The impact of the new COM-HPC standard
It’s been three years since the latest Computer on Module (COM) specification, COM Express 3.0, was released for industry use. Now, the embedded computer industry is on the verge of a new standard: COM for high-performance computing (COM-HPC), which is due to be ratified this year.
Here, Chairman of the PICMG COM-HPC technical subcommittee and Marketing Manager at congatec, Christian Eder, and Martin Frederiksen, Managing Director of embedded computing systems provider Recab UK, have explained the impact this new standard will bring to the market.
What are the main differences between COM-HPC and COM Express?
Christian Eder (CE): “Computer-on-Modules based on the new COM-HPC standard promise considerably higher transmission performance, many more high-speed interfaces and significantly faster network connection, besides other benefits. This is down to a completely redesigned, more powerful new module to carrier board connector. While COM Express establishes this connection with 440 pins, the COM-HPC specification provides 800 pins. This doubles the maximum number of PCIe lanes from 32 for COM Express Type 7 to 64 for COM-HPC/Server.
“While COM Express supports a maximum of PCIe Gen 3.0 with 8 Gb/s per lane, a COM-HPC module achieves up to 32 Gb/s per lane via PCIe-5.0 — that’s four times the data rate of COM Express. COM-HPC modules will therefore be used in particularly performance-hungry applications, for instance to embed artificial intelligence with deep learning in embedded systems, or even to implement tactile Internet at the edge server level.”
On the subject of edge servers, what performance enhancements can be expected from COM-HPC modules in terms of Ethernet connectivity?
CE: “The enormous speed increase has an immense effect on the connectivity performance. Current COM Express modules (Type 7) at edge server level offer a maximum of 10 Gb Ethernet per signal pair. COM-HPC, on the other hand, specifies 25 Gb Ethernet, and more.
“With up to eight network connections, it then becomes possible to achieve transfer rates of 100 Gbit/s, and theoretically even 200 Gbit/s. Such rates are needed in the first instance for high-performance edge server solutions at the edge of telecom networks. Here, fast up, down and crosslinks in all directions must be established: i.e. north in the direction of the central cloud; east and west in the direction of neighbouring edge fogs; and also south in the direction of industry 4.0 controls at process level.”
How will the changes presented by COM-HPC impact board design, and what new system potential might this bring?
Martin Frederiksen (MF): “The most significant changes to baseboard design will relate to signal routing. With the COM-HPC standard, the higher speeds of PCIe-4.0 and 5.0 — which as Christian mentioned, can be up to four times faster than the PCIe-3.0 speed — will require very careful routing to ensure signal integrity. In addition, these signals will not travel as far as previous versions.
“There are several steps that COM system design and production companies such as Recab UK can take to mitigate for this. For example, PCIe retimer chips may be used to extend signal strength if the trace length requirements are long. We can also look at the material of the printed circuit board (PCB) itself. For many years, the base material of the PCB has been FR-4, which has been sufficient for the data transmission required for COM Express modules with PCIe-3.0. With COM-HPC, achieving the best performance will require changing to a base material with lower transmission loss, such as Megtron-4 laminates.
“However, these adaptions to baseboard design will certainly pay off in the boundless system potential of the standard. Bringing high performance computing out of the server room and into the embedded market will open up new opportunities in areas such as artificial intelligence, 5G networking and machine vision.
“For example, the capacity for high data throughput and low latency will benefit imaging applications, such as 3D imaging in medical equipment and areas like 3D mapping of land for rail infrastructure and the seabed for subsea operations. Overall, this means a new generation of embedded computing applications for a wide range of vertical markets, such as telecommunications.”
As an experienced developer and provider of embedded systems, where do you see the most challenges for baseboard designs using COM-HPC modules?
MF: “The higher data transfer speed of up to 100 Gbit/s and 65 PCIe lanes means that the baseboard design becomes really tricky and you need the right equipment to ensure good signal integrity. Here, the experience of Recab UK is invaluable, as we have made hundreds of baseboard designs and have good connections with congatec’s engineers to ensure we have access to the best equipment.
“One of the biggest challenges beyond that of maintaining signal integrity will be thermal design. These systems will feature processors operating in excess of 100 Watts in a compact footprint, so an effective means of cooling these processors will be imperative to minimise the risk of overheating and component degradation in these embedded systems.”
Speaking of footprints, does the new COM-HPC standard specify several module classes?
CE: “Yes, just as there are currently Type 6 and Type 7 high-end specifications for COM Express, we have also planned two module classes for COM-HPC that address different application and performance requirements. In addition, there are two different form factors within these two module classes, similar to COM Express Basic and COM Express Compact. To be precise, we currently distinguish between server and client modules, in analogy to client/server computing.
“COM-HPC/Server modules are tailored for use in edge server environments and require the largest possible memory capacity, a particularly powerful network connection and the option to provide many cores for consolidating high workloads. These Server-on-Modules will host the mentioned eight DIMM sockets on a 200x160mm footprint, while the smaller 160x160mm server modules will integrate up to four DIMM sockets.
“The COM-HPC/Client modules have a slightly more compact design, are also planned in two footprint variants — 120x120mm and 160x120mm — and are designed for use in high-end embedded computing applications. Unlike the server modules, they provide a maximum of 2x GbE interfaces (via NBASE-T) for Ethernet connection. In addition, COM-HPC/Client modules integrate video interfaces such as DDI and eDP/MIPI-DSI, which – in contrast to COM-HPC/Server modules – can be used to control up to four independent high-resolution displays.”
For end users, what will COM-HPC systems make possible?
MF: “We anticipate that telecom and broadcasting will be an interesting area to watch for COM-HPC. This was where we saw the COM Express Type 7 quickly accepted and where you have the need for 24/7 operation, high data throughput and low latency. The COM-HPC will be used where you cannot use a temperature cooled data centre, such as edge cloud applications.
“Therefore, I can see a need for these modules for faster telecommunications in rail and defence. In both these areas, this will allow closer to real-time communication of data between on-board or remote embedded systems and centralised, manned computers. Naturally, faster transmission of data in these critical sectors is highly advantageous.
“Another area will be the emerging 5G network infrastructure, where fast computing and communications will be a necessity and the flexibility of scalable processor modules and 25Gb ethernet will come to the fore.”
The COM-HPC standard is expected to be fully ratified by mid-2020, with the first COM-HPC modules beginning to come to market.