NVIDIA GH200 CPU Performance Benchmarks Against AMD EPYC Zen 4 & Intel Xeon Emerald Rapids

It was very interesting to see the GH200 CPU performance competing surprisingly well against the single socket x86_64 Intel / AMD current generation server processors in raw performance. Too bad that there wasn't any power monitoring support available for comparison in power efficiency for today's benchmarks.

On a geo mean basis across all the benchmarks conducted, the GH200 Grace CPU performance nearly matched the Intel Xeon Platinum 8592+ Emerald Rapids processor. The Arm Neoverse-V2 based Grace CPU tended to be much faster than the 128-core Ampere Altra Max AArch64 server. It will be interesting to see how AmpereOne can compete albeit no hardware available yet for testing. (Unfortunately no AMD MI300A hardware either for testing right now.) The NVIDIA ARM CPU performance has certainly come a long way from benchmarking the NVIDIA Tegra early days for ARM performance.

More of the CPU benchmark numbers are available via this result file. There's also some other benchmarks here from some of the preliminary testing.

Overall the NVIDIA GH200 CPU benchmarking was quite fascinating to see its early potential. There still are some workloads not too well optimized for AArch64 and in some cases the higher core counts and dual socket configurations available with Intel Xeon Emerald Rapids and AMD EPYC Genoa(X) / Bergamo could drive the results much higher. NVIDIA does also have a 144 core Grace Superchip version too, albeit not tested yet. There is also the H100 GPU with this NVIDIA Grace Hopper superchip which will be part of my next benchmark investigation, among other tests from this GPTshop.ai GH200 system.

Thanks to GPTshop.ai for providing the GH200 system access for making this benchmarking possible. Those wanting to learn more about the GPTshop.ai systems can do so via GPTshop.ai.