[Openmcl-devel] Speed, compilers and multi-core processors

Alexander Repenning ralex at cs.colorado.edu
Tue May 19 17:58:51 UTC 2009


When I came to the University of Colorado that was my first job to  
program the connection machine (up to 65536 CPUs) in Lisp. Needless to  
say, the 12 dimensional hypercube architecture did not work out. Back  
then parallelism was super expensive. Now, probably the machine that  
you are reading this email on has at least two cores.  Here is a slide  
comparing performance and price. Notice the price/GFlop ratio change:




Having scientists with Fortran background write code in StarLisp for  
the CM2 was not a good idea at the time. The SIMD architecture was too  
limiting. But some of that work is ready to go on multi cores. For  
instance, if are interested in optimization and pathfinding you may  
find this interesting: http://www.cs.colorado.edu/~ralex/papers/PDF/OOPSLA06antiobjects.pdf

Alex




On May 19, 2009, at 12:44 PM, Ron Garret wrote:

> Didn't the Lisp community already solve this problem with *Lisp on  
> the Connection Machine?
>
> On May 19, 2009, at 6:13 AM, Glen Foy wrote:
>
>> This is a fascinating area and clearly the wave of the future.  We  
>> could have processors with 512 cores ten years from now.  That  
>> power has to be utilized.
>>
>> A Lisp that focused on parallel execution would be an amazing  
>> tool.  New worlds to conquer ...
>>
>> -Glen
>>
>>
>>
>> On May 19, 2009, at 8:05 AM, Alexander Repenning wrote:
>>
>>> not so fast ;-)
>>>
>>> The "how can we make use of multiple cores" is currently on the  
>>> the hottest funding topics supported by NSF, DOE, Microsoft, .....
>>>
>>> Perhaps it is the Lisp way to look at architectures such as the  
>>> x86 and see mostly limitations when indeed there are plenty of  
>>> opportunities. This is not about registers but about enabling end  
>>> user programmers such as scientists to make use of parallelism.  
>>> The big question is how to reconceptualize programming. One of the  
>>> main problems is the need to overcome bad algorithmic assumptions  
>>> especially the use of unnecessary loops. For instance, in  
>>> Bioinformatics textbooks are full of loop based implementations of  
>>> algorithms dealing with huge data structures such as gene  
>>> sequences. In many cases one could replace sequential loops with  
>>> parallel execution.
>>>
>>> Zoom out of the low level view of things. What could multi core  
>>> Lisp do? Look at the computational challenges that users are  
>>> dealing with. Try to come up with new computational paradigms that  
>>> could help. Lisp could be a great platform to explore these  
>>> issues. Careful: if you can contribute to this you may actually  
>>> receive funding.
>>>
>>> alex
>>>
>>>
>>>
>>> On May 18, 2009, at 10:45 AM, Brian Mastenbrook wrote:
>>>
>>>> On Mon, 2009-05-18 at 10:13 -0400, Glen Foy wrote:
>>>>
>>>>> My ignorance of compiler design is breathtaking, but could multi- 
>>>>> core
>>>>> compiler techniques be used to compensate for Intel's register- 
>>>>> starved
>>>>> architecture?
>>>>
>>>> In a word, no.
>>>
>>> Prof. Alexander Repenning
>>>
>>> University of Colorado
>>> Computer Science Department
>>> Boulder, CO 80309-430
>>>
>>> vCard: http://www.cs.colorado.edu/~ralex/AlexanderRepenning.vcf
>>>
>>>
>>
>> _______________________________________________
>> Openmcl-devel mailing list
>> Openmcl-devel at clozure.com
>> http://clozure.com/mailman/listinfo/openmcl-devel
>
> _______________________________________________
> Openmcl-devel mailing list
> Openmcl-devel at clozure.com
> http://clozure.com/mailman/listinfo/openmcl-devel

Prof. Alexander Repenning

University of Colorado
Computer Science Department
Boulder, CO 80309-430

vCard: http://www.cs.colorado.edu/~ralex/AlexanderRepenning.vcf


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.clozure.com/pipermail/openmcl-devel/attachments/20090519/3f1fef54/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: pastedGraphic.jpg
Type: image/jpeg
Size: 331278 bytes
Desc: not available
URL: <http://lists.clozure.com/pipermail/openmcl-devel/attachments/20090519/3f1fef54/attachment.jpg>


More information about the Openmcl-devel mailing list