Intel Xeon 6980P "Granite Rapids" Linux Benchmarks

[phoronix]

Phoronix: Intel Xeon 6980P "Granite Rapids" Linux Benchmarks

With the Intel Xeon 6900P &quopt;Granite Rapids" launch today the review embargo has now expired. I began with my Intel Granite Rapids Linux benchmarking a few days ago and have initial benchmarks to share for the flagship Xeon 6980P processors paired with MRDIMM 8800MT/s memory. This is just the beginning of a lot of Granite Rapids benchmarks to come on Phoronix. Compared to the existing AMD EPYC competition and prior generation Intel Xeon processors, the Xeon 6900P series performance surpassed my expectations and has debuted as an incredibly strong performer. In some areas of HPC and other workloads, Intel is able to regain leadership performance with Granite Rapids paired with MRDIMMs. In AI workloads where the software is optimized for AMX, the new Xeon 6900P CPUs can showcase staggering leads.

https://www.phoronix.com/review/intel-xeon-6980p-performance

[chuckula]

Thanks Michael!! Obviously a few launch day hiccups, which are common for major platforms, but overall Linux is running the platform very well on launch day.
I like the variety of benchmarks too that hit different workloads you'd expect to see across HPC/cloud/productivity/AI/etc.

[Michael]

Thanks Michael!! Obviously a few launch day hiccups, which are common for major platforms, but overall Linux is running the platform very well on launch day.
I like the variety of benchmarks too that hit different workloads you'd expect to see across HPC/cloud/productivity/AI/etc.

Thanks yep will be having a lot more Granite Rapids benchmarks over the days ahead...

[JEBjames]

Michael

Great benchmarks.

Typo on page one. The html tag has a typo and shows up as text "& quopt;" instead of a quote symbol.

[Anux]

Uhhh, is it really true? Intel releases a server CPU that isn't worse than AMDs last generation and it might even be on par in power efficiency. I can't wait for the power numbers ...

From what we know of Zen 5 this might be the closest in competition we have seen in years. And in some cases the Intel CPU is twice as fast as the Zen 4 one, I don't believe that Zen 5 will give such massive boosts but it might still be slightly faster overall.

256T vs 256T and roughly similar performance and efficiency. Hopefully I don't wake up in a few seconds ...
Makes me a little more confident in the leaks about desktop 200 series.

Also can't wait for the Zen 5 comparison, thanks Michael.

[Michael]

Michael

Great benchmarks.

Typo on page one. The html tag has a typo and shows up as text "& quopt;" instead of a quote symbol.

Whoops, thanks, busy morning...

[sophisticles]

This is why I keep telling people to buy as many Intel shares as they can.

It has gone from a low of just over 19 a share to almost 23 today and I expect it to hit 27 shortly with 35 a strong possibility by years end.

My forecasting software has it hitting 55 by June 2025 and possibly 100 by end 2025, beginning 2026.

Intel has had some trouble in recent years which caused the stock to take a serious hit but this isn't going to last.

With some of the new products it's going to launch, and the deals it has inked recently that have given it some much needed cash infusion, Intel is ready to take off.

Buy now, buy as much as you can, in a couple of years you will be glad you did.

[coder]

Uhhh, is it really true? Intel releases a server CPU that isn't worse than AMDs last generation and it might even be on par in power efficiency. I can't wait for the power numbers ...

It's being compared against their previous generation. Intel on a 3nm-class node vs. AMD on a 5nm-class node. It's no wonder that it beats EPYCs with fewer or smaller cores.

Good job on Intel for getting this out the door before AMD could launch Turin. Once that happens, it'll be a return to the usual picture where AMD is back on top.

From what we know of Zen 5 this might be the closest in competition we have seen in years. And in some cases the Intel CPU is twice as fast as the Zen 4 one, I don't believe that Zen 5 will give such massive boosts but it might still be slightly faster overall.

Other than the cases involving AMX, the ones where Granite Rapids achieved the greatest margin of victory generally tended to be ones that favored more L3 cache over having more cores. You can tell, because the 96-core EPYC with the X (3D) cache placed ahead of the 128-core EPYC with the C-cores.

Zen 5 doesn't increase cache per-core, so Zen 5 probably won't do enough to overturn those results. However, its larger out-of-order structures should help offset the impact of having to fetch a cache line from another CCD. So, we'll see.

[coder]

This is why I keep telling people to buy as many Intel shares as they can.

This is a tech forum, not investing. Please stop pumping (or trashing) stocks on here.

[aerospace]

A 500"intel watts" parts vs an 360W part doesn't mean same efficiency. I'm very curious about Turin, it's better efficiency with the same TDP, 1.5X the cores and possibly faster ram. AMX is the new AVX, any software running on the dedicated extension will run circles around the cpu that hasn't got it yet...