Hacker News: jfkfif

New comment by jfkfif in "Sandia National Labs SA3000 8085 CPU"

jfkfif — Mon, 29 Jun 2026 17:19:03 +0000

Sandia is operated by a government contractor (Honeywell)

New comment by jfkfif in "Reproducible and traceable configuration for Conan C and C++ package manager"

jfkfif — Sat, 21 Feb 2026 04:27:57 +0000

use spack.io instead

New comment by jfkfif in "Using SQLite as storage for web server static content"

jfkfif — Sun, 27 Oct 2024 20:24:22 +0000

More performant than using HDF5?

New comment by jfkfif in "CPU Throttling for containerized Go applications explained"

jfkfif — Tue, 01 Oct 2024 19:02:16 +0000

I am working on something super similar. If you remember the name of the startup I would appreciate it deeply

New comment by jfkfif in "GPU utilization can be a misleading metric"

jfkfif — Fri, 23 Aug 2024 11:18:06 +0000

Depending on the size of your application you can calculate flops by hand

https://docs.nersc.gov/tools/performance/roofline/

New comment by jfkfif in "Why is Chile so long?"

jfkfif — Thu, 04 Jul 2024 09:34:18 +0000

In the desert? It’s the driest place in the world

New comment by jfkfif in "AMD MI300x GPUs with GEMM tuning improves throughput and latency by up to 7.2x"

jfkfif — Sat, 29 Jun 2024 16:35:00 +0000

this good enough for you?

https://www.amd.com/en/newsroom/press-releases/2024-5-21-amd...

New comment by jfkfif in "Testing AMD's Giant MI300X"

jfkfif — Wed, 26 Jun 2024 03:19:45 +0000

It is not a reasonable assumption to compare your local cluster to the largest clusters within DOE or their equivalents in Europe/Japan. These machines regularly run at >90% utilization and you will not be given an allocation if you can’t prove that you’ll actually use the machine.

I do see the phenomenon you describe on smaller university clusters, but these are not power users who know how to leverage HPC to the highest capacity. People in DOE spend their careers working to use as much as these machines as efficiently as possible.

New comment by jfkfif in "Japan's push to make all research open access"

jfkfif — Fri, 31 May 2024 12:27:54 +0000

DOE already mandates this

New comment by jfkfif in "Japan's push to make all research open access"

jfkfif — Fri, 31 May 2024 12:27:11 +0000

osti.gov

New comment by jfkfif in "Japan's push to make all research open access"

jfkfif — Fri, 31 May 2024 12:24:08 +0000

Econ has a big working paper culture

New comment by jfkfif in "Patagonia's New Study Finds Fleece Jackets Are a Serious Pollutant (2016)"

jfkfif — Tue, 07 May 2024 07:28:36 +0000

PFAS is able to be removed via reverse osmosis which direct potable reuse facilities utilize, so not really a problem

New comment by jfkfif in "Porting HPC Applications to AMD Instinct MI300A Using Unified Memory and OpenMP"

jfkfif — Sat, 04 May 2024 21:13:43 +0000

nvidia absolutely gives deals to national labs and universities. See Crossroads @ LANL, Isambard in the UK, Perlmutter @ LBL. While AMD is being deployed at LLNL and ORNL, Nvidia isn’t done with their HPC game. Maybe not at the leadership level, but we’ll see how Oak Ridge and LANL decide their next round of procurements

New comment by jfkfif in "Cheyenne Super Computer Auction"

jfkfif — Mon, 29 Apr 2024 22:12:13 +0000

Academic departments with low budgets and cheap electricity who can make due with old CPUs

New comment by jfkfif in "Nvidia to Acquire Run:AI"

jfkfif — Wed, 24 Apr 2024 18:21:15 +0000

the problem is multinode runs that communicate through the network

New comment by jfkfif in "Compilers for continuous integration of Fortran projects"

jfkfif — Tue, 12 Mar 2024 22:39:14 +0000

HPC, or scientific computing more generally, are slow when it comes to adopting modern software development practices. Most researchers used to only care about results above all, rather than reliability or reproducibility for other users. DOE initiatives [0] in the past couple years have done a lot to change this, though there are significant hurdles from a security and logistical standpoint [1]. For instance, to uncover issues in a PR, you might need to run the code at >64 nodes on a shared system.

[0] https://ecp-ci.gitlab.io/docs/admin/jacamar/introduction.htm...

[1] https://arxiv.org/abs/2303.17034

New comment by jfkfif in "Building Meta's GenAI infrastructure"

jfkfif — Tue, 12 Mar 2024 18:18:23 +0000

What’s the company?

New comment by jfkfif in "Fortran 2023"

jfkfif — Wed, 22 Nov 2023 22:30:37 +0000

LLNL has ported most if not all of their codes to C++, but I think LANL is still full on Fortran

New comment by jfkfif in "Chapel 1.32"

jfkfif — Tue, 10 Oct 2023 02:20:30 +0000

please email us at hpccenter@stanford.edu, and ask to be put in touch with someone at PSAAP. I would be happy to help!

New comment by jfkfif in "Chapel 1.32"

jfkfif — Mon, 09 Oct 2023 16:15:26 +0000

I really like Legion as an alternative for HPC applications, among many others (https://legion.stanford.edu/)