Tensilica
Latest
Huawei's first octa-core chip promises faster LTE than its rivals
While MediaTek's trotting its way into the premium smartphone market with an LTE octa-core chip later this year, Huawei's creeping up right behind with its own octa-core offering. Like Samsung's newer Exynos 5 Octa variants, Huawei's new Kirin 920 consists of quad Cortex-A15 plus quad Cortex-A7 CPUs that work simultaneously, as well as a powerful Mali-T628 GPU. But what makes this 28nm chip special is its integrated multi-mode LTE Cat 6 radio, meaning it can offer data speeds of up to 300Mbps on networks that are set up for carrier aggregation. These are already live or being tested in the likes of Hong Kong, South Korea, Singapore and Germany.
Tensilica proves Blu-ray audio decoding can be done on a single core
Traditionally, Blu-ray decks have relied on multi-core chips to process and decode that succulent audio that tickles your eardrums, but Tensilica has a better idea. In an effort to shrink the amount of components within a BD deck and to offer up "significant cost savings and a simplified programming model," it has recently demonstrated DTS-HD Master Audio Lossless decoding on a single-core SoC. The outfit's HiFi 2 Audio DSP can handle codecs from both DTS and Dolby, and apparently it's already filtering into select players. Too bad you'll probably never know if your deck has one without rolling up your sleeves and breaking out the screwdriver.
Researchers tout 20 million processor-strong supercomputer to study climate change
It looks like a group of researchers at UC Berkeley have come up with a rather unique way of solving the problem of getting supercomputers past the processing power / energy consumption barrier, with them now touting the possibility of using millions of low-power embedded microprocessors instead of conventional server processors. That tantalizing prospect has apparently already lead to a deal with Tensilica Inc, which will provide the Berkeley researchers with some of its Xtensa LX extensible processor cores to use as the "basic building blocks in a massively parallel system design." Ultimately, the researchers say they could one day build a massive supercomputer consisting of 20 million embedded microprocessors at a cost of $75 million, which they say would have a power consumption of less than 4 megawatts and a peak performance of 200 petaflops. That, they say, would be enough for it to create climate models at 1-kilometer scale or, as the researchers put it, more than 1,000 times more powerful than anything available today.[Via TG Daily]
