Gerardo Cisneros S., Ph.D.'s Avatar

Gerardo Cisneros S., Ph.D.

@gcs-hpc.bsky.social

Trilingual HPC expert and benchmarker, erstwhile educator and occasional translator. Princeton Ph.D. (EECS).

464 Followers  |  142 Following  |  43 Posts  |  Joined: 12.11.2024  |  2.0619

Latest posts by gcs-hpc.bsky.social on Bluesky

Video thumbnail

An update from us here at PBS πŸ’™

07.08.2025 18:27 β€” πŸ‘ 3484    πŸ” 2002    πŸ’¬ 51    πŸ“Œ 128

Motorola 68000. 😜

09.08.2025 03:07 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Video thumbnail

Motherfucking wind farms…

30.07.2025 17:02 β€” πŸ‘ 46090    πŸ” 17388    πŸ’¬ 1150    πŸ“Œ 2308

"A full 16 percent (that's over one in six people)". Actually, 16% is under one in six (1/6=0.16+0.02/3).

22.07.2025 23:14 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

history | grep "cmd_you_want_to_repeat" | tail
usually works for me with no ill effects.

19.07.2025 03:29 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Perhaps it's something up with which he will not put. (Stolen from someone famous whose name I can't remember.)

03.07.2025 22:06 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Springer Nature book on machine learning is full of made-up citations Would you pay $169 for an introductory ebook on machine learning with citations that appear to be made up? If not, you might want to pass on purchasing Mastering Machine Learning: From Basics to Ad…

I wouldn't.
retractionwatch.com/2025/06/30/s...

03.07.2025 16:21 β€” πŸ‘ 5    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0
5-panel comic. (1) [teacher with long hair next to whiteboard] TEACHER: I’m supposed to give you the tools to do good science. (2) [teacher addressing students] But what *are* those tools? Methodology is hard and there are so many ways to get incorrect results. What is the magic ingredient that makes for good science? (3) TEACHER: To figure it out, I ran a regression with all the factors people say are important: [embedded list in sub-panel, cut off at end] Outcome variable: correct scientific results. Predictors: collaboration; skepticism of others’ claims; questioning your own beliefs; trying to falsify hypotheses; checking citations; statistical rigor; blinded analysis; financial disclosure; open data (4) TEACHER: The regression says two ingredients are the most crucial: 1) genuine curiosity about the answer to a question, and 2) ammonium hydroxide. (5) STUDENT: Wait, why did *ammonia* score so high? How did it even get on the list? LONG HAIR: ...And now you’re doing good science!

5-panel comic. (1) [teacher with long hair next to whiteboard] TEACHER: I’m supposed to give you the tools to do good science. (2) [teacher addressing students] But what *are* those tools? Methodology is hard and there are so many ways to get incorrect results. What is the magic ingredient that makes for good science? (3) TEACHER: To figure it out, I ran a regression with all the factors people say are important: [embedded list in sub-panel, cut off at end] Outcome variable: correct scientific results. Predictors: collaboration; skepticism of others’ claims; questioning your own beliefs; trying to falsify hypotheses; checking citations; statistical rigor; blinded analysis; financial disclosure; open data (4) TEACHER: The regression says two ingredients are the most crucial: 1) genuine curiosity about the answer to a question, and 2) ammonium hydroxide. (5) STUDENT: Wait, why did *ammonia* score so high? How did it even get on the list? LONG HAIR: ...And now you’re doing good science!

Good Science

xkcd.com/3101/

12.06.2025 20:28 β€” πŸ‘ 3522    πŸ” 629    πŸ’¬ 24    πŸ“Œ 34

Β‘Hasta luego y gracias!

11.06.2025 17:21 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

As of this month we're closer to 2050 than we are 2000.

Have a great day!

10.06.2025 17:07 β€” πŸ‘ 266    πŸ” 25    πŸ’¬ 33    πŸ“Œ 8

More BS (and I don't mean BlueSky) from "AI slop".
Cc: @chromamagic.com

06.05.2025 00:28 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

I've never attended ISC, and it is unlikely I will ever attend unless I get rich enough to afford it on my own dime.

30.04.2025 00:18 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
With β€˜AI slop’ distorting our reality, the world is sleepwalking into disaster | Nesrine Malik A perverse information ecosystem is being mined by big tech for profit, fooling the unwary and sending algorithms crazy, says Guardian columnist Nesrine Malik

Funny you should mention "AI slop": www.theguardian.com/commentisfre...

30.04.2025 00:15 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

Tariffs xkcd.com/3073

08.04.2025 00:03 β€” πŸ‘ 31661    πŸ” 8874    πŸ’¬ 264    πŸ“Œ 477

Join us 26-MAR-2025 1700 UTC at aka.ms/hpc_hallway to mark 5 years of #HPChuddle #HPChallway - the weekly open informal online gathering of #HPC people set up to support our HPC community as in-person meetings closed down & later inspiring creation of @hpc.social

hpc-hallway.github.io/The-Hallway/

24.03.2025 18:20 β€” πŸ‘ 8    πŸ” 8    πŸ’¬ 3    πŸ“Œ 2

The thing is, gallium arsenide will never come even close to being as cheap as silicon.

Don't get me wrong. I like GaAs. I got my Ph.D. by bouncing low-energy electrons off of the (110) surface of pure GaAs single crystals. 😜
2/2

06.03.2025 02:22 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

GaAs has been the semiconductor of the future for decades, presumably because of its higher electron mobility. Unfortunately, Seymour Cray's CRAY-3, based on GaAs, was no faster than the ho-hum silicon CRAY C90 when they both became almost simultaneously available in the mid 90s.
1/2

06.03.2025 02:22 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

The directive-based predecessors to #OpenMP that were available in both Cray Research, Inc., and Silicon Graphics, Inc., compilers in the early to mid-90s. After the so-called merger, OpenMP arose from both.

06.03.2025 02:12 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Stand with UKRAINE! #standWithUkraine

28.02.2025 21:16 β€” πŸ‘ 100    πŸ” 29    πŸ’¬ 4    πŸ“Œ 0

Cameo by The Addams Family's Thing? πŸ€”πŸ˜œπŸ˜‚

17.02.2025 18:54 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Never let go of your self-esteem, James!

17.02.2025 18:51 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
Scaling of the GROMACS Molecular Dynamics Code to 65k CPU Cores on an HPC Cluster We benchmarked the performance of the GROMACS 2024 molecular dynamics (MD) code on a modern high-performance computing (HPC) cluster with AMD CPUs on up to 65,536 CPU cores with input systems ranging...

Breaking from JCC: GROMACS reaches a new height in #HPC scalability! @mpibp.bsky.social @mpi-nat.bsky.social onlinelibrary.wiley.com/doi/full/10....

15.02.2025 16:14 β€” πŸ‘ 3    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0

Huh. (1+i)Β² = 2i. How is that real? On the other hand, you can count on zz* to be the real thing!

16.02.2025 21:44 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Is it just me or is this something that should have remained in the "proofs of concept that didn't need proving" category? πŸ€”

16.02.2025 21:36 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
differences between AI and HPC System architecture There are a few differences between designing a supercomputer for AI and designing a supercomputer for traditional modeling and simulation ...

I wrote a little text to accompany this slide. It sums up the hour-long presentation in just a few words.

www.glennklockwood.com/garden/diffe...

#HPC #AI

16.02.2025 19:13 β€” πŸ‘ 9    πŸ” 7    πŸ’¬ 0    πŸ“Œ 1

I suppose it sorta makes sense that early humans traded off fur coats and physical strength for big brains that allowed us to create clothes and tools and now we’re apparently trading off those big brains for the ability to use hallucinatory auto-complete to write reports for us.

10.02.2025 16:23 β€” πŸ‘ 1083    πŸ” 228    πŸ’¬ 34    πŸ“Œ 11
Meme showing a kid making a gesture of disbelief, and the legend "When you ask someone a boolean question and they return a string".

Meme showing a kid making a gesture of disbelief, and the legend "When you ask someone a boolean question and they return a string".

Lots of people, a lot of the time.
[Found on #Mastodon.]

24.01.2025 23:39 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 0    πŸ“Œ 1

@cisnerosres.bsky.social 😁

21.01.2025 14:33 β€” πŸ‘ 3    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

You missed the fourth spirit.

Tequila.

25.12.2024 14:17 β€” πŸ‘ 5    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Wasn't that something the recently elected convicted felon suggested last time he was occupying the White House? πŸ€” (Let's nuke hurricanes! Yes, he suggested that in 2019.)

21.12.2024 18:48 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

@gcs-hpc is following 20 prominent accounts