) required to use general purpose microprocessors by physically moving and reorganizing functional elements (e.g. with needed memory and support located nearby).

Groq’s says its TSP is capable of 18,900 IPS (inferences per second) on ResNet-50 v2 at batch size one and says it the fastest commercially available AI/ML accelerator, with a responsiveness measured in hundredths of a millisecond.

Here’s a brief portion of the description of the architecture excerpted from a paper presented at IEEE’s 2020 International Symposium on Computer Architecture (link to paper):

“To understand the novelty of our approach, consider the chip organization shown in Figure 1(a). In a conventional chip multiprocessor (CMP) each “tile” is an independent core which is interconnected using the on-chip network to exchange data between cores. Instruction execution is carried out over several stages: 1) instruction fetch (IF), 2) instruction decode (ID), 3) execution on ALUs (EX), 4) memory access (MEM), and 5) writeback (WB) to update the results in the GPRs. In contrast from conventional multicore, where each tile is a heterogeneous collection of functional units but globally homogeneous, the TSP inverts that and we have local functional homogeneity but chip-wide (global) heterogeneity.

“The TSP reorganizes the homogeneous two-dimensional mesh of cores in Figure 1(a) into the functionally sliced microarchitecture shown in Figure 1(b). In this approach, each tile implements a specific function and is stacked vertically into a “slice” in the Y-dimension of the 2D on-chip mesh. We disaggregate the basic elements of a core in Figure 1(a) per their respective functions: instruction control and dispatch (ICU), memory (MEM), integer (INT) arithmetic, float point (FPU) arithmetic, and network (NET) interface, as shown by the slice labels at the top of Figure 1(b).

“In this organization, each functional slice is independently controlled by a sequence of instructions specific to its on-chip role. For instance, the MEM slices support Read but not Add or Multiply, which are only in arithmetic functional slices (the VXM and MXM slices).”

Ross said the company was now shipping its latest Groq card, Groq node and Groq ware SDK solutions to customers worldwide. “We’re shipping to our customers both as individual PCIe cards and systems with eight cards each, and there’s even more on the roadmap to come,” said Ross.

As noted earlier there were many more activities in the first day. Here’s a link to coverage of the panel on AI use in chip design appearing in HPCwire‘s sister pub, EnterpriseAI.

Link to AI Hardware Summit: https://www.aihardwaresummit.com/events/ai-hardware-summit-2020

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!

UT Dallas Grows HPC Storage Footprint for Animation and Game Development

October 28, 2020

Computer-generated animation and video game development are extraordinarily computationally intensive fields, with studios often requiring large server farms with hundreds of terabytes – or even petabytes – of storag Read more…

By Staff report

Frame by Frame, Supercomputing Reveals the Forms of the Coronavirus

October 27, 2020

From the start of the pandemic, supercomputing research has been targeting one particular protein of the coronavirus: the notorious “S” or “spike” protein, which allows the virus to pry its way into human cells a Read more…

By Oliver Peckham

AMD Reports Record Revenue and $35B Deal to Buy Xilinx

October 27, 2020

AMD this morning reported record quarterly revenue of $2.8 billion and a finalized deal to buy FPGA-maker Xilinx for $35 billion in an all-stock transaction. The acquisition helps AMD keep pace during a time of consolida Read more…

By John Russell

Nvidia-Arm Deal a Boon for RISC-V?

October 26, 2020

The $40 billion blockbuster acquisition deal that will bring chip maker Arm into the Nvidia corporate family could provide a boost for the competing RISC-V architecture. As regulators in the U.S., China and the Europe Read more…

By George Leopold

OpenHPC Progress Report – v2.0, More Recipes, Cloud and Arm Support, Says Schulz

October 26, 2020

Launched in late 2015 and transitioned to a Linux Foundation Project in 2016, OpenHPC has marched quietly but steadily forward. Its goal “to provide a reference collection of open-source HPC software components and bes Read more…

By John Russell

AWS Solution Channel

Rapid Chip Design in the Cloud

Time-to-market and engineering efficiency are the most critical and expensive metrics for a chip design company. With this in mind, the team at Annapurna Labs selected Altair AcceleratorRead more…

Intel® HPC + AI Pavilion

Berlin Institute of Health: Putting HPC to Work for the World

Researchers from the Center for Digital Health at the Berlin Institute of Health (BIH) are using science to understand the pathophysiology of COVID-19, which can help to inform the development of targeted treatments. Read more…

NASA Uses Supercomputing to Measure Carbon in the World’s Trees

October 22, 2020

Trees constitute one of the world’s most important carbon sinks, pulling enormous amounts of carbon dioxide from the atmosphere and storing the carbon in their trunks and the surrounding soil. Measuring this carbon sto Read more…

By Oliver Peckham

AMD Reports Record Revenue and $35B Deal to Buy Xilinx

October 27, 2020

AMD this morning reported record quarterly revenue of $2.8 billion and a finalized deal to buy FPGA-maker Xilinx for $35 billion in an all-stock transaction. Th Read more…

By John Russell

OpenHPC Progress Report – v2.0, More Recipes, Cloud and Arm Support, Says Schulz

October 26, 2020

Launched in late 2015 and transitioned to a Linux Foundation Project in 2016, OpenHPC has marched quietly but steadily forward. Its goal “to provide a referen Read more…

By John Russell

Nvidia Dominates (Again) Latest MLPerf Inference Results

October 22, 2020

The two-year-old AI benchmarking group MLPerf.org released its second set of inferencing results yesterday and again, as in the most recent MLPerf training resu Read more…

By John Russell

HPE, AMD and EuroHPC Partner for Pre-Exascale LUMI Supercomputer

October 21, 2020

Not even a week after Nvidia announced that it would be providing hardware for the first four of the eight planned EuroHPC systems, HPE and AMD are announcing a Read more…

By Oliver Peckham

HPE to Build Australia’s Most Powerful Supercomputer for Pawsey

October 20, 2020

The Pawsey Supercomputing Centre in Perth, Western Australia, has had a busy year. Pawsey typically spends much of its time looking to the stars, working with a Read more…

By Oliver Peckham

DDN-Tintri Showcases Technology Integration with Two New Products

October 20, 2020

DDN, a long-time leader in HPC storage, announced two new products today and provided more detail around its strategy for integrating DDN HPC technologies with Read more…

By John Russell

Is the Nvidia A100 GPU Performance Worth a Hardware Upgrade?

October 16, 2020

Over the last decade, accelerators have seen an increasing rate of adoption in high-performance computing (HPC) platforms, and in the June 2020 Top500 list, eig Read more…

By Hartwig Anzt, Ahmad Abdelfattah and Jack Dongarra

Nvidia and EuroHPC Team for Four Supercomputers, Including Massive ‘Leonardo’ System

October 15, 2020

The EuroHPC Joint Undertaking (JU) serves as Europe’s concerted supercomputing play, currently comprising 32 member states and billions of euros in funding. I Read more…

By Oliver Peckham

Supercomputer-Powered Research Uncovers Signs of ‘Bradykinin Storm’ That May Explain COVID-19 Symptoms

July 28, 2020

Doctors and medical researchers have struggled to pinpoint – let alone explain – the deluge of symptoms induced by COVID-19 infections in patients, and what Read more…

By Oliver Peckham

Nvidia Said to Be Close on Arm Deal

August 3, 2020

GPU leader Nvidia Corp. is in talks to buy U.K. chip designer Arm from parent company Softbank, according to several reports over the weekend. If consummated Read more…

By George Leopold

Intel’s 7nm Slip Raises Questions About Ponte Vecchio GPU, Aurora Supercomputer

July 30, 2020

During its second-quarter earnings call, Intel announced a one-year delay of its 7nm process technology, which it says it will create an approximate six-month shift for its CPU product timing relative to prior expectations. The primary issue is a defect mode in the 7nm process that resulted in yield degradation... Read more…

By Tiffany Trader

Google Hires Longtime Intel Exec Bill Magro to Lead HPC Strategy

September 18, 2020

In a sign of the times, another prominent HPCer has made a move to a hyperscaler. Longtime Intel executive Bill Magro joined Google as chief technologist for hi Read more…

By Tiffany Trader

HPE Keeps Cray Brand Promise, Reveals HPE Cray Supercomputing Line

August 4, 2020

The HPC community, ever-affectionate toward Cray and its eponymous founder, can breathe a (virtual) sigh of relief. The Cray brand will live on, encompassing th Read more…

By Tiffany Trader

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

Aurora’s Troubles Move Frontier into Pole Exascale Position

October 1, 2020

Intel’s 7nm node delay has raised questions about the status of the Aurora supercomputer that was scheduled to be stood up at Argonne National Laboratory next year. Aurora was in the running to be the United States’ first exascale supercomputer although it was on a contemporaneous timeline with... Read more…

By Tiffany Trader

Is the Nvidia A100 GPU Performance Worth a Hardware Upgrade?

October 16, 2020

Over the last decade, accelerators have seen an increasing rate of adoption in high-performance computing (HPC) platforms, and in the June 2020 Top500 list, eig Read more…

By Hartwig Anzt, Ahmad Abdelfattah and Jack Dongarra

Leading Solution Providers

Contributors

European Commission Declares €8 Billion Investment in Supercomputing

September 18, 2020

Just under two years ago, the European Commission formalized the EuroHPC Joint Undertaking (JU): a concerted HPC effort (comprising 32 participating states at c Read more…

By Oliver Peckham

Nvidia and EuroHPC Team for Four Supercomputers, Including Massive ‘Leonardo’ System

October 15, 2020

The EuroHPC Joint Undertaking (JU) serves as Europe’s concerted supercomputing play, currently comprising 32 member states and billions of euros in funding. I Read more…

By Oliver Peckham

Google Cloud Debuts 16-GPU Ampere A100 Instances

July 7, 2020

On the heels of the Nvidia’s Ampere A100 GPU launch in May, Google Cloud is announcing alpha availability of the A100 “Accelerator Optimized” VM A2 instance family on Google Compute Engine. The instances are powered by the HGX A100 16-GPU platform, which combines two HGX A100 8-GPU baseboards using... Read more…

By Tiffany Trader

Microsoft Azure Adds A100 GPU Instances for ‘Supercomputer-Class AI’ in the Cloud

August 19, 2020

Microsoft Azure continues to infuse its cloud platform with HPC- and AI-directed technologies. Today the cloud services purveyor announced a new virtual machine Read more…

By Tiffany Trader

Oracle Cloud Infrastructure Powers Fugaku’s Storage, Scores IO500 Win

August 28, 2020

In June, RIKEN shook the supercomputing world with its Arm-based, Fujitsu-built juggernaut: Fugaku. The system, which weighs in at 415.5 Linpack petaflops, topp Read more…

By Oliver Peckham

HPE, AMD and EuroHPC Partner for Pre-Exascale LUMI Supercomputer

October 21, 2020

Not even a week after Nvidia announced that it would be providing hardware for the first four of the eight planned EuroHPC systems, HPE and AMD are announcing a Read more…

By Oliver Peckham

DOD Orders Two AI-Focused Supercomputers from Liqid

August 24, 2020

The U.S. Department of Defense is making a big investment in data analytics and AI computing with the procurement of two HPC systems that will provide the High Read more…

By Tiffany Trader

Oracle Cloud Deepens HPC Embrace with Launch of A100 Instances, Plans for Arm, More 

September 22, 2020

Oracle Cloud Infrastructure (OCI) continued its steady ramp-up of HPC capabilities today with a flurry of announcements. Topping the list is general availabilit Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This