Lab Update: Old P4s in Bench & OCZ's 30GB/60GB Vertex SSDs
by Anand Lal Shimpi on June 9, 2009 12:00 AM EST- Posted in
- Anand
A few weeks back I introduced you all to a tool I’d been working on for a while called Bench.
Bench, in its current form, is a database of CPU performance data allowing you to compare virtually any modern day desktop CPUs. With the recent launch of the Core i7 975 and the Athlon II X2 processors there are now 78 individual CPUs represented in Bench.
In my introductory post I asked what sort of older CPUs you’d like to see included. The top suggestions were as follows:
Intel’s Pentium 4
AMD’s Athlon XP
VIA’s Nano
You asked, and I delivered. Well...I started to at least.
The first chip I added was the Pentium 4 660. Based on Intel’s Prescott core, the 660 was a single-core Pentium 4 with Hyper Threading enabled. In today’s more threaded world, HT is more useful than when the 660 first came out. The chip runs at 3.6GHz and was built on a 90nm process.
In many tests even a Pentium E2160 (1.6GHz dual-core Conroe derivative) is 15 - 50% faster than the Pentium 4 660. The Pentium E5200 kicks the advantage up to the 50 - 80% range thanks to a much higher clock speed than the E2160 (2.50GHz for the E5200). The main take away point is that you don’t have to spend more than $50 - $70 on a CPU to see a significant performance improvement over the Pentium 4 660.
The Pentium EE 955 (left) and the Pentium 4 660 (right)
The second chip I added was the Pentium Extreme Edition 955. This was one of the fastest processors ever made in the Pentium 4 era, only bested by the Pentium EE 965. Take two 65nm Cedar Mill die put them on the same package and you’ve got a dual-core Presler. With 376 million transistors the Pentium EE 955 ran at 3.46GHz and thanks to its Hyper Threading support, could execute four threads at the same time.
Intel was right about threading being the future. The quad-threaded Pentium EE 955 fared much better today than I expected, partly due to its ability to juggle more threads. The Pentium E5300 is significantly faster in many areas (40%+ in some tests), but surprisingly there are some situations where the golden oldie is close. Fallout 3 has the Pentium EE 955 within 10% of the E5300, as did the multi-threaded PAR2 test. Overall you’d see a significant performance improvement going to a $70 CPU. Although you may never again spend $1000 on a CPU if you decide to pursue that upgrade.
Lynnfield and then SSDs
In my last Lab Update I talked about working on SSDs, unfortunately I had to leave out the part about me working on a preview of Intel's Lynnfield processor. I must say that the Lynnfield testing went much better than I expected. I had the whole thing wrapped up in under a day and didn't have a single crash or performance issue to try and resolve.
Compared to my early Nehalem testing, Lynnfield actually fared even better. While my first Nehalem ran at higher clock speeds, the first Nehalem motherboards had issues with memory performance. Lynnfield worked very well for what I was testing, although I did hear that CrossFire/SLI weren't working very well on those early platforms.
I am curious to see how Intel manages the LGA-1156 vs. LGA-1366 platform split. Intel claims to be committed to LGA-1366 but I do see a lot of potential in LGA-1156; I believe it'll be a difficult job to maintain both platforms without artificially crippling one. We'll see if Intel is up to the task later this year.
My SSD testing is progressing well. There are a couple of items worth reporting on.
1) Windows 7 does currently support TRIM.
2) No SSDs currently enable TRIM support under Windows 7.
OCZ is expected to have TRIM support on its Vertex drives shortly, potentially within the next month from what I've read on their forums. Samsung's latest drive will have TRIM support once Microsoft has released Windows 7; I'm guessing that means September/October.
Intel is remaining curiously quiet on the TRIM issue. I would like to see the existing X25-M drives retrofitted with TRIM as I think that would be a tremendous goodwill gesture on Intel's part; I get that the X25-M is already the fastest thing on the market, but that's no reason to avoid thanking your customers for their support in my mind.
The WePC Update
Last week I talked about two important trends I'm seeing in the CPU industry. Here's a hint: power management is really becoming more important in microprocessor design.
OCZ's Vertex 30GB and 60GB Drives: Slower?
I've been testing the OCZ Vertex 30GB and 60GB drives fairly thoroughly over the past couple of weeks and I've got some early data to report.
1) The 30GB and 60GB drives are about 20 - 35% slower in sequential read and write speed than the 120GB drives.
2) Small file random read/write speed is unaffected. The entire lineup of Vertex drives, regardless of size, performs the same when dealing with small file random access.
3) As a result, real world performance is mostly unaffected by going for a smaller drive. PCMark scores are only around 4 - 5% lower on the smaller drives.
You should have no issues opting for a smaller Vertex drive, but the 120GB drive continues to be a better buy. Not only do you get better performance, but from what I've seen you get a much lower cost per GB than the smaller drives. OCZ's 30GB Vertex actually has a cost per GB greater than Intel's X25-M.
Expect more of this in my upcoming SSD article.
Facebook
Twitter
RSS
41 Comments
View All Comments
rundll - Tuesday, June 9, 2009 - link
I guess most people are mainly interested in the cheapest possible yet with good performance loaded SSDs. In this prospect there are far too few reviews on those new cheapest SSDs.Samsung SSD PB22-J 2.5" 64GB, SATA II (MMCRE64G5MXP-0VB) costs only 152 euros here in Europe. It also have great (but few) feedback on this price comparing site. How ever, I can't find any review on this particurarly SSD (now, be careful with the right type).
Also, there is a Solidata K6 32GB SSD at only 99 euros.
Those two chips are in my mind the cheapest SSDs with a good performance. Even a quick look into these two would be very interesting.
leexgx - Tuesday, June 9, 2009 - link
corsair S128 is an better buy, i find any thing below that is to small allso the smaller the SSD shorter it lastalso you should not fill the SSD to the point it has no free space left (keep 20gb free)
rundll - Tuesday, June 9, 2009 - link
Raid 0, dude, raid 0.deputc26 - Tuesday, June 9, 2009 - link
I'm building a friend a computer (all components chosen) and I was really hoping that AT would have reviews of the other 60gb indilinx SSDs. Can you just say whether or not buying a G.Skill Falcon would be a mistake instead of a vertex? (Newegg ran out of them).leexgx - Tuesday, June 9, 2009 - link
ignore the data rate of the SSDs as long as it has cache on it you will blow away any hdd on load times and game load timesif you want stable firmware get an Samsung based SSD be it Corsair you can get an Corsair S128 gb for £171 ($200) its based on samsung and has 32MB of cache as all first gen SSDs do it, the second gen SSDs have 128mb of cache on them (64mb on 64gb one, any above 128gb has 128MB cache), samsung have been used in alot of dells for some time now
OCZ vertex is realy an beta drive for now
i have the corsair S128 and do not be put off with the read speeds of this drive as its the access times that makes SSDs far faster then HDDs,
samsung have not updated there firmware for quite an long time thay will be when windows 7 comes around to get Trim support out and any other bug fix's
michaely - Tuesday, June 9, 2009 - link
You are going to get similar performance just because they are both indilinx controllers. What I like about OCZ is the fact that their forums seems so much more lively than others. Also, OCZ keeps coming up with firmware updates which can be both a good and bad thing. On one hand, new firmware tends to mean better performance. On the other hand, if you don't have that much time on your hands, maybe the G.Skill will fit your purposes as a general SSD. I'm not sure how active G.Skill is in updating firmware. It does seems like OCZ is leading the group in terms of development though. I personally would choose OCZ over G.Skill.TA152H - Tuesday, June 9, 2009 - link
When you look at the dreadful performance of the Lynnfield compared to the Nehalem, it looks Intel did cripple the Lynnfield intentionally.Now, I know the average person here jumped on the Lynnfield bandwagon, because they were expecting it to be good, and people can't see what they don't expect too clearly, but the performance was dreadful compared to the Nehalem, considering it was only a change in the memory controller. It's hard, really hard, to see big drop offs in performance due to memory, because caches are so effective now, and hide poor memory performance pretty well, but we did see it with Lynnfield. You'd be hard pressed to get a drop in that performance with Nehalem using very poor/slow memory compared to super fast memory. Try it, and see. So, whether Intel intentionally crippled Lynnfield, or if it's pre-release hardware, we'll see. One thing is for sure though, there's no way the Lynnfield should be that slow when it's released, and if it is, Intel degraded it intentionally. It's not the first time, do you remember the Coppermine and Tualatin Celerons? On top of having the normal smaller cache (although some Pentium III Tualatins only had 256K L2 cache as well), and slower bus speed, Intel added a wait state in the L2 cache just to be extra sure the thing was slow enough. Maybe they did something like that with Lynnfield? It's hard to lose so much performance with just main memory accesses, so I suspect something is amuck. Hopefully it's just pre-release silicon.
Oh, and here's a very subtle hint
http://shop.ebay.com/Pentium%20EE%20965?_from=R40&...">http://shop.ebay.com/Pentium%20EE%20965...m38&...
Keep in mind, the Pentium EE 965 should go down in value, and then back up as a collector's piece. It's the king of the notorious Pentium 4 family, and that's always going to have some value. It's also rare. The 955 is going to just go down, since no one cares about second best - and that isn't just with regards to collecting them; it includes reading about it :-P .
The 570 or 670 will probably not be worth anything,since they will not remain the highest clocked processors ever released forever, and their performance was surpassed in the Pentium 4 family. So, I wouldn't waste money on buying one.
Natfly - Tuesday, June 9, 2009 - link
You're nuts man. You keep posting in all the Lynnfield articles about how gimped out and "dreadful" the performance is.1) Less than 5% worse in performance is not "dreadful," no matter how you look at it. Especially considering Nehalem has a 50% increase in memory bandwidth over it.
2) You are comparing leaked early silicon, not to mention turbo mode wasn't working as the same level as on Nehalem (Only 1 speed bin vs Nehalem's 2)
3) Pre-production motherboard and bios are clearly not going to be on the same level as something that has been out for 6+ months. Even switching motherboards or updating the bios can potentially have an effect of several percent on benchmarks.
Denithor - Wednesday, June 10, 2009 - link
He's just an AMD fanboy troll.Don't feed the troll.
MadMan007 - Tuesday, June 9, 2009 - link
'dreadful'? What the heck are you talking about? Did you actually read the Lynnfield preview or are you just thinking up numbers out of thin air? In the preview, at equal clocks with HT enabled, Lynnfield is frequently <5% slower than an i7-920 and the max is just under 10% for a few tests. The only 'gimped' Lynnfield will be non-HT chips so there's your answer. Even then the performance will hardly be dreadful since it's meant to replace C2Q CPUs.