Overview
The Synopsys High-Bandwidth Interconnect PHY IP enables high bandwidth, low-power and low-latency die-to-die connectivity in a package for hyperscale data centers, AI, and networking applications. Implementing a wide-parallel and clock-forwarded PHY interface, the IP targets advanced 2.5D packaging to take advantage of much finer pitch die-to-die connections in interposer-based technologies, such as TSMC® Chip-on-Wafer-on-Substrate (CoWoS), than traditional flip-chip organic substrates. The Synopsys High-Bandwidth Interconnect PHY delivers data rates up to 4Gbps per pin in a flexible architecture that includes up to 80 receive and 80 transmit connections per channel and up to 24 channels per PHY with one redundant lane per channel to improve production yield. The Synopsys High-Bandwidth Interconnect PHY IP is compliant with IEEE 1149.1 (JTAG) and 1149.6 (AC JTAG) boundary scan. The built-in self-test (BIST), internal loopback, and external PHY-to-PHY link tests provide on-chip testability and visibility into channel performance. The Synopsys High-Bandwidth Interconnect PHY IP with Synopsys’ USR/XSR PHY IP, supporting 16 lanes with a data rate of up to 112Gbps per lane using NRZ and PAM-4 signaling, provide a comprehensive die-to-die IP portfolio that is suitable for all packaging technologies.
Learn more about Custom IP core
Synopsys delivers standards-compliant 112G PHY IP for linear optics, helping reduce AI interconnect power, latency, and heat.
“We are in an era of pervasive intelligence,” said Shankar Krishnamoorthy, chief product development officer at Synopsys. Moderating a panel discussion at the inaugural Synopsys Executive Forum, he described the transformative impact of artificial intelligence (AI) and the challenges ahead.
As artificial intelligence (AI) reshapes industries and advances technological frontiers, its success hinges on advanced memory capabilities. Leading this transformation is High Bandwidth Memory (HBM), which offers unparalleled speeds and efficiencies.
With more than 25 years of experience in delivering field-proven silicon IP solutions, we are thrilled to partner with NVIDIA and the NVIDIA NVLink ecosystem to enable and accelerate the creation of custom AI silicon. This strategic collaboration will leverage Synopsys' expertise in silicon IPs to assist in the development of bespoke AI silicon, forming the foundation for advanced compute clusters aimed at delivering the next generation of transformative AI experiences.
The new ARC VPX6 processor introduces 1024-bit vector processing to the lineup, extending the existing VPX family, which includes VPX5 (512-bit), VPX3 (256-bit), and VPX2 (128-bit) variants. As such, VPX6 doubles the attainable peak performance while preserving full software compatibility with the other members of the VPX family. By simply upgrading hardware without any recoding, designers can instantly realize performance gains from day one.
For AI workloads to be processed reliably at a fast rate, the die-to-die interface in multi-die designs must be robust, low latency, and most importantly high bandwidth. This article outlines the need for 40G UCIe IP in AI data center chips leveraging multi-die designs.