From 5743bc77a8cc5b7aa8884e08836cb07dd63bad3b Mon Sep 17 00:00:00 2001
From: Don Lipari <lipari1@llnl.gov>
Date: Fri, 31 Jul 2009 20:50:31 +0000
Subject: [PATCH] + -- Applied patch from Rod Schultz (Rod.Schultz@Bull.com)
that eliminates + ambiguity in the documentation over use of the terms
"CPU" and "socket".
---
NEWS | 2 ++
doc/html/mc_support.shtml | 27 +++++++++++++--------------
doc/man/man1/salloc.1 | 4 ++--
doc/man/man1/sbatch.1 | 4 ++--
doc/man/man1/srun.1 | 4 ++--
src/common/proc_args.c | 4 ++--
src/salloc/opt.c | 4 ++--
src/sbatch/opt.c | 4 ++--
src/srun/opt.c | 4 ++--
9 files changed, 29 insertions(+), 28 deletions(-)
diff --git a/NEWS b/NEWS
index 61312a497bb..adc06f35991 100644
--- a/NEWS
+++ b/NEWS
@@ -31,6 +31,8 @@ documents those changes that are of interest to users and admins.
-- Applied patch from Doug Parisek (Doug.Parisek@bull.com) for speeding up
start of sview by delaying to creation of tooltips until requested.
-- Changed GtkToolTips to GtkToolTip for newer versions of GTK.
+ -- Applied patch from Rod Schultz (Rod.Schultz@Bull.com) that eliminates
+ ambiguity in the documentation over use of the terms "CPU" and "socket".
* Changes in SLURM 2.1.0-pre2
=============================
diff --git a/doc/html/mc_support.shtml b/doc/html/mc_support.shtml
index 0944446c7b7..99456da8cfc 100644
--- a/doc/html/mc_support.shtml
+++ b/doc/html/mc_support.shtml
@@ -70,7 +70,7 @@ by their application. Table 1 summarizes the new multi-core flags.
</td></tr>
<tr>
<td> --cores-per-socket=<i>C</i></td>
- <td> Number of cores in a CPU to dedicate to a job (minimum or range)
+ <td> Number of cores in a socket to dedicate to a job (minimum or range)
</td></tr>
<tr>
<td> --threads-per-core=<i>T</i></td>
@@ -130,10 +130,10 @@ to dedicate to a job (minimum or range)
</td></tr>
<tr>
<td> --hint=compute_bound</td>
- <td> use all cores in each physical CPU
+ <td> use all cores in each socket
</td></tr>
<td> --hint=memory_bound</td>
- <td> use only one core in each physical CPU
+ <td> use only one core in each socket
</td></tr>
<td> --hint=[no]multithread</td>
<td> [don't] use extra threads with in-core multi-threading
@@ -294,15 +294,14 @@ to -m block:cyclic with --cpu_bind=thread.</p>
<a name="srun_constraints">
<h3>New Constraints</h3></a>
-<p>To compliment the existing SLURM job minimum constraints
-(CPUs, memory, temp disk),
-constraint flags have also been added to allow a user to
-specify a minimum number of sockets, cores, or threads:</p>
+<p>To complement the existing SLURM job minimum constraints (CPUs,
+memory, temp disk), constraint flags have also been added to allow a
+user to request nodes with a minimum set of resources:</p>
<PRE>
---mincpus=<i>n</i> minimum number of logical cpus per node
+--mincpus=<i>n</i> minimum number of logical processors (threads) per node
<u>--minsockets=<i>n</i></u> minimum number of sockets per node
-<u>--mincores=<i>n</i></u> minimum number of cores per cpu
+<u>--mincores=<i>n</i></u> minimum number of cores per socket
<u>--minthreads=<i>n</i></u> minimum number of threads per core
--mem=<i>MB</i> minimum amount of real memory
--tmp=<i>MB</i> minimum amount of temporary disk
@@ -422,7 +421,7 @@ the right mappings.</p>
<p>For computationally intensive applications, all cores in a multi-core
system would normally be used. For memory bound applications, only
-using a single core on each CPU will result in the highest per
+using a single core on each socket will result in the highest per
core memory bandwidth. For communication intensive applications,
using in-core multi-threading (e.g. hyperthreading, SMT, or TMT)
may also improve performance.
@@ -431,8 +430,8 @@ types of application hints to the SLURM multi-core support:</p>
<PRE>
--hint= Bind tasks according to application hints
- compute_bound use all cores in each physical CPU
- memory_bound use only one core in each physical CPU
+ compute_bound use all cores in each socket
+ memory_bound use only one core in each socket
[no]multithread [don't] use extra threads with in-core multi-threading
help show this help message
</PRE>
@@ -476,7 +475,7 @@ a different layout using the high-level flags since users do not have to
recalculate mask or CPU IDs. The new approach is very effortless compared to
rearranging the mask or map.</p>
-<p>Given a 32-process MPI job and a four dual-CPU dual-core node
+<p>Given a 32-process MPI job and a four dual-socket dual-core node
cluster, we want to use a block distribution across the four nodes and then a
cyclic distribution within the node across the physical processors. We have had
several requests from users that they would like this distribution to be the
@@ -537,7 +536,7 @@ nodes. The --cpu_bind option only allows users to specify a single
mask for all the nodes. Using SLURM high-level flags remove this limitation
since SLURM will correctly generate the appropriate masks for each requested nodes.</p>
-<h3>On a four dual-CPU dual-core node cluster with core block numbering </h3>
+<h3>On a four dual-socket dual-core node cluster with core block numbering </h3>
<p>The cores are shown as c0 and c1 and the processors are shown
as p0 through p3. The CPU IDs within a node in the block numbering are:
diff --git a/doc/man/man1/salloc.1 b/doc/man/man1/salloc.1
index 1b030f15d0e..0b5f5c29333 100644
--- a/doc/man/man1/salloc.1
+++ b/doc/man/man1/salloc.1
@@ -311,11 +311,11 @@ Bind tasks according to application hints
.TP
.B compute_bound
Select settings for compute bound applications:
-use all cores in each physical CPU
+use all cores in each socket
.TP
.B memory_bound
Select settings for memory bound applications:
-use only one core in each physical CPU
+use only one core in each socket
.TP
.B [no]multithread
[don't] use extra threads with in-core multi-threading
diff --git a/doc/man/man1/sbatch.1 b/doc/man/man1/sbatch.1
index cd6850da998..d6a306b8c92 100644
--- a/doc/man/man1/sbatch.1
+++ b/doc/man/man1/sbatch.1
@@ -327,11 +327,11 @@ Bind tasks according to application hints
.TP
.B compute_bound
Select settings for compute bound applications:
-use all cores in each physical CPU
+use all cores in each socket
.TP
.B memory_bound
Select settings for memory bound applications:
-use only one core in each physical CPU
+use only one core in each socket
.TP
.B [no]multithread
[don't] use extra threads with in-core multi-threading
diff --git a/doc/man/man1/srun.1 b/doc/man/man1/srun.1
index 3b00b8e71b2..96fd06ab7d4 100644
--- a/doc/man/man1/srun.1
+++ b/doc/man/man1/srun.1
@@ -357,11 +357,11 @@ Bind tasks according to application hints
.TP
.B compute_bound
Select settings for compute bound applications:
-use all cores in each physical CPU
+use all cores in each socket
.TP
.B memory_bound
Select settings for memory bound applications:
-use only one core in each physical CPU
+use only one core in each socket
.TP
.B [no]multithread
[don't] use extra threads with in-core multi-threading
diff --git a/src/common/proc_args.c b/src/common/proc_args.c
index 5c768d60393..2f72baeb1fc 100644
--- a/src/common/proc_args.c
+++ b/src/common/proc_args.c
@@ -494,8 +494,8 @@ bool verify_hint(const char *arg, int *min_sockets, int *max_sockets,
printf(
"Application hint options:\n"
" --hint= Bind tasks according to application hints\n"
-" compute_bound use all cores in each physical CPU\n"
-" memory_bound use only one core in each physical CPU\n"
+" compute_bound use all cores in each socket\n"
+" memory_bound use only one core in each socket\n"
" [no]multithread [don't] use extra threads with in-core multi-threading\n"
" help show this help message\n");
return 1;
diff --git a/src/salloc/opt.c b/src/salloc/opt.c
index 41708fc65eb..0b00b28afbb 100644
--- a/src/salloc/opt.c
+++ b/src/salloc/opt.c
@@ -1686,9 +1686,9 @@ static void _help(void)
" -C, --constraint=list specify a list of constraints\n"
" -F, --nodefile=filename request a specific list of hosts\n"
" --mem=MB minimum amount of real memory\n"
-" --mincpus=n minimum number of cpus per node\n"
+" --mincpus=n minimum number of logical processors (threads) per node\n"
" --minsockets=n minimum number of sockets per node\n"
-" --mincores=n minimum number of cores per cpu\n"
+" --mincores=n minimum number of cores per socket\n"
" --minthreads=n minimum number of threads per core\n"
" --reservation=name allocate resources from named reservation\n"
" --tmp=MB minimum amount of temporary disk\n"
diff --git a/src/sbatch/opt.c b/src/sbatch/opt.c
index 81224e4d1e4..97b72dea2f5 100644
--- a/src/sbatch/opt.c
+++ b/src/sbatch/opt.c
@@ -2512,9 +2512,9 @@ static void _help(void)
" -C, --constraint=list specify a list of constraints\n"
" -F, --nodefile=filename request a specific list of hosts\n"
" --mem=MB minimum amount of real memory\n"
-" --mincpus=n minimum number of cpus per node\n"
+" --mincpus=n minimum number of logical processors (threads) per node\n"
" --minsockets=n minimum number of sockets per node\n"
-" --mincores=n minimum number of cores per cpu\n"
+" --mincores=n minimum number of cores per socket\n"
" --minthreads=n minimum number of threads per core\n"
" --reservation=name allocate resources from named reservation\n"
" --tmp=MB minimum amount of temporary disk\n"
diff --git a/src/srun/opt.c b/src/srun/opt.c
index 3326d853981..bbc79ab1719 100644
--- a/src/srun/opt.c
+++ b/src/srun/opt.c
@@ -2234,8 +2234,8 @@ static void _help(void)
"Constraint options:\n"
" -C, --constraint=list specify a list of constraints\n"
" --contiguous demand a contiguous range of nodes\n"
-" --mincpus=n minimum number of cpus per node\n"
-" --mincores=n minimum number of cores per cpu\n"
+" --mincpus=n minimum number of logical processors (threads) per node\n"
+" --mincores=n minimum number of cores per socket\n"
" --minsockets=n minimum number of sockets per node\n"
" --minthreads=n minimum number of threads per core\n"
" --mem=MB minimum amount of real memory\n"
--
GitLab