eSilicon has designed custom high-speed single-port cache memories that are optimized to meet the high-performance requirements of industry-standard processor cores. eSilicon cache memories deliver one of the highest levels of performance in the high-performance computing and networking market segments.
The performance of network devices, servers, cloud computing and other compute-intensive applications is often limited by the performance at which the processor cores can run. At the same time, the performance of processor cores is often limited by the performance of memory instances used in the L1 cache of the processor core. eSilicon has delivered fast-cache memories to customers in the networking and high-performance computing segment at advanced nodes down to 7nm. The 7nm high-speed fast cache offers more than a 35% increase in performance from previous FinFet generations.
Our philosophy for developing cache memories is to first meet the end customer’s performance requirements. Then we map the circuitry to the customer’s other key metrics, such as low power/leakage or small area. This philosophy has helped us consistently deliver fast-cache memories that meet customer requirements.
Front-end views of our 7nm fast cache, as well as silicon quality results, white papers or complete data sheets, are available from firstname.lastname@example.org. Additional features and benefits for eSilicon’s fast cache and the rest of the 7nm IP platform are available under NDA. Contact email@example.com.
All eSilicon IP is available in IP Navigator at https://star.esilicon.com, our online IP exploration tool. Navigator provides access to eSilicon’s full portfolio of IP products. Memory instances may be generated, analyzed and downloaded. Power, performance, and area (PPA) data is pre-loaded for easy data comparison and analysis.