50 lines
1.7 KiB
Diff
50 lines
1.7 KiB
Diff
|
From 47f747217811db35854ea06741be3685e8bbd44d Mon Sep 17 00:00:00 2001
|
||
|
|
From: Noah Goldstein <goldstein.w.n@gmail.com>
|
||
|
|
Date: Mon, 17 Jul 2023 23:14:33 -0500
|
||
|
|
Subject: [PATCH] x86: Fix slight bug in `shared_per_thread` cache size
|
||
|
|
calculation.
|
||
|
|
Content-type: text/plain; charset=UTF-8
|
||
|
|
|
||
|
|
After:
|
||
|
|
```
|
||
|
|
commit af992e7abdc9049714da76cae1e5e18bc4838fb8
|
||
|
|
Author: Noah Goldstein <goldstein.w.n@gmail.com>
|
||
|
|
Date: Wed Jun 7 13:18:01 2023 -0500
|
||
|
|
|
||
|
|
x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4`
|
||
|
|
```
|
||
|
|
|
||
|
|
Split `shared` (cumulative cache size) from `shared_per_thread` (cache
|
||
|
|
size per socket), the `shared_per_thread` *can* be slightly off from
|
||
|
|
the previous calculation.
|
||
|
|
|
||
|
|
Previously we added `core` even if `threads_l2` was invalid, and only
|
||
|
|
used `threads_l2` to divide `core` if it was present. The changed
|
||
|
|
version only included `core` if `threads_l2` was valid.
|
||
|
|
|
||
|
|
This change restores the old behavior if `threads_l2` is invalid by
|
||
|
|
adding the entire value of `core`.
|
||
|
|
Reviewed-by: DJ Delorie <dj@redhat.com>
|
||
|
|
---
|
||
|
|
sysdeps/x86/dl-cacheinfo.h | 4 ++--
|
||
|
|
1 file changed, 2 insertions(+), 2 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
|
||
|
|
index c98fa57a7b..43be2c1229 100644
|
||
|
|
--- a/sysdeps/x86/dl-cacheinfo.h
|
||
|
|
+++ b/sysdeps/x86/dl-cacheinfo.h
|
||
|
|
@@ -614,8 +614,8 @@ get_common_cache_info (long int *shared_ptr, long int * shared_per_thread_ptr, u
|
||
|
|
/* Account for non-inclusive L2 and L3 caches. */
|
||
|
|
if (!inclusive_cache)
|
||
|
|
{
|
||
|
|
- if (threads_l2 > 0)
|
||
|
|
- shared_per_thread += core / threads_l2;
|
||
|
|
+ long int core_per_thread = threads_l2 > 0 ? (core / threads_l2) : core;
|
||
|
|
+ shared_per_thread += core_per_thread;
|
||
|
|
shared += core;
|
||
|
|
}
|
||
|
|
|
||
|
|
--
|
||
|
|
2.39.3
|
||
|
|
|