This site may earn affiliate commissions from the links on this page. Terms of use.

AMD Carrizo

When AMD launched Carrizo before this yr, it kept the function mobile-only. Carrizo'due south entire pattern was tuned for mobile hardware, and AMD did a number of briefings on how the scrap'south power consumption improvements and overall operation per watt were strongest in low ability envelopes. Information technology's therefore a touch surprising to hear that AMD is reportedly planning to bring a desktop version of the chip to market.

Zen'south delay, notwithstanding, may have left AMD with little choice, since it tin't afford to get an unabridged year without at to the lowest degree some new products in the marketplace. The company is reportedly prepping a gear up of both mobile and desktop cores under the Bristol Ridge moniker, congenital for socket FP4 and AM4 respectively. FP4 would continue to back up both DDR3 and DDR4, while AM4 would supposedly be DDR4-only. We know Carrizo has a DDR4 controller on-board, since the embedded version of the production launched with DDR4 support before this fall, then it's non surprising to hear that the same hardware would whorl over to desktop.

Here'southward the supposed list of desktop SKUs:

BristolRidge-AMD

There's well-nigh certainly some errors here, since information technology's highly unlikely that AMD would launch a dual-core SKU with a 2.8GHz core clock at 65W. The high-cease SKU, if authentic, would essentially match Kaveri'due south clock range (3.6GHz – 4GHz) but offer faster DDR4 back up for APUs, and a much-improved power envelope (65W vs. 95W). Unfortunately, the functioning gain is yet going to be thin — v-10% clock for clock, two years afterwards Kaveri offset shipped, simply isn't going to impress desktop users. Overclocking headroom isn't going to be annihilation to write home most either; Carrizo volition be stretching as it is to button into 4GHz territory and 65W — only every bit Kaveri's power consumption and thermals rose more than quickly above three.5GHz, we'd expect Carrizo to exercise something similar. One of Carrizo'due south great strengths in mobile was the fact that the improved design let AMD transport 15W parts would more graphics cores enabled. Desktop Kaveri / Godavari never had that problem, robbing the withal-hypothetical new bit of one of its competitive advantages against its predecessor.

Could Bristol Ridge exist a 14nm chip?

One betoken raised past Tech Report is that Bristol Ridge could be an early 14nm processor. In theory, this makes some sense — it'due south a bad idea to try and pull off a die shrink and a new CPU architecture simultaneously, and the Excavator uarch is well known to AMD. Looking at the range of 15W – 35W parts, however, the information suggests a relatively pocket-sized bump of 200-300MHz, and TDP envelopes within the ranges AMD has already gear up.

BristolRidge2

The bigger reason I recall Bristol Ridge volition be a 28nm flake, however, is because die shrinks are both expensive and fourth dimension consuming. In order to have Bristol Ridge ready for a mid-2016 product window, AMD would've needed to tape it out by late summer. Keep in heed that back in May, AMD fabricated it quite clear that Zen would make it past mid-2016, and that Zen was the hereafter of AMD products.

AMD essentially would have had to design Carrizo for 28nm, record it out, and immediately begin converting the blueprint to 14nm earlier it even had silicon back from the foundry. I'm not going to say that's impossible, but it's insanely risky and I've never heard of a foundry doing information technology.

It's exceedingly unlikely that AMD took this road, peculiarly given the modest gains 14nm would deliver. The Excavator cadre family is played out, everyone knows it, and the company's engineers have already performed a almost-phenomenon just squeezing a Bulldozer-derived into a 15W form cistron. Pouring money into further Excavator R&D would be throwing good funds after bad, and AMD merely doesn't have the coin to waste matter these days.