Sponsored Content
Special Forums UNIX and Linux Applications High Performance Computing What does high performance computing mean? Post 302389938 by linuxpenguin on Tuesday 26th of January 2010 12:22:35 PM
Old 01-26-2010
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" sounds like the edge we need today. I will be very happy to see more activity in here.
 

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 Replies)
Discussion started by: wilder.mellotto
2 Replies

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... (0 Replies)
Discussion started by: Linux Bot
0 Replies

3. High Performance Computing

High Performance Computing

I am interested in setting up some High Performance Computing clusters and would like to get people's views and experiences on this. I have 2 requirements: 1. Compute clusters to do fast cpu intensive computations 2. Storage clusters of parallel and extendable filesystems spread across many... (6 Replies)
Discussion started by: humbletech99
6 Replies

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 . (0 Replies)
Discussion started by: rahul_viz
0 Replies

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... (8 Replies)
Discussion started by: Solarius
8 Replies

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... (0 Replies)
Discussion started by: JPJPJPJP
0 Replies
cprof(3erl)						     Erlang Module Definition						       cprof(3erl)

NAME
cprof - A simple Call Count Profiling Tool using breakpoints for minimal runtime performance impact. DESCRIPTION
The cprof module is used to profile a program to find out how many times different functions are called. Breakpoints similar to local call trace, but containing a counter, are used to minimise runtime performance impact. Since breakpoints are used there is no need for special compilation of any module to be profiled. For now these breakpoints can only be set on BEAM code so s cannot be call count traced. The size of the call counters is the host machine word size. One bit is used when pausing the counter, so the maximum counter value for a 32-bit host is 2147483647. The profiling result is delivered as a term containing a sorted list of entries, one per module. Each module entry contains a sorted list of functions. The sorting order in both cases is of decreasing call count. Call count tracing is very lightweight compared to other forms of tracing since no trace message has to be generated. Some measurements indicates performance degradation in the vicinity of 10 percent. EXPORTS
analyse() -> {AllCallCount, ModAnalysisList} analyse(Limit) -> {AllCallCount, ModAnalysisList} analyse(Mod) -> ModAnlysis analyse(Mod, Limit) -> ModAnalysis Types Limit = integer() Mod = atom() AllCallCount = integer() ModAnalysisList = [ModAnalysis] ModAnalysis = {Mod, ModCallCount, FuncAnalysisList} ModCallCount = integer() FuncAnalysisList = [{{Mod, Func, Arity}, FuncCallCount}] Func = atom() Arity = integer() FuncCallCount = integer() Collects and analyses the call counters presently in the node for either module Mod , or for all modules (except cprof itself), and returns: FuncAnalysisList : A list of tuples, one for each function in a module, in decreasing FuncCallCount order. ModCallCount : The sum of FuncCallCount values for all functions in module Mod . AllCallCount : The sum of ModCallCount values for all modules concerned in ModAnalysisList . ModAnalysisList : A list of tuples, one for each module except cprof , in decreasing ModCallCount order. If call counters are still running while analyse/0..2 is executing, you might get an inconsistent result. This happens if the process executing analyse/0..2 gets scheduled out so some other process can increment the counters that are being analysed, Calling pause() before analysing takes care of the problem. If the Mod argument is given, the result contains a ModAnalysis tuple for module Mod only, otherwise the result contains one Mod- Analysis tuple for all modules returned from code:all_loaded() except cprof itself. All functions with a FuncCallCount lower than Limit are excluded from FuncAnalysisList . They are still included in ModCallCount , though. The default value for Limit is 1 . pause() -> integer() Pause call count tracing for all functions in all modules and stop it for all functions in modules to be loaded. This is the same as (pause({'_','_','_'})+stop({on_load})) . See also pause/1..3 below. pause(FuncSpec) -> integer() pause(Mod, Func) -> integer() pause(Mod, Func, Arity) -> integer() Types FuncSpec = Mod | {Mod,Func,Arity}, {FS} Mod = atom() Func = atom() Arity = integer() FS = term() Pause call counters for matching functions in matching modules. The FS argument can be used to specify the first argument to erlang:trace_pattern/3 . See erlang(3erl). The call counters for all matching functions that has got call count breakpoints are paused at their current count. Return the number of matching functions that can have call count breakpoints, the same as start/0..3 with the same arguments would have returned. restart() -> integer() restart(FuncSpec) -> integer() restart(Mod, Func) -> integer() restart(Mod, Func, Arity) -> integer() Types FuncSpec = Mod | {Mod,Func,Arity}, {FS} Mod = atom() Func = atom() Arity = integer() FS = term() Restart call counters for the matching functions in matching modules that are call count traced. The FS argument can be used to specify the first argument to erlang:trace_pattern/3 . See erlang(3erl). The call counters for all matching functions that has got call count breakpoints are set to zero and running. Return the number of matching functions that can have call count breakpoints, the same as start/0..3 with the same arguments would have returned. start() -> integer() Start call count tracing for all functions in all modules, and also for all functions in modules to be loaded. This is the same as (start({'_','_','_'})+start({on_load})) . See also start/1..3 below. start(FuncSpec) -> integer() start(Mod, Func) -> integer() start(Mod, Func, Arity) -> integer() Types FuncSpec = Mod | {Mod,Func,Arity}, {FS} Mod = atom() Func = atom() Arity = integer() FS = term() Start call count tracing for matching functions in matching modules. The FS argument can be used to specify the first argument to erlang:trace_pattern/3 , for example on_load . See erlang(3erl). Set call count breakpoints on the matching functions that has no call count breakpoints. Call counters are set to zero and running for all matching functions. Return the number of matching functions that has got call count breakpoints. stop() -> integer() Stop call count tracing for all functions in all modules, and also for all functions in modules to be loaded. This is the same as (stop({'_','_','_'})+stop({on_load})) . See also stop/1..3 below. stop(FuncSpec) -> integer() stop(Mod, Func) -> integer() stop(Mod, Func, Arity) -> integer() Types FuncSpec = Mod | {Mod,Func,Arity}, {FS} Mod = atom() Func = atom() Arity = integer() FS = term() Stop call count tracing for matching functions in matching modules. The FS argument can be used to specify the first argument to erlang:trace_pattern/3 , for example on_load . See erlang(3erl). Remove call count breakpoints from the matching functions that has call count breakpoints. Return the number of matching functions that can have call count breakpoints, the same as start/0..3 with the same arguments would have returned. SEE ALSO
eprof(3erl), fprof(3erl), erlang(3erl), User's Guide Ericsson AB tools 2.6.6.3 cprof(3erl)
All times are GMT -4. The time now is 06:48 PM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy