TweakTown NewsRefine News by Category:
AMD has a new Embedded single-chip system-on-chip (SOC) processor family on the scene with its new R-Series. It's aimed at the high-end market, and packs its latest 64-bit CPU core "Excavator", as well as a third-gen GCN GPU architecture. It's also the first of its kind to support dual-channel 64-bit DDR4 (with speeds as high as DDR4-2400; DDR3 is also supported with speeds up to 2133).
On the graphics and video front, the R-Series supports High Efficiency Video Coding (HEVC)1 for full 4K decode and DirectX 12; the specifications note up to eight compute units and two rendering blocks and GPU clock speeds up to 800MHz resulting in 819 GFLOPS. The company claims 22 percent better performance over the 2nd Generation AMD Embedded R-Series APU2 and 58 percent better performance over the Intel Broadwell Core i7 in graphics-intensive benches.
As for efficiency, AMD boasts full HSA implementation and hUMA utilization for what they feel results in great CPU, GPU, and memory performance. Additionally, thermal design power is configurable, and power usage is said to be reduced 35 percent compared to the 2nd Generation AMD Embedded R-Series APU.
AMD CEO and President Lisa Su affirmed her company's commitment to high performance x86 CPUs in its earnings call last week, for anyone in doubt following the recent news of financial troubles.
"In terms of long-term roadmap we are extremely committed to high performance x86 CPUs," she says. "And there should be no confusion on that point. [Chief Technology Officer] Mark Papermaster is currently directly engaging with the team on that execution and we'll have more details to come. But [we're] overall pleased with the execution and it continues to be our number one priority for the company."
More, she states Zen's impressive target 40% IPC performance is "on track" and that multiple FinFET designs have been taped out (meaning design is finalized, and the chips need only be produced).
It looks like AMD is preparing to launch a new 8-core server SoC codenamed "Hierofalcon", based on a 64-bit ARM design using eight A57 cores clocked at 2GHz each. AMD's new Hierofalcon SoC has a TDP of 30W, so we should expect some decent performance from the new chip.
An engineering sample of the new 8-core "Hierofalcon" processor has been spotted, where it has been put up against a bunch of desktop processors from both Intel and AMD. We have those results above. These results are looking at the performance on a single core, at a normalized clock speed. The new Hierofalcon processor does quite well, taking swings at some of AMD's desktop chips.
When it comes to "Whetstone" performance, the desktop processors kick some serious ass, but that's to be expected. The same thing goes for the Execl benchmark and the kCopy and kPipe results.
The power efficiency estimation results are interesting, as the new 8-core Hierofalcon processor from AMD comes in quite well. But we have to remember, this is an early chip and performance/power efficiency is only going to get better as we get closer to the final chip.
Qualcomm has just unveiled its plans to enter the server CPU market with a new custom processor based on an ARM design. Qualcomm's latest chip is being aimed at the likes of hyper-scale customers like Google and Facebook, as well as many service providers and large enterprises.
The new chip was shown off last week, with the CPU being a purpose-built system-on-chip that is different to other Snapdragon processors. The first version of Qualcomm's new chip is a 24-core processor, combining PCIe, storage and other features into the SoC. According to Qualcomm Senior Vice President Anand CHandrasekher, the first pre-production processor has 24 cores, but future chips will have many more.
The chipmaker is now shipping its processor to big customers for testing, but Qualcomm isn't naming names. The company said it would provide a release window for the chip, but it would update the world in 2016.
Intel has been sitting pretty on two and four core CPUs for a long time now, but an Intel LinkedIn profile indicates the upcoming Cannonlake CPU, built on 10nm technology, will make the jump and support four, six, and eight cores.
Don't get too excited, though: Intel CEO Brian Krzanich indicated this past summer that consumers can expect Kaby Lake in the second half of 2016, and Cannonlake in the second half of 2017.
Intel isn't far away from releasing its Skylake Purley-powered Xeon processors, with the new platform set to feature a huge 28 Skylake cores, and thanks to Hyper-Threading, a total of 56 threads of CPU power.
These new Xeon processors are not destined for the consumer desktop, as they will include multi-processor setups. The new Xeon E5 and Xeon E7 processor ranges will see the Xeon E5 range packing between two and four CPUs on a motherboard, while the Xeon E7 steps it up, considerably. The upcoming Xeon E7 range will pack an 8-socket design, allowing for an insane amount of CPU horsepower, especially when each CPU has 56 threads.
Intel will be unleashing its new Omnipath Architecture inside of the new Skylake-powered Xeon processors, something it calls Storm Lake (Generation 1). This new PCH will be codenamed Lewisburg, where it will include updated Ethernet controllers. The Skylake Purley update will also pave the way for Socket P, with a TDP that's configurable between 45W and 165W. The PCIe slots will have 48 lanes of bandwidth to play with, but this could change at any time.
The Skylake Purley update is said to be the biggest update Intel has done since Nehalem, and with a 56-threaded CPU that rocks a 6-channel DDR4 architecture, as well as the new AVX 512 instruction set and 100G Omni Path interconnect, we're in for one heck of a ride.
Intel took everyone by surprise when they launched the Broadwell 5775C and 5675C desktop SKUs around Computex. The CPUs not only took the crown with the fastest desktop integrated graphics, but they also were able to overclock.
Building upon the success of their Iris Pro line with integrated eDRAM, Intel is adding eDRAM to their more affordable Iris lineup as well. For Skylake, both GT3 and GT4 integrated graphics will feature 22nm eDRAM. The eDRAM will be treated as normal system memory (instead of cache), but should prove to be beneficial for graphics performance.
While the 5775C and 5675C were both launched months ago, only recently did they start to sell. Their prices are also sky high, but we hear that there is demand for desktop CPUs with strong integrated graphics. The overclocking potential of the "C" SKUs was also low, the CPUs didn't overclock well. Intel told us that this was due to the mobile nature of Broadwell; transforming the BGA CPU to an LGA CPU proved to be cumbersome because of the eDRAM implementation and expected overclocking capabilities.
As of August 9th Intel had shipped 1 million Skylake CPUs worldwide. The new CPUs will go on sale on September 1st in Asia and in 6 weeks will be available worldwide. While Intel already launched their K series Skylake desktop SKUs last month, they are now announcing the launch of their entire introductory Skylake lineup including both desktop and mobile segments.
Intel predicts that Skylake will last approximately 4 years, meaning that we should expect even more SKUs in the future. A lot of microarchitecture information was disclosed during technical sessions at IDF and I already wrote that up here.
Qualcomm may seem like its been out of the game lately, but their upcoming Snapdragon 820 processor is shaping up to be a real beast. Not only is it going to offer up 40% more performance, while using 40% less power, but it's also going to take DSLR-quality photos, too.
The company has just announced a new technology that will be featured in the Snapdragon 820 called Smart Protect, which will use real-time, on-device machine learning to detect zero-day malware threats. Awesome. The Snapdragon 820 will do this by "looking at the actual behavior of device applications to detect and classify behavior that seems suspicious or anomalous", reports TechSpot.
Qualcomm has also said that its Smart Protect technology will work alongside existing signature-based anti-malware solutions, as Smart Protect is able to analyze and identify enw threats before the signature is even available. All of this can be done without requiring a connection to the Internet, too. Qualcomm is using Zeroth, its first cognitive computing platform, to power Smart Protect. The company has been working with many of the industry's biggest security providers including Avast, AVG and Lookout to utilize Smart Protect capabilities inside of their commercial products.
Intel is about to drop the rest of its Skylake processors into the market, after the release of the Core i7-6700K and Core i5-6600K just recently. There will be eight more processors released, but the rest of them will not be unlocked models for overclocking.
The chipmaker will be offering up 10 total SKUs, with two of them already in the wild. The remaining 8 processors will be made up of four 65W, and four 35W low TDP chips. All of these processors will slot into the new LGA 1151 motherboards using the Z170, H170 and B150 chipsets. The new Skylake-S processors are as follows:
- Intel Core i7-6700K
- Intel Core i5-6600K
- Intel Core i7-6700
- Intel Core i5-6600
- Intel Core i5-6500
- Intel Core i5-6400
- Intel Core i7-6700T
- Intel Core i5-6600T
- Intel Core i5-6500T
- Intel Core i5-6400T