PPT-NUMA I/O Optimizations

Bruce Worthington Software Development Manager Microsoft Corporation Key Takeaways Be a leader in advancing 64bit computing Adopt best practices and new tools Lets partner on new hardware directions. Nuno Lopes . and. José Monteiro. Deriving preconditions by hand is hard; WPs are often non-trivial. WPs derived by hand are often wrong!. Weaker preconditions expose more optimization opportunities. in . Dyninst. Andrew . Bernat. , Matthew Legendre. Instrumentation is Complicated. User perspective: . “Insert some new code here, here, and here.”. Dyninst’s. perspective:. Relocation. – Move code to make space for instrumentation. and High-Coverage Tests. Presented by Yoni Leibowitz. EXE & KLEE. Automatically Generating Inputs of Death. David Dill. Vijay . Ganesh. Cristian Cadar. Dawson Engler. Peter Pawlowski. KLEE. EXE. Unassisted & Automatic Generation of High-Coverage Tests for Complex System Programs. for NUMA Systems. Zoltán Majó. Thomas R. Gross. Department of Computer Science. ETH Zurich, Switzerland. 1. A Library for. Portable and Composable. NUMA. . systems. Key to good performance: data locality. What Hardware used to look like…. Northbridge connects CPU and memory to rest of system. Memory controller implemented in Northbridge chipset. Devices and CPU can access memory via requests to Northbridge. Nuno Lopes . and. José Monteiro. Deriving preconditions by hand is hard; WPs are often non-trivial. WPs derived by hand are often wrong!. Weaker preconditions expose more optimization opportunities. Thomas Kejser. Senior Program Manager. Microsoft. Agenda. Windows Server 2008R2 and SQL Server 2008R2 improvements. Scale architecture. Customer Requirements. Hardware setup. Transaction log essentials. Thomas Kejser. Senior Program Manager. Microsoft. Agenda. Windows Server 2008R2 and SQL Server 2008R2 improvements. Scale architecture. Customer Requirements. Hardware setup. Transaction log essentials. Phil Pennington. philpenn@microsoft.com. Microsoft. WSV317. . What will you look for?. Overall Solution Scalability. Agenda. Windows Server 2008 . R2. New NUMA APIs. New User-Mode Scheduling APIs. New C++ Concurrency Runtime. The EfcthoeNUcMMcAoMMNu hcMMcAonigsMCPcr aU-T:,Wl,SNTcktKf sPN‡n M fd ZeccvhxrosN?xf csxMNlxgcexfced Co-authorሙ Costin Caramarcu, William Streܞer-Kellogg, Tony Wong, Alexandr ⌗ytsev Wȗt is By Patryk Kaminski Patryk.Kaminski@amd.com Introduction Writing software for multi-processor systems is not an easy task. In an ideal scenario, as the total number of processors increase in a syste A Dell EMC Dell EMC NUMA Configuration for AMD EPYC (Naples) Processors Dell Engineering February 2018 2 Dell EMC NUMA Configuration for AMD EPYC (Naples) Processo rs | version 1.0 Revisions Date D 2. Arkaprava Basu. 1. Abhishek Bhattacharjee. 3. Kanchi. Gopinath. 1. Jayneel. Gandhi. 4. 1 . Indian Institute of Science . 2. University of British Columbia . 3 . Yale University . In a NUMA machine, data placement and thread binding will have impact on the performance of an application. OpenMP. data allocation. OpenMP. thread affinity. NUMA . Shared memory architecture. Current SMP systems adopt mostly NUMA shared memory architecture..