English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Response time requirements for big data processing systems are shrinking. Tomeet this strict response time requirement, many big data systems store all ormost of their data in main memory to reduce the access latency. Main memorycapacities have grown, and systems with 2 TB of main memory capacity availabletoday. However, the rate at which processors can access this data--the memorybandwidth--has not grown at the same rate. In fact, some of these big-memorysystems can access less than 10% of their main memory capacity in one second(billions of processor cycles).  3D die-stacking is one promising solution to this bandwidth problem, andindustry is investing significantly in 3D die-stacking. We use a simpleback-of-the-envelope-style model to characterize if and when the 3D die-stackedarchitecture is more cost-effective than current architectures for in-memorybig data workloads. We find that die-stacking has much higher performance thancurrent systems (up to 256x lower response times), and it does not requireexpensive memory over provisioning to meet real-time (10 ms) response timeservice-level agreements. However, the power requirements of the die-stackedsystems are significantly higher (up to 50x) than current systems, and itsmemory capacity is lower in many cases. Even in this limited case study, wefind 3D die-stacking is not a panacea. Today, die-stacking is the mostcost-effective solution for strict SLAs and by reducing the power of thecompute chip and increasing memory densities die-stacking can be cost-effectiveunder other constraints in the future.

When to use 3D Die-Stacked Memory for Bandwidth-Constrained Big Data Workloads