Live data from Hacker News

I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

twitter.com

81–90 of 139 posts

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#81
post #18

I love this insider view into this interesting point in computing history, especially about AMD. However, I was a little put off by the glorification of nVidia's shady practices and lock-in policies as key to their current leading position. While technically true, I dislike "ends justify the means"-style thinking. All this as the OP glorifies AMD's engineering and grit-based culture to drive through all though tough…

Yeah, I really feel like AMD is struggling with the software aspect. Even back when they were ATI and AMD bought them, the ATI drivers were garbage compared to Nvidia (from my PC gaming experience). After a few AMD and ATI cards, I just accepted the Nvidia tax, where my cards are more expensive and on paper worse, but in practice worked better. I'm really surprised AMD isn't throwing a whole bunch of money on emulati…

AMD also doesn't understand that CUDA got big because they worked on cheap consumer cards; once things were working people got interested in expensive specialized cards. Their stack is still focused on the high end only, but there's no ecosystem to support it.

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#83

I love this insider view into this interesting point in computing history, especially about AMD. However, I was a little put off by the glorification of nVidia's shady practices and lock-in policies as key to their current leading position. While technically true, I dislike "ends justify the means"-style thinking. All this as the OP glorifies AMD's engineering and grit-based culture to drive through all though tough…

She turned the company around and got it on the right path, but in interviews I get the feeling that she might also be responsible for the "Hardware 1st, 2nd, 3rd, 4th.... eh, maybe software can be 5th" culture and AMD's deep denial that it has a problem. https://news.ycombinator.com/item?id=40790924 That was OK for the CPU turnaround, but on the GPU front it completely shut them out of the first rounds of the AI par…

I'm hopeful and optimistic for AMD but if anything were to make me bearish on their prospects, it'd be this.

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#84
post #33

Earlier quoted context omitted.

Nvidia was pushing CUDA forward for over a decade before it started getting serious commercial traction. It's not like they blocked anyone else from developing viable GPGPU tech, they were just the only ones pushing it. For like 8 years their drivers on Linux were a nightmare and AMD could have come in and done better.

AMD and Apple tried to push OpenCL but the design of it, a C-like kernel compiled to the GPU with LLVM and managed by the Khronos consortium, tended to lag in absolute performance to CUDA which was able to take advantage of evolutions in GPU design more closely. Nowadays almost nobody cares about OpenCL.

The feature lag wasn't the problem, the bugs were the problem: the only reliable OpenCL implementation was the one from Nvidia, but this meant it tended to drive people towards Nvidia rather than steal them away.

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#85

People keep yelling about nvidia stock but that feels like a huge bubble. AI disillusionment will hit and the stock will implode. Nvidia hasn’t made any inroads on producing actual systems, just gpus. Once Apple or Microsoft have a fast enough chip (TOPs wise), nobody will care about nvidia lead except in the datacenter. Seems like a failing position to me.

Google has powerful TPUs. The real question is, why isn't Meta building their own?

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#86

Earlier quoted context omitted.

I'm quite familiar as I worked for Intel for over a decade as an engineer. It's absolutely true that leadership has fluctuated a lot but the 2003-2010 era had fairly clear cut leaders for each generation. AMD was the choice for just about everything through the Athlon 64 single core era but the Core 2 Duo run had them relegated to superiority in the very bottom end of the market only for a long time. https://www.anan…

Is it possible that maybe your view point is biased against AMD since you worked for for Intel during that time?

K7/K8 were great, and while the follow-on K10 Athlon2/Phenom/etc were definitely not bad, they weren't great and they were competing against Conroe/Core2 onwards. That kind of tag-team trading places highlights how (mostly) good the CPU market is now, both AMD and intel are putting out some really nice products with variety so you can pick the most suitable for you, but there's no default "just pick [company]"

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#87
post #79

Earlier quoted context omitted.

Is it possible that maybe your view point is biased against AMD since you worked for for Intel during that time?

Nah, btouellette is correct. AMD only led for a few years around 2003-2005.

AMD did become at least competitive in high end CPUs with the original Athlon or Athlon XP. Not sure whether they were faster than the Pentium 3 but they weren't trailing.

So perhaps a bit more than a couple of years, but my impression is also that they fell behind on (single-thread) performance for a long time after that.

I've also understood that in more ancient history AMD CPUs sometimes beat contemporary Intel parts in performance, although releasing their parts later than Intel. I'm not sure that's relevant to any remotely recent developments anymore though.

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#88
post #41

Is he really trying to say that AMD had a superior product in the Core 2 Duo era and Intel was only dominating due to marketing? It's hard to take any of the rest of his opinions seriously when he starts with that take

I'm not sure if you're familiar with CPU history, but this is roughly true. Intel's catchup to multicore offerings was trippy and severely lagged behind AMD. I think it's often forgotten that CPU leadership has fluctuated between different companies many times in the past!

The OP is right. Pentium D was a single generation in which Intel offering was worse that Athlon 64 X2 . But Intel quickly shifted to Core 2 Duo architecture and it was much better than AMD.

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#89
post #80

I predicted years ago they would make a CPU and you would be able to buy an All-NVidia PC. I think the reason that hasn't happened is because of the failed purchase of ARM. And looking at the market dominance of NVidia, it seems they were right to block that acquisition.

Supercomputers are now Nvidia-only with Grace Hopper chips.

Re: I was at AMD in the mid-late 2000s helping design CPU/APU/GPUs

#90
post #61

> SUPERIOR PRODUCTS LOSE TO SUPERIOR DISTRIBUTION LOCK-INS & GTM. This takeaway was a little odd to me in the context of 2008. I had been an AMD stalwart in my PCs since about 2000 (Athlon Thunderbird), but IIRC in 2008 Intel had the better processor. Better single core performance, better performance/watt, and I think AMD processors tended to have stability issues around this time. I remember I built a PC in 2009 wi…

Agree. It took a truly superior product at lower cost to make a dent in Intel's dominance in server, all the while Intel tried their best to flex their lock in muscle. That happened well after 2008, with the advent of Zen and chiplet bases tech and better perf/W

Ryzen 1 was far from superior, performance-wise it was already behind Intel at around Haswell-level but it brought the first reasonably-priced octacore x64 for the masses.
Post reply on HN