Sign in

NON-TOXICNo ads · No shady algorithms

iiinova is part of the Atmosphere — an open, public network where you own your identity.

Glenn K. Lockwood

@glennklockwood.mast.hpc.social.ap.brid.gy
67 followers 0 following 361 posts

I am a supercomputing enthusiast, but I usually don't know what I'm talking about. I post about large-scale infrastructure for #HPC and #AI. 🌉 bridged from mast.hpc.social/@glennklockwood on the fediverse by fed.brid.gy

PostsRepliesMedia
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 26/10/2026
Jensen's claim of not being able to give away Hoppers back at GTC25 were incorrect; their value has skyrocketed recently. My guess is that this reflects HBM scarcity. Old GPUs with just as much(ish) memory are just fine for inference's bottlenecks. Source […] [Original post on mast.hpc.social]
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 21/10/2026
Memory, storage, and GPUs are so expensive in part because hyperscale GPU clusters are only 87% usable. The remaining 13% are kept as powered-on hot spares that sit idle. Could you imagine #HPC doing this? […] [Original post on mast.hpc.social]
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 13/10/2026
TIL that essentially NONE of the AI cloud providers are exhibiting at #SC26, though many left in 2025. Seems the overlap between the SC #HPC community and hyperscale #AI infra industry is asymptotically approaching zero. There's also a ton of churn in the […] [Original post on mast.hpc.social]
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 13/08/2026
This is the diagram I’m most proud of. Stacking ~700 different LLM training jobs observed from the VAST fleet on a common timescale to figure out whether there is a “feeding the GPU” problem anywhere close to the write intensity of periodic checkpoints. There is not. Only read burst is at job start.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 28/07/2026
I am ready! Almost #PEARC26
131 3
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 15/07/2026
We are now in the age of AI-generated conferences. Today’s keynote by Gropp prominently features distinctly Claude-generated plots; yesterday had an entire presentation delivered by an AI voiceover of slides. And slides are full of Claude design tells.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 14/07/2026
First time I’ve seen someone with a PhD actually predict that data centers in space will be a real thing. Granted, it’s a CS PhD, not a physical sciences one. #HPC #notreallythough
110 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 26/06/2026
Interesting that C-DAC, whose indigenous Indian interconnect Trinetra is based around libfabric, opted to implement verbs support to make Lustre work instead of adopting Cray’s kfabric LND. #ISC26
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 26/06/2026
1. General LLMs beat coding-specific models at writing Fortran, likely bc code models are overfitted to Python 2. This conf begins the age of Claude-generated pptx. Clear tells 3. My phone doesn’t like these #ISC26 projectors
101 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 25/06/2026
He has a chance to mention the Ozaki scheme but instead cites a 20-year-old algorithm that is the problematic core of HPL-MxP.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 25/06/2026
I wonder if ground has been broken on this datacenter yet. Because it takes two years to build such a facility without the federal land red tape part. How commercially meaningful will Blackwells be in two years?
100 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 25/06/2026
How many wrong statements can you fit into a single sentence? Holy cow.
100 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 24/06/2026
Supercomputer for agents is a bold bet by SJTU and a great thought exercise (if not more). There’s a lot of crap that we drag along in the #HPC stack simply because it makes humans comfortable.
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 24/06/2026
lol James Lin at #ISC26 #HPC
110 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 23/06/2026
The jump of LineShine over El Cap in efficiency is staggering. Suggests the benefit of balance and design for FP64-first over wedging FP64 into a socket whose chiplets were AI-first. LineShine’s poor HPL-MxP underscores. #ISC26 #HPC
021 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 23/06/2026
20 minutes into the opening keynote at #ISC26 and Martin Schulz has managed to say AI only once; it’s changing everything, but let’s talk about quantum and #HPC instead. Impressive.
100 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 11/06/2026
@kpdooty These guys? They’re the official bird of Oakland! I can send you some if you want; they’re always in our garbage.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 03/06/2026
Virtual DAOS User Group slides just dropped (daos.io/event/virtual-dug26). Interesting content, and glad DAOS is still trucking along. Surprises: ALCF has only 37% servers in production; LinkedIn trying to run DAOS on 20% of cores on HGX servers; long feature roadmap. #HPC #storage
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 01/06/2026
I got to work with VAST's architects on integrating NVIDIA Vera BlueField-4 STX in-silicon security features with VAST's agent policy enforcement engine. Agent interactions can be inspected and governed at line rate, and policies can adapt in real time based […] [Original post on mast.hpc.social]
Architecture diagram illustrating how VAST PolicyEngine can offload policy enforcement to NVIDIA Vera BlueField-4 STX for real-time, line-rate inspection and enforcement. Also shows how PolicyEngine policies can be updated by CrowdStrike Falcon based on data streamed from NVIDIA DOCA Argus (memory analysis) and VAST's own traces and observability data.
121 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 29/05/2026
Claude offered to create an SVG of Europe for me (I did not ask), and this is what came out. We have a long ways to go before the Terminators take over.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 20/05/2026
A career in collaborative grant writing, writing papers, and peer review has prepared me for spending days (weeks?) of scrubbing deep technical marketing copy
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 20/05/2026
I just got confirmation that my login credentials on NERSC supercomputers were revoked at some point and no longer work. With my Microsoft free Azure credit gravy train also ending last year, I am officially without a supercomputer. First time in my career 😢
110 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 18/05/2026
The shiny silver rack door for NERSC's upcoming Doudna is quite different from the Cray racks that NERSC historically had. Wonder how the rack graphics will work. End-of-row, like OLCF Summit's? (also shown: an 11-node VAST cluster in the second rack) #HPC […] [Original post on mast.hpc.social]
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 13/05/2026
There is no bubble, there is no bubble... Image from the author of this article over on bsky. www.cnbc.com/2026/05/13/cerebras-pr…
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 16/02/2026
RE: mastodon.world/@knowmadd/1160727731… Works for me.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 15/02/2026
Was a good year. The Cray XC50 with ThunderX was the hot new thing. Little did we know that Nvidia, not Cavium, would wind up putting Arm CPUs in every datacenter. #HPC #SC17
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 15/02/2026
Going through old photos this morning and found this one from an SC17 presentation. Wish I had more context! #HPC
100 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 12/02/2026
I got to visit the early access system for NERSC’s upcoming Doudna supercomputer. A TALL order of GB200s. Surprisingly noisy. Also got to see the VAST EBox cluster that was installed with the Doudna early access system. Just eleven plain ol’ Dell nodes on […] [Original post on mast.hpc.social]
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 14/01/2026
NERSC just got their first rack of the Doudna early access system from Dell--36 nodes of GB200 NVL4 in a 50OU rack. It's TALL! #HPC Source: www.linkedin.com/posts/national-ene…
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 31/12/2025
I use this read-it-later app that continually resurfaces old things I’ve read and found interesting. Headed into 2026 in a job that is all #AI all the time, I feel like this quote is more meaningful than ever. Everyone is an expert, yet so few actually […] [Original post on mast.hpc.social]
120 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 23/12/2025
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 21/12/2025
Career interest test I took at age ~13 (I think). Science and technical was top which isn’t far off from where I eventually landed, but I’m surprised communication and education scored so low.
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 03/12/2025
Wouldn’t be a trip to Oak Ridge National Lab without a leg on one of these lil guys.
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 30/11/2025
@kpdooty Interesting. @openvibe does the union of the two and shows the RE and embeds the original post. Surprised the client apps haven’t all updated to handle this uniformly; quote boosts are two months old now.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 18/11/2025
Andreas Dilger is now working for The Lustre Collective (thelustrecollective.com) after leaving DDN. I am glad to see his leadership continue to drive Lustre into the future. Say what you will about it, Lustre is the standard to which every other #HPC file system is compared. #SC25
101 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 17/11/2025
When I spent a Thanksgiving week after SC writing the non-MPI layer for Darshan years ago, I thought to myself “surely this work will make me famous!” I guess my ship finally came in at the PDSW keynote by Rob Ross. #SC25
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 14/11/2025
Chatting with a pal reminded me of a fun pre-SC activity: looking back at old conference takes that aged like milk. Remember this one? #HPC #zettascale #hedoesntworkthereanymore
220 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 14/11/2025
🎶 It's the most wonderful time of the year 🎶 #SC25
010 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 24/09/2025
I’m in North Dakota this week celebrating Scandinavian heritage. That liquid on top is butter.
001 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 20/09/2025
Visited some of my old pals at NERSC this afternoon. It feels like a lot has changed, but at the same time, it’s the same old place. I do miss working here, but am glad I now get a chance to visit under the auspices of my new role at VAST.
100 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 09/08/2025
Getting on a plane for VAST for the first time on Monday. But I’m not so sure about the destination 🥵
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 09/08/2025
GPT-5 is cool and all, but it's still not to be trusted. Didn't take me long to get "PhD-level" made-up facts. What really distinguishes "PhD-level" from whatever GPT-4 was is the ability to critically think, be skeptical, and stand behind the information […] [Original post on mast.hpc.social]
020 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 05/08/2025
One thing I really enjoy about working at VAST (or perhaps that I enjoy about not working at Microsoft) is that I can go out and talk to people again as part of my job. Here’s a view from where I got to spend my afternoon today. #notHPC #butthatsok
100 1
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 16/07/2025
I am a sucker for photos of cool #HPC infrastructure, and here is a dense GB200 NVL72 cluster going up somewhere in Canada (I think). Impressive to see this many racks in row; the DC must have facility water which is still uncommon in hyperscale. Source […] [Original post on mast.hpc.social]
021 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 08/07/2025
In the last 18 hours, I’ve learned way more about adjuvanted vaccines and adverse reactions to them in cats than I ever cared to. And the real kick is that the choice to re-up the cat’s vaccines was an afterthought, because we had to take other cat in for […] [Original post on mast.hpc.social]
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 28/06/2025
Photos of a new, big, naked Cerebras cluster in Oklahoma appearing on the socials today. Pretty neat. Wonder if this is another G42 install.
020 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 10/06/2025
The #ISC25 conference has a strong keynote speaker lineup from around the world this week. Looking forward to hearing all three.
021 2
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 27/05/2025
Here's a photo of an Azure datacenter coming online later this year that "will run a single, large cluster of hundreds of thousands of interconnected NVIDIA GB200 GPUs," "exabytes of storage," and "millions of CPU compute cores." Source […] [Original post on mast.hpc.social]
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 08/05/2025
Cleaning out old photos and I found this blast from the past. ISC19 specifically. My how times have changed. Not shown: the slide that followed talking up Optane DC PMM.
000 0
Glenn K. Lockwood @glennklockwood.mast.hpc.social.ap.brid.gy · 21/03/2025
And here is the silicon photonics switch that was announced at #GTC25. The laser modules slot in along the top and look like familiar transceivers, just without the fibers. Ring resonators modulate the laser light out of the MPOs(?) that connect directly to the switch below the lasers. Wild.
000 0