J
Julien Sebot
Researcher at Intel
Publications - 18
Citations - 551
Julien Sebot is an academic researcher from Intel. The author has contributed to research in topics: SIMD & Cache. The author has an hindex of 8, co-authored 17 publications receiving 546 citations. Previous affiliations of Julien Sebot include South University & University of Paris-Sud.
Papers
More filters
Proceedings ArticleDOI
Adaptive insertion policies for managing shared caches
Aamer Jaleel,William C. Hasenplaugh,Moinuddin K. Qureshi,Julien Sebot,Simon C. Steely,Joel Emer +5 more
TL;DR: This paper proposes Thread-Aware Dynamic Insertion Policy (TADIP), a adaptive insertion policy that can take into account the memory requirements of each of the concurrently executing applications and provides performance benefits similar to doubling the size of an LRU-managed cache.
Patent
Method and apparatus for parallel shift right merge of data
TL;DR: In this article, a method for a parallel shift right merge of data is proposed, where a first operand having a first set of L data elements is shifted left by ''L - M'' data elements.
Patent
Fast full search motion estimation with SIMD merge instruction
TL;DR: In this article, a method for fast full search motion estimation with SIMD merge instruction is presented, which consists of loading a first line of K data elements for a current macroblock and a shift right merge operation on the first and second sets of data elements to generate a second line of k data elements.
Proceedings ArticleDOI
Improving 3D geometry transformations on a simultaneous multithreaded SIMD processor
TL;DR: It is shown that latency is not fully recovered by SMT; the use of L2 data prefetching does not succeed in increasing the performance; and a hardware mechanism to predict L2 misses and control this pollution is proposed.
Proceedings ArticleDOI
Post-silicon CPU adaptation made practical using machine learning
Stephen J. Tarsa,Hong Wang,Rangeen Basu Roy Chowdhury,Julien Sebot,Gautham N. Chinya,Jayesh Gaur,Karthik Sankaranarayanan,Chit-Kwan Lin,Robert S. Chappell,Ronak Singhal +9 more
TL;DR: This paper presents an adaptive CPU based on Intel SkyLake that closes the loop to deployment, and provides a novel mechanism for post-silicon customization, and shows how to optimize PPW using models trained to different SLAs or to specific applications, e.g. to improve datacenter hardware in situ.