Live data from Hacker News

Nvidia announces financial results for second quarter fiscal 2024

nvidianews.nvidia.com

271–280 of 444 posts

Re: Nvidia announces financial results for second quarter fiscal 2024

#271
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

I do wonder though, why has moore's law stopped in its tracks? Using CS:GO benchmark, a 1070 got 218 FPS, while a 4090 is at 477 FPS. Only a ~2.2x increase in FPS in 6 years? :(

FPS of one specific game isn't a great indicator of GPU grunt.

Re: Nvidia announces financial results for second quarter fiscal 2024

#272
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

I do wonder though, why has moore's law stopped in its tracks? Using CS:GO benchmark, a 1070 got 218 FPS, while a 4090 is at 477 FPS. Only a ~2.2x increase in FPS in 6 years? :(

Admittedly knowing nothing, I’m going to assume that a great deal of the advantages of the latest generation aren’t going to improve performance in a decade old game since the engine won’t touch them.

How does a 1070 fare versus a 4090 in Hogwarts Legacy or another modern game at 1440 or 4K?

Re: Nvidia announces financial results for second quarter fiscal 2024

#273

Earlier quoted context omitted.

Facebook, Amazon, Apple, Microsoft, and Google

While I hate using the stupid "meta" name, MAGMA is a much more fun acronym than FAAMG, or GMFAA, or MAGAF, etc.

Meta Apple Microsoft Alphabet Amazon

MAMAA

Re: Nvidia announces financial results for second quarter fiscal 2024

#274
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

Do you still own stock?

Re: Nvidia announces financial results for second quarter fiscal 2024

#275
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

I do wonder though, why has moore's law stopped in its tracks? Using CS:GO benchmark, a 1070 got 218 FPS, while a 4090 is at 477 FPS. Only a ~2.2x increase in FPS in 6 years? :(

Fps in CSGO isn’t really so dependent on the GPU as more modern games, so comparing with a different game might be more accurate.

Re: Nvidia announces financial results for second quarter fiscal 2024

#276
post #274
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

Do you still own stock?

He probably didn’t get any as an intern.

Re: Nvidia announces financial results for second quarter fiscal 2024

#277
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

I do wonder though, why has moore's law stopped in its tracks? Using CS:GO benchmark, a 1070 got 218 FPS, while a 4090 is at 477 FPS. Only a ~2.2x increase in FPS in 6 years? :(

My guess is that we've reached a peak in the amount of new investment that can be made annually, based on tech nearing total proliferation throughout society. The tech can sort of only advance as fast as tech companies can grow, and they can't grow exponentially after they account for some percentage of the global workforce.

My guess is that we'll see improvements at closer to the current rate rather than at an increasing rate.

Re: Nvidia announces financial results for second quarter fiscal 2024

#278
post #245

Earlier quoted context omitted.

What really strikes me is Nvidia's been working hard on doing practical work on their GPUs even just 10~15 years ago with PhysX, while both Intel and AMD just existed. Nvidia's dominance today is the product of at least over a decade of work and investments to make better products. Today they are finally reaping their rewards.

>doing practical work ... even just 10~15 years ago with PhysX practical work with PhysX 13 years ago: https://www.realworldtech.com/physx87/ "For Nvidia, decreasing the baseline CPU performance by using x87 instructions and a single thread makes GPUs look better." Nvidia magically released PhysX compiled with multithreading enabled and without flags disabling SSE a week after this publication. But couple of days bef…

> But GameWorks' capabilities are necessarily Nvidia-optimized; such code may perform poorly on AMD GPUs.

From the arstechnica article about Witcher 3.

How dare Nvidia optimize their game enhancing effects for Nvidia hardware and forget to do it for their competitors hardware as well! And as for a lot of these complaints, could it be that a lot of companies only optimize for hardware that has the largest market share?

According to the steam hardware survey in July of 2023, Nvidia accounts for 75% of the GPUs[0]. Nvidia and Amd have a lot of incompatibilities, and it can be hard to make the same code performant on both. It makes sense, as a game company, to prioritize optimizations for the largest market. No collusion and evil corporate mega lord scheming needed for this.

Edit: Also, Nvidia does put out a lot of research efforts for free. Path rendering on the GPU for example (PhysX being another). You can find research papers and videos published by Nvidia for these things. I would consider that practical work. You can hate on Nvidia for lots of things, but this is one thing I find weird to be combative over.

Second Edit: Also, why do you find the statements Nvidia said about the PhysX improvements funny? They’re right. Most games 13 years ago left a lot of idle time on the GPU while the CPU worked overtime to do logic, physics, sound, culling, etc. Lots of that stuff has also been moved to the GPU to minimize the amount of idle time on either the CPU or GPU. Nothing funny about what they said there.

[0]: https://store.steampowered.com/hwsurvey/

Re: Nvidia announces financial results for second quarter fiscal 2024

#279
post #74
post #25

The good new is that Nvidia's high GPU prices motivate everyone (Intel, AMD, ARM, Google, etc.) to try and tackle the problem by making new chips, making more efficient use of current chips, etc. For all the distributed computing efforts that have existed (prime factorization, SETI@Home, Bitcoin, etc.), I'm surprised there isn't some way for gamers to rent out use of their GPU's when idle. It wouldn't be efficient, b…

They’re all pretty motivated, they’ve been motivated for years, and almost nothing is happening. This situation isn’t exactly a poster child for the Efficient Markets Hypothesis. Every year just sounds like “Nvidia’s new consumer GPUs are adding new features, breaking previous performance ceilings, running games at huge resolutions and framerates. Their datacenter cards are completely sold out because they can spin s…

To play the free market advocate:

The situation is created by artificial restrictions on free market (namely state enforced monopolies on "IPR", or as some call it, imaginary property).

Re: Nvidia announces financial results for second quarter fiscal 2024

#280
post #261

I interned at NVIDIA in 2009 on the kernel mode driver team. Was super fun there in terms of the project work and the people. If the code still exists, I created the main class that schedules work out to the GPU on Windows. That level of programming gave such rewarding moments in between difficult debugging sessions. When I wanted to test a new kernel driver build I needed to walk into some massive room with all of t…

I do wonder though, why has moore's law stopped in its tracks? Using CS:GO benchmark, a 1070 got 218 FPS, while a 4090 is at 477 FPS. Only a ~2.2x increase in FPS in 6 years? :(

GS:go aside, the 1070 is said to do 6.5 TFlops to the 4090's 1,321 TFlops, for a 203x improvement in 6 years. Not bad!
Post reply on HN