Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nvidia’s Vera Whitepaper Has a Thread Loose

chipsandcheese.com

Post reply on HN
Print view View original

21–30 of 48 posts

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#21

Post by wtallis »

pjmlp wrote: post #18
lstodd wrote: post #14

Earlier quoted context omitted.

Death of Itanium was that it was a) VLIW and b) Intel was too arrogant. So it went to the same destination as later Larrabee and ATI/AMD attempts at VLIW GPUs. That is, nowhere. Also you are wrong and anyone sizing up an arch to put their loads onto must first try that load on it and not rely on "bah, compilers compile on it".

Itanium only died because AMD exists, and due to various licensing reasons they were allowed to come up with AMD64.

In a hypothetical world where AMD wasn't allowed to do AMD64, and Intel stayed committed to Itanium: Itanium would still have sucked, and both PowerPC and SPARC would have out-sold Itanium by an even wider margin than they did in this reality. Itanium could only have succeeded if AMD64 wasn't possible and literally all of the competing 64-bit architectures were killed off by their owners so they could jump on the Itanium bandwagon. Itanium managed to kill off PA-RISC and Alpha and (high-end) MIPS roadmaps, but it still had competitors that were not just viable but actually more successful.

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#22

Post by torginus »

jcranmer wrote: post #7
twoodfin wrote: post #4

I don’t think picking a handful of SPEC benchmarks that approximate today’s most common agentic workloads (compiling code, interpreting Python) and then calling them “agentic benchmarks” is misleading at all. That you need a whole lot of “ordinary” compute to benefit from the scaling properties of agents is the reason Nvidia is making this chip in the first place.

The four benchmarks selected are cppcheck, llvm, cpython, and gcc [1]. These are all essentially compiler benchmarks... and all of the compiler benchmarks in SPEC cpu2026! This makes the benchmark selection somewhat suspicious to me, since it's not particularly representative of a diverse set of workloads. I also don't buy that it's a particularly representative set of tasks you might do with agents. Also included in…

I think the choices of these workloads are deliberate, considering this is a large core count CPU linked to a FP-monster GPU with a high speed, low latency datalink.

The former implies per core memory bandwidth is probably not great, meaning SQLite wont perform as well, the latter meaning FP workloads are better done on the GPU, so video encoding wont be a high point. The idea is to run branchy integer workloads that fit into RAM imo, which is what these benchmarks measure.

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#23

Post by wtallis »

KeplerBoy wrote: post #20

AMDs marketing is just as sketchy. Their new Zen6 server page claims 3.3x performance per watt over vera on "agentic workloads" for a 100 kW rack. Maybe they are comparing a CPU heavy rack to an nvidia vera rack with 50 kW of GPUs sitting idle, who knows? https://www.amd.com/en/products/processors/server/epyc/9006-...

> who knows?

You could try reading the footnotes, which include a link to https://www.amd.com/content/dam/amd/en/documents/solutions/a...

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#24

Post by KeplerBoy »

wtallis wrote: post #23
KeplerBoy wrote: post #20

AMDs marketing is just as sketchy. Their new Zen6 server page claims 3.3x performance per watt over vera on "agentic workloads" for a 100 kW rack. Maybe they are comparing a CPU heavy rack to an nvidia vera rack with 50 kW of GPUs sitting idle, who knows? https://www.amd.com/en/products/processors/server/epyc/9006-...

> who knows? You could try reading the footnotes, which include a link to https://www.amd.com/content/dam/amd/en/documents/solutions/a...

That doesn't clarify it and AMD says as much "Because these estimates rely on published results, internal measurements and projection-based scaling factors, they are intended to provide directional comparison rather than direct measured rack benchmarks."

It's marketing after all and nobody should make buying decisions based on that.

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#25

Post by 14113 »

fibonacci112358 wrote: post #10
jcranmer wrote: post #7

Earlier quoted context omitted.

The four benchmarks selected are cppcheck, llvm, cpython, and gcc [1]. These are all essentially compiler benchmarks... and all of the compiler benchmarks in SPEC cpu2026! This makes the benchmark selection somewhat suspicious to me, since it's not particularly representative of a diverse set of workloads. I also don't buy that it's a particularly representative set of tasks you might do with agents. Also included in…

The code in compilers is the closest to your typical app you can get in a benchmark like SPEC, eveerything else is actually far more specialized. Compiler code is full of small basic blocks, lots of branches, indirect memory access; it's actually harder to get good performance for such code, both for CPUs and compilers (that was part of the death of Itanium too).

I mildly disagree - depending on your definition of "typical app". Most applications have much greater use of multi-processing and concurrent cross-thread (or cross-process) communication. Compilers, aside from high-level parallelism across modules, tend to be quite single-threaded applications.

If you're solely interested in single-core performance, then I would agree that they are a good stress test, but I think for a processor that is being sold on it's parallelism, they are not a great benchmark.

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#26

Post by samrus »

archipelago123 wrote: post #13
amluto wrote: post #11

In today’s “agentic” world, everyone seems to have forgotten approximately everything we used to know about security. And this new CPU is going all in on value speculation. Delightful. Maybe if “cyber” models get good enough at exploiting speculation attacks, people will start demanding equipment that is less prone to these attacks.

Attacker: I can run any code on this machine? Time for speculation attacks! Attacker: Oh wait, I can run any code? I already own the machine...

Did you forget about spectre and meltdown?

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#27

Post by 14113 »

jcranmer wrote: post #12
fibonacci112358 wrote: post #10

Earlier quoted context omitted.

The code in compilers is the closest to your typical app you can get in a benchmark like SPEC, eveerything else is actually far more specialized. Compiler code is full of small basic blocks, lots of branches, indirect memory access; it's actually harder to get good performance for such code, both for CPUs and compilers (that was part of the death of Itanium too).

That's true of most of the applications in SPECint (SPECfp is a different matter); there's nothing special about compilers there. Where compiler code is going to get really unusual, I suspect, is that compilers tend to be a little mono-focused on relatively few data structures. I know I was able to get measurable (single-digit percent!) performance differences in LLVM making very small tweaks to layout in llvm::Value…

Seconding this - having worked on LLVM and Firefox, the performance tuning of each application was very different. Even measuring the performance of an application like Firefox (in a meaningful way) is non-trivial, wheras compilers are much more approachable with traditional profilers (either tracing or sampling).

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#28

Post by pjmlp »

wtallis wrote: post #21
pjmlp wrote: post #18

Earlier quoted context omitted.

Itanium only died because AMD exists, and due to various licensing reasons they were allowed to come up with AMD64.

In a hypothetical world where AMD wasn't allowed to do AMD64, and Intel stayed committed to Itanium: Itanium would still have sucked, and both PowerPC and SPARC would have out-sold Itanium by an even wider margin than they did in this reality. Itanium could only have succeeded if AMD64 wasn't possible and literally all of the competing 64-bit architectures were killed off by their owners so they could jump on the Ita…

Except you would never had Windows running on either PowerPC and SPARC.

Remember, the very first Windows XP 64 bit release was on Itanium.

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#29

Post by dzaima »

amluto wrote: post #11

In today’s “agentic” world, everyone seems to have forgotten approximately everything we used to know about security. And this new CPU is going all in on value speculation. Delightful. Maybe if “cyber” models get good enough at exploiting speculation attacks, people will start demanding equipment that is less prone to these attacks.

aarch64 has a CPU mode, DIT (Data Independent Timing), specifically for allowing software to request all fancy value prediction stuff to be disabled for the duration of processing of sensitive data.

(doesn't help when the attack target is general-purpose/user-controlled code leaking things, but if you're relying on a process not leaking memory plainly available to it without full careful control of what the process runs, you've already been fully-SOL on that for decades and nothing has nor will nor can change about that)

Re: Nvidia’s Vera Whitepaper Has a Thread Loose

#30

Post by lostmsu »

transcriptase wrote: post #9

Let’s not forget the fact that despite their new market cap and being the beneficiary of having a near monopoly on making incredibly complex pickaxes during a gold rush… Nvidia is still the company with a long and consistent history of misleading their customers via marketing. Their greatest hits include: - The digital equivalent of the VW emissions scandal where drivers detected when they were being benchmarked and…

You forgot their tensor core performance numbers "with sparsity".
Post reply on HN