This site may earn affiliate commissions from the links on this page. Terms of use.

Well-nigh four years ago, Intel announced a major shift in its overall silicon strategy. Instead of just focusing on x86 cores, or even developing a line of specialized many-core accelerators like Xeon Phi, the company would also bring a Xeon CPU to market with an FPGA (field-programmable gate array) integrated directly into the die.

Intel has talked up this shift before, every bit Anandtech notes, including some product demonstrations, but always behind airtight doors or nether very restricted circumstances. The Xeon Scalable Gilt 6138 is already an existing CPU, and the x86 silicon on the 6138P looks to be identical between the two parts: A 20C/40T CPU, with a 2GHz base clock, 3.7GHz boost, with vi channels of DDR4 support. The PCIe lane count is different — 48 lanes on the base 6138 compared with 32 lanes on the 6138P — simply this virtually certainly means that sixteen of those PCIe 3.0 lanes have been diverted for bandwidth for the FPGA.

The integrated Arria ten GX 1150 has one.fifteen meg logic elements, 53Mb of embedded memory and, according to Anandtech, is priced at "Arm, Leg" with an estimated TDP betwixt 190W – 200W. Given that the not-FPGA 1138 is a $2,600 CPU, that pricing seems accurate. The Xeon CPU connects to the FPGA with 160Gbps of bandwidth per socket, and the configuration may be limited to two-socket systems or beneath.

Maximum TDP is 255W, which is high but not extraordinary. Some of you may recollect that AMD'south Piledriver FX-9590 was rated for a 220W TDP, and our discussions of the topic with high end CPU cooler vendors has unsaid that the upper limit for how much rut you lot can dissipate without using water cooling is probably effectually ~250W in a conventional CPU socket. Of course, these are LGA3647 CPUs, which ways they're designed for a very large CPU socket and a hefty cooler — and Intel could always theoretically design to an explicitly higher TDP target if it wished.

In its proclamation, Intel writes:

Fujitsu, a pb partner, plans to evangelize systems based on the Intel® Xeon® processor with integrated FPGA and Intel's OVS reference design. They are making the Intel® virtual switching reference design fifty-fifty more robust for the networking surroundings through their reliability, availability, and serviceability (RAS) with performance monitoring and debug assisting functions.

Intel as well claims that the 6138P delivers "upwardly to 3.2x the throughput with one-half the latency and 2x more VMs" when compared with the bones 6138 with "software OVS (Open Virtual Switch) DPDK forwarding in the CPU userspace awarding."

For now, Intel is clearly keeping its FPGA capabilities separate and bars to a small segment of products rather than rolling it out as an inexpensive way to make FPGAs more affordable. Whether the company will stick to this plan or gradually expand its integrated CPU + FPGA offerings is nevertheless unclear, but if the segment proves important to Intel's overall fight for positioning in the AI/ML space, yous can bet we'll start seeing more Xeon silicon with Arria FPGAs onboard.