Intel's first Xe GPU built on the company's 7 nm silicon fabrication process will be codenamed "Ponte Vecchio," according to a VideoCardz report. These are not gaming GPUs, but rather compute accelerators designed for exascale computing, which leverage the company's CXL (Compute Express Link) interconnect that has bandwidth comparable to PCIe gen 4.0, but with scalability features slated to come out with future generations of PCIe. Intel is preparing its first enterprise compute platform featuring these accelerators codenamed "Project Aurora," in which the company will exert end-to-end control over not just the hardware stack, but also the software.

"Project Aurora" combines up to six "Ponte Vecchio" Xe accelerators with up to two Xeon multi-core processors based on the 7 nm "Sapphire Rapids" microarchitecture, and OneAPI, a unifying API that lets a single kind of machine code address both the CPU and GPU. With Intel owning the x86 machine architecture, it's likely that Xe GPUs will feature, among other things, the ability to process x86 instructions. The API will be able to push scalar workloads to the CPU, and and the GPU's scalar units, and vector workloads to the GPU's vector-optimized SIMD units. Intel's main pitch to the compute market could be significantly lowered software costs from API and machine-code unification between the CPU and GPU.Image Courtesy: Jan Drewes

With 64 Gbps bandwidth per lane, 256 Gbps in x4, and a whopping 1 Tbps in x16 (128 GB/s per direction), PCI-Express 6.0 will debut in 2021 as 5G adoption hits critical mass in markets across the globe, to support server nodes, high-bandwidth network infrastructure, and lighting fast I/O for HPC and AI applications. Development of the new standard is already underway, with the specification having achieved a pre-release version 0.3, according to the PCI-SIG, the body that develops and maintains the PCI IP.

Further development, prototyping, and testing of the standard will run through 2020 as drafts of the standard are dispatched to interested parties. With the specification published in 2021, the first devices implementing it could arrive the following year. Granted, very few devices need 1 Tbps bandwidth, but the exercise of doubling bandwidth every 3 or so years has its maximum impact on devices that only have wiring for one PCIe lane, and directly impacts bandwidth of other I/O specifications that are derived from PCIe, such as USB, Thunderbolt, CXL, etc.

Intel has finalized design of its next-generation Xeon Scalable enterprise CPU socket for its "Sapphire Rapids" processors. Called LGA4677, the socket succeeds LGA3647, and is bound for a 2021 market release. Intel will have transitioned to its advanced 7 nm EUV silicon fabrication node on the CPU front, and has adopted an "enterprise-first" strategy for the node. LGA4677 will be designed to handle the extremely high bandwidth of PCI-Express Gen 5, which doubles bandwidth over PCIe gen 4.0, and adds several enterprise-specific features Intel is rolling out in advance as part of its CXL interconnect. These details, along with a prototype LGA4189 socket, was revealed at an exhibit by TE Connectivity, a company that manufactures the socket. The additional pin-count could enable Intel to not just deploy PCI-Express Gen 5, but also expand I/O in other directions, such as more memory channels, dedicated Persistent Memory I/O, etc.

Today, Alibaba, Cisco, Dell EMC, Facebook, Google, Hewlett Packard Enterprise, Huawei, Intel Corporation and Microsoft announce the incorporation of the Compute Express Link (CXL) Consortium, and unveiled the names of its newly-elected members to its Board of Directors. The core group of key industry partners announced their intent to incorporate in March 2019, and remain dedicated to advancing the CXL standard, a new high-speed CPU-to-Device and CPU-to-Memory interconnect which accelerates next-generation data center performance.

The five new CXL board members are as follows: Steve Fields, Fellow and Chief Engineer of Power Systems, IBM; Gaurav Singh, Corporate Vice President, Xilinx; Dong Wei, Standards Architect and Fellow at ARM Holdings; Nathan Kalyanasundharam, Senior Fellow at AMD Semiconductor; and Larrie Carr, Fellow, Technical Strategy and Architecture, Data Center Solutions, Microchip Technology Inc.

Intel today announced that it has begun shipments of the first Intel Agilex field programmable gate arrays (FPGAs) to early access program customers. Participants in the early access program include Colorado Engineering Inc., Mantaro Networks, Microsoft and Silicom. These customers are using Agilex FPGAs to develop advanced solutions for networking, 5G and accelerated data analytics.

"The Intel Agilex FPGA product family leverages the breadth of Intel innovation and technology leadership, including architecture, packaging, process technology, developer tools and a fast path to power reduction with eASIC technology. These unmatched assets enable new levels of heterogeneous computing, system integration and processor connectivity and will be the first 10nm FPGA to provide cache-coherent and low latency connectivity to Intel Xeon processors with the upcoming Compute Express Link," said Dan McNamara, Intel senior vice president and general manager of the Networking and Custom Logic Group.

As if the mother of all ironies, prior to its effective death-sentence dealt by the U.S. Department of Commerce, Huawei's server business developed an ambitious product roadmap for its Fusion Server family, aligning with Intel's enterprise processor roadmap. It describes in great detail the key features of these processors, such as core-counts, platform, and I/O. The "Sapphire Rapids" processor will introduce the biggest I/O advancements in close to a decade, when it releases sometime in 2021.

With an unannounced CPU core-count, the "Sapphire Rapids-SP" processor will introduce DDR5 memory support to the data-center, which aims to double bandwidth and memory capacity over the DDR4 generation. The processor features an 8-channel (512-bit wide) DDR5 memory interface. The second major I/O introduction is PCI-Express gen 5.0, which not only doubles bandwidth over gen 4.0 to 32 Gbps per lane, but also comes with a constellation of data-center-relevant features that Intel is pushing out in advance as part of the CXL Interconnect. CXL and PCIe gen 5 are practically identical.

CXL, short for Compute Express Link, is an ambitious new interconnect technology for removable high-bandwidth devices, such as GPU-based compute accelerators, in a data-center environment. It is designed to overcome many of the technical limitations of PCI-Express, the least of which is bandwidth. Intel sensed that its upcoming family of scalable compute accelerators under the Xe band need a specialized interconnect, which Intel wants to push as the next industry standard. The development of CXL is also triggered by compute accelerator majors NVIDIA and AMD already having similar interconnects of their own, NVLink and InfinityFabric, respectively. At a dedicated event dubbed "Interconnect Day 2019," Intel put out a technical presentation that spelled out the nuts and bolts of CXL.

Intel began by describing why the industry needs CXL, and why PCI-Express (PCIe) doesn't suit its use-case. For a client-segment device, PCIe is perfect, since client-segment machines don't have too many devices, too large memory, and the applications don't have a very large memory footprint or scale across multiple machines. PCIe fails big in the data-center, when dealing with multiple bandwidth-hungry devices and vast shared memory pools. Its biggest shortcoming is isolated memory pools for each device, and inefficient access mechanisms. Resource-sharing is almost impossible. Sharing operands and data between multiple devices, such as two GPU accelerators working on a problem, is very inefficient. And lastly, there's latency, lots of it. Latency is the biggest enemy of shared memory pools that span across multiple physical machines. CXL is designed to overcome many of these problems without discarding the best part about PCIe - the simplicity and adaptability of its physical layer.

Intel has been working on CXL, short for Compute Express Link gen 1, for over four years new. This new interconnect protocol was donated to a new consortium of tech companies for release as a the CXL 1.0 standard. Its protocol layer will pave the way for PCI-Express gen 5.0 to sustain its bandwidth growth target of being twice as fast as PCIe gen 4.0. CXL 1.0 is out to compete with other established PCIe-alternative slot standards such as NVLink from NVIDIA, and InfinityFabric from AMD. It has one killer advantage, though: the CXL 1.0 is pin-compatible and backwards-compatible with PCI-Express, and uses PCIe physical-layer and electrical interface.

This reduces hardware upgrade costs for data-centers. CXL maintains memory coherency between the CPU's memory-space and memory on installed devices. The CXL Consortium, or SIG, includes data-center and cloud-computing giants, including Alibaba, Cisco, DellEMC, Facebook, Google, HPE, Huawei, Microsoft, and of course Intel. CXL will be used bot as a socketed/slotted interface for add-on cards and GPU boards, and as an embedded interface. We estimate bandwidth of CXL to be 32 Gbps per lane, or four times that of PCIe gen 3.0, keeping in line with PCIe gen 5.0 bandwidth growth estimates.