High Performance Computing Post: 302278831

Sponsored Content

Special Forums UNIX and Linux Applications High Performance Computing High Performance Computing Post 302278831 by otheus on Wednesday 21st of January 2009 09:22:27 AM

01-21-2009

Registered User

So this problem used to be rather "simple". Just use some CPU metric (MPIS, FLOPS, SPECint, SPECfloat, whatever) and divide it by the cost of a computer. Then we had a clear choice: 2 CPUs per "1U" system. Now the choice has expanded to cores per chip and we have 2, 4, and even 8-way systems (AMD). You could build a rack of Sunx6400, each containing 64 cores. But we also shouldn't forget Sun's T1 processor line, with 128 "virtual" cores.

Further complicating the issue: cost is no longer just for the compute node. Now you have to consider the networking costs between them. 100 Mbit Ethernet switches are cheap, but may not be suitable for a cluster of very fast machines. Infiniband gives you great performance, but scaling is very expensive -- just the cabling alone can cost as much as your CPUs!

Further complications: the operating costs of cooling and electricity are not insignificant. For every watt used by the CPU, you can count on needing 2 watts to cool it (depends on the climate you're in). Thus, if every computer node requires 1.5 A, and you have 256 compute nodes, you will need 1.5 * 256 * 3 = 1152 Amps of power and maybe 2 30-ton chillers.

otheus

View Public Profile for otheus

Find all posts by otheus

6 More Discussions You Might Find Interesting

1. AIX

Performance Problem - High CPU utilization

Hello everybody. I have a problem with my AIX 5.3. Recently my unix shows a high cpu utilization with sar or topas. I need to find what I have to do to solve this problem, in fact, I don't know what is my problem. I had the same problem with another AIX 5.3 running the same...

2. High Performance Computing

IBM Scheduler for High Throughput Computing on IBM Blue Gene P

A lightweight scheduler that supports high-throughput computing (HTC) applications on Blue Gene/P. (NEW: 06/12/2008 in grid) More...

3. High Performance Computing

What does high performance computing mean?

Sorry, I am not really from a computer science background. But from the subject of it, does it mean something like multi processor programming? distributed computing? like using erlang? Sound like it, which excite me. I just had a 3 day crash course in erlang and "Cocurrency oriented programming"...

4. High Performance Computing

High performance Linkpack

hello everyone , Im new to HPL. i wanted to know whether High performance linpack solves linear system of equations for single precision airthmatic on LINUX. it works for double precision , so is there any HPL version which is for single precision.\ thanks .

5. Emergency UNIX and Linux Support

Performance investigation, very high runq-sz %runocc

I've just been handed a hot potato from a colleague who left :(... our client has been complaining about slow performance on one of our servers. I'm not very experienced in investigating performance issues so I hoping someone will be so kind to provide some guidance Here is an overview of the...

6. High Performance Computing

High Performance Linpack Compiling Issue

I'm trying to compile Linpack on a Ubuntu cluster. I'm running MPI. I've modified the following values to fit my system TOPdir MPdir LAlib CC LINKER. When compiling I get the following error: (the error is at the end, the other errors in between are because I've ran the script several times so...

LEARN ABOUT CENTOS

pmtrimnamespace

PMTRIMNAMESPACE(3)					     Library Functions Manual						PMTRIMNAMESPACE(3)

NAME

       pmTrimNameSpace - prune a performance metrics name space

C SYNOPSIS

       #include <pcp/pmapi.h>

       int pmTrimNameSpace(void);

       cc ... -lpcp

DESCRIPTION

       If  the current Performance Metrics Application Programming Interface (PMAPI) context corresponds to a version 1 archive log of Performance
       Co-Pilot (PCP) performance metrics (as collected by pmlogger(1) -V1), then the currently loaded Performance Metrics Name Space  (PMNS),	is
       trimmed to exclude metrics for which no description can be found in the archive.  The PMNS is further trimmed to remove empty subtrees that
       do not contain any performance metric.

       Since PCP archives usually contain some subset of all metrics named in the default PMNS, pmTrimNameSpace  effectively  trims  the  applica-
       tion's PMNS to contain only the names of the metrics in the archive.

       Since PCP 2.0, pmTrimNameSpace is only needed for dealing with version 1 archives.  Version 2 archives actually store the "trimmed" PMNS.

       Prior to any trimming, the PMNS is restored to the state as of the completion of the last pmLoadASCIINameSpace(3) or pmLoadNameSpace(3), so
       the effects of consecutive calls to pmTrimNameSpace with archive contexts are not additive.

       If the current PMAPI context corresponds to a host and a pmLoadASCIINameSpace(3) or pmLoadNameSpace(3) call was made, then the PMNS reverts
       to all names loaded into the PMNS at the completion of the last pmLoadASCIINameSpace(3) or pmLoadNameSpace(3), i.e. any trimming is undone.

       On success, pmTrimNameSpace returns zero.

SEE ALSO

       pmlogger(1), PMAPI(3), pmLoadASCIINameSpace(3), pmLoadNameSpace(3), pmNewContext(3) and pmns(5).

DIAGNOSTICS

       PM_ERR_NOPMNS
	      you must have loaded a PMNS using pmLoadASCIINameSpace(3) or pmLoadNameSpace(3) before calling pmTrimNameSpace

       PM_ERR_NOCONTEXT
	      the current PMAPI context is invalid

Performance Co-Pilot							PCP							PMTRIMNAMESPACE(3)