Saturday, January 24th 2009

First AMD Benchmarks With DDR3 Memory Posted

Better late than never, AMD is embracing the DDR3 memory standard. Its newest desktop CPU socket, the AM3, connects the processor to dual-channel DDR3 memory. Initial specifications about AMD's processors on the new socket suggest that DDR3 1333MHz (PC3-10600) will be held as the memory standard the integrated memory controllers on AMD's processors support. The far-east team of Tom's Hardware posted the first series of benchmarks of a Phenom II AM3 processor, when paired with DDR3-1333. The benchmarks featured Gigabyte's MA790FXT-UD5P motherboard along with Corsair's dual-channel DDR3-1333 kit running at DRAM timings of 9-9-9-24. The CPU-Z window also shows that the memory modules are running unganged, meaning that the two memory controllers of the Deneb core are independent, with each controller handling a 64-bit wide memory channel. This state is somewhat comparable to that of single-channel memory, except that multi-threaded applications will still be able to independently address memory on each channel, utilizing all the bandwidth on offer.

At the center of the test-bench was the AMD Phenom II X4 910, the company's first flagship quad-core AM3 processor. The X4 910 features a default clock speed of 2.60 GHz. The same chip was tested in two settings: default clock-speeds, and overclocked to 3.12 GHz (240 x 13.0 @ default vCore). The screenshots below show the test results for WPrime. The overclocked chip scored a crunch-time of 46.613 s (1M). The overclock did not affect SuperPi at all, with insignificant differences in the scores between the two. PC Mark 05 got a decent boost, while 3DMark06 didn’t. Memory bandwidth and latency tests showed something strange, with the overclocked CPU (in effect memory) turning up with lesser latency (while normally, increase in clock speeds tend to step up latencies). The tests show that there are increments in performance with the use of DDR3 memory, though they are merely proportional to the clock speeds the memory is running at.


Source: Tom's Hardware
Add your own comment

75 Comments on First AMD Benchmarks With DDR3 Memory Posted

#1
WarEagleAU
Bird of Prey
Very nice jumps when the 910 is oc'd. Looking good though I Wish they did a triple channel like intel did.
Posted on Reply
#2
cdawall
where the hell are my stars
these tests seemed a bit odd when i found them and wprime looks to have been run on a single core when you factor in a 3.89x efficiency factor (about what these get) for the chip it is pretty close to the numbers a phenom 2+DDR2 gives


also this is set for stability not performance so you could easily see them saving several seconds off everything with proper settings
Posted on Reply
#3
oli_ramsay
The benchmarks featured Gigabyte's MA790FXT-UD5P motherboard along with Corsair's dual-channel DDR3-1333 kit running at DRAM timings of 9-9-9-24.
FAIL.

Why use RAM that's barely faster than DDR2 and ridiculously loose timings?
Posted on Reply
#4
Darksaber
W1zzard's Sidekick
just my two cents...that looks more like gigabyte marketing than anything else...Gigabyte GPUs, Board, CPU Cooler (which cannot be qualified as an OC cooler by any means)
Posted on Reply
#5
cdawall
where the hell are my stars
by: Darksaber
just my two cents...that looks more like gigabyte marketing than anything else...Gigabyte GPUs, Board, CPU Cooler (which cannot be qualified as an OC cooler by any means)
it is GB marketing but thats against the point lol
Posted on Reply
#6
Octavean
Phenom II X4 910,……?

I thought the first AM3 chips were going to be Phenom II X4 945,….?
Posted on Reply
#7
suraswami
hmm another sh**y review from sh**y one sided site. why bother seeing this?
Posted on Reply
#8
Weer
Everyone always thanks the AMD-news poster.
Posted on Reply
#9
zithe
by: Weer
Everyone always thanks the AMD-news poster.
Because this is something everyone wants to see. AMD got a chip that's competitive with core 2. Both will be in focus for maybe a year or two longer as most people don't really need more power. I'd say that making the chips as good as they are wasn't a bad move by AMD. They need a cash cow, not a killer flagship chip.
Posted on Reply
#10
Mega-Japan
And I'll be one of the first to be feeding that cash cow the minute the 945 or 950 is released.
Posted on Reply
#11
EastCoasthandle
by: oli_ramsay
FAIL.

Why use RAM that's barely faster than DDR2 and ridiculously loose timings?
Ding-Ding, that's what I was thinking as well. Who would actually buy this type of ram for an enthusiast PC? I checked newegg and found a 2gig kit of G.Skill DDR3 1333Mhz ram at 7-7-7-18 for $65 + shipping. I wonder what the result are when that ram is used.

Edit:
It looks like they used these the cheapest I know of right now. I still believe they should have used a much lower timing for such low speed ram.
Posted on Reply
#12
EastCoasthandle
Not to nit-pick results but the CineBench results when OC shows a pretty big gain. Only time will tell if high latency DDR3 negatively impacts PII performance. I await more results from synthetics as well as games!
Posted on Reply
#13
Blacklash
Yep I want to see gaming results, particularly with HD 4870 1Gb Crossfire.
Posted on Reply
#14
HolyCow02
by: Mega-Japan
And I'll be one of the first to be feeding that cash cow the minute the 945 or 950 is released.
Here Here! :toast:

Nice to see a 510MHz overclock on stock voltage. Should get pretty good when you have a non-shitty cooler on it
Posted on Reply
#15
Weer
by: zithe
Because this is something everyone wants to see. AMD got a chip that's competitive with core 2. Both will be in focus for maybe a year or two longer as most people don't really need more power. I'd say that making the chips as good as they are wasn't a bad move by AMD. They need a cash cow, not a killer flagship chip.
And I'd like to believe that what I see as fanboy-ism is actually civil-minded market-competition protection.
Posted on Reply
#16
FordGT90Concept
"I go fast!1!11!1!"
As far as I'm concerned, it's a worthless benchmark. All they do is test stock vs. overclocked. So? Of course it will be slightly faster is that not the point of overclocking (dah)? We need to know how this processor, at stock, stacks up to the DDR2 processors (Phenom II 920 or 940), at stock. Stock vs overclocked proves absolutely nothing. Pathetic.
Posted on Reply
#17
Mega-Japan
by: FordGT90Concept
As far as I'm concerned, it's a worthless benchmark. All they do is test stock vs. overclocked. So? Of course it will be slightly faster is that not the point of overclocking (dah)? We need to know how this processor, at stock, stacks up to the DDR2 processors (Phenom II 920 or 940), at stock. Stock vs overclocked proves absolutely nothing. Pathetic.
I don't find it to be THAT bad but I do would like to see comparison with Core 2 at the same memory.
Posted on Reply
#18
EastCoasthandle
Agreed, as a sneek-peek it does provide some information. This really isn't a full blown review of PII using DDR3. It just gives you an idea of what to expect using cheap ram IMO. What I didn't like was that they didn't provide good information as to CF results since they used it.
Posted on Reply
#19
TheScavenger
What this article is really lacking is a control setup/processor to test the DDR3/AM3 setup against. Those benchmarks mean nothing to me because there isn't a Phenom II AM2+ to compare them against! :banghead:
Posted on Reply
#20
EastCoasthandle
by: TheScavenger
What this article is really lacking is a control setup/processor to test the DDR3/AM3 setup against. Those benchmarks mean nothing to me because there isn't a Phenom II AM2+ to compare them against! :banghead:
We are just going to have to wait until full reviews are published. After reading this article I didn't get the impression that information was needed at this time until a complete and full review is shown.
Posted on Reply
#21
Octavean
by: oli_ramsay
FAIL.

Why use RAM that's barely faster than DDR2 and ridiculously loose timings?
LOL, it wasn't too long ago people were saying the same thing about DDR2 with respect to DDR1 on both AMD and Intel platforms.
Posted on Reply
#22
Swansen
by: Octavean
LOL, it wasn't too long ago people were saying the same thing about DDR2 with respect to DDR1 on both AMD and Intel platforms.
exactly, thats because there isn't any noticeable gain in performance with any new DDR jump.... and there won't be until they can figure out how to bring down latency.
Posted on Reply
#23
1Kurgan1
The Knife in your Back
What does it matter how DDR3 run vs DDR3 OC'd. Why didn't they toss the 910 into an AM2+ board after set it to the same clocks and test it compared to DDR2?
Posted on Reply
#24
EastCoasthandle
Hold on a sec, why are they using Wprime 1.55? WPrime 2.00 was released Sept 2008.
Posted on Reply
#25
ShadowFold
by: EastCoasthandle
Hold on a sec, why are they using Wprime 1.55? WPrime 2.00 was released Sept 2008.
It's tomshardware funded by Gigashit. What else do you expect?
Posted on Reply
Add your own comment