Skip to main content

Benchmarks, Part 1

Unix Bench 5.1.3

Unix Bench is an open source GPLv2-licensed suite that originated in 1983 at Mondash University. Byte Magazine then updated and expanded the set of metrics. It includes nine benchmarks that quantify various aspects of system performance, but we focus on Dhrystone and Whetstone specifically. The former isolates string handling; there are no floating-point operations. Whetstone measures the speed and efficiency of floating-point operations typically employed in scientific applications.

Image 1 of 4

Image 2 of 4

Image 3 of 4

Image 4 of 4

The Xeon Platinum 8176 provides a nice single-threaded boost to integer operations compared to the previous-generation E5-2697 v4. We also observe a notable increase in the single-threaded Whetstone test compared Intel's previous generation. Also, the E5-2643 comes close with its 3.4 GHz base and 3.7 GHz Turbo Boost clock rate.

The Platinum takes an easy lead in both tests when we spread the workload across all 28 cores. The E5-2697 v4 is its nearest competitor, but a 10-core deficit is downright unforgiving compared to the Platinum 8176. Whetstone addresses a minuscule amount of data that tends to reside entirely in L1 cache.

NAMD Scalable Molecular Dynamics

NAMD is a parallel molecular dynamics workload that performs high-performance simulations of large biomolecular systems. It's designed to test the boundaries of parallel computing by scaling up to 500,000 cores. The Theoretical and Computational Biophysics Group at the University of Illinois at Urbana-Champaign developed and maintains the project, which is the recipient of several prestigious awards.

Core counts reign supreme in this floating-point-heavy test. The Platinum 8176 leverages its hefty armada of cores to take an easy lead over the rest of the field. Like many of the multi-threaded tests, this is a one-sided competition. We'd need a 28-core Broadwell-EP for a fairer match-up, but one doesn't exist.  

NAS Parallel Benchmarks

The NAS Parallel Benchmarks (NPB) are a set of programs developed by the NASA Advanced Supercomputing Division to evaluate the performance of parallel supercomputers. The suite characterizes Computational Fluid Dynamics (CFD) applications, and NASA designed it to measure performance from smaller CFD applications up to "embarrassingly parallel" operations. The FT test characterizes a 3D partial differential equation using Fast Fourier Transform, while BT measures Block Tri-Diagonal solver performance.

Image 1 of 4

Image 2 of 4

Image 3 of 4

Image 4 of 4

The E5-2699 v3 and E5-2697 v4 both feature 18 Hyper-Threaded cores, so it isn't surprising to find them closely matched. The Platinum 8176 doesn't provide a performance increase commiserate with its hefty core advantage because other factors, such as clock rates, also come into play. In either case, the new processor is still quite a bit faster.

Due to its lower frequency, the 8176 provides fewer M/ops (Millions of Operations Per Second) per thread. That's a measure of per-core performance. The rest of the field aligns nicely based on clock rate, it appears. Provided you have a big core count advantage in your favor, the lower M/ops per thread value isn't as important for highly-parallelized workloads.


REmote DIctionary Server (Redis) is a popular in-memory data structure store that is used as a database, cache, and message broker. It's dependent on both CPU performance and memory bandwidth. Redis is open source (BSD-licensed) software.

Memory throughput plays a big role in this test, as evidenced by the DDR3-equipped v2 models at the bottom of the chart. Redis is a single-threaded workload, so its indicative of per-core memory throughput and performance. That's why the six-core E5-2643 v3s lead over the 10-core E5-2699 v3. In light of Platinum's vastly improved memory throughput, it appears a lower operating frequency hinders the Platinum 8176. A multi-threaded in-memory database would extract much more performance from the Platinum's memory throughput capabilities.

Open SSL

SSL (Secure Sockets Layer) is the go-to technology for securing encrypted links between a server and client. It's an important protocol for every level of the Web in today's security-conscious climate.

Image 1 of 2

Image 2 of 2

Intel worked diligently on accelerating encryption/decryption from several angles, as we measured in the Core i9-7900X Review. Our Platinum-based test system comes outfitted with Intel's QuickAssist Technology, which boosts performance in a range of encryption/decryption tasks.


MORE: Intel & AMD Processor Hierarchy

MORE: All CPU Content

Paul Alcorn is the Deputy Managing Editor for Tom's Hardware US. He writes news and reviews on CPUs, storage and enterprise hardware.