Skip to content

Commit d54e37e

Browse files
committed
Nvidia post
1 parent 249bcbc commit d54e37e

File tree

1 file changed

+73
-0
lines changed

1 file changed

+73
-0
lines changed

content/posts/2025-01-06-nvidia.md

Lines changed: 73 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,73 @@
1+
---
2+
title: "NVIDIA CES Keynote"
3+
date: 2025-01-06T21:46:16-08:00
4+
tags: [dev, nvidia, cuda, pc, gpu, nas]
5+
categories:
6+
- Dev
7+
- Personal
8+
---
9+
10+
I just watched the [CES 2025 Keynote](https://www.youtube.com/watch?v=k82RwXqZHY8)
11+
by NVIDIA CEO Jepsen Huang.
12+
13+
<!--more-->
14+
15+
I'm feeling the hype.
16+
17+
I've never heard him speak before. He's a nerd. I love it, even if it is a bit
18+
corny. The keynote was very well staged.
19+
20+
I kinda want to get the 5080FE if I can swing it when they release on the 30th.
21+
Wish me luck!
22+
23+
The 4080 Super is already more than twice as powerful as the 2070 Super that I have.
24+
(See [here](https://gpu.userbenchmark.com/Compare/Nvidia-RTX-2070S-Super-vs-Nvidia-RTX-4080-S-Super/4048vs4156).)
25+
And if the numbers bear out, the 5080 should be
26+
27+
Along with the [NAS](/tags/nas), this is the year to replace my GPU to avoid
28+
having a full computer to buy and build in 3-4 years. What's the point of an
29+
machine with upgradable components if you don't do it one piece at a time?
30+
31+
I have already checked and my exisitng PSU should be enough to power it. I
32+
can also get an official cable for the dramatic power connector it requires,
33+
instead of a tricky adapter set up.
34+
35+
The 2070 Super I have is unfortunately 7mm too long to simply migrated into the
36+
NAS case though. Either I'll need to do some surgery to it, or the case itself
37+
to make it fit. The overkill PSU I'm putting into it could certainly power it
38+
at least.
39+
40+
-----
41+
42+
Related, I recently read [The NVIDIA Way](https://wwnorton.com/books/9781324086710) by Tae Kim,
43+
while sitting by a pool in San Jose del Cabo, and the flights there and back.
44+
It was an interesting read! I liked learning the story of the company, along with
45+
the major milestones in the hardware development process. I was taken back to my
46+
point of view from growing up as a gamer and CS student.
47+
48+
It did briefly make me want to try out CUDA programming, but the urge passed.
49+
50+
Overall it seemed too finicky to do more than a passing hack or two. If it does
51+
come up, I'll be sure to write about it here. There are a number of existing Go
52+
packages that bind to the CUDA libraries.
53+
54+
I liked the blend of history, interviews and technical details the book had.
55+
56+
It did not make me want to work for Jepsen though. I don't think I've ever been
57+
that ambitious. But then, if I were, I'd be a CEO wouldn't I?
58+
59+
-----
60+
61+
The Keynote covered the new GPUs, a few demo, and a multitude of collaborations
62+
they have with clients for their various AI powers.
63+
64+
I'm still a bit negative on the current GenAI/LLM trends, in particular for all
65+
the ways it generates spam, or devalues real artists and creators.
66+
But the use in simulations seems useful enough. We need more automation, and
67+
this is a valid way to enable that.
68+
69+
I'd probably feel differently if I started to try and find ethical uses for it,
70+
and the power of the hardware I have. As much as one can do it within modern
71+
society at least.
72+
73+
But that's a topic for another time.

0 commit comments

Comments
 (0)