<div dir="ltr">I'll second what Russell said, and expand a little. Invariably, becoming part of an HPC group means at some point (due to team demands or your own personal interest) you will likely become the subject matter expert (SME) for something, and thus, yes, you will be the one that will be teaching something to others. The flip side of that statement can also be true: because you'll develop a focus on a few areas means you will have to lean on someone else for another. There is too much to know. That's how I became "the storage guy" when it came to clusters but knew nothing about schedulers other than basic care (making sure it was up and how to get it limping) and fast interconnects (InfiniBand) even though we were actively using them.<div><br></div><div>And I'll also share one of the most maddening things I dealt with in my time in HPC was the focus on speed of results, not efficiency of computing (though code efficiency was occasionally a focus). There are such groups, but certainly in research the focus is on speed so results can be published before anyone else. That invariably means there's clock time available for other projects during lulls if they could be made ready, but we were always focused on faster hardware, not efficient use of it.</div><div><br></div><div>bnm</div></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Mon, Dec 30, 2024 at 8:44 PM Russell L. Carter via Ale <<a href="mailto:ale@ale.org">ale@ale.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">I'm loving it! Old school: see below for the reply<br>
<br>
On 12/30/24 7:59 PM, Leam Hall via Ale wrote:<br>
> On 12/30/24 17:50, Russell L. Carter via Ale wrote:<br>
>> Yes, exactly so. This is what I meant by economically inefficient.<br>
>> You can be a specialist and employed at say a National Lab. of some<br>
>> sort located *not* in an expensive housing city (ie, not NASA Ames)<br>
>> and enjoy the work immensely. I know I did: if you check out the<br>
>> original published NAS Parallel Benchmarks you will find my name right<br>
>> there, and that job was the grandest adventure of my life.<br>
>><br>
>> But!! I don't know anything about SLURM because my own household/small<br>
>> biz clusters just can't justify the overhead for *all the other stuff*<br>
>> that is required to make such a system viable with a low headcount<br>
>> support crew of ahem uno ein un yep *1*.<br>
>><br>
>> I mean it's all cool stuff and if you believe it's for you (it was for<br>
>> me at the time) go for it but have no illusions that anybody on say<br>
>> Hacker News will understand such a thing. (That could be a good reason<br>
>> to do it anyway, yep I get it)<br>
>><br>
>> Basically the whole cloud ecosystem which is heating up the planet so<br>
>> successfully is predicated on *waste*. Maybe somebody has calculated<br>
>> how much of the cloud is simply tests. You need tests, to be sure, but<br>
>> real work is always jobs of days, weeks, months. What the cloud don't<br>
>> care about is efficiency, in the HPC context.<br>
>><br>
>> Good luck and all the best,<br>
>> Russell<br>
>><br>
>> Did I just top post... again? I mean &*^@(*&^#$ Firefox for getting<br>
>> rid of the emacs editing ability.<br>
> <br>
> I'll just remove all else and respond. :D<br>
> <br>
> You, Brian, Vernard, and Jim, became my target audience, although Jim <br>
> was the only person I knew doing HPC. Vernard, Russell, it is good to <br>
> meet you!<br>
> <br>
> Much of my career has been on things most technologists don't care <br>
> about: OS vulnerability scanning, supply chain security, and not dumping <br>
> 27,315 third-party packages on a node because the STDLIB method isn't <br>
> the newest or coolest thing. Having done cloud, and even supported an <br>
> enterprise-specific cloud backend, your opinion seems to match mine. The <br>
> cloud is flexible, but not overly efficient. Many cloud start-ups don't <br>
> seem to care what OS is underneath, they just want their app to run and <br>
> keep running. Which is a fine thing! If it pays the bills for them and <br>
> adds value to the world, then more power to them.<br>
> <br>
> I have a chance at an HPC job. During the interview I was honest about <br>
> what I didn't know, even admitting that I had to do a web search on <br>
> "Slurm". I like to think I can learn, given a task list, but with HPC "I <br>
> don't know what I don't know". Hence the original question. I chased the <br>
> "AppDev" career path for a while, and while I like playing with code, <br>
> front end development just isn't my joy. I like Linux, I've built a <br>
> career supporting it, and HPC seems like a cool path.<br>
> <br>
<br>
Ok, all good.<br>
<br>
> One of the things I'm looking forward to is not being the smartest <br>
> person in the "room". Which is funny, as I'm not particularly smart. <br>
> I've just been doing this for a long time and enjoy learning more about <br>
> whatever I'm doing. If I can get into an HPC shop I'll have a lot to <br>
> learn and smart people to learn from.<br>
<br>
No.<br>
<br>
I worked at NASA Ames "NAS", and at Sandia Livermore, and traveled to <br>
about 30 research labs across the country, including later when I was <br>
doing SBIRS. You are as good as your technical chops are. If you are in <br>
the room, or on the call, or responding constructively in a distributed<br>
email (or whatever the kidz do these days) you are already there. You<br>
learn, yes, everybody learns. Those smart people are learning from<br>
*you*, my friend.<br>
<br>
The problem with software shops that I have had experience with is that<br>
tenure is so understandably tenuous that people don't speak frankly;<br>
they don't prepare you for the "life of the mind" that we had way<br>
back then. I can tell you that it is very likely that as a software<br>
person with (proven?) experience in the cloud that the interviewing<br>
person is probably *very* interested in that perspective, as will be<br>
the people you support. You can't possibly understand any of the codes<br>
though and no sane person at the institution would ever suspect it.<br>
<br>
But! As you may have surmised from the replies those technical<br>
people mainly want their codes to run efficiently. Days -> hours.<br>
hours -> minutes. That sort of thing. I find that kind of puzzle<br>
intoxicatingly seductive; if only it could have paid for our life.<br>
<br>
<br>
All the best,<br>
Russell<br>
<br>
> So I'm hoping and praying for the job; we'll see what happens.<br>
> <br>
> Thanks!<br>
> <br>
> Leam<br>
> <br>
> <br>
<br>
_______________________________________________<br>
Ale mailing list<br>
<a href="mailto:Ale@ale.org" target="_blank">Ale@ale.org</a><br>
<a href="https://mail.ale.org/mailman/listinfo/ale" rel="noreferrer" target="_blank">https://mail.ale.org/mailman/listinfo/ale</a><br>
See JOBS, ANNOUNCE and SCHOOLS lists at<br>
<a href="http://mail.ale.org/mailman/listinfo" rel="noreferrer" target="_blank">http://mail.ale.org/mailman/listinfo</a><br>
</blockquote></div>