Vik

AMD Releases Radeon Software Adrenalin Edition 18.2.2 & Inaugural Ryzen Desktop APU WHQL Drivers
  • Comments are Closed

AMD Releases Radeon Software Adrenalin Edition 18.2.2 & Inaugural Ryzen Desktop APU WHQL Drivers

This week, AMD released Radeon Software Adrenalin Edition 18.2.2, a smaller patch bringing support for the just-launched Kingdom Come: Deliverance, as well as performance optimizations for Fortnite and PlayerUnknown’s Battlegrounds (PUBG). Purely game-focused, 18.2.2 documents no new bugfixes or issues. And alongside Monday’s launch of AMD Ryzen 5 2400G and Ryzen 3 2200G, AMD has put out the inaugural Windows 10 WHQL drivers specific to those two new APUs.

Released just yesterday, Kingdom Come: Deliverance is a CryEngine-powered first-person single player historical RPG, thematically reminiscent of Mount and Blade and The Witcher. The developers, Warhorse Studios, have stated their desire to focus on realism, story, open-world freedom, and hardcore combat mechanics, the latter of which is not too surprising considering the Operation Flashpoint and ARMA pedigree of Warhorse Studio’s team members.

For Kingdom Come: Deliverance, AMD cites their 18.2.2 testing to show up to 3% faster 1440p performance for the Radeon RX Vega 56 and up to 4% faster 1080p performance for the Radeon RX 580 compared to Radeon Software Adrenalin Edition 18.2.1. As it so happens, Warhorse Studios marks down the Radeon RX 580 as the recommended AMD GPU requirement, with the Radeon HD 7870 as the minimum.

As for Fortnite and PUBG, AMD compares Radeon Software Adrenalin Edition 17.12.1 performance to 18.2.2, claiming 1440p improvements for the Radeon RX Vega 56 up to 3% faster for Fortnite and up to 5% faster for PUBG. Meanwhile, for the Radeon RX 580 at 1080p, AMD cites up to 6% faster performance in Fortnite and up to 7% faster performance in PUBG.

Wrapping things up on the 18.2.2 side, there has been no documented bugfixes and the list of open issues remain identical to 18.2.1:

  • FreeSync intermittently engages during Chrome video playback incorrectly, resulting in playback flicker.
  • Radeon Overlay hotkey fails to bring up the overlay or causes a Radeon Host Application crash intermittently on a limited number of gaming titles.
  • FreeSync may rapidly change between min and max range when enabled causing stutter in fullscreen games on multi display system configurations.
  • When Enhanced Sync is enabled on some FreeSync connected displays, flickering occurs with the performance metrics overlay.
  • Water textures appear to be missing in World of Final Fantasy.
  • A random system hang may be experienced after extended periods of use on system configurations using 12 GPU’s for compute workloads.
  • The GPU Workload feature may cause a system hang when switching to Compute while CrossFire is enabled. A workaround is to disable CrossFire before switching the toggle to Compute workloads.

Radeon Software for New Ryzen Desktop APUs

Released as “Radeon Software for Ryzen Desktop Processors with Radeon Vega Graphics,” the inaugural public graphics drivers are WHQL certified and are documented as version 17.40.3701 (Windows Driver Store Version 23.20.827.0). The update applies only to the Ryzen 5 2400G and Ryzen 3 2200G, and notes the following:

  • RAID drivers are not included in display driver packages. Users wishing to use RAID should navigate to the amd.com APU chipset driver page to find and install RAID drivers.
  • AMD has noted a potential system crash while running certain OpenCL applications like Linpack-DGEMM & Indigo benchmark. AMD is currently testing a solution to this issue and an updated driver will be released very shortly. Please visit amd.com for updates.
  • 3DMark Firestrike may experience an application hang during GT2 test.

Additionally, AMD has put up a support page for issues with system boot-up failure on configurations with some 2nd generation Ryzen desktop processors (CPUs & APUs) and AM4 motherboards. Unsurprisingly, AMD notes that the likely cause in this scenario is a motherboard that has not been updated to the latest BIOS with APU support, but offers a boot kit solution under warranty if this is not the root cause.

The updated drivers for AMD’s desktop, mobile, and integrated GPUs are available through the Radeon Settings tab or online at the AMD driver download page. More information on these updates and further issues can be found in the respective Radeon Software Adrenalin Edition 18.2.2 release notes and Radeon Software for Ryzen Desktop Processors with Radeon Vega Graphics release notes.

Gen-Z Interconnect Core Specification 1.0 Published
  • Comments are Closed

Gen-Z Interconnect Core Specification 1.0 Published

The first major release of the Gen-Z systems interconnect specification is now available. The Gen-Z Consortium was publicly announced in late 2016 and has been developing the technology as an open standard, with several drafts released in 2017 for public comment.

Gen-Z is one of several standards that emerged from the long stagnation of the PCI Express standard after the PCIe 3.0 release. Technologies like Gen-Z, CAPI, CCIX and NVLink seek to offer higher throughput, lower latency and the option of cache coherency, in order to enable much higher performance connections between processors, co-processors/accelerators, and fast storage. Gen-Z in particular has very broad ambitions to blur the lines between a memory bus, processor interconnect, peripheral bus and even straying into networking territory.

The Core Specification released today primarily addresses connecting processors to memory, with the goal of allowing the memory controllers in processors to be media-agnostic: the details of whether the memory is some type of DRAM (eg. DDR4, GDDR6) or a persistent memory like 3D XPoint are handled by a media controller at the memory end of a Gen-Z link, while the processor itself issues simple and generic read and write commands over the link. In this use case, Gen-Z doesn’t completely remove the need for traditional on-die memory controllers or the highest-performance solutions like HBM2, but Gen-Z can enable more scalability and flexibility by allowing new memory types to be supported without altering the processor, and by providing access to more banks of memory than can be directly attached to the processor’s own memory controller.

At the lowest level, Gen-Z connections look a lot like most other modern high-speed data links: fast serial links, bonding together multiple lanes to increase throughput, and running a packet-oriented protocol. Gen-Z borrows from both PCI Express and IEEE 802.3 Ethernet physical layer (PHY) standards to offer per-lane speeds up to the 56Gb/s raw speed of 50GBASE-KR, and will track the speed increases from future versions of those underlying standards. The PCIe PHY is incorporated more or less as-is, while the Ethernet PHY standards have been modified to allow for lower power operation when used for shorter links within a single system, such as communication between dies on a multi-chip module. Gen-Z allows for asymmetric links with more links and bandwidth in one direction than the other. The Gen-Z protocol supports various connection topologies like basic point to point links, daisy-chaining, and switched fabrics, including multiple paths of connection between endpoints. Daisy-chain links are estimated to add about 5ns of latency per hop, and switch latencies are expected to be on the order of 10ns for a small 8-port switch up to 50-60ns for a 64-port switch, so using Gen-Z for memory access is reasonable, especially where the somewhat slower persistent memory technologies are concerned. The Gen-Z protocol expresses almost everything in memory terms, but with each endpoint performing its own memory mapping and translation rather than attempting to form a unified single address space across a Gen-Z fabric that could scale beyond a single rack in a data center.

Wide Industry Participation

The Gen-Z Consortium launched with the support of a dozen major technology companies, but its membership has now grown to the point that it is easier to list the big hardware companies who aren’t currently involved: Intel and NVidia. Gen-Z has members from every segment necessary to build a viable product ecosystem: semiconductor design and IP (Mentor, Cadence, PLDA), connectors (Molex, Foxconn, Amphenol, TE), processors and accelerators (AMD, ARM, IBM, Cavium, Xilinx), switches and controllers (IDT, Microsemi, Broadcom, Mellanox), every DRAM and NAND flash memory manufacturer except Intel, software vendors (RedHat, VMWare), system vendors (Lenovo, HPE, Dell EMC). It is clear that most of the industry is paying attention to Gen-Z, even if most of them haven’t yet committed to bringing Gen-Z products to market.

At the SuperComputing17 conference in November, Gen-Z had a multi-vendor demo of four servers sharing access to two pools of memory through a Gen-Z switch. This was implemented with heavy use of FPGAs, but with the Core Specification 1.0 release we will start seeing Gen-Z show up in ASICs. The focus for now is on datacenter use cases with products potentially hitting the market in 2019.

In the meantime, it will be interesting to see where industry support concentrates between Gen-Z and competing standards. Many companies are members or supporters of more than one of the new interconnect standards, and there’s no clear winner at this time. Nobody is abandoning PCI Express, and it isn’t clear which new interconnect will offer the most compelling advantages over the existing ubiquitous standards or over proprietary interconnects. Gen-Z seems to have one of the widest membership bases and the widest target market, but it could still easily be doomed to niche status if it only receives half-hearted support from most of its members.

Panasonic Unveils Let’s Note SV7: 12.1-Inch, Quad-Core CPU, TB3, ODD, 21 Hrs, 2.4 Lbs
  • Comments are Closed

Panasonic Unveils Let’s Note SV7: 12.1-Inch, Quad-Core CPU, TB3, ODD, 21 Hrs, 2.4 Lbs

Panasonic has upgraded its 12.1-inch series laptops with Intel’s quad-core 8th Generation Core i5/i7 CPUs. The new Panasonic Let’s Note CF-SV7-series notebooks are the only ultra-compact PCs to feature Intel’s latest mobile processors, a Thunderbolt 3 interconnection, an optical drive and an optional LTE modem in a package that weighs from 999 grams to 1.124 kilograms (2.2 – 2.47 pounds).

Panasonic is one of a few companies nowadays that offers highly-integrated ultra-compact laptops with optical disc drives. These machines are very light because they are made of plastic (they are still rugged enough and can be dropped from a height of 76 cm) and their weight is about a kilogram, but they are not ultra-thin like modern notebooks from Apple, HP or Lenovo. To a large degree, they are relatively thick because they are designed to offer their owners the best possible connectivity, feature set and battery life, something that we usually see on 14”/15.6” laptops from other manufacturers. In Europe and the U.S. many people nowadays prefer ultra-thin PCs even if they lack replaceable batteries or certain ports (and I am not even talking about laptops with ODDs — they have become exotic). User preferences are different in Japan, which is why Panasonic still offers 12”-class laptops with optical drives, thick replaceable batteries and plenty of connectors.

The Panasonic Let’s Note CF-SV7 family of notebooks succeeds the company’s Let’s Note CF-SZ6 lineup that featured a similar appearance, a 12.1” WUXGA (1920×1200) display, comparable weight and dimensions as well as a very long battery life of up to 21 hours (enabled by a removable accumulator). Meanwhile, even though the CF-SV7 continues traditions of the CF-SZ6, it does not mean that Panasonic just installed new quad-core CPUs into an old chassis.

The Let’s Note SV7-series based on Intel’s quad-core Core i5/i7 processors actually uses a new chassis that is 24.5 mm thick (down from 25.3 mm in case of the SZ6) and features a new cooling system for its new CPUs. Because of the new cooler, the SV7 PCs are a bit heavier than their predecessors, but even when equipped with a high-capacity “L” battery, their weight does not exceed 1.124 kilograms. Besides the new quad-core 8th Generation Core i5/i7 processors, Panasonic’s latest SV7-series laptops obtained a Thunderbolt 3 port, a rare feature for 12”-class mobile computers.

Exact configurations of Panasonic’s Let’s Note CF-SV7 vary greatly. Retail versions of the CF-SV7 are equipped with Intel’s Core i5-8250U or Core i7-8550 CPUs, 8 GB of LPDDR4-1866 memory and a SATA SSD (128 GB – 1 TB). Meanwhile, built-to-order models bought directly from Panasonic can be customized to feature Intel’s Core i5-8350U or Core i7-8650U, 16 GB RAM as well as a 1 TB PCIe SSD. As for connectivity, the systems are outfitted with an 802.11ac + Bluetooth 4.1 wireless module, a GbE connector, three USB 3.0 Type-A ports, a D-Sub output, an HDMI 2.0 header (supporting 4Kp60 resolution), a TRRS audio connector and so on. In addition, the systems feature stereo speakers, a microphone, a 720p webcam with an IR sensor compatible with Windows Hello, an SD card reader supporting SDHC/SDXC cards with UHS-II interface as well as a CD/DVD burner/reader or a Blu-ray reader/CD/DVD burner. Some systems come with a 4G/LTE modem, other can be configured to include a 1 TB HDD in addition to a 128 GB SSD. It is noteworthy that the width of a key on SV7’s keyboard is 19 mm, comparable to that of a modern MacBook Pro. Meanwhile, the new SV7 continues to feature Panasonic’s round touchpad that does not look too comfy.

Besides high integration, the Let’s Note CF-SV7-series can be proud of its battery life. When equipped with an “S” battery and an SSD, the laptop can work for up to 14 hours, according to Panasonic. Meanwhile, if an “L” accumulator is installed, the system is rated for 21 hours, probably a record for 12”-class PCs in general.

General Specifications of Panasonic Let’s Note CF-SV7-Series
  “High-End” “Mainstream” “Entry”
Display 12.1″ non-glossy
1920×1200 resolution
SoC Core i7-8550U
Core i7-8650U*		 Core i5-8250U
Core i5-8350U*
RAM 8 GB LPDDR3
16 GB LPDDR3*
Storage 256 – 512 GB SSD SATA
up to 1 TB SSD PCIe*		 128 – 256 GB SSD SATA
up to 1 TB SSD PCIe*		 1 TB HDD
128 GB SSD + 1 TB HD*
up to 1 TB SSD PCIe*
ODD CD/DVD burner
BD reader/CD/DVD burner*
No ODD*		 –
Camera 720p webcam with IR sensor for Windows Hello
Wireless  802.11ac Wi-Fi
Bluetooth 4.1
optional 4G/LTE modem 300/50 Mbps
I/O ports 3 × USB 3.0 Type-A
1 × Thunderbolt 3/USB Type-C
1 × HDMI
1 × D-Sub
1 × GbE
SD card reader with UHS-II support
Audio Integrated speakers and microphone
1 × TRRS 3.5-mm jack for headset
Dimensions 283.5 × 203.8 × 24.5 mm
Weight 999 – 1124 grams
Battery Life Based on JEITA 2.0 Up to 21 hours with L battery and SSD
Up to 14 hours with S battery and SSD
Up to 11 hours with S battery and HDD
OS Windows 10 Pro Windows 10 Home
Windows 10 Pro		 Windows 10 Pro
Finish Body: Silver or Black*
Top Cover: Silver, Black*, Blue*, Dark Red*
Notes *Available only directly from Panasonic

As mentioned above, Panasonic’s Let’s Note CF-SV7 laptops will come in different configurations. A basic one featuring Intel’s Core i5-8350U, 8 GB of RAM, a 256 GB SSD, a DVD drive and an “S” battery pack costs ¥253,584 w/taxes (~$2320) when bought online. A premium one equipped with Intel’s Core i7-8650U, 16 GB of RAM, a 1 TB SSD, a Blu-ray drive, an LTE modem and an “S” battery is priced at ¥425,304 w/taxes (~$3880) when bought directly from Panasonic. The Let’s Note CF-SV7 PCs are definitely priced well above average, but the systems offer unique features that tend to cost a lot.

Related Reading:

Sources: Panasonic, PC Watch

ARM Announces Project Trillium Machine Learning IPs
  • Comments are Closed

ARM Announces Project Trillium Machine Learning IPs

Today’s Arm announcement is a bit out of the norm for the company, as it’s the first in a series of staggered releases of information. For this first announcement Arm is publicly unveiling “Project Trillium” – a group of software solutions as well IP for object detection and machine learning.

Machine learning is indeed the hot new topic in the semiconductor business and has particularly seen a large focus in the mobile world over the last couple of months, with announcements from various IP companies as well as consumer solutions from the likes of Huawei. We’ve most recently had a more in-depth look and exploration of the topic of machine learning and neural network processing in a dedicated section of our review of the Kirin 970.

Whilst we had a great amount of noise from many industry players on the topic of machine learning IPs. Arm was conspicuously absent from the news and until now the focus has been on the CPU ISA extensions of Armv8.2, which introduce specialised instructions which simplify and accelerate implementations of neural networks with the help of half-precision floating point and integer dot products.

Alongside the CPU improvements we’ve also seen GPU improvements for machine learning in the G72. While both of these improvements help, they are insufficient in use-cases where maximum performance and efficiency are required. For example, as we’ve seen in the our test of the Kirin 970’s NPU and Qualcomm’s DSP – the efficiency of running inferencing on specialized IPs is above an order of magnitude higher than running it on a CPU.

As Arm explains it, the Armv8.2 and GPU improvements were only the first results towards establishing solutions for machine learning, while in parallel they’ve examined the need for dedicated solutions. Industry pressure from partners made it clear that the performance and efficiency requirements made dedicated solutions inevitable and started work on its machine learning (ML) processors.

Today’s announcement covers the new ML processors as well as object detection processors (OD). The latter IP is a result of Arm’s Apical acquirement in 2016 which saw the company add solutions for the display and camera pipelines to their IP portfolio.

Starting with the ML processor – what we’re talking about here is a dedicated IP for neural network model inferencing acceleration. As we’ve emphasised in our NN related announcements of late, Arm also emphasises that having an architecture which is specifically designed for such workloads can have significant advantages over traditional CPU and GPU architectures. Arm also made a great focus on the need to design an architecture which is able to do optimised memory management of the data that flows through a processor when executing ML workloads. These workloads have high data reusability and minimising the in- and out-bound data through the processor is a key aspect of reaching high performance and high efficiency.

Arm’s ML processor promises to reach theoretical throughput of over 4.6TOPs (8-bit integer) at target power envelopes of around 1.5W, advertising up to 3TOPs/W. The power and efficiency estimates are based on a 7nm implementation of the IP.

In regards to the performance figures, Arm agrees with me that the TOPs figure alone might not be the best figure to represent performance of an IP; however it’s still useful until the industry can work towards some sort of standardisation for benchmarking on popular neural network models. The ML processor can act as a fully dedicated and standalone IP block with its own ACE-Lite interface for incorporation into a SoC, or it can be integrated within DynamiQ cluster, which is a lot more novel in terms of implementation. Arm wasn’t ready to disclose more architectural information of the processor and reserves that for future announcements.

An aspect that seemed confusing is Arm’s naming of the new IP. Indeed Arm doesn’t see that the term “accelerator” is appropriate here as traditionally accelerators for Arm meant things such as packet handling accelerators in the networking space. Instead Arm sees the new ML processor as a more fully-fledged processor and therefore deserving of that naming.

The OD processor is a more traditional vision processor and is optimised for the task of object detection. There is still a need for such IP as while the ML processor could do the same task via neural networks, the OD processor can do it faster and more efficiently. This showcases just how far the industry is going to make dedicated IP for extremely specialised tasks to be able to extract the maximum amount of efficiency.

Arm envisions use-cases where the OD and ML processors are integrated together, where the OD processor would isolate areas of interest within an image and forward them to the ML processor where more fine-grained processing is executed on. Arm had a slew of fun examples as ideas, but frankly we still don’t know for sure how use-cases in the mobile space will evolve. The same can’t be said about camera and surveillance systems where we see the opportunity and need for continuous use of OD and ML processing.

Arm’s first generation of ML processors is targeted at mobile use while variants for other spaces will follow on in the future. The architecture of the IP is said to be scalable both upwards and downwards from the initial mobile release.

As part of Project Trillium, Arm also makes available a large amount of software that will help developers implement their neural network models into different NN frameworks. These are going to be available starting today on Arm’s developer website as well as Github.

The OD processor is targeted for release to partners in Q1 while the ML processor is said to be ready mid 2018. Again this is highly unusual for Arm as usually public announcements happen far after IP availability to customers. Due to the nature of SoC development we should thus not expect silicon based on the new IP until mid to late 2019 at the earliest, making Arm one of the slow-adopters among the semiconductor IP vendors who offer ML IP.

Related Reading