Why Nvidia will rush to Tegra 4 as fast as it can

When Nvidia finally announced the Tegra 3 platform a few months ago, it was undeniably the best ARM-based system-on-a-chip (SoC) to be had. However, as other manufacturers begin to detail next generation ARM chips, Tegra 3 is already starting to lose a little of its luster. Last year’s Tegra 2 SoC had an advantage for a number of reasons, but the Tegra 3 will be on a level playing field, and the competition will be tough.

Early reports from MWC indicate that Nvidia stamped the first samples of Tegra 4 (codenamed Wayne) in December, and have sent them to OEM partners to work with over the coming months. Wayne will run multiple Cortex-A15 cores with a smaller 28nm manufacturing process, whereas Tegra 3 still uses Cortex-A9 at 40nm. Improved Tegra 3 parts with higher clock speeds are also on the way.

Prior to 2011, building a product with a Tegra chip was essentially the kiss of death. The early Tegra parts powered uninspiring devices like the Microsoft Kin, Zune HD, and Samsung YP-M1. None of them did particularly well, and many prototype smartbooks running Tegra were cast aside as well. All that changed with Tegra 2.

Nvidia’s Tegra 2 SoC was running two ARM Cortex-A9 cores and had a solid GPU behind it. Nvidia was able to get Google to officially bless its platform by making it the reference design for Android 3.0 Honeycomb. Because of the closed nature of Honeycomb, OEMs were forced to use Tegra 2 until Android 3.2 expanded support. By that time, Tegra was firmly entrenched and powering not just tablets, but phones like the Motorola Atrix 4G, Droid X2, and LG Optimus 2X.

For its encore, Nvidia has opted to up the ante on cores with the Tegra 3 rather than move to a new architecture. Tegra 3 still uses Cortex-A9, but runs four of them on a single die. As manufacturers like Qualcomm begin showing off upcoming chips, Nvidia might have cause to worry. Snapdragon S4 is benchmarking very well with its two Krait cores, and Qualcomm has plans for even more powerful versions of the chip in the coming months.

Krait is a processing core that is unique to Qualcomm, and is designed to compete with Cortex-A15, not the older A9 used in Tegra 3. If this is indicative of what manufacturers can do with A15, OMAP5 and the revamped Exynos could also prove problematic for Nvidia’s Tegra 3.

Another concern for Nvidia’s current Tegra is that it has traditionally not played nicely with LTE modems. In early 2011, that was not terribly important as LTE was just beginning to roll out in the US market. In 2012, consumers are starting to expect LTE in devices, and Tegra still lacks an integrated LTE radio.

It is telling that HTC’s US variant of the One X will have a Snapdragon S4 standing in for the Tegra 3 precisely because of the LTE support. Asus is also using Snapdragon S4 in the 3G/4G version of the new Transformer Infinity 700 tablet. This puts Tegra 3 at a disadvantage when compared to Snapdragon S4, and possibly future SoCs.

Nvidia has recently put out its first SoC with an integrated radio chip in the ZTE Mimosa, but this is just a Tegra 2. A version of the Tegra 4 codenamed “Grey” is expected in early 2013 that will have a built-in 4G LTE Icera modem along with Cortex-A15 cores. Can Nvidia really wait a year to fully answer the SoCs launching this Spring? Nvidia is standing behind Tegra to the end, so the company is sure to give it a good shot.

Read more at VR-Zone

Source

AMD’s Analyst Day confirms APU cancellations, trims core counts

AMD’s Analyst Day kicks off today and the news is starting to flow. Additional details will be disclosed throughout the various presentations, so we’ll update this story or publish follow-ups as appropriate.

So what are the headlines so far? As we expected, AMD has canceled its Krishna and Wichita APUs that were to follow Brazos, in favor of what it calls Brazos 2.0. Brazos 2.0, as it turns out, looks just like Brazos 1.0, but with minimally faster clock speeds and USB 3.0 tossed in. We spoke with the company yesterday in a pre-briefing.

This could be problematic for the company’s lower-end products. Qualcomm has given notice that it intends to push into the netbook market late this year or early next, while Brazos’ 40nm technology will face competition from Intel’s 32nm Atom, as well as 28nm Qualcomm and Cortex-A15 chips.

Hondo — a chip we discussed last August, and rumored to be cancelled — is still on target. It’s a respun version of Brazos that’s been rearchitected for low-power operation. AMD has had several wins with Desna, its 5.9W TDP tablet option; Hondo brings this down to 4.9W. With Microsoft’s Windows 8 not expected until the end of the year, AMD has time to ready something more competitive before the x86 tablet market really takes off.

Come 2013, we’ve got debuts from Temash, Kabini, Kaveri, and Sea Islands, AMD’s next-generation graphics core. Temash will use the next-generation Jaguar CPU core and will be AMD’s first SoC, building on the expertise that AMD gains from Hondo. Kabini, meanwhile, uses the same core but fits into a slightly higher power envelope. It’s not clear if Kabini is also an SoC or not — keeping a separate APU part would give AMD more die space to devote to CPU/GPU processing cores.

Finally, there’s Steamroller, a third-generation Bulldozer core and what AMD calls “HSA” (Heterogeneous System Architecture) features. Based on the current rate of progression, the GPU at the heart of Temash, Kabini, and Kaveri will be based on AMD’s Tahiti (aka 7900). The Trinity GPU is based on Cayman.

This slide breaks down the differences between mobile and desktop. One surprising factor in AMD’s pre-briefing is that the third-generation CPU at the heart of Kabini and Kaveri doesn’t appear to have a high-end variant — at least not in 2013. AMD also intends to move to 28nm production in 2013. GlobalFoundries has a 28nm-SHP process that uses SOI, but everything we’ve heard from the foundry suggests that 28nm is a very modest improvement over 32nm as far as power consumption is concerned. As we’ve explored recently, however, modest improvements are the best the semiconductor industry can deliver these days.

The left-hand column shows server plans for 2012, the right side is 2013. This new roadmap is significantly different from slides that leaked back in August. At that point, AMD’s plan was to release new platforms, with 10 and 20-core Bulldozer chips launching in 2012 on 32nm, followed by 28nm die shrinks in 2013. As the new slide shows, AMD’s G34 and C32 platforms will survive through 2012. According to company executives, the performance improvements from Piledriver are significant enough to make the switch to deca-core and icosa-core processors unnecessary. Instead, AMD will hold upper core counts steady at octal and hexadeca levels. (This crash course in Greek nomenclature brought to you by the letter Qoppa).

This is good news. AMD’s previous guidance implied Piledriver would deliver a 10-15% improvement in performance-per-watt. Hopefully the company managed to exceed that target — but even if it didn’t, what BD needs is a combination of improved architectural efficiency, faster caches, and higher clock speeds. AMD’s roadmap doesn’t show anything beyond 32nm — a discrepancy that may be explained by the following older slide.

“Bulldozer NG,” in this case, is Piledriver. Given that the company has canceled its original plan to move to a new platform and 10/20-core architecture in 2013, it’s possible that AMD’s server platforms will move directly from the configuration on the far left to the far right, SoC-style implementation. Historically, AMD’s desktop and server CPUs have been tightly linked as far as their CPU architectures are concerned — the fact that we don’t see third-generation CPU core anywhere in 2013 could mean that the company will move to a unified SoC for servers and high-end desktop in 2014.

There’s still considerable question as to Trinity’s CPU performance and whether it’ll be strong enough to keep AMD competitive with Intel through 2012. The good news is that things should improve in 2013 with the launch of new 28nm hardware across the company’s entire product line.

Source