Category: Uncategorized

Ted Weatherford (Lin), VP Business Development and John Carney (Lin), Distinguished Engineer, SW Architecture of Xsight Labs, presented at a recent AI Infrastructure Field Day (AIIFD4, see video of their session here) I attended and thought they had a great way to solve the need for high speed/software defined networking (SDN) in modern data centers.

Turns out Xsight Labs is a fabless semiconductor company, specializing in SDN ASICs and currently have an X2 Switch ASIC and a E1 DPU ASIC out on the market today. They are the first vendor to have an 800Gbps DPU ASIC and their 12.8T X2 switch chip is focused on low power SDN for ToR, edge and extreme edge environments. Listen to the podcast to learn more.

Podcast: Play in new window | Download (Duration: 50:44 — 69.7MB) | Embed

Subscribe: Apple Podcasts | Spotify | RSS

Ted said there are 6 primary chips which make up AI data centers: GPU, CPU, NIC, Scale up networking switch, Scale out networking switch, & DPU chips. And there are maybe 20 semiconductor dev groups around the world capable of developing these. Their current monolithic die chips use the TSMC N5 process. While their networking X2 switch chip has been out in volume for a while now and is in its second generation, their E1 DPU chip is brand new.

We started discussing their X2 SDN switch chip. The X2 supports up to 128 ports/12.8T in 1RU (based on reference switch architecture) at under 200W and any port can configured to support 10G to 400G.

In addition to their switch form factor and power envelope, the X2’s programability is a major strength. They have over 3000 dedicated, “MAP” core CPUs or Harvard (separate instructions and data memory and access paths) core CPUs to process, in parallel, the data flows in and out of the chip plus separate parser cores. The 3072 MAP cores are allocated statically to 64 parallel packet forwarding engines and 64 data plane units and there’s a 64MB packet buffer shared across all ports.

They have had a couple of PoCs where customers managed to code X2 switch support for their application in a matter of weeks (days maybe).

Moving on to the E1 DPU chip, the story gets even more interesting. Traditionally, DPUs have had a hybrid architecture where the data path processing is done in parallel cores and the management processing in a handful of RISC cores requiring clients to code in multiple architectural environments. Xsight labs took a different tack.

The E1 has up to 64 N2 ARM cores and can literally run Linux or other OSs (at the same time) to support DPU processing. (Btw, the latest gen Apple M5 CPU only has 8 fast ARM cores and 4 slow ARM cores). On the server side of the DPU, it supports up to 40 PCIe Gen5 lanes and on the ethernet side 1-800Gbps port, 2-400Gbps ports, 4-200Gbps ports, etc..

The E1 also supports 4 DDR5 5200 MHz memory interfaces which means E1 can support TBs of memory!? John went into the software architecture a bit more on our podcast than at AIIFD4 and said it had 32MB of system cache.

John said main memory would mostly be used to host static/slowly changing databases and tables. Actual instructions to support DPU IO would all reside in ARM l1-l2-l3 instruction caches during processing. The E1 operates the 800G port at line speed within 75W of power.

At AIIFD4, they discussed their SONiC DASH benchmark VNET to VNET scenario results. SONiC DASH is an open source project started by Microsoft, used to assess smart switches under cloud service provider workloads. There are many levels for the SONiC DASH benchmark and their E1 DPU-X2 network (reference architecture) smart switch was the first smart switch to sustain Hero800 performance (800Gbps link support) using only a single DPU. This means their E1 DPU-X2 switch processed in excess of 14M TCP connections/second for over a minute and a half, all while sustaining over 120M TCP&UDP background data flows.

As for customer wins, Ted mentioned each SpaceX Starlink V3 satellite uses multiple X2 chips and that the Open Flash Platform (OFP) organization is currently implementing an NFS server using a single E1 DPU and PBs of flash in a single sled. This means OFP is mapping a Linux file system across all the flash in the sled and presenting it as a NFS storage server out the front end. No server required…

Ted Weatherford, VP Business Development, Xsight Labs

Ted Weatherford is Vice President of Business Development at Xsight Labs, where he was hired to build out a commercial team, discover and close first strategic customer engagements, manages HW and SW partner ecosystems, and contribute to go-to-market activities for the company’s products and engineering services.

Ted brings over 30 years of experience in product line management, business development, and strategic marketing in the semiconductor industry. Over his career, his work has contributed to hundreds of chip design-wins globally and generated more than $2 billion in revenue for leading merchant silicon suppliers including BRCM, INTL, CRDO, MTK, MRVL and many others

John Carney, Distinguished Engineer, Software Architecture, Xsight Labs

John is a Distinguished Engineer at Xsight Labs, focused on software architecture for Xsight’s E-series DPU products.

Prior to Xsight, John held hardware and software technical leadership roles at Broadcom, Cisco and Juniper.

John is an expert in high-performance networking data planes.

This is our first time talking with David Friend, (@Wasabi_Dave) Co-founder and CEO, Wasabi Technologies, but he certainly knows his way around storage. He has started a number of successful companies, the last one prior to Wasabi was Carbonite, a cloud backup company. 

Before we get to the podcast, Howard Marks has retired from active GreyBeards co-hosting duty and has become Co-host Emeratus. We will all miss him and his astute insight. We wish him well. Howard did volunteer to be a co-host on the occasional podcast. So he will be back, just not a regular co-host anymore.

In his stead, Ray’s recruited a band of technical wizards that will share co-hosting duties with Howard. This is our first podcast with a new co-host, Matt Leib (@MBLeib). If you want to learn more about Matt his bio is on our About page and his website is linked in our menu above. Matt’s been a long time friend and chief IT architect for a number of firms in the past and present. Although he might not sport a grey beard, Matt certainly qualifies as a IT GreyBeard from our perspective.

One of the many things that make’s Wasabi cloud storage special is that it has no egress charges. Dave spent a lot of time after his last company talking to customers about cloud storage. Their number one complaint was unpredictable expense. Public cloud storage expense is unpredictable because it’s hard to predict data egress. With Wasabi cloud storage, customers get a one line invoice charge, just for the amount of data they are storing.

They also support immediate consistency. David said when customer applications receive an ack, their data has been received and can read back from anywhere in the world. Most other cloud storage vendors only support eventual consistency, which means “sometime” later the data on your cloud storage will be updated.

Wasabi does not support cloud compute. However, they do have software partners that can provide this. In some cases, these partners share proximity to Wasabi cloud data centers so access latencies can be minimized.

Their storage interface is fully S3 compliant and as mentioned above, have a number (>100) of “certified” software partners that can provide application storage access services, rather than having to use the S3 interface directly. Further, Wasabi supports both CommVault and Veeam for data protection cloud storage tiering.. 

Wasabi is also faster than AWS S3 storage because they’ve taken the time to optimize their writing to understand disk geometry, seeking and head switching. There’s upsides and downsides to this level of optimization. Yes you can write and subsequently read data faster but every new disk that comes along requires work to optimize to its unique geometry. For an example of their performance, David said that they can support direct surveillance camera video at 4K or 8K resolution to Wasabi cloud storage.

They are also cheaper than AWS S3. Dave mentioned Wasabi cloud storage is 1/5th the cost, on a GB/month basis, of AWS S3. We asked about Glacier support and he said at these prices, why add the complexity of another storage media.

Wasabi has 3 data centers, one in Virginia, one on the west coast of the US and the other in Amsterdam in Europe. The one in Europe is fully GDPR compliant. Wasabi supports data at rest encryption where the customer owns and holds encryption keys. They also support a WORM bucket, where you can supply an expiration date and the data will remain unmodified until that time has expired.

Matt asked if Wasabi could be used to replace all the storage at a data center. David said possibly for file data but not for block. However, customers would need to be aware that access latencies may suffer if they are far away from Wasabi data centers.

The podcast runs ~42 minutes. We feel that David qualifies as a GreyBeard. He . Ray and David could have talked at length optimizing disk storage performance. Also, this was Matt’s first time as a GreyBeard co-host and we think he did just fine. Listen to the podcast to learn more. .

Podcast: Play in new window | Download (Duration: 42:33 — 58.4MB) | Embed

Subscribe: Apple Podcasts | Spotify | RSS

David Friend, Co-Founder and CEO, Wasabi Cloud Systems

David Friend is the co-founder and CEO of Wasabi, a revolutionary cloud storage company. David’s first company, ARP Instruments developed synthesizers used by Stevie Wonder, David Bowie, Led Zeppelin and even helped Steven Spielberg communicate with aliens providing that legendary five-note communication in Close Encounters of the Third Kind.

Friend founded or co-founded five other companies: Computer Pictures Corporation – an early player in computer graphics, Pilot Software – a company that pioneered multidimensional databases for crunching large amounts of customer data, Faxnet – which became the world’s largest provider of fax-to-email services, Sonexis – a VoIP conferencing company, and immediately prior to Wasabi, what is now one of the world’s leading cloud backup companies, Carbonite.

David is a respected philanthropist and is on the board of Berklee College of Music, where there is a concert hall named in his honor, serves as president of the board of Boston Baroque, an orchestra and chorus that has received 7 Grammy nominations. An avid mineral and gem collector he donated Friend Gem and Mineral Hall at the Yale Peabody Museum of Natural History.

David graduated from Yale and attended the Princeton University Graduate School of Engineering where he was a David Sarnoff Fellow.