“Zeppelin”: An SoC for Multichip Architectures

AMD’s “Zeppelin” system-on-a-chip (SoC) combines eight high-performance “Zen” cores with a shared 16-MB L3 Cache, along with six high-speed I/O links and two DDR4 channels, using the infinity fabric (IF) to provide a high speed, low latency, and power-efficient connectivity solution. This solution allows the same SoC silicon die to be designed into three separate packages and provides highly competitive solutions in three different market segments. IF is critical to this high-leverage design re-use, utilizing a coherent, scalable data fabric (SDF) for on-die communication, as well as inter-die links, extending up to eight dies across two packages. To support this scalability, an energy efficient, custom physical-layer link was designed for in-package, high-speed communication between the dies. Using an additional scalable control fabric (SCF), a hierarchical power and system management unit (SMU) was used to monitor and manage a distributed set of dies to ensure the products stay within infrastructure limits. It was essential that the floor plan of the SoC was co-designed with the package substrate. The SoC used a 14-nm FinFET process technology and contains 4.8B transistors on a 213 mm2 die.

[1]  Samuel Naffziger,et al.  Bristol Ridge: A 28-nm $\times$ 86 Performance-Enhanced Microprocessor Through System Power Management , 2017, IEEE Journal of Solid-State Circuits.

[2]  Pat Conway,et al.  The AMD Opteron Northbridge Architecture , 2007, IEEE Micro.

[3]  Teja Singh,et al.  3.2 Zen: A next-generation high-performance ×86 core , 2017, 2017 IEEE International Solid-State Circuits Conference (ISSCC).

[4]  Taejoong Song,et al.  A 14 nm FinFET 128 Mb SRAM With V $_{\rm MIN}$ Enhancement Techniques for Low-Power Applications , 2015, IEEE Journal of Solid-State Circuits.

[5]  Sean White,et al.  ‘Zeppelin’: An SoC for multichip architectures , 2018, 2018 IEEE International Solid - State Circuits Conference - (ISSCC).

[6]  Mike Clark,et al.  A new ×86 core architecture for the next generation of computing , 2016, IEEE Hot Chips Symposium.

[7]  Jonathan White,et al.  Carrizo: A High Performance, Energy Efficient 28 nm APU , 2016, IEEE Journal of Solid-State Circuits.

[8]  Taejoong Song,et al.  13.2 A 14nm FinFET 128Mb 6T SRAM with VMIN-enhancement techniques for low-power applications , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).