Articles by Nicolas Poggi - Databricks Blog

Page 1

Announcing GA of Predictive I/O for Updates: Faster DML Queries, Right Out of the Box

November 2, 2023 by Sirui Sun, Ala Luszczak, Sabir Akhadov, Andreas Chatzistergiou, Carmen Kwan, Ole Sasse, Tom van Bussel, Lars Kroll, Pengfei Xu, Polo-François Poli, Bart Samwel, Himanshu Raja, Christos Stavrakakis, Venki Korukanti, Tathagata Das and Nicolas Poggi in Platform & Products & Announcements

Announcing GA of Predictive I/O for Updates, which harnesses Photon and AI atop Deletion Vectors in order to significantly speed up MERGE, UPDATE and DELETE operations. We've prevented over 15 trillion unnecessary row writes, and we’re just getting started.

Reduce Time to Decision With the Databricks Lakehouse Platform and Latest Intel 3rd Gen Xeon Scalable Processors

May 17, 2022 by Swastik Chakraborty, Lakshman Chari, Nicolas Poggi, Robert Saxby and Mostafa Mokhtar in Platform Blog

This is a collaborative post from Databricks and Intel. We thank Swastik Chakroborty,Regional Technical Sales Director-APJ, and Lakshman Chari, Cloud ISV Partner Manager...

Meltdown and Spectre: Exploits and Mitigation Strategies

January 16, 2018 by Chris Stevens, Nicolas Poggi, Thomas Desrosiers and Reynold Xin in Engineering Blog

In an earlier blog post , we analyzed the performance impact of Meltdown and Spectre on big data workloads in the cloud. In...

Meltdown and Spectre's Performance Impact on Big Data Workloads in the Cloud

January 13, 2018 by Chris Stevens, Nicolas Poggi, Thomas Desrosiers and Reynold Xin in Engineering Blog

Last week, the details of two industry-wide security vulnerabilities, known as Meltdown and Spectre , were released. These exploits enable cross-VM and cross-process...

Learn about Apache Spark’s Memory Model and Spark’s State in the Cloud

September 20, 2017 by Wenchen Fan and Nicolas Poggi in Company Blog

Since Apache Spark 1.6, as part of the Project Tungsten , we started an ongoing effort to substantially improve the memory and CPU...