
However, when the researchers used a kernel specifically optimized for Olympus, Vera’s performance increased to 7.53 instructions per clock and 21.75 FP64 operations per cycle. As a result, Vera outperformed its predecessor by nearly 67% on a per-core, per-clock basis in this particular workload.
Grace's Neoverse V2 microarchitecture has four 128-bit SIMD pipelines that can perform a total of 16 FP64 operations per clock, whereas Nvidia's Olympus has six such pipelines that can execute up to 24 FP64 operations per cycle, a 50% improvement.
But where the Neoverse V2-optimized kernel uses 81.4% of Grace's peak FP64 throughput, it uses only about 66.5% of Vera's computational capabilities. With changes to matrix tile organization, register allocation, and instruction scheduling that better suit the Olympus microarchitecture, the researchers managed to utilize 90.6% of its peak FP64 throughput, according to Nvidia's tutorial published at SC26.
While software developed and optimized for existing Arm-based data center processors can still benefit from the capabilities of Nvidia's Olympus cores without any specific optimizations, the company's SC26 benchmark results demonstrate that at least some applications will need to be fine-tuned for the new microarchitecture to take full advantage of its execution resources. Of course, it remains to be seen how much performance can be gained through Olympus-specific optimizations in workloads other than matrix multiplication .
As Nvidia expands beyond CPUs that primarily serve as companions to its data center GPUs and chases the standalone server CPU market, the company will have to ensure that performance-critical software takes advantage of the architectural peculiarities of its processors, much like Intel and AMD have done for decades.
But the company is already deeply experienced with partner and ecosystem development for platforms like CUDA, so as Vera is more widely adopted, that experience could prove useful in spurring optimizations for these CPUs going forward.
Anton Shilov Social Links Navigation Contributing Writer Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.
bit_user The article said: But despite offering unbeatable single-thread performance , the CPU is not positioned for general-purpose workloads. Huh?? It's good, but not that good! It barely equals int performance on Zen 6C and is easily outstripped by the frequency-optimized Zen 6 (which is about 20% faster). Source: https://chipsandcheese.com/p/amds-zen-6-family-feeding-the-beast Its floating point performance is only 83% of a Zen 6C and only about 70% as fast as Zen 6. While the 39% improvement seems like it'd close that gap, keep in mind that this optimization applies to only one specific computational kernel over data that fits in L1 cache. Don't expect to see similar gains across-the-board. Reply
JeffreyP55 I could care less. Not spending 3 mortgage payments on a soon-to-be obsolete junker. Reply
bit_user JeffreyP55 said: I could care less. Not spending 3 mortgage payments on a soon-to-be obsolete junker. Yeah, I mainly look at these server cores as a sign of what could trickle down to consumer products, in the future. Vera is an impressive CPU core, for what's effectively Nvidia's first modern effort. It's also interesting to see how much room is still left for code optimization. In spite of what I said above, Vera's FPU performance is already quite good for using 128-bit vectors (i.e. compared to AMD's full 512-bit implementation). Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/pc-components/cpus/SPONSORED_LINK_URL
- https://www.tomshardware.com/pc-components/cpus/nvidia-claims-its-vera-cpu-can-gain-up-to-39-percent-performance-boost-via-software-optimization-at-sc26-architectural-fine-tuning-is-needed-to-fully-unleash-custom-olympus-cores#main
- https://www.tomshardware.com/my-account
- Ian Buck Kicks Off NVIDIA’s Week at SC26 as Science Enters the Age of Agents
- Retro Kickstarter speaker can play soundtracks directly from original Game Boy cartridges
- Nvidia claims its Vera CPU can gain up to 39% performance boost via software optimization at SC26 — architectural fine-tuning is needed to fully unleash custom
- GTA VI runs at 1440p on PS5 and Xbox Series X, but just 720p with upscaling on Series S
- Ian Buck Kicks Off NVIDIA’s Week at SC26 as Science Enters the Age of Agents
Informational only. No financial advice. Do your own research.