summaryrefslogtreecommitdiff
path: root/2005/flow-accounting-ols2005/OLS2005/siddha/siddha-abstract.tex
diff options
context:
space:
mode:
Diffstat (limited to '2005/flow-accounting-ols2005/OLS2005/siddha/siddha-abstract.tex')
-rw-r--r--2005/flow-accounting-ols2005/OLS2005/siddha/siddha-abstract.tex43
1 files changed, 43 insertions, 0 deletions
diff --git a/2005/flow-accounting-ols2005/OLS2005/siddha/siddha-abstract.tex b/2005/flow-accounting-ols2005/OLS2005/siddha/siddha-abstract.tex
new file mode 100644
index 0000000..f8f1bbe
--- /dev/null
+++ b/2005/flow-accounting-ols2005/OLS2005/siddha/siddha-abstract.tex
@@ -0,0 +1,43 @@
+
+% Registration Chip Multi Processing(CMP) aware Linux Kernel Scheduler
+% [2]Register/Submit Suresh Siddha (suresh.b.siddha@intel.com)
+
+Recent advances in semiconductor manufacturing and
+engineering technologies have led to the inclusion of
+more than one CPU core in a single physical package.
+This, popularly know as Chip Multi Processing (CMP),
+allows multiple instruction streams to execute at the
+same time. CMP is in addition to today's Simultaneous
+Multi Threading (SMT) capabilities, like Intel{\textregistered}
+Hyper-Threading technology which allows a processor to
+present itself as two logical processors, resulting in
+best use of execution resources. With CMP, today's
+Linux Kernel will deliver instantaneous performance
+improvement. Linux Kernel scheduler could be further
+optimized by making it CMP-aware.
+
+In this paper, we will start with an overview of
+different CMP implementation's and then look into
+performance, power related optimization opportunities.
+We will describe the trade-offs between peak
+performance and power saving requirements. We will
+discuss how scheduler enhancements like
+
+\begin{itemize}
+\item adding a new scheduler domain for CMP
+
+\item setting up domain properties based on CMP
+characteristics
+
+\item active load balancing in the context of CMP and SMT
+\end{itemize}
+
+will improve the peak performance. Secondly, we will
+look at scheduler enhancements focusing power savings.
+We will then present scheduling policies that an
+administrator can select based on the performance and
+power requirements. We will close the paper with a
+brief look at CMP trends in future generation Intel(R)
+processors.
+
+
personal git repositories of Harald Welte. Your mileage may vary