Gigabyte K8NNXP-940: Built on Athlon64 FX51 Strengths
by Wesley Fink on October 9, 2003 11:52 PM EST- Posted in
- Motherboards
Gigabyte K8NNXP-940: Stress Testing
We performed stress tests on the Gigabyte K8NNXP-940 in these areas and configurations:1. Chipset and motherboard stress testing, conducted by running the FSB at 219MHz.
2. Memory stress testing, conducted by running RAM at 400MHz with 2 DIMM slots filled and at 400MHz with all 4 DIMM slots filled at the lowest memory timings possible.
Front Side Bus Stress Test Results:
As is normal in our testing, we ran a full range of stress tests and benchmarks to ensure the Gigabyte K8NNXP-940 was absolutely stable at each overclocked FSB speed. This included Prime95 torture tests, and the addition of other tasks - data compression, various DX8 and DX9 games, and apps like Word and Excel — while Prime95 was running in the background. Finally, we ran our benchmark suite, which includes ZD Winstone suite, Unreal Tournament 2003, SPECviewperf 7.0, and Gun Metal Benchmark 2. At default voltage, 219MHz was the highest overclock that we were able to achieve with the K8NNXP without encountering any reliability issues. We will take another look at the K8NNXP-940 when a new BIOS update corrects the multiplier and FSB adjustment issues.Memory Stress Test Results:
This memory stress test is very basic, as it simply tests the ability of the KX18D PROII to operate at its officially supported memory frequency (400MHz DDR) at the lowest supported memory timings that our Mushkin High Performance ECC Registered Modules will support:| Stable DDR400 Timings — 2 DIMMs (1/2 Dual-Channel banks populated) |
|
| Clock Speed: | 200MHz |
| Timing Mode: | N/A |
| CAS Latency: | 2.0 |
| Bank Interleave: | N/A |
| RAS to CAS Delay: | 3T |
| RAS Precharge: | 8T |
| Precharge Delay: | 2T |
| Command Rate: | N/A |
We currently have 4 DIMMs each of Registered ECC DDR400 from both Legacy Electronics and Mushkin. The Legacy runs well at 2.5-3-4-5 timings, while the Mushkin has SPD timings of 2-2-3-8. Until we complete our upcoming roundup of Registered (ECC) DDR400 memory, we are using the Mushkin as our test standard. We had no problem at all with absolutely stable performance of the Mushkin High Performance ECC Registered at SPD timings.
Filling all available memory banks is more strenuous on the memory subsystem than testing 1 bank (2 DIMMs) in dual-channel mode, as it tests four DIMMs (2 banks) of Registered ECC memory running 400MHz DDR at the most aggressive memory timings the memory will allow.
| Stable DDR400 Timings — 4 DIMMs (2/2 Dual-Channel banks populated) |
|
| Clock Speed: | 200MHz |
| Timing Mode: | N/A |
| CAS Latency: | 2.0 |
| Bank Interleave: | N/A |
| RAS to CAS Delay: | 3T |
| RAS Precharge: | 8T |
| Precharge Delay: | 2T |
| Command Rate: | N/A |
Running both Dual-Channel Banks required the same timings as a single Dual-Channel Bank. It appears you can load the Gigabyte K8NNXP-940 with four DIMMs and still expect the fastest performance that your memory is capable of achieving.
We tested all these memory timings using several stress tests and general applications to guarantee stability. Prime95 torture tests were successfully run at the timings listed in the above charts. We also ran Sciencemark (memory tests only) and Super Pi. None of the three stress tests created any stability problems for the Gigabyte K8NNXP-940 at these memory timings.
Facebook
Twitter
RSS
35 Comments
View All Comments
Anonymous User - Friday, October 10, 2003 - link
64-bit tests running Linux and hand-compiled programs would be:a) Really time consuming
b) Artificial
c) Not relevant to the real world
Anonymous User - Friday, October 10, 2003 - link
It is odd that NO 64-bit tests has been made. Why don't people fire up Linux and compile a few programs like MPEG encoding, video/divx processing etc etc?Anonymous User - Friday, October 10, 2003 - link
Has anyone tried decreasing both the memory speed and the LDT speed when overclocking an athlon 64 board via the fsb?The reason I ask is that being able to set the memory, and hypertransport ratio's, may make an independant CPU multiplier adjusment redundant.
(obviously it would be nice to rule CPU frequency out of such a test)
PrinceGaz - Friday, October 10, 2003 - link
...almost forgot, why was the P4EE 3.2 not included in the benchmarks?PrinceGaz - Friday, October 10, 2003 - link
Very very nice board and CPU, and impressive benchmarks throughout (you can't expect it to match the P4 for encoding). But next year's 939-pin FX is definitely the one to wait for.#4- QDR is just as unlikely as RDRAM but for different reasons, a key point of the A64/FX is the on-die memory-controller but that means you can't just add another couple of memory-channels to it without a total socket re-design (and for QDR a ridicoulously high pin-count). DDR2 is the way forwards in the future rather than more channels.
I'd really expected the fastest CPU nearly two years after getting my XP1700+ to be more than just 85% or so faster than it (the Barton 3200+ is barely over 50% faster, and the A64 3200+ about 70% faster). Unfortunately I can't justify an upgrade until its over 2x, preferably 3x as fast so I'll wait into next year and see what speed increases the shift to 90nm brings.
Anonymous User - Friday, October 10, 2003 - link
Very impressive board, We've used Gigabyte boards almost exclusively for the past few years at our computer shop and they just keep getting better with every revision. What I'm looking forward to is what they're going to have coming out early next year for the FX, by that time, having an FX system will become a reality for those of us who can't pay an arm and a testes.Anonymous User - Friday, October 10, 2003 - link
I want to know whats up with Gunmetal. Otherwise, great review. I just hope that the prices come down, alot, by spring for my upgrade.Anonymous User - Friday, October 10, 2003 - link
If anyone had doubts about the A64 and FX performance there should be no questions now!FX is intended to satisfy the extreme demands of power users who want the best and they want it now. A64 is a more cost effective solution for those who want outstanding performance at a consumer price point.
As A64/FX ramp all prices will drop as is normal. You'll likely find that the FX series is quite affordable to the enthusiast market and a Helleva value as things ramp.
And there are some more goodies on the way from AMD and it's partners to make all consumers very happy. Stay tuned!
Wesley Fink - Friday, October 10, 2003 - link
#5 - Regular Opterons are locked - at least that is what we found in the 2 we tested. The FX is unlocked.#6 - Yes, this is the first 1394b 800mb/sec Firewire board.
mcveigh - Friday, October 10, 2003 - link
is this the first PC board with firewire800?