Rambus has announced its GDDR6 PHY memory has achieved the industry’s highest performance figures at 18 Gbps. The company also said in the announcement that its PHY GDDR6 memory is best suited to artificial intelligence, machine learning and autonomous driving systems that require higher bandwidth memory.
Rambus claims its GDDR6 PHY memory is the industry’s fastest with 18 GB/s performance, which delivers peak performance of four-to-five times faster than current DDR4 solutions and continues the company’s tradition of delivering industry-leading technology advancements.
PHY GDDR6 is paired with a Rambus GDDR6 memory controller which comes from the company’s recent acquisition of Northwest Logic, to provide a complete and optimized memory subsystem solution.
A recent increase in applications such as artificial intelligence, machine learning and automotive systems drives the need for high bandwidth memory. The upcoming introduction of 5G mobile networks will further intensify this challenge, according to Rambus. The company is working closely with partners to provide more options to system designers for selecting the correct memory to meet both their bandwidth and cost requirements.
“Memory bandwidth poses a significant obstacle for designers working on performance-intensive applications such as AI/ML,” said Hemant Dhulla, vice president and general manager of IP cores at Rambus. “With our GDDR6 18 Gbps memory subsystem, Rambus technology can unleash the power of leading-edge designs with a proven and cost-effective memory architecture.”
Key benefits of Rambus GDDR6 PHY memory:
- Achieves the industry’s highest speed of up to 18 Gbps, delivering a maximum bandwidth of up to 72 GB/s
- Complete and optimised memory subsystem solution with companion GDDR6 memory controller
- Offers PCB and package design support – allowing customers to quickly and reliably bring their high-speed designs to production
- Provides access to Rambus system and SI/PI experts helping ASIC designers to ensure maximised signal and power integrity for devices and systems
- Features LabStation development environment that enables quick system bring-up, characterisation and debug
- Supports high-performance applications including networking, data centre, ADAS, machine learning and AI
Discuss on our Facebook page HERE.
KitGuru says: Although Rambus says its PHY memory is best suited for AI, ML and automotive systems, it could also be used to increase performance in consumer-grade graphics products too. But that all depends on whether the company feels its memory has a place in these products in future.