AMD's Sempron 3300+: 90nm Budget Computing
by Anand Lal Shimpi on April 18, 2005 2:10 AM EST- Posted in
- CPUs
When AMD offered to send us their latest Sempron CPU for review, we honestly felt a little ashamed - we had almost entirely forgotten about the budget CPU that launched last June. Had we missed other Sempron reviews since its launch? Were we too tied up in the higher end desktop processors and the dual core migration to pay attention to AMD's brand new budget line? After a moment's panic, we calmed ourselves and realized something that had surprised us a bit - AMD hadn't released a faster Socket-754 Sempron since its launch in June 2004. Not a single new CPU in ten and a half months. We stopped feeling so bad.
Intel was slightly better, but not by much. After our original review of the 90nm Celeron D, Intel released one more CPU, the Celeron D 345, late last year, but it's been quiet since then. And we thought the mainstream CPU race had slowed down.
So, it was time for an updated comparison, but luckily, the field hadn't changed much - or had it? Remembering back to our original Sempron review, AMD initially introduced two Semprons: a Socket-A and an Socket-754 version. The Socket-A version has topped out at 3000+ (2.0GHz) and it doesn't look like there's any future beyond it for the aging platform. The Socket-754 platform has yet to out-live its welcome and thus, AMD's newest Sempron, the Sempron 3300+, is a Socket-754-only CPU. The Socket-754 Sempron is based on AMD's K8 architecture, but is a 32-bit only CPU (no x64 support here). As a Socket-754 CPU, the Sempron only features a single channel DDR400 memory controller.
Intel's Celeron D 345 was merely a clock bump to the Celeron D 335 that we reviewed last June, bringing Intel's fastest Celeron up to 3.06GHz while still remaining on the 533MHz FSB. AMD's Sempron 3300+ isn't as simple of a transition, however. The original Socket-754 Sempron was built on a 130nm process and featured a 256KB L2 cache, whereas the new Sempron 3300+ is built on AMD's 90nm process and features a 128KB L2 cache. The new Sempron also features all of the enhancements that made it into the 90nm Athlon 64 processors - mainly SSE3 support and some enhancements to the memory controller.
The higher rating is due to a higher clock speed; the Sempron 3300+ runs at 2.0GHz compared to the 3100+'s 1.8GHz clock. But with half of the L2 cache, the performance picture is bound to be much more interesting than just a regular clock bump.
With only a 128KB L2 cache, the Sempron 3300+ is definitely a step back in terms of the cache sizes that we expect to see on modern day microprocessors. At the same time, halving the cache while moving to a smaller process ensures that AMD can enjoy larger profit margins on these new Sempron CPUs. But AMD's profit margins aren't our concern here; what we care about is how the 3300+ performs and going one step further, a cool running 90nm chip with a very small 128KB L2 cache is quite attractive to the overclocker in us.
With an on-die memory controller, the Socket-754 Semprons can get away with having relatively small L2 caches, since their main memory access latencies are very low to begin with. But even if we estimate that the on-die memory controller of a Sempron reduces memory accesses to around ~120 cycles, an access from L2 cache is going to still take about 1/10th that. In the end, while AMD's K8 architecture is less dependent on large caches, it is still not impervious to the impact that a small one can have.
Priced at $127, the Sempron 3300+ is priced similarly to Intel's Celeron D 345 ($133) and the Athlon 64 3000+ ($140). That being said, let's see how it competes...
The Test
AMD Athlon 64 Configuration
Socket-939 Athlon 64 CPUs
2 x 512MB OCZ PC3200 EL Dual Channel DIMMs 2-2-2-10
MSI nForce4 SLI Motherboard
ATI Radeon X800 XT PCI Express
AMD Sempron Configuration
Socket-754 Sempron CPUs
2 x 512MB OCZ PC3200 EL Dual Channel DIMMs 2-2-2-10
ABIT NF8 nForce3 Motherboard
ATI Radeon X800 XT AGP
Intel Celeron D Configuration
LGA-775 Intel Celeron D 345 (3.06GHz)
2 x 512MB Crucial DDR-II 533 Dual Channel DIMMs 3-3-3-12
Intel 915P Motherboard
ATI Radeon X800 XT PCI Express
Facebook
Twitter
RSS
53 Comments
View All Comments
coldpower27 - Monday, April 18, 2005 - link
Maybe this is a way for AMD to get rid of "sucky" Venices. Though at 127US pricing, it's value is questionable over getting the Athlon 64 2800+.Illissius - Monday, April 18, 2005 - link
s/half the memory controllers/half the channels of memory/Illissius - Monday, April 18, 2005 - link
Are we looking at the same graphs? There were quite a lot where the 3300+ significantly outperformed the 3100+ (granted, also a few where they were identical, but very few where the 3100+ was faster).Which begs the question: wtf has AMD done to these things' memory controller? In many tests it ran dead even with or even outperformed the A64 3200+, with half the memory controllers and a fourth the cache (note: no, I didn't miss eg. the gaming benches where it rather sucked, but it's very surprising for it to give that kind of performance *anywhere*). At the same time, from every benchmark I've seen, Venices (Venii? :D) are only very slightly faster than Newcastles/Winchesters... strange.
paulsiu - Monday, April 18, 2005 - link
With a reduce cache, the 3300 did not seemed like a good deal especially if it barely beats the 3100. Why not just get a 3100 or overclock it. Better yet, get a A64 2800+.Once you hit a Sempron 3100+, their value becomes highly questionable because an A64 only cost a little bit more. The problem is that AMD appears to be discontinueing all A64 for the 754 socket with the exception of mobile A64. Few Mb manufacturer support mobiles directly.
AtaStrumf - Monday, April 18, 2005 - link
AT only got 2,4 GHz with increased voltage, XBIT Labs only got 2,3 GHz; damn these are some bad 90 nm chips. WTF is AMD up to? Venice chips did 2,7 GHz easy.As soon as get my hand on some $$$ I'm switching to S939, PCIe and a nice Venice chip. With dual core desktop Hammers not likely to appear before 2006, this will be the only game in town for the remainder of 2005 That is of course unless Pentium D tickles your fancy.
As for X800XT distorting the gaming value CPU picture, I think this is something worth thinking about. Maybe you should include a test with a 6600GT, just to see if a more expensive CPU, coupled with a value graphics card actually makes any difference.
Anand Lal Shimpi - Monday, April 18, 2005 - link
The 2.4GHz overclock was the most reasonable air-cooled overclock we could obtain. Regardless of how hard we tried, 2.50GHz was not possible with our chip.Take care,
Anand
Calin - Monday, April 18, 2005 - link
One big disadvantage of the Socket 754 Sempron would be the reduced memory bandwidth for an hypothetical "onboard video" solution. This is the main reason why I would like a dual channel Sempron that would cost much less than an Athlon 64. For now Sempron on Socket 754 (even with the lower price of the mainboards) is not a good choice in many regardsoverclockingoodness - Monday, April 18, 2005 - link
#14: Do you think AnandTech really have time for max overclocking experiements with phase cooling and stock cooling? It's all a waste. Besides, even though AT is an enthusiast site, they have more than enough projects to tackle than some enthuisiast sites who keep posting their maximum overclocks on the net. There are far too many forums and sites for that.And yeah, enough with the conspiracy theories. It is starting to become a regular thing in comments section of every article. People always find a way to doubt AT.
#13: I disagree. Imagine if they used 6600GT for the CPUs and almost all CPUs scored identical. This would mean that the GPU is the bottleneck. AT's goal is to remove the potential bottleneck. I am sure some people would come in and whine about the incorrect results due to GPU limitations. Although you will not get the same performance as AT did, at least it shows the product's strenghts/weeknesses. :)
knitecrow - Monday, April 18, 2005 - link
Considering the price of an sempron 3100+ to be $113 @ newegg and the price of a athlon64 2800+ to be $120; I see absolutely no reason to get a sempron!!!!!!!!!!!Visual - Monday, April 18, 2005 - link
wooo, bobsmith1492, that's the one!and its on top of the news section too... how didn't i notice it... i must be going nuts.
well sorry about that.
THEY SPY ON US WITH RAY! Wait, I must have my tinfoil hat here somewhere....
P.S. and yeah, it'd be good to see the actual overclock max of the chip, with a mem divider and lowered htt multi and all. at various voltages. with stock and phase-change cooling. :p