Tyan Transport SX TS65A-B8036 Performance
For this exercise, we are using our legacy Linux-Bench scripts which help us see cross-platform “least common denominator” results we have been using for years as well as several results from our updated Linux-Bench2 scripts. Starting with our 2nd Generation Intel Xeon Scalable benchmarks, we are adding a number of our workload testing features to the mix as the next evolution of our platform.
At this point, our benchmarking sessions take days to run and we are generating well over a thousand data points. We are also running workloads for software companies that want to see how their software works on the latest hardware. As a result, this is a small sample of the data we are collecting and can share publicly. Our position is always that we are happy to provide some free data but we also have services to let companies run their own workloads in our lab, such as with our DemoEval service. What we do provide is an extremely controlled environment where we know every step is exactly the same and each run is done in a real-world data center, not a test bench.
We are going to show off a few results, and highlight a number of interesting data points in this article.
Python Linux 4.4.2 Kernel Compile Benchmark
This is one of the most requested benchmarks for STH over the past few years. The task was simple, we have a standard configuration file, the Linux 4.4.2 kernel from kernel.org, and make the standard auto-generated configuration utilizing every thread in the system. We are expressing results in terms of compiles per hour to make the results easier to read:
Here we wanted to show off the range of CPU options scaling from the sub-$500 AMD EPYC 7232P to the $6,950 AMD EPYC 7742. Even though AMD has far fewer SKUs than Intel, it still covers a wide range of performance scenarios, even in a single CPU server. To give some context, the single AMD EPYC 7742 here is faster than two Intel Xeon Platinum 8280‘s.
c-ray 1.1 Performance
We have been using c-ray for our performance testing for years now. It is a ray tracing benchmark that is extremely popular to show differences in processors under multi-threaded workloads. We are going to use our 8K results which work well at this end of the performance spectrum.
With the AMD EPYC 7002 series, there are special “P” SKUs that range from 8 to 64 cores. These CPUs are single-socket only SKUs and therefore pair well with the Tyan Transport SX TS65A-B8036. They also provide a lot of value as they offer the same performance, but at a lower cost than their dual-socket capable non-P SKU counterparts.
7-zip Compression Performance
7-zip is a widely used compression/ decompression program that works cross-platform. We started using the program during our early days with Windows testing. It is now part of Linux-Bench.
For a system like the Tyan Transport SX TS65A-B8036, we see the EPYC 7302P as the lower-end of the SKU stack that users will configure. That is a 16 core SKU that can be paired with low cost 16GB DDR4-3200 DIMMs for a very cost-effective platform.
OpenSSL is widely used to secure communications between servers. This is an important protocol in many server stacks. We first look at our sign tests:
Here are the verify results:
We think that the AMD EPYC 7402P may be a better match in this server than the 7302P. It only adds $400-500 incremental cost to the server over the EPYC 7302P, but again adds eight more cores. If a system is utilizing all sixteen U.2 NVMe drive bays, this $400-500 is a relatively small percentage cost increase for the system.
Chess is an interesting use case since it has almost unlimited complexity. Over the years, we have received a number of requests to bring back chess benchmarking. We have been profiling systems and are ready to start sharing results:
Overall, we picked the above SKUs because we think they are the most common. For most users, the AMD EPYC 7702P is realistically the highest they will consider since the EPYC 7742 has a significantly increased cost at a relatively small performance benefit. The AMD EPYC “P” series parts are likely going to be the most popular in this Tyan server.
Tyan Transport SX TS65A-B8036 Network Performance
Taking a quick look at network performance shows some of the primary benefits of the Tyan-AMD solution over a traditional Xeon server.
Utilizing the PCIe Gen4 slots allows for two 50GbE ports or a single 100GbE port to be driven from a single PCIe x8 NIC. Practically that means one gets around twice the bandwidth per Mellanox ConnectX-5 PCIe Gen4 NIC than it does with the Gen3 versions of the same cards. For customers, that means higher performance per card, or potentially significantly lower costs by reducing the number of NICs, switch ports, and transceivers/ cables required to hit given performance targets. It also means more efficient use of valuable PCIe lanes in the platform. That is especially noticeable when coupled with many NVMe SSDs.
Tyan Transport SX TS65A-B8036 Storage Performance
We do not yet have PCIe Gen4 U.2 NVMe SSDs, but we now have a set of 16x Micron 9300 Pro 9300 3.84TB SSDs which we could use to fill drive bays.
The importance of this is to show 64x PCIe lanes, albeit at PCIe Gen3 speeds. With the AMD EPYC, there are still plenty of expansion slots open for high-speed networking such as 100GbE NICs. With Intel Xeon Scalable, one cannot get enough PCIe lanes in a single socket server and would have to resort to a switch that can handle around a quarter of this performance. A dual Intel Xeon Scalable server would have a maximum of 32 additional PCIe lanes which leaves only enough for two 50/100GbE NICs. With the AMD EPYC, this storage configuration can be handled with ease, leaving room for more networking and accelerators.
Next, we are going to look at power consumption, our STH Server Spider, and give our final words.