# HG changeset patch
# User Pradeep Ramachandran <[email protected]>
# Date 1440585642 -19800
# Wed Aug 26 16:10:42 2015 +0530
# Node ID dd7ef2bd657f8e8369c2b8c10e0452b9ff6e37f5
# Parent d8091487bc9749e702c468786b0cd9e663478a91
Performance: Prevent small thread-pools if NUMA disabled and # CPUs >
MAX_POOL_THREADS
When NUMA is disabled and if # CPUs is > MAX_POOL_THREADS (64 or 32 depending
on 64-bit
or 32-bit builds), the last pool may have few threads. This patch allows the
last pool to
exist only if it has > MAX_POOL_THREADS/2 threads; the 50% number is a heurstic.
Feature gains performance of 5% on Intel Xeon E5-2699v3 measured in slower
preset with 4K video.
diff -r d8091487bc97 -r dd7ef2bd657f source/common/threadpool.cpp
--- a/source/common/threadpool.cpp Tue Aug 25 16:39:12 2015 -0700
+++ b/source/common/threadpool.cpp Wed Aug 26 16:10:42 2015 +0530
@@ -289,6 +289,14 @@
}
}
+ // In the case that numa is disabled and we have more CPUs than 64,
+ // spawn the last pool only if the # threads in that pool is > 1/2 max
(heuristic)
+ if ((numNumaNodes == 1) && (cpusPerNode[0] % MAX_POOL_THREADS <
(MAX_POOL_THREADS / 2)))
+ {
+ cpusPerNode[0] -= (cpusPerNode[0] % MAX_POOL_THREADS);
+ x265_log(p, X265_LOG_DEBUG, "Creating only %d worker threads to
prevent asymmetry in pools; may not use all HW contexts\n", cpusPerNode[0]);
+ }
+
numPools = 0;
for (int i = 0; i < numNumaNodes; i++)
{
_______________________________________________
x265-devel mailing list
[email protected]
https://mailman.videolan.org/listinfo/x265-devel
