Hardware

NVIDIA Titan V Benchmarks Show Volta GPU Compute, Mining and Gaming Strength (hothardware.com) 32

MojoKid shares a report from Hot Hardware: Although NVIDIA officially unveiled its Volta-based GV100 GPU a few months ago, the NVIDIA TITAN V featuring the GV100 began shipping just this past week. The card targets a very specific audience and is designed for professional and academic deep learning applications, which partly explains its lofty $3,000 price tag. Unlike NVIDIA's previous-gen consumer flagship, the TITAN Xp, the TITAN V is not designed for gamers. However, since it features NVIDIA's latest GPU architecture, it potentially foreshadows next-year's consumer-targeted GeForce cards that could possibly be based on Volta. The massive 21.1 billion transistor GV100 GPU powering the TITAN V has a base clock of 1,200MHz and a boost clock of 1,455MHz. The card has 12GB of HBM2 memory on-board that is linked to the GPU via a 3072-bit interface, offering up 652.8 GB/s of peak bandwidth, which is about 100GB/s more than a TITAN Xp. Other features of the GV100 include 5,120 single-precision CUDA cores, 2,560 double-precision FP64 cores, and 630 Tensor cores. Although the card is not designed for gamers, the fact remains that the TITAN V significantly outpaces every other graphics card in a variety of games with the highest image quality settings. In GPU compute workloads, the TITAN V is much more dominant and can offer many times the performance of a high-end NVIDIA TITAN Xp or AMD Radeon RX Vega 64. Finally, when it comes to Ethereum mining, NVIDIA's Titan V is far and away the fastest GPU on the planet currently.
AMD

AMD Is Open-Sourcing Their Official Vulkan Linux Driver (phoronix.com) 65

An anonymous reader writes: While many of you have likely heard of the "RADV" open-source Vulkan driver, it's been a community-written driver up to this point in the absence of AMD's official, cross-platform Vulkan driver being open-source. That's now changed with AMD now open-sourcing their official Vulkan driver. The code drop is imminent and they are encouraging the use of it for quick support of new AMD hardware, access to the Radeon GPU Profiler, easy integration of AMD Vulkan extensions, and enabling third-party extensions. For now at least it does provide better Vulkan performance than RADV but the RADV developers have indicated they plan to continue development of their Mesa-based Vulkan driver.
AI

Elon Musk Says Tesla Is Building Dedicated Chips For Autopilot (theregister.co.uk) 32

Elon Musk says Tesla is developing its own chip to run the Autopilot system in future vehicles from the firm. The news was revealed at a Tesla party that took place at the intelligence conference NIPS. Attendees at the party told The Register that Musk said, "I wanted to make it clear that Tesla is serious about AI, both on the software and hardware fronts. We are developing custom AI hardware chips." From the report: Musk offered no details of his company's plans, but did tell the party that "Jim is developing specialized AI hardware that we think will be the best in the world." "Jim" is Jim Keller, a well-known chip engineer who was lead architect on a range of silicon at AMD and Apple and joined Tesla in 2016. Keller later joined Musk on a panel discussing AI at the Tesla Party alongside Andrej Karpathy, Tesla's Director of AI and chaired by Shivon Zilis, a partner and founding member at Bloomberg Beta, a VC firm. Musk is well known for his optimism about driverless cars and pessimism about whether AI can operate safely. At the party he voiced a belief that "about half of new cars built ten years from now will be autonomous." He added his opinion that artificial general intelligence (AGI) will arrive in about seven or eight years.
AMD

AMD Quietly Made Some Radeon RX 560 Graphics Cards Worse (pcworld.com) 40

Brad Chacos: When the Radeon RX 560 launched in April it was the only RX 500-series card with a meaningful under-the-hood tech boost compared to the RX 400-series. The graphics processor in the older RX 460 cards packed 14 compute units and 896 stream processors; the upgraded Radeon RX 560 bumped that to 16 CUs and 1,024 SPs. Now, some -- but not all -- of the Radeon RX 560s you'll find online have specs that match the older 460 cards, and sometimes run at lower clock speeds to boot. AMD's Radeon RX 560 page was also quietly altered to include the new configurations at some point, Heise.de discovered. The last snapshot of the page by the Internet Archive's Wayback Machine occurred on July 7 and only lists the full-fat 16 CU version of the card, so the introduction of the nerfed 896 SP model likely occurred some time after that. Sifting through all of the available Radeon RX 560s on Newegg this morning reveals a fairly even split between the two configurations, all of which are being sold under the same RX 560 name. In a statement, AMD acknowledged the existence of 14 Compute Unit (896 stream processors) and 16 Compute Unit (1024 stream processor) versions of the Radeon RX 560. "We introduced the 14CU version this summer to provide AIBs and the market with more RX 500 series options. It's come to our attention that on certain AIB and etail websites there's no clear delineation between the two variants. We're taking immediate steps to remedy this: we're working with all AIB and channel partners to make sure the product descriptions and names clarify the CU count, so that gamers and consumers know exactly what they're buying. We apologize for the confusion this may have caused."
Intel

Clear Linux Beats CentOS, openSUSE, and Ubuntu in (Enterprise) Benchmark Tests (phoronix.com) 136

An anonymous reader writes: Recently completed Linux distro benchmarks by Phoronix show Intel's Clear Linux is the most powerful on x86 hardware. A six-way, enterprise-focused Linux distro comparison show Clear Linux being the fastest with a Core i9 and Xeon systems, easily beating CentOS, openSUSE, and Ubuntu in a majority of the tests.

When doing an 11-way Linux distro boot test they also found Clear Linux easily booted the fastest followed by the Clear-inspired Solus distribution. Clear Linux does work on AMD hardware and works on Intel CPUs back to Sandy Bridge but leverages its speed from optimized compiler settings, specially built libraries capable of AVX instructions on supported systems, a specially tuned kernel configuration, and other optimizations/patches.

Debian 9.2 and Fedora 27 "ended up being dropped from this article due to data overload," the article concludes, "and those distributions really not offering anything really different in terms of the performance."
AMD

First AMD Ryzen Mobile Laptop Tested Shows Strong Zen-Vega Performance (hothardware.com) 85

MojoKid writes: AMD Ryzen Mobile processors are arriving now in retail laptops from the likes of HP, Lenovo and Acer. With the first CPUs to hit the market, AMD took quad-core Ryzen and coupled it with 8 or 10-core Vega GPUs on a single piece of silicon in an effort to deliver a combination of strong Ryzen CPU performance along with significantly better integrated graphics performance over Intel's current 8th Gen Kaby Lake laptop chips. AMD Ryzen 7 2700U and Ryzen 5 2500U chips have 4MB of shared L3 cache each, but differ with respect to top-end CPU boost clock speeds, number of integrated Radeon Vega Compute Units (CUs), and the GPU's top-end clocks. Ryzen 7 2700U is more powerful with 10 Radeon Vega CUs, while Ryzen 5 2500U sports 8. Ryzen 7 2700U also boosts to 3.8GHz, while Ryzen 5 2500U tops out at 3.6GHz. In the benchmarks, Ryzen Mobile looks strong, competing well with Intel quad-core 8th Gen laptop CPUs, while offering north of 60 percent better performance in graphics and gaming. Battery life is still a question mark, however, as some of the very first models to hit the market from HP have inefficient displays and hard drives instead of SSDs. As more premium configurations hit the market in the next few weeks, hopefully we'll get a better picture of Ryzen Mobile battery life in more optimized laptop builds.
Linux

Linux 4.14 Has Been Released (kernelnewbies.org) 89

diegocg quotes Kernel Newbies: Linux 4.11 has been released. This release adds support for bigger memory limits in x86 hardware (128PiB of virtual address space, 4PiB of physical address space); support for AMD Secure Memory Encryption; a new unwinder that provides better kernel traces and a smaller kernel size; support for the zstd compression algorithm has been added to Btrfs and Squashfs; support for zero-copy of data from user memory to sockets; support for Heterogeneous Memory Management that will be needed in future GPUs; better cpufreq behaviour in some corner cases; faster TBL flushing by using the PCID instruction; asynchronous non-blocking buffered reads; and many new drivers and other improvements.
Phoronix has more on the changes in Linux 4.14 -- and notes that its codename is still "Fearless Coyote."
Intel

Intel Recruits AMD RTG Exec Raja Koduri To Head New Visual Computing Group (hothardware.com) 58

MojoKid writes: Intel just announced that former AMD Radeon Technologies Group SVP, Raja Koduri, would be joining its team to head up a newly formed Core and Visual Computing Group, and as a general manager of a new initiative to drive edge and client visual computing solutions. With Koduri's help, Intel plans to unify and expand its IP across multiple segments including core computing, graphics, media, imaging and machine learning capabilities for the client and data center segments, artificial intelligence, and emerging opportunities. Intel also explicitly stated that it would also expand its strategy to develop and deliver high-end, discrete graphics solutions. This announcement also comes just after Intel revealed it would be employing AMD's Vega GPU architecture in a new mobile processor that will drive high-end graphics performance into smaller, slimmer, and sleeker mobile form factors. With AMD essentially spinning the Radeon Technologies Group into its own entity, Intel now leveraging AMD graphics technology, and a top-level executive like Koduri responsible for said graphics tech switching teams, we have to wonder how the relationship between Intel and AMD's RTG with evolve.
AMD

Raja Koduri, AMD's Radeon Tech Group Leader, Resigns (anandtech.com) 38

Ryan Smith, writing for AnandTech: On the day following what's perhaps one of the greatest (and oddest) product design wins for AMD's Radeon Technologies Group, a second bit of surprising news is coming out of AMD. Raja Koduri, the Senior VP and Chief Architect of the group, who has been its leader since the RTG was formed two years ago, has announced that he is resigning from the company, effective tomorrow. Word of Raja's resignation originally broke via an internal memo penned by Raja and acquired by Hexus. And while AMD will not confirm the validity of the memo, the company is confirming that Raja has decided to leave the company.
Intel

Arch-rivals Intel and AMD Team Up on PC Chips To Battle Nvidia (pcworld.com) 169

Intel and AMD, arch-rivals for decades, are teaming up to thwart a common competitor, Nvidia. On Monday, the two companies said they are co-designing an Intel Core microprocessor with a custom AMD Radeon graphics core inside the processor package. The chip is intended for laptops that are thin and lightweight but powerful enough to run high-end videogames, the companies said. From a report: Executives from both AMD and Intel told PCWorld that the combined AMD-Intel chip will be an "evolution" of Intel's 8th-generation, H-series Core chips, with the ability to power-manage the entire module to preserve battery life. It's scheduled to ship as early as the first quarter of 2018. Though both companies helped engineer the new chip, this is Intel's project -- Intel first approached AMD, both companies confirmed. AMD, for its part, is treating the Radeon core as a single, semi-custom design, in the same vein as the chips it supplies to consoles like the Microsoft Xbox One X and Sony Playstation 4. Some specifics, though, remain undisclosed: Intel refers to it as a single product, though it seems possible that it could eventually be offered at a range of clock speeds. [...] Shaking hands on this partnership represents a rare moment of harmony in an often bitter rivalry that began when AMD reverse-engineered the Intel 8080 microchip in 1975.
AMD

AMD, Which Lost Over $2.8 Billion In 5 Years, Takes a Hit After New Report (arstechnica.com) 91

An anonymous reader quotes a report from Ars Technica: On Monday, AMD's stock price plunged nearly 9 percent after a report by Morgan Stanley, a major investment bank, which found that "microprocessor momentum" has slowed. According to CNBC, a new report by analyst Joseph Moore found that "cryptocurrency mining driven sales for AMD's graphics chips will decline by 50 percent next year or a $250 million decline in revenue. He also forecasts video game console demand will decline by 5.5 percent in 2018." As per AMD's own SEC filings, the company lost over $2.8 billion from 2012 through 2016. However, new releases from AMD suggest that it may be on something of a resurgent track. As Ars reported last month, AMD's Ryzen and Threadripper processors re-established AMD's chips as competitive with Intel's.
AMD

AMD Unveils Ryzen Mobile Processors Combining Zen Cores and Vega Graphics (hothardware.com) 41

MojoKid writes: AMD is officially launching a processor family today known by the code name Raven Ridge, but now referred to as Ryzen Mobile. The architecture combines AMD's new Zen CPU core architecture, along with its RX Vega GPU integrated into a single chip for laptops. There are two initial chips in the mobile processor family that AMD is announcing today: the Ryzen 5 2500U and the Ryzen 7 2700U. Both processors feature four cores capable of executing 8 threads with SMT. However, there are differences with respect to processor clocks and GPU specs. AMD's Ryzen 5 2500U has a base clock of 2GHz and a boost clock of 3.6GHz, while Ryzen 7 2700U cranks up another 200MHz on both of those figures. Ryzen 5 2500U features 8 Radeon Vega graphics CUs (Compute Units) and a GPU clock of 1.1GHz, compared to 10 Radeon Vega CUs and a GPU clock of 1.3GHz for the higher-end Ryzen 7 2700U. AMD is making rather ambitious claims for the new processors, and promises some impressive gains over its 7th generation Bristol Ridge predecessors. According to AMD, CPU and GPU performance will see 200 percent and 128 percent uplifts, respectively. AMD is also showcasing benchmark numbers that have the new CPUs outgunning Intel's new quad-core Kaby Lake R chips in spots, along with significant performance advantages in gaming and graphics, on par with discrete, entry-level laptop GPUs like NVIDIA's GeForce 950M. Thin and light laptops from HP, Lenovo and Acer powered by Ryzen Mobile are expected to ship in Q4 this year.
Intel

Intel's Just Launched 8th Gen 'Coffee Lake' Processors Bring the Heat To AMD's Ryzen 137

bigwophh writes: The upheaval of the high-end desktop processor segment continues today with the official release of Intel's latest Coffee Lake-based 8th Generation Core processors. The flagship in the new lineup is the Core i7-8700K. It is a 6C/12T beast, with a base clock of 3.7GHz, a boost clock of 4.7GHz, and 12MB of Intel Smart Cache. The Core i5-8400 features the same physical die, but has only 9MB of Smart Cache, no Hyper-Threading, and base and boost clocks of 2.8GHz and 4GHz, respectively. The entire line-up features more cores, support for faster memory speeds, and leverages a fresh platform that's been tweaked for more robust power delivery and, ultimately, more performance. The Core i7-8700K proved to be an excellent performer, besting every other processor in single-threaded workloads and competing favorably with 8C/16T Ryzen 7 processors. The affordably-priced 6-core Core i5-8400 even managed to pull ahead of the quad-core Core i7-7700K in some tests. Overall, performance is strong, especially for games, and the processors seem to be solid values in their segment.
AMD

AMD Unveils E9170 Embedded GPU (zdnet.com) 49

AMD is releasing a new embedded Radeon GPU, the first to be based on the Polaris architecture. From a report: But this one isn't aimed at the desktop or laptop markets, but instead it expands AMD's offerings in the digital casino games, thin clients, medical displays, retail and digital signage, and industrial systems markets. The AMD Embedded Radeon E9173 GPU, based on the Polaris architecture, uses an optimized 14-nanometer FinFET manufacturing process to provide up to three times the performance-per-watt over previous generations of AMD Embedded GPUs. And the Radeon E9170 is quite a powerhouse, delivering up to 1.25 TFLOPS at sub-40W TDP board power, and includes 4K HEVC/H.265 and AVC/H.264 decode and encode support, 4K and 3D support, and is capable of driving up to five 4K displays using HDMI 2.0 and/or DisplayPort 1.4. AMD is planning for the Radeon E9173 to have a long lifecycle -- which high-end customers demand -- and plans for it to be available through to 2024.
AMD

Super Fast NVMe RAID Comes To Threadripper (zdnet.com) 59

Adrian Kingsley-Hughes, writing for ZDNet: A week later than planned, AMD has released a free driver update for the X399 platform to support NVMe RAID. The driver allows X399 motherboards to combine multiple NVMe SSDs together into a RAID 0, 1, or 10 array, which will greatly enhance disk performance or data integrity. Benchmarking carried out by AMD shows that the platform allows for a throughput of 21.2GB/s from six 512GB Samsung 960 Pro NVMe SSDs in RAID0. But there are a couple of caveats. The first is that X399 motherboards will require BIOS updates before they will support NVMe RAID, so when it will be available for your system will depend on your motherboard vendor. The second -- and perhaps more important -- is that currently the NVMe RAID driver is in beta, and as such things may go wrong, so you might want to test this before rolling it out onto systems you rely on.
Intel

Intel Launches 16 and 18-Core Core i9 Desktop Chips To Take On AMD Threadripper (hothardware.com) 119

MojoKid writes: Intel has officially launched its Skylake-X processor offering in response to AMD's Ryzen Threadripper series of desktop CPUs. The new Core i9-7980XE and Core i9-7960X are 18 and 16-core configurations respectively, with 2.6GHz and 2.8GHz base clocks and 4.4GHz max boost clocks. Both chips support Intel HyperThreading, with 36 threads of processing for the 7980XE and 32 for the 7960X, while both also have 44 lanes of PCI Express connectivity and support for DDR4-2666MHz memory. Both chips also utilize Intel's X299 chipset platform and are LGA 2066 socket compatible. The Core i9-7980XE has 24.75MB of shared L3 cache, 1MB of L2 cache per core, and a TDP of 165W. The Core i9-7960X's details are essentially same, though two processor cores and the cache associated with them have been lopped off. The Core i9-7960X has a couple of advantages, however, in that its base clock is 200MHz higher than the flagship Core i9-7980XE and it has higher all-core frequency boost to 3.6GHz, while the 7908XE tops out at 3.4GHz on all cores. The new chips are multi-threaded beasts in the benchmarks, posting the highest scores seen to date in heavily threaded workloads. They also offer strong single-threaded performance that outpaces AMD's Ryzen processors. Power consumption is surprisingly good as well and only marginally higher than the 10-core Core i9-7900X. However, at $1999 for the Core i9-7980XE and $1699 for the Core i9-7960X, as usual with Intel high-end chips, they're certainly not cheap.
AI

Tesla Is Working With AMD To Develop Its Own AI Chip For Self-Driving Cars (cnbc.com) 50

An anonymous reader quotes a report from CNBC: Tesla is getting closer to having its own chip for handling autonomous driving tasks in its cars. The carmaker has received back samples of the first implementation of its processor and is now running tests on it, said a source familiar with the matter. The effort to build its own chip is in line with Tesla's push to be vertically integrated and decrease reliance on other companies. But Tesla isn't completely going it alone in chip development, according to the source, and will build on top of AMD intellectual property. On Wednesday Sanjay Jha, CEO of AMD spin-off GlobalFoundries, said at the company's technology conference in Santa Clara, California, that the company is working directly with Tesla. GlobalFoundries, which fabricates chips, has a wafer supply agreement in place with AMD through 2020. Tesla's silicon project is bounding ahead under the leadership of longtime chip architect Jim Keller, the head of Autopilot hardware and software since the departure of Apple veteran Chris Lattner in June. Keller, 57, joined Tesla in early 2016 following two stints at AMD and one at Apple. Keller arrived at Apple in 2008 through its acquisition of Palo Alto Semiconductor and was the designer of Apple's A4 and A5 iPhone chips, among other things. More than 50 people are working on the initiative under Keller, the source said. Tesla has brought on several AMD veterans after hiring Keller, including director Ganesh Venkataramanan, principal hardware engineer Bill McGee and system circuit design lead Dan Bailey.
China

China Arms Upgraded Tianhe-2A Hybrid Supercomputer (nextplatform.com) 23

New submitter kipperstem77 shares an excerpt from a report via The Next Platform: The National University of Defense Technology (NUDT) has, according to James Lin, vice director for the Center of High Performance Computing (HPC) at Shanghai Jiao Tong University, who divulged the plans last year, is building one of the three pre-exascale machines [that China is currently investing in], in this case a kicker to the Tianhe-1A CPU-GPU hybrid that was deployed in 2010 and that put China on the HPC map. This exascale system will be installed at the National Supercomputer Center in Tianjin, not the one in Guangzhou, according to Lin. This machine is expected to use ARM processors, and we think it will very likely use Matrix2000 DSP accelerators, too, but this has not been confirmed. The second pre-exascale machine will be an upgrade to the TaihuLight system using a future Shenwei processor, but it will be installed at the National Supercomputing Center in Jinan. And the third pre-exascale machine being funded by China is being architected in conjunction with AMD, with licensed server processor technology, and which everyone now thinks is going to be based on Epyc processors and possibly with Radeon Instinct GPU coprocessors. The Next Platform has a slide embedded in its report "showing the comparison between Tianhe-2, which was the fastest supercomputer in the world for two years, and Tianhe-2A, which will be vying for the top spot when the next list comes out." Every part of this system shows improvements.
AMD

AMD Opteron Vs EPYC: How AMD Server Performance Evolved Over 10 Years (phoronix.com) 34

New submitter fstack writes: Phoronix has carried out tests comparing AMD's high-end EPYC 7601 CPU to AMD Opteron CPUs from about ten years ago, looking at the EPYC/Opteron Linux performance and power efficiency. Both on the raw performance and performance-per-Watt, the numbers are quite staggering though the single-threaded performance hasn't evolved quite as much. The EPYC 7601 is a $4,200 USD processor with 32 cores / 64 threads. The first of many tests was with NAS Parallel Benchmarks: "For a heavily threaded test like this, going from a single Opteron 2300 series to the EPYC 7601 yielded around a 40x increase in performance," reports Phoronix. "Not bad when also considering it was only a 16x increase in the thread count (4 physical cores to 32 cores / 64 threads). The EPYC 7601 has a lower base clock frequency than the Opteron 2300 CPUs tested but has a turbo/boost frequency higher, among many architectural advantages over these K10 Opterons. With the NASA test's Lower-Upper Gauss-Seidel solver, going from the dual Opteron 2384 processors to a single EPYC 7601 yields around a 25x improvement in performance over the past decade of AMD server CPUs. Or in looking at the performance-per-Watt with the LU.C test, it's also around a 25x improvement over these older Opterons."
AMD

French Company Plans To Heat Homes, Offices With AMD Ryzen Pro Processors 181

At its Ryzen Pro event in New York City last month, AMD invited a French company called Qarnot to discuss how they're using Ryzen Pro processors to heat homes and offices for free. The company uses the Q.rad -- a heater that embeds three CPUs as a heat source -- to accomplish this feat. "We reuse the heat they generate to heat homes and offices for free," the company says in a blog post. "Q.rad is connected to the internet and receives in real time workloads from our in-house computing platform."

The idea is that anyone in the world can send heavy workloads over the cloud to a Q.rad and have it render the task and heat a person's home in the process. The two industries that are targeted by Qarnot include movies studios for 3D rendering and VFX, and banks for risk analysis. Qarnot is opting in for Ryzen Pro processors over Intel i7 processors due to the performance gain and heat output. According to Qarnot, they "saw a performance gain of 30-45% compared to the Intel i7." They also report that the Ryzen Pro is "producing the same heat as the equivalent Intel CPUs" they were using -- all while providing twice as many cores.

While it's neat to see a company convert what would otherwise be wasted heat into a useful asset that heats a person's home, it does raise some questions about the security and profitability of their business model. By using Ryzen Pro's processors, OS independent memory encryption is enabled to provide additional security layers to Qarnot's heaters. However, Q.rads are naturally still going to be physically unsecured as they can be in anyone's house.

Further reading: The Mac Observer, TechRepublic

Slashdot Top Deals