Polish computer site PCLab managed to secure an engineering sample of an Intel chip manufactured on the Westmere 32nm process, containing six-cores and 12MB of L3. Yes, it certainly looks like Gulftown – the codename for what likely will end up being marketed as Core i9.
Despite Gulftown not being officially supported yet the testers managed to get Gulftown to work on three boards: Gigabyte EX58-Extreme, ASUS Rampage II Gene and ASUS P6T SE, thanks to the chip using LGA 1366 socket. Of course, the BIOSes for the motherboards weren’t optimized for Gulftown just yet, so there were some performance issues – particularly in the memory department.
Overall, test results showed that Gulftown performs as many would hope it would with an extra two Hyperthreaded cores. Multithreaded applications saw impressive gains thanks to the bump in 50 percent greater number of cores.
The early benchmarks show a very impressive chip from the Westmere family that we’ll be seeing in 2010. Check out PCLab for the full preview (partial content below)
For the last seven years we’ve been doing our best to provide you with reviews of the very latest computer components. We have always been trying to publish product reviews on the day of their world premiere. This time we are presenting something special: a detailed review of the upcoming Intel Core i9 processor codenamed Gulftown. Manufactured in the 32 nm process technology, this CPU is expected to launch somewhere in Q1’10. You don’t have to wait for its benchmarks. Today we are presenting a complete performance overview of an early engineering sample.
The Westmere processor family and the 32 nm process technology
Our readers probably remember Intel’s technology roadmap for the coming months presented in our “manic essentials toolkit”. Let us have a look back at that processor “roadmap”:
The Intel processors currently available on the market are members of two families: Nehalem and Penryn, and all are made using the 45-nanometer process technology. The Nehalem processors are Core i7 for the LGA 1366 socket (codename: Bloomfield), Core i7 and Core i5 for the LGA1156 socket (codename: Lynnfield) as well as the laptop-dedicated Core i7 (codename: Clarksfield). Later this year and early next year, Intel plans to launch the Westmere processor family. The Westmere codename stands for all circuits, which, based on the Tick-Tock strategy, will be manufactured using the same architecture as Nehalem, but using 32 nanometer processing. The first ones to land in the stores will probably be the Clarkdale processors – dual-core systems with integrated graphics cores designed for the LGA1156 socket. With time, the Westmere family will grow in view of the advent of laptop-dedicated dual-cores with integrated graphics – the Arrandale and Gulftown processors. And it is none other than the Gulftown that is the central figure of today’s article.
The Gulftown core
Like Conroe (Core 2 Duo 65 nm) and Penryn (Core 2 Duo 45 nm), Gulftown has a whole lot in common with Bloomfield. In short, we can say that the Bloomfield has been given two cores and some third-level cache love. The capacity ratio of the L3 cache to the number of cores remains the same: Bloomfield has 4 cores and 8 MB of L3, Gulftown has 6 cores and 12MB of L3. The L1D, L1C and L2 cache capacity remains unchanged. Also unchanged is the processor’s “make-up” – in addition to six cores in a single block of silicon there is a block of L3 cache, a triple-channel memory controller and two QPI links. One of them is used to communicate with the IOH system and with the rest of the system (X58 desktop chipset or 5520 server chipset). The other one is used for communication with the second processor on dual-processor machines, and it will be disabled in the desktop and workstation version (similar to Core i7-900 and Xeon W35x0). Intel has not yet shown a silicon wafer with the Gulftown cores or the processor itself with the core uncovered. According to unofficial sources, its size should be approximately 21.1 × 11.4 mm. The core surface area is probably around 240 mm2, i.e. about 10% less than the Bloomfield core (263 mm 2). This means that if the yield on Intel’s 32-nanometer process technology is as good as that on 45-nanometer technology, the manufacturing cost of a single Gulftown is less than that of a Bloomfield. But let us not count on Intel’s six core price tag to be low. Firstly, Intel’s throughput in the 45-nanometer process is much higher – only one plant (D1D in Oregon) is ready to produce 32 nm circuits. Another three are being converted. Meanwhile, 45-nm systems are produced in three facilities. In addition, the Gulftown prices will be tailored to their target consumers – prepare to spend about 1,000-1,200 dollars for the desktop version. We still do not know what commercial name the Gulftowns will be given – various sources report it to be i9 Core or Core i7-1000 series.
Microarchitecture changes
It is true that the Tick-Tock strategy implies a change in the microarchitecture and updating the technology process, but when changing processes, Intel also makes certain improvements in the core logic. A good example of this was the Penryn processor family – although built based on the Conroe architecture, they featured such improvements as a faster division algorithm and SSE4.1 instructions. The most important and most publicized change to the Westmere compared to the Nehalem is a new AES-NI set of instructions (Advanced Encryption Standard – New Instructions). There are seven new instructions, six of which have been designed specifically to accelerate AES encryption. Encryption using this algorithm requires keys to be generated first, which is performed by the AESKEYGENASSIST instruction. The AESENC and AESENCLAST instructions perform further encryption steps, while AESDEC and AECDECLAST do the decryption. The AESIMC instruction makes decryption key generation faster. The last PCLMULQDQ instruction (carry-less multiplication of two 64-bit operands) is not directly associated with the AES algorithm, but also speeds up the encryption process. Details of the AES-NI instructions and the AES encryption algorithm can be found on an Intel website dedicated to this subject. Similar hardware-based encryption mechanisms were applied long ago now by VIA in their C3 and Nano processors. The AES-NI and PCLMULQDQ instructions will also be implemented on all Westmere processors, including the desktop Arrandale and the laptop Clarkdale. They are also to be implemented in AMD’s future processor architecture (codename: Bulldozer).
The second of the changes relevant to users is the change in the operation of the memory controller. As in the Lynnfield processors (Core i5 and Core i7-800), the 1 uncore timing part memory clock speed limit does not apply any more. While the uncore in a Bloomfield has to work with a 4000 MHz frequency so that the memory can reach a clock speed of 1000 MHz (DDR3-2000), three times the memory clock is enough for the Gulftows and the Lynnfields. In our test item, the uncore operation frequency was 2400 MHz and could not be changed due to early BIOS versions. Intel has not confirmed yet whether the Gulftown processors will provide official support for memories faster than DDR3-1333, but it can be expected that with one module per memory channel, the fastest official speed will be DDR3-1600.
(note from PcLab.Pl – We have been contacted by the reps of Intel Corporation. We agreed to remove the article. We will bring it back once Gulftown hits the stores, somewhere in 2010 )
Alas, this is going to be a challenging Tech week, I can tell. All I can report for now is that the current revision of Acronis Trueimage Home 2010 (version number 13.0.6053) doesn’t seem to work well with my TrueCrypt’d boot partition setup, under Windows 7 x64 [Version 6.1.7600].
Back to the drawing board – I’d really like to upgrade from DriveImage XML at some point [ahem] but at least it works!
My simple solution, for detachable external storage (i.e. it shouldn’t fry from the same power surge, if not cabled up in any way at the time of the electrical havoc . . .)
Some of these models require a port-multiplier eSata / e-sas type port, but usually include at least a software-raid sort of PciE card with the package – check to make sure, or you’ll only get one drive showing up instead of 4 or more . . .
If I were to go with the more expensive option (still relatively affordable, above – compared to a true NAS, etc.) I might consider some of the 1 terabyte or > “Green” SATA drives. This is due to me wanting to have a good backup locally (c.f. Acronis) as well as remotely (expect an article this coming week on more discoveries here). Yes, having been around the corporate world, I tend to back up like an OCD person washes hands – once you’ve been bitten, you understand the data is worth a lot more than the hardware.
The development of DHT has reached a stage where a tracker is no longer needed to use a torrent. DHT (combined with PEX) is highly effective in finding peers without the need for a centralized service. If you run uTorrent you might have noticed in the tracker tab of your torrents that the [Peer Exchange] (PEX) row is often reporting a lot more peers than the trackers you might have for that torrent. These peers all came to you without the use of a central tracker service! This is what we consider to be the future. Faster and more stability for the users because there is no central point to rely upon.
Now that the decentralized system for finding peers is so well developed, TPB has decided that there is no need to run a tracker anymore, so it will remain down! It’s the end of an era, but the era is no longer up2date. We have put a server in a museum already, and now the tracking can be put there as well.
By moving to a more decentralized system of handling tracking (DHT+PEX) and distributions of torrent files (Magnet Links), BitTorrent will become less vulnerable to downtime and outages:
With decentralized peer acquisition, there is no central tracker that can be down.
With decentralized fetching of metadata (torrents) we don’t need to rely on a single server that stores and distributes torrent files.
I can even imagine this extended a bit to house educational video clips, distributed. Perhaps not as easily streamed, but certainly viable as a file-based video download approach. c.f. http://www.godaddy.com/hosting/word-camp.aspx for an example; not sure how much they captured, but as I’ve said there is little reason these days not to capture the vast majority of it these days, given low space costs and the huge userbase of WordPress.
Google Wave : I’ve been there for a while now, by all means shoot me a wave to LeveronJ if you’d like to play with the capabilities some. As well, there’s a good bit of explanation here (along with a heavy-duty video), and a nice general (aka short) video below :
Posted November 18, 2009 by Matt. Filed under General.
I was very excited last week to learn that WordPress has been awarded the Overall Best Open Source CMS Award in the 2009 Open Source CMS Awards. This is a landmark for us, as it is the first time we’ve won this award, and it marks a shift in the public perception of WordPress, from blog software to full-featured CMS. No small contest, the Open Source CMS Awards received over 12,000 nominations and more than 23,000 votes across five categories.
As Hiro Nakamura said when he first bent time and space to land in Times Square: “Yatta!”
In addition to winning in the Overall Best Open Source CMS category, WordPress was named first runner-up in the Best Open Source PHP CMS category. This is significant because we weren’t even in the top 5 last year, and now we’re #2, ahead of Joomla! As is stated on the Award site, “WordPress made its way into the top five for the first time. The fact that it was outranked by Drupal by a very slight margin indicates how popular it has become with users as well as developers over the past year.”
Every day thousands of new people are embracing WordPress to power not just their blogs but entire sites and communities without compromising on usability or scalability (as would be the case with a legacy CMS). Every member of the WordPress community, from core developer to beginning user, should be proud to be part of this momentum: congratulations to us all!
Stick around the WordPress community for a period of time and you’re bound to come across a few folks who say Automattic is an evil company or Matt Mullenweg is evil in the way in which he runs WordPress.org. The more time I spend talking to Matt and with other employees of Automattic, the more I don’t understand where these thoughts and feelings of evilness come from. Sure, there is a decision made from time to time that a vocal group of people disagree with but you can’t make the right decision 100% of the time. Let’s take a closer look at Automattic as it relates to WordPress.
When I interviewed Matt at WordCamp New York, one of the things I asked him to address is the notion that Automattic commercially benefits from those who work for free. This indeed happens but on the flip side, Automattic gives a ton back to the project and to the community. For example, I think there is a lot that can be said for the progression of WordPress thanks to the resources that Automattic has been able to provide due to their funding. It’s also worth mentioning that Automattic pays a couple of folks to work on WordPress the majority of their time such as Ryan Boren who is always slaving away committing code and Jane Wells who works on the usability front.
It’s not like Automattic hoards the contributions to the project and gives nothing back. Matt said something during the interview that really stuck a chord with me and that is “Automattic is just one member of the WordPress community. We are a huge contributor. Myself, Jane everyone involved tries to give as much back to the WordPress community as possible.” So far, I can’t see anything that portrays the individuals or the company as evil. (read “the rest of the story” at http://weblogtoolscollection.com/archives/2009/11/18/is-automattic-evil/ )
So there you go. A number of folks that I know of in the FOSS world make their living there; income and FOSS aren’t incompatible. Beats the heck out of going mobster
. This is due to me wanting to have a good backup locally (c.f. 
