The AMD A8-7650K APU Review, Also New Testing Methodology
by Ian Cutress on May 12, 2015 10:00 AM ESTProfessional Performance: Linux
Built around several freely available benchmarks for Linux, Linux-Bench is a project spearheaded by Patrick at ServeTheHome to streamline about a dozen of these tests in a single neat package run via a set of three commands using an Ubuntu 11.04 LiveCD. These tests include fluid dynamics used by NASA, ray-tracing, OpenSSL, molecular modeling, and a scalable data structure server for web deployments. We run Linux-Bench and have chosen to report a select few of the tests that rely on CPU and DRAM speed.
C-Ray: link
C-Ray is a simple ray-tracing program that focuses almost exclusively on processor performance rather than DRAM access. The test in Linux-Bench renders a heavy complex scene offering a large scalable scenario.
Being a scaling benchmark, C-Ray prefers threads and seems more designed for Intel.
NAMD, Scalable Molecular Dynamics: link
Developed by the Theoretical and Computational Biophysics Group at the University of Illinois at Urbana-Champaign, NAMD is a set of parallel molecular dynamics codes for extreme parallelization up to and beyond 200,000 cores. The reference paper detailing NAMD has over 4000 citations, and our testing runs a small simulation where the calculation steps per unit time is the output vector.
NAMD is similar to our office benchmarks, puttin the bulk of the APUs between the i3-4130T and the i3-4330.
NPB, Fluid Dynamics: link
Aside from LINPACK, there are many other ways to benchmark supercomputers in terms of how effective they are for various types of mathematical processes. The NAS Parallel Benchmarks (NPB) are a set of small programs originally designed for NASA to test their supercomputers in terms of fluid dynamics simulations, useful for airflow reactions and design.
Despite the rated memory on the APUs being faster, NPB seems to require more IPC than DRAM speed.
Redis: link
Many of the online applications rely on key-value caches and data structure servers to operate. Redis is an open-source, scalable web technology with a b developer base, but also relies heavily on memory bandwidth as well as CPU performance.
Facebook
Twitter
RSS
177 Comments
View All Comments
TheJian - Friday, May 15, 2015 - link
I don't think it's sheer luck when you're doing one of two things: 1. you write the compiler they're using. 2. you're the chip/platform etc they are DOING the coding on and thus optimizing for best perf on the platform they're using. Granted, these two things might not help in ALL cases, but it's a pretty sure bet if EVERYONE decided to code their app/game ON Intel/Nvidia, if you're AMD you're not likely to win many things. You may code how you know how to code, but you OPTIMIZE for whatever is in your hands, and get to others if financing allows (or someone pays you, like Dice/B4F netting 8mil for frostbite running on mantle).If you don't have access for platform X, and it runs well on it vs. platform Y that you program on, THEN that was luck. But when it runs well on what you're programming/compiling on, that probably has much less to do with luck. It's just common sense to get that. I'm not saying that's the case here, but you're making a general statement that would seem to go against simple logic in what I'd guess was MOST cases. IE, how many ports of console games do you see that are BETTER on a PC. In most cases we get "another crappy port" comments all over the place. Consoles are admittedly (generally) a worst case scenario, but you get the point. Usually the 2nd platform etc is an afterthought to milk the original cow, not coded with the care of the main platform. Large firms with bigger teams (EA, Blizzard etc) may depend on the skill of the teams doing said work (but even then it's quite rare), but for smaller firms where financing is a big issue, other platform optimization may never happen at all.
Why do you think Nvidia bought a company like PGI? To make sure they were on even footing with Intel compilers for HPC. Being the vid card that ~75% of workstations and 76% of gamers (according to peddie) use doesn't hurt either, but compilers/tools are a big help too.
shadowjk - Friday, May 15, 2015 - link
Linux has adapted to some AMD specialities rather quickly, like the module/core division, and further back in time, discovered you could have iommu on amd cpus before they even were released.Unfortunately, I don't think AMD participates as actively in compiler development..
LarsBars - Tuesday, May 12, 2015 - link
Glad to see the IGP benchmarks updated, they are so much more relevant now! No more 1280x1024 ;) Great work!BrokenCrayons - Wednesday, May 13, 2015 - link
I agree, the new IGP benchmarks are a much-needed realignment to make them more current.darkfalz - Tuesday, May 12, 2015 - link
I love AMD's naming scheme, mimicking Intel's but using higher numbers. I wonder how many would fall for that? Surely a 7850K is much faster than a 4560K? And an A8 or A10 clearly a better CPU than an i5 or i7? Awesome chutzpah.akamateau - Tuesday, May 12, 2015 - link
Another piece of JUNK SCIENCE and yellow journalism from the journalistically bankrupt Anand Tech.What happened to the API Overhead Tests?
What HAPPENED to the DX12 benchmarks?
I am not INTERESTED in OBSOLETE GARBAGE.
There is nothing that you use for benchmarking that is relevant.
ALL gaming is now written to DX11 MAXSPEC. DX12 MINSPEC is 12x broader and allows for far more performance.
When you FAIL to use relevant benchmarks the you are LYING to the consumer.
ANAND TECH is nothing more than a garbage website.
extide - Tuesday, May 12, 2015 - link
This isnt a GPU benchmark article, it is a CPU benchmark articleCrunchy005 - Tuesday, May 12, 2015 - link
Why are you even here reading the articles or commenting on them if you think they are garbage?Michael Bay - Tuesday, May 12, 2015 - link
Your post lacks capitalization.NeatOman - Wednesday, May 13, 2015 - link
this is the only time I've liked what Michael Bay has said or done lol