AMD To Attack Performance Desktop Market With RYZEN, More Zen Architecture Details Revealed
We’ve been hearing about AMD’s next-generation Zen-based processors for quite a while now, though the company just officially announced that desktop and mobile variants will be branded RYZEN. Over the past few months, we’ve seen Zen in action in both high-performance desktop and server applications and have been able to disclose a handful of features, specifications, and performance details. Today however, with AMD poised to host its “New Horizon” webcast, we have some more information to share related to the RYZEN branding, the ZEN architecture, and AM4 platform as a whole.
First and foremost is the actual branding for its Zen-based processors for desktops, formerly codenamed “Summit Ridge”. AMD will be branding its Zen-architecture based desktop processors RYZEN -- pronounced Rye-Zen (like horizon, without the “ho”). We’ve also got some new details regarding RYZEN’s speeds and feeds, and some additional performance-related data to share.
Zen-based processors will eventually target desktops, servers, and mobiles device, but the first wave of products will be targeted at the performance desktop market, where gamers and VR continue to spur growth. PC gaming hardware is predicted for 35% growth from 2015 to 2020, and VR-capable PCs are predicted to grow by a factor of 10 by 2020. Interest in eSports continues to skyrocket as well.
AMD is positioning RYZEN as a high-performance option targeting all of those market segments. Though there will be other core configurations, AMD has disclosed that one of the high-end options in the initial RYZEN line-up will feature 8 cores (16 threads with SMT) and at minimum a 3.4 GHz base clock, with higher turbo frequencies. That processor will also be outfitted with 20MB of cache – 4MB of L2 and 16MB of L3 – and it will be infused with what AMD is calling SenseMI technology. SenseMI is essentially fancy branding for the updated branch predictor, prefetcher, and power and control logic in Zen.
This is a bit of review, but AMD also drove the point home that its upcoming AM4 platform for RYZEN will be outfitted with all of the features expected of a modern PC enthusiast platform. AM4 motherboards will use DDR4 memory and feature PCIe Gen 3 connectivity, and support for USB 3.1 Gen 2, NVMe, and SATA Express. We expect to see a deluge of AM4 motherboards at CES 2017 in a few weeks.
Infinity Fabric consists of two key elements, a scalable control fabric and a scalable data fabric. The scalable control fabric has all of the central control elements, with small remote elements that are dispersed in each different block of the SoC. And feeding into the control elements across the fabric is the data from a myriad of sensors embedded across the SoC. The scalable data fabric is much like a high performance network pathway. It features a high-performance common bus, with low latency, and a coherent Hyper Transport Plus bus, that’s multi-socket and multi die-ready.
Every AMD SoC going forward will leverage Infinity Fabric. It was designed to handle the needs of the fabric within a die, and within the sockets on a multi-socket configuration. It will scale from notebooks right up on to data centers, on products that consume just a handful of watts up to systems that burn hundreds of watts.
Over and above Precision Boost, RYZEN also feature something AMD is calling Extended Frequency Range, or XFR. XFR caters to enthusiasts by allowing boost frequencies above and beyond normal Precision Boost limits, when there is thermal headroom available. With XFR enabled, clock speeds will scale higher when more exotic cooling solutions are used.
As we mentioned, AMD claims there is a “true AI network” inside every RYZEN processor. There is no doubt some salesmanship going on there, because all modern processors have some form of intelligent branch prediction. The smart prediction built-into RYZEN builds a model of the decisions the predictor needs to make, based on the software being executed at the time. Functionally, AMD has doubled the size of the branch history table over previous generation processors, and has doubled the number of weights in the prefetch table as well. All told, the neural net prediction in RYZEN anticipates future decisions, pre-loads pertinent instructions, and chooses the best path through the CPU for them, with the goal to reduce stalls and improve accuracy.
Smart Prefetch anticipates the location of future data accesses the processor may need, based on the application code. The learning algorithms RYZEN employs model and learn application data access patterns dynamically, and prefetch pertinent data, which is then stored into a local cache, so it’s ready for use without having to go out to main memory. That’s essentially how all modern prefetchers work, but AMD is claiming big improvements over previous generations.
In the demo, the RYZEN system outpaced the Core i7-6900K by a few seconds.
Keep in mind, video encoding will hammer all cores in a CPU, so the Core i7-6900K would not have hit its maximum boost frequency for very long. Still, it shows some strong multi-threaded performance on RYZEN.
Over and above the video encoding, we also saw real-time power consumption of the system during the test. The AMD RYZEN system idled in the 93-94 Watt range, while the Intel system was consuming about 106 Watts at idle. Under load, the AMD RYZEN-based system’s power consumption went up to about 187 Watts, while the Intel system’s went up to about 191 Watts. While this looks competitive on the surface, AMD claims they are not finished optimizing their platform and they expect power consumption to be lower on shipping product. Then again, had turbo boost been abled on RYZEN, power consumption may be higher. We’ll have to test on our own to know for sure.
In another demo, we got to play a bit of Battlefield 1 running with ultra settings at 4K on the RYZEN and 6900K-based system, each with a pair of GeForce GTX Titan X cards installed in SLI. We were not able to run any benchmarks, but rather to do somewhat of a side-by-side taste test of the machines, to see if we could detect any performance differences – which we did not. The goal of this demo was to show that RYZEN has the horsepower and bandwidth to keep an extremely high-end graphics configuration fed while gaming with the latest titles.
Based on what we’ve seen and heard so far, we’re optimistically anticipating RYZEN’s release. In the meantime, if you want to get an additional taste of what AMD has in store, the “New Horizon” event in which AMD will demo RYZEN live is happening right here in the stream below...
First and foremost is the actual branding for its Zen-based processors for desktops, formerly codenamed “Summit Ridge”. AMD will be branding its Zen-architecture based desktop processors RYZEN -- pronounced Rye-Zen (like horizon, without the “ho”). We’ve also got some new details regarding RYZEN’s speeds and feeds, and some additional performance-related data to share.
Zen-based processors will eventually target desktops, servers, and mobiles device, but the first wave of products will be targeted at the performance desktop market, where gamers and VR continue to spur growth. PC gaming hardware is predicted for 35% growth from 2015 to 2020, and VR-capable PCs are predicted to grow by a factor of 10 by 2020. Interest in eSports continues to skyrocket as well.
AMD is positioning RYZEN as a high-performance option targeting all of those market segments. Though there will be other core configurations, AMD has disclosed that one of the high-end options in the initial RYZEN line-up will feature 8 cores (16 threads with SMT) and at minimum a 3.4 GHz base clock, with higher turbo frequencies. That processor will also be outfitted with 20MB of cache – 4MB of L2 and 16MB of L3 – and it will be infused with what AMD is calling SenseMI technology. SenseMI is essentially fancy branding for the updated branch predictor, prefetcher, and power and control logic in Zen.
This is a bit of review, but AMD also drove the point home that its upcoming AM4 platform for RYZEN will be outfitted with all of the features expected of a modern PC enthusiast platform. AM4 motherboards will use DDR4 memory and feature PCIe Gen 3 connectivity, and support for USB 3.1 Gen 2, NVMe, and SATA Express. We expect to see a deluge of AM4 motherboards at CES 2017 in a few weeks.
AMD SenseMI
AMD’s SenseMI is a set of sensing and adapting technologies, including what AMD is calling “an artificial intelligence network” inside every Zen processor. There’s definitely some marketing speak going on there to describe the next-generation prediction algorithms for the processor’s branch predictor and prefetcher, but nevertheless AMD is claiming big gains in this area. SenseMI, however, encompasses much more. There are five main features of SenseMI that include Pure Power, Precision Boost, and Extended Frequency Range (or XFR), along with the neural net prediction algos and smart prefetcher.
Pure Power
Pure Power is probably what you’re expecting it to be. In real-time, Pure Power senses what’s going on with the processor’s current workload and provides a closed-loop control system to scale performance and power, over what AMD is calling its Infinity Fabric. Pure Power monitors temperatures, frequencies, and voltage, and adaptively controls each element to optimize performance and power usage.Infinity Fabric
Infinity Fabric is the name AMD is giving to the latest interconnect technologies the company is using to link not only the individual pieces of IP within a processor, but the processor to other IO. AMD created Infinity Fabric because it needed a new approach to scale its products, beyond moving to new process nodes. AMD needed to increase performance and efficiency, scale bandwidth, improve latency and QoS, and it required flexible, coherent interfaces across CPU and GPU cores, and the other functional blocks within the chipsInfinity Fabric consists of two key elements, a scalable control fabric and a scalable data fabric. The scalable control fabric has all of the central control elements, with small remote elements that are dispersed in each different block of the SoC. And feeding into the control elements across the fabric is the data from a myriad of sensors embedded across the SoC. The scalable data fabric is much like a high performance network pathway. It features a high-performance common bus, with low latency, and a coherent Hyper Transport Plus bus, that’s multi-socket and multi die-ready.
Every AMD SoC going forward will leverage Infinity Fabric. It was designed to handle the needs of the fabric within a die, and within the sockets on a multi-socket configuration. It will scale from notebooks right up on to data centers, on products that consume just a handful of watts up to systems that burn hundreds of watts.
Precision Boost
Precision Boost works in conjunction Pure Power. The goal with Precision boost is to consistently provide higher performance, for the same or lower power than un-optimized silicon. It essentially offers on-the-fly frequency adjustments, with fine grained increments of 25MHz, determined by the processor’s workload and health data at the time.
Over and above Precision Boost, RYZEN also feature something AMD is calling Extended Frequency Range, or XFR. XFR caters to enthusiasts by allowing boost frequencies above and beyond normal Precision Boost limits, when there is thermal headroom available. With XFR enabled, clock speeds will scale higher when more exotic cooling solutions are used.
As we mentioned, AMD claims there is a “true AI network” inside every RYZEN processor. There is no doubt some salesmanship going on there, because all modern processors have some form of intelligent branch prediction. The smart prediction built-into RYZEN builds a model of the decisions the predictor needs to make, based on the software being executed at the time. Functionally, AMD has doubled the size of the branch history table over previous generation processors, and has doubled the number of weights in the prefetch table as well. All told, the neural net prediction in RYZEN anticipates future decisions, pre-loads pertinent instructions, and chooses the best path through the CPU for them, with the goal to reduce stalls and improve accuracy.
Smart Prefetch
Smart Prefetch anticipates the location of future data accesses the processor may need, based on the application code. The learning algorithms RYZEN employs model and learn application data access patterns dynamically, and prefetch pertinent data, which is then stored into a local cache, so it’s ready for use without having to go out to main memory. That’s essentially how all modern prefetchers work, but AMD is claiming big improvements over previous generations.
RYZEN Performance Expectations
In addition to learning a few more of the technical details regarding RYZEN, we also got the chance to witness a few performance-related demos and play with a couple of machines. In one demo – similar to the Blender benchmark AMD showed off a few months ago -- we watched Handbrake encode a video clips, side by side on two systems. One was powered by a RYZEN processor, the other by a stock Intel Core i7-6900K (3.2GHz base, 3.7GHz turbo). Turbo Boost was enabled on the 6900K, but it was not on the RYZEN system. The CPU in the RYZEN system was running at 3.4GHz flat.In the demo, the RYZEN system outpaced the Core i7-6900K by a few seconds.
Keep in mind, video encoding will hammer all cores in a CPU, so the Core i7-6900K would not have hit its maximum boost frequency for very long. Still, it shows some strong multi-threaded performance on RYZEN.
Over and above the video encoding, we also saw real-time power consumption of the system during the test. The AMD RYZEN system idled in the 93-94 Watt range, while the Intel system was consuming about 106 Watts at idle. Under load, the AMD RYZEN-based system’s power consumption went up to about 187 Watts, while the Intel system’s went up to about 191 Watts. While this looks competitive on the surface, AMD claims they are not finished optimizing their platform and they expect power consumption to be lower on shipping product. Then again, had turbo boost been abled on RYZEN, power consumption may be higher. We’ll have to test on our own to know for sure.
In another demo, we got to play a bit of Battlefield 1 running with ultra settings at 4K on the RYZEN and 6900K-based system, each with a pair of GeForce GTX Titan X cards installed in SLI. We were not able to run any benchmarks, but rather to do somewhat of a side-by-side taste test of the machines, to see if we could detect any performance differences – which we did not. The goal of this demo was to show that RYZEN has the horsepower and bandwidth to keep an extremely high-end graphics configuration fed while gaming with the latest titles.
Based on what we’ve seen and heard so far, we’re optimistically anticipating RYZEN’s release. In the meantime, if you want to get an additional taste of what AMD has in store, the “New Horizon” event in which AMD will demo RYZEN live is happening right here in the stream below...
