From af0606f5d626b92d6e59da3a797548e9daab5580 Mon Sep 17 00:00:00 2001
From: Qingqing Li <liqingqing3@huawei.com>
Date: Sat, 25 Jun 2022 15:36:44 +0800
Subject: [PATCH] x86: use total l3cache for non_temporal_threshold

Below glibc upstream patch modified the default behavoir for large size of memcpy,
such as 1M~10M. revert it and use GLIBC_TUNABLES="glibc.cpu.x86_non_temporal_threshold=xxx"
to tune the application when needed.

d3c57027470b78dba79c6d931e4e409b1fecfc80
Author: Patrick McGehearty <patrick.mcgehearty@oracle.com>
Date:   Mon Sep 28 20:11:28 2020 +0000

    Reversing calculation of __x86_shared_non_temporal_threshold
    
    The __x86_shared_non_temporal_threshold determines when memcpy on x86
    uses non_temporal stores to avoid pushing other data out of the last
    level cache.
    uses non_temporal stores to avoid pushing other data out of the last
    level cache.
    
    This patch proposes to revert the calculation change made by H.J. Lu's
    patch of June 2, 2017.
    
    H.J. Lu's patch selected a threshold suitable for a single thread
    getting maximum performance. It was tuned using the single threaded
    large memcpy micro benchmark on an 8 core processor. The last change
    changes the threshold from using 3/4 of one thread's share of the
    cache to using 3/4 of the entire cache of a multi-threaded system
    before switching to non-temporal stores. Multi-threaded systems with
    more than a few threads are server-class and typically have many
    active threads. If one thread consumes 3/4 of the available cache for
    all threads, it will cause other active threads to have data removed
    from the cache. Two examples show the range of the effect. John
    McCalpin's widely parallel Stream benchmark, which runs in parallel
    and fetches data sequentially, saw a 20% slowdown with this patch on
    an internal system test of 128 threads. This regression was discovered
    when comparing OL8 performance to OL7.  An example that compares
    normal stores to non-temporal stores may be found at
    https://vgatherps.github.io/2018-09-02-nontemporal/.  A simple test
    shows performance loss of 400 to 500% due to a failure to use
    nontemporal stores. These performance losses are most likely to occur
    when the system load is heaviest and good performance is critical.
    
    The tunable x86_non_temporal_threshold can be used to override the
    default for the knowledgable user who really wants maximum cache
    allocation to a single thread in a multi-threaded system.
    The manual entry for the tunable has been expanded to provide
    more information about its purpose.

            modified: sysdeps/x86/cacheinfo.c
            modified: manual/tunables.texi
---
 sysdeps/x86/dl-cacheinfo.h | 4 ++++++
 1 file changed, 4 insertions(+)

diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
index e6c94dfd..c5e8deb3 100644
--- a/sysdeps/x86/dl-cacheinfo.h
+++ b/sysdeps/x86/dl-cacheinfo.h
@@ -926,6 +926,10 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
   if (tunable_size != 0)
     shared = tunable_size;
 
+  /* keep x86 to use the same non_temporal_threshold like glibc2.28 */
+  if (threads != 0)
+    non_temporal_threshold *= threads;
+
   tunable_size = TUNABLE_GET (x86_non_temporal_threshold, long int, NULL);
   if (tunable_size > minimum_non_temporal_threshold
       && tunable_size <= maximum_non_temporal_threshold)
-- 
2.30.0