Sponsored Content
Special Forums UNIX and Linux Applications High Performance Computing IBM Hardware: Test speed of an execution core reliably. Post 302852907 by Corona688 on Thursday 12th of September 2013 03:12:05 PM
Old 09-12-2013
Multithreading does not work that way; two cores can't cooperate to run a single-threaded program faster. Single-threaded programs will run slower on machines with lots of slower cores; we've had some puzzled folks ask us why their new machines have worse single-threaded benchmarks than their old ones.

But more cores means you can run more threads or processes at once without sharing time; more total work can be accomplished in the aggregate; but a program has to be designed with this in mind (or multiple instances of it run) to take advantage of this capability.
 

8 More Discussions You Might Find Interesting

1. AIX

FTP Speed Problem on IBM P-Series equiped with AIX 5.2

Hi, We have IBM P-Series servers (P690, P650) equiped with AIX 5.2. Further we have 10/100 MB ethernet cards in P650 and 10/100/1000 MB ethernet cards in P690 servers. Servers are on a LAN connected with Cisco 3750 catalyst switch. FTP from one server to another is very slow,,,even 3-4 MB... (3 Replies)
Discussion started by: aqeelcu@hotmail
3 Replies

2. AIX

IBM Hardware question

I am looking to buy a 7044 - either a 170 or 270. From what I can find on web searchs the 170 is NOT upgradable to more that one CPU? Is that correct? Can I upgrade the planer on a 170 to a 270 to support multiple CPU's? Does anyone have any other suggestion for AIX hardware? (5 Replies)
Discussion started by: dizman67
5 Replies

3. UNIX for Advanced & Expert Users

speed test +20,000 file existance checks too slow

Need to make a very fast file existence checker. Passing in 20-50K num of files In the code below ${file} is a file with a listing of +20,000 files. test_speed is the script. I am commenting out the results of <time test_speed try>. The normal "test -f" is much much too slow when a system... (2 Replies)
Discussion started by: nullwhat
2 Replies

4. AIX

core dump generation in IBM machine

Hi, im getting a core dump file in a AIX machine while using a complex c++ program. The same program is working without any core error in another system with sun OS 5.9. The program has used structs, LL's and lots of call by references. What may be the reason. will it be a problem with the OS ? (3 Replies)
Discussion started by: suresh_kb211
3 Replies

5. Solaris

hardware test fails

Hi, I have a SunFire 280R abd when I boot it there is a hardware check running and it fails. Here is a long output of the test rsc> poweron Are you sure you want to turn your system power on (Yes/No)? yes rsc> console RSC Alert: Host System has Reset @(#)OBP 4.5.10 2002/02/11 10:39... (2 Replies)
Discussion started by: Tex-Twil
2 Replies

6. Hardware

Hardware Correction: How to change DVD write speed

I am now on Kernel 2.6.32-26 For me 16x CD write speed is okay. I have old hardware which was able to write DVDs at 1x, back in previous linux version. Now, I dont get speed of less than 4x. Tested on k3b, xfburn, and brasero. But all start at bottom 4x write speed. k3b forced back to... (0 Replies)
Discussion started by: makh
0 Replies

7. AIX

New to AIX and IBM Hardware. Need some info

Hello all. I'm new to AIX and IBM hardware and I have a question around the configuration of the service processor on the power series. I need to know: 1) How do I get into the service processor from the serial console when AIX is up and running. I come from the Sun world and I tried all I know.... (1 Reply)
Discussion started by: glenc2004
1 Replies

8. Hardware

How to test the speed of your WIFI network?

Dear all, Would you know how to measure the max speed of a WIFI connection between a router and a laptop for instance? Many thanks for your help! Regards, (3 Replies)
Discussion started by: freddie50
3 Replies
HWLOC-BIND(1)							       hwloc							     HWLOC-BIND(1)

NAME
hwloc-bind - Launch a command that is bound to specific processors and/or memory. SYNOPSIS
hwloc-bind [options] <location1> [<location2> [...] ] [--] <command> ... OPTIONS
See below for a description of valid <location> formats. --cpubind Use following arguments for CPU binding (default). --membind Use following arguments for memory binding. If --mempolicy is not also given, the default policy is bind. --mempolicy <policy> Change the memory binding policy. The available policies are default, firsttouch, bind, interleave replicate and nexttouch. This option is only meaningful when an actual binding is also given with --membind. If --membind is given without --mempolicy, the default policy is bind. --get Report the current bindings. When combined with --membind, report the memory binding instead of CPU binding. --get-last-cpu-location Report the last processors where the process ran. Note that the result may already be outdated when reported since the operating system may move the process to other processors at any time according to the binding. This option cannot be combined with --mem- bind. --single Bind on a single CPU to prevent migration. --strict Require strict binding. --get Retrieve the current process binding --pid <pid> Operate on pid <pid> -p --physical take OS/physical indexes instead of logical indexes -l --logical take logical indexes instead of physical/OS indexes (default) --taskset Display CPU set strings in the format recognized by the taskset command-line program instead of hwloc-specific CPU set string format. This option has no impact on the format of input CPU set strings, both formats are always accepted. -v Verbose output. --version Report version and exit. DESCRIPTION
hwloc-bind execs an executable (with optional command line arguments) that is bound to the specified location (or list of locations). Upon successful execution, hwloc-bind simply sets bindings and then execs the executable over itself. NOTE: It is highly recommended that you read the hwloc(7) overview page before reading this man page. Most of the concepts described in hwloc(7) directly apply to the hwloc-bind utility. EXAMPLES
hwloc-bind's operation is best described through several examples. More details about how locations are specified on the hwloc-bind com- mand line are described in hwloc(7). To run the echo command on the first logical processor of the second socket: hwloc-bind socket:1.pu:0 -- echo hello which is exactly equivalent to hwloc-bind socket:1.pu:0 echo hello To bind the "echo" command to the first core of the second socket and the second core of the first socket: hwloc-bind socket:1.core:0 socket:0.core:1 echo hello Note that binding the "echo" command to multiple processors is probably meaningless (because "echo" is likely implemented as a single- threaded application); these examples just serve to show what hwloc-bind can do. To run on the first three sockets on the second and third nodes: hwloc-bind node:1-2.socket:0:3 echo hello which is also equivalent to: hwloc-bind node:1-2.socket:0-2 echo hello Note that if you attempt to bind to objects that do not exist, hwloc-bind will not warn unless -v was specified. To run on processor with physical index 2 in socket with physical index 1: hwloc-bind --physical socket:1.core:2 echo hello To run on odd cores within even sockets: hwloc-bind socket:even.core:odd echo hello To run on the first socket, except on its second and fifth cores: hwloc-bind socket:0 ~socket:0.core:1 ~socket:0.core:4 echo hello To run anywhere except on the first socket: hwloc-bind all ~socket:0 echo hello To run on a core near the network interface named eth0: hwloc-bind os=eth0 echo hello To run on a core near the PCI device whose bus ID is 0000:01:02.0: hwloc-bind pci=0000:01:02.0 echo hello To bind memory on second memory node and run on first node (when supported by the OS): hwloc-bind --cpubind node:1 --membind node:0 echo hello The --get option can report current bindings. This example shows nesting hwloc-bind invocations to set a binding and then report it: hwloc-bind node:1.socket:2 hwloc-bind --get On one of the hwloc developer's machines, this example reports "0x00004444,0x44000000". The mask reported on your machine may be differ- ent. Locations may also be specified as a hex bit mask (typically generated by hwloc-calc). For example: hwloc-bind 0x00004444,0x44000000 echo hello hwloc-bind `hwloc-calc node:1.socket:2` echo hello Memory binding may also be reported: hwloc-bind --membind node:1 --mempolicy interleave -- hwloc-bind --get --membind This returns a string describing the memory binding, such as "0x000000f0 (interleave)". Note that if the system does not contain any NUMA nodes, the reported string will indicate that the process is bound to the entire system memory (e.g., "0xf...f"). RETURN VALUE
Upon successful execution, hwloc-bind execs the command over itself. The return value is therefore whatever the return value of the com- mand is. hwloc-bind will return nonzero if any kind of error occurs, such as (but not limited to): failure to parse the command line, failure to retrieve process bindings, or lack of a command to execute. SEE ALSO
hwloc(7), lstopo(1), hwloc-calc(1), hwloc-distrib(1) 1.4.1 Feb 27, 2012 HWLOC-BIND(1)
All times are GMT -4. The time now is 03:20 AM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy