Samsung Foundry and Synopsys Accelerate Multi-Die System Design
Multi-die systems are making big inroads in the semiconductor world. With compute-intensive applications like AI, high-performance computing (HPC), and automotive demanding more bandwidth and performance, heterogeneously integrated dies provide a way to deliver on these needs. While the chip design steps may be similar to those of their monolithic system on chip (SoC) counterparts, multi-die systems bring new challenges that call for holistic new approaches and technologies.
To support its customers on their journeys, Samsung Foundry needed to solve key system implementation challenges for their multi-die system. The foundry found its answers working with Synopsys, which has pioneered a comprehensive and scalable solution for fast heterogeneous integration. Working together, the two companies have developed Samsung Foundry’s Multi-Die System Implementation Flow with Synopsys 3DIC Compiler, supporting Samsung process nodes and I-Cube™ and X-Cube™ technologies. Two test chips successfully validate the manufacturing technology and design methodology. Samsung Foundry discussed its journey at this year’s SNUG Silicon Valley 2023 conference. Read on for details.
To read the full article, click here
Related Semiconductor IP
- SHA-256 Secure Hash Algorithm IP Core
- EdDSA Curve25519 signature generation engine
- DeWarp IP
- 6-bit, 12 GSPS Flash ADC - GlobalFoundries 22nm
- LunaNet AFS LDPC Encoder and Decoder IP Core
Related Blogs
- The Integrated Design Challenge: Developing Chip, Software, and System in Unison
- Samsung Foundry Accelerates Billion-Gate Low-Power Signoff with Synopsys VC LP
- Avoiding Multi-Die System Re-spins with New Early Architecture Exploration Technology
- Can GPUs Accelerate Digital Design Implementation?
Latest Blogs
- Area, Pipelining, Integration: A Comparison of SHA-2 and SHA-3 for embedded Systems.
- Why Your Next Smartphone Needs Micro-Cooling
- Teaching AI Agents to Speak Hardware
- SOCAMM: Modernizing Data Center Memory with LPDDR6/5X
- Bridging the Gap: Why eFPGA Integration is a Managed Reality, Not a Schedule Risk