Language Selection

English French German Italian Portuguese Spanish

AMD SLI vs Intel SLI

Filed under
Hardware
Reviews

This year has seen the arrival of many new interesting technologies such as PCI Express and DDR2. Yet to this day SLI still remains by far the most hyped about technology. SLI was designed by NVIDIA and allows two select graphics cards to work together. The ability to link two powerful NVIDIA graphics cards together does sound impressive. However I believe that the most important reason that NVIDIA has received so much attention is because they were the first to deliver AMD followers with PCI Express technology.

They did this with the nForce4 chipset series which of course does come in an SLI flavor. SLI (Scalable Link Interface) allows a single system to combine two NVIDIA graphics cards to scale system performance. This technology takes advantage of the increased bandwidth of the PCI Express bus. Currently the ability to operate the GeForce 6600 GT, 6800, 6800 GT and 6800 Ultra in SLI mode is possible. The two cards are linked together using what is known as a bridge chip.

While this technology has the power to almost double the frame rates when operating in SLI mode, you have to remember it will also cost twice as much to use. For example, a GeForce 6800 Ultra SLI setup will cost around $1000 US for the graphics cards alone. This technology is however reasonably good value for GeForce 6600 GT setups, as it will cost no more than $400 US for the graphics cards. The nForce4 chipset series has already become hugely successful for a number of reasons. First and foremost they bring PCI Express support to the AMD64 platform and they do this by offering a flexible upgrade path.

Although SLI enabled motherboards do hold a fair price premium, their unique abilities are worth this price penalty. This is evident through the 750,000+ nForce4 chipsets already sold by NVIDIA. In order to utilize SLI technology there is currently only one chipset that will give a motherboard this support. Known as the NVIDIA "nForce4 SLI", this chipset supports a whole host of new and exciting features. The nForce4 series looks to be the best NVIDIA chipset creation yet. Until recently the nForce4 SLI chipset only included AMD 939-pin support. However, the chipset has been re-released with support for the Intel LGA775 platform.

The chipset still goes by the same model name; now there is simply an AMD and Intel version. The list of supported features is very extensive, covering everything from SLI support to built-in firewalls. Initially some motherboard manufacturers were unhappy with the Intel Edition SLI chipset performance, saying that it was nothing like the AMD version. However, since then Gigabyte, ASUS and MSI just to name a few, have been sampling Intel Edition SLI motherboards. The results have been good, leaving us to wonder who really does offer the best SLI performance, AMD or Intel.

Full Review.

More in Tux Machines

Security: VPNFilter, Encryption in GNU/Linux, Intel CPU Bug Affecting rr Watchpoints

  • [Crackers] infect 500,000 consumer routers all over the world with malware

    VPNFilter—as the modular, multi-stage malware has been dubbed—works on consumer-grade routers made by Linksys, MikroTik, Netgear, TP-Link, and on network-attached storage devices from QNAP, Cisco researchers said in an advisory. It’s one of the few pieces of Internet-of-things malware that can survive a reboot. Infections in at least 54 countries have been slowly building since at least 2016, and Cisco researchers have been monitoring them for several months. The attacks drastically ramped up during the past three weeks, including two major assaults on devices located in Ukraine. The spike, combined with the advanced capabilities of the malware, prompted Cisco to release Wednesday’s report before the research is completed.

  • Do Not Use sha256crypt / sha512crypt - They're Dangerous

    I'd like to demonstrate why I think using sha256crypt or sha512crypt on current GNU/Linux operating systems is dangerous, and why I think the developers of GLIBC should move to scrypt or Argon2, or at least bcrypt or PBKDF2.

  • Intel CPU Bug Affecting rr Watchpoints
    I investigated an rr bug report and discovered an annoying Intel CPU bug that affects rr replay using data watchpoints. It doesn't seem to be hit very often in practice, which is good because I don't know any way to work around it. It turns out that the bug is probably covered by an existing Intel erratum for Skylake and Kaby Lake (and probably later generations, but I'm not sure), which I even blogged about previously! However, the erratum does not mention watchpoints and the bug I've found definitely depends on data watchpoints being set. I was able to write a stand-alone testcase to characterize the bug. The issue seems to be that if a rep stos (and probably rep movs) instruction writes between 1 and 64 bytes (inclusive), and you have a read or write watchpoint in the range [64, 128) bytes from the start of the writes (i.e., not triggered by the instruction), then one spurious retired conditional branch is (usually) counted. The alignment of the writes does not matter, and it's not related to speculative execution.

In Memoriam: Robin "Roblimo" Miller, a Videographer and Free Software Champion

Videographer Robin Roblimo Miller

Robin "Roblimo" Miller was a clever, friendly, and very amicable individual who everyone I know has plenty of positive things to say about. I had the pleasure of speaking to him for several hours about anything from personal life and professional views. Miller was a very knowledgeable person whose trade as a journalist and video producer I often envied. I have seen him facing his critics in his capacity as a journalist over a decade ago when he arranged a debate about OOXML (on live radio). Miller, to me, will always be remembered as a strong-minded and investigative journalist who "did the right thing" as the cliché goes, irrespective of financial gain -- something which can sometimes be detrimental to one's longterm health. Miller sacrificed many of his later years to a cause worth fighting for. This is what we ought to remember him for. Miller was - and always will be - a FOSS hero.

May everything you fought for be fulfilled, Mr. Miller. I already miss you.

Today in Techrights

Tux Machines Privacy Statement

Summary: Today, May 25th, the European General Data Protection Regulation (GDPR) goes into full effect; we hereby make a statement on privacy AS a matter of strict principle, this site never has and never will accumulate data on visitors (e.g. access logs) for longer than 28 days. The servers are configured to permanently delete all access data after this period of time. No 'offline' copies are being made. Temporary logging is only required in case of DDOS attacks and cracking attempts -- the sole purpose of such access. Additionally, we never have and never will sell any data pertaining to anything. We never received demands for such data from authorities; even if we had, we would openly declare this (publicly, a la Canary) and decline to comply. Privacy is extremely important to us, which is why pages contain little or no cross-site channels (such as Google Analytics, 'interactive' buttons for 'social' media etc.) and won't be adding any. Google may be able to 'see' what pages people visit because of Google Translate (top left of every page), but that is not much worse than one's ISP 'seeing' the same thing. We are aware of this caveat. Shall readers have any further questions on such matters, do not hesitate to contact us.