AMD Athlon 64 3800+ and FX-53: The First 939 CPUs
by Derek Wilson on June 1, 2004 12:30 AM EST- Posted in
- CPUs
Comparing Sockets: Gaming Performance
DX9 and Media Encoding benchmarks confirm 939 is the fastest CPU at 2.2GHz.
2-pass Media Encoding was about 6% faster on 939 than 754 at the same speed. Direct X 9 games were closer in performance among the 3processors, but still showed a consistent 754-940-939 pattern from slowest to fastest.
Quake 3 and other games based on the Quake Open GL engine are sensitive to memory bandwidth variations. So it was not a surprise to see Quake 3 increase in performance a bit over 6% from 754 to 939. Across all DX8 games 939 again came out as the top performer.
We did not expect large improvements in performance as Athlon 64 moved from 754 to 939. Since we have found the performance of the Dual-Channel Socket 940 and the Single-Channel 754 to be close when they ran the same speed with the same cache, it was already clear the Athlon 64 was not an architecture that was starved for memory bandwidth like the 'deep-pipes' Pentium 4 design. When P4 went dual-channel the performance improvement was dramatic. Athlon 64 shows more modest increases in performance, but that performance increase is still real and measurable. Dual-Channel 939 is the fastest Athlon 64 socket, followed closely by 940. It appears that the reduced latency of unbuffered memory actually does translate into slightly improved performance for 939. Socket 754 is slower than either of the DC solutions, but the difference between fastest and slowest among the 3 sockets is still relatively small.
Facebook
Twitter
RSS
38 Comments
View All Comments
Icewind - Tuesday, June 1, 2004 - link
Slight gramatical problem here......As we have mentioned in previous news articles, these new CPUs will run at the 3500+ will run at 2.2GHz while the 3800+ and FX-53 will run at 2.4 GHz each.
I think you wanted to say "These new CPU"S will be starting at the 3500+ model running at 2.2ghz to the 3800+ running at 2.4ghz."
Viditor - Tuesday, June 1, 2004 - link
"I have updated the article to reflect the fact that we did indeed run our tests with 1T timings on the MSI K8T800 Pro 939 board"Thanks Derek...that's why I always read you guys!
WBurton - Tuesday, June 1, 2004 - link
I'm getting a bit frustrated with the Sponsored Links constantly crashing my Opera 7.x. It'd be nice to review an article without having to reboot all the time.MIDIman - Tuesday, June 1, 2004 - link
Is it possible that the release of a 64-bit OS will change all of these numbers and conlcusions?Lonyo - Tuesday, June 1, 2004 - link
1066MHz HT bus?I thought the HT bus ram 200xmult
So isn't it 200x5, or 1000MHz?
(Typo on the first page?)
boban10 - Tuesday, June 1, 2004 - link
what i dont like about many review sites that they encoding always the same codec and then say p4 is faster.well look here how they test it:
http://www.extremetech.com/article2/0,1558,1603531...
i hope that your and anandtech next reviews will be more in depth about encoding, cause if people read your reviews about encoding they will buy p4.
but p4 is not faster in all encoding and that is important to say and test. and i like this site, but if next time i see again only one test in encoding (and that where is know that p4 win) then i will not read your page anymore. and no im not amd fan, im performance fan.
mechBgon - Tuesday, June 1, 2004 - link
Jeff7181, you asked "Is running four unbuffered DIMMs really that necessary?"I was running three 512MB modules on my A7N8X Deluxe before replacing it with my K8V Deluxe. That was working out nicely for what I was using it for. When I installed my A64 and K8V Deluxe, I stepped *down* to 1.0GB because if I used all three modules, it would want to run them at DDR200/PC1600 speeds. If I could add a fourth module for 2.0GB total, that would be a welcome improvement. Yeah, I could invest in two 1GB DIMMs, I guess...
Intel's i865 and i875 families have brought 4 DDR400 DIMMs to Pentium4 owners, and that capability, along with CSA Gigabit, are two places where I have to admit Intel trumped AMD & Co. nicely, and has kept them trumped for quite a while too. So it would be nice to see AMD get their mojo working here.
DerekWilson - Tuesday, June 1, 2004 - link
I have updated the article to reflect the fact that we did indeed run our tests with 1T timings on the MSI K8T800 Pro 939 board.I appologize for the omission.
Viditor - Tuesday, June 1, 2004 - link
I wonder if Derek caught the bios setting tweak that Aces found."An incredible difference: with a faster bus turnaround, the memory subsystem is able to serve up to 24% more bandwidth, and the latency goes down from 51 (21.25 ns) to 47 cycles (19.6 ns). This results in measurable real world performance gains:
In 3DS Max 5.1, we gained 3% of performance
In Medieval War, Comanche we also gained 3%
In Wolfenstein: Enemy Territory, we gained 5.5%
In WinRAR and Plasma, the performance advantage was no less than 9%"
http://www.aceshardware.com/read.jsp?id=65000305
nycxandy - Tuesday, June 1, 2004 - link
Which motherboard was used for the 939 processors?