AMD finally brings a workstation-class -- in other words, security-conscious -- processor to challenge the Intel Xeon on the desktop with its Ryzen Threadripper Pro. With up to 64 cores, the pro version of AMD's multicore powerhouse Threadripper processors incorporates essentials like support for massive amounts of memory and board-level security, critical for uses which move a ton of sensitive data, ranging from aerospace visualization to Hollywood video editing and CGI rendering. The CPU debuts in Lenovo's ThinkStation P620; Lenovo has a limited exclusive on the processor. From a report: The CPU comes in four variants: 3945WX (12 cores, with the fastest single-core speeds), 3955WX (16 cores), 3975WX (32 cores) and 3995WX (64 cores). At the moment, to achieve core counts that high with the Intel Xeon, you have to use multiple CPUs. They all come with some of the perks of AMD's architecture, including support for PCI Gen4 -- in this case, up to 128 lanes. And the Pro versions add support for more types of memory, notably RDIMM and LRDIMM, over the high-end consumer-focused Threadripper, plus 8 memory channels vs. 4, which lets it support up to 2TB of memory. On the downside, while AMD supports faster internal transfers than Intel via PCI 4, it doesn't offer any high-speed external data transfer capabilities a la Thunderbolt 3. And in fact, the ThinkStation P620's fastest connections are USB 3.2 Gen 2 and 10Gb Ethernet.

The world's fastest computer is now part of "a vast supercomputer-powered search for new findings pertaining to the novel coronavirus' spread" and "how to effectively treat and mitigate it," according to an emerging tech journalist at Nextgov.

It's part of a consortium currently facilitating over 65 active research projects, for which "Dozens of national and international members are volunteering free compute time...providing at least 485 petaflops of capacity and steadily growing, to more rapidly generate new solutions against COVID-19."

"What started as a simple concept has grown to span three continents with over 40 supercomputer providers," Dario Gil, director of IBM Research and consortium co-chair, told Nextgov last week. "In the face of a global pandemic like COVID-19, hopefully a once-in-a-lifetime event, the speed at which researchers can drive discovery is a critical factor in the search for a cure and it is essential that we combine forces...."

[I]ts resources have been used to sort through billions of molecules to identify promising compounds that can be manufactured quickly and tested for potency to target the novel coronavirus, produce large data sets to study variations in patient responses, perform airflow simulations on a new device that will allow doctors to use one ventilator to support multiple patients — and more. The complex systems are powering calculations, simulations and results in a matter of days that several scientists have noted would take a matter of months on traditional computers.
The Undersecretary for Science at America's Energy Department said "What's really interesting about this from an organizational point of view is that it's basically a volunteer organization."

The article identifies some of the notable participants:

• IBM was part of the joint launch with America's Office of Science and Technology Policy and its Energy Department.
• The chief of NASA's Advanced Supercomputing says they're "making the full reserve portion of NASA supercomputing resources available to researchers working on the COVID-19 response, along with providing our expertise and support to port and run their applications on NASA systems."
• Amazon Web Services "saw a clear opportunity to bring the benefits of cloud... to bear in the race for treatments and a vaccine," according to a company executive.
• Japan's Fugaku — "which surpassed leading U.S. machines on the Top 500 list of global supercomputers in late June" — also joined the consortium in June.

Other consortium members:

• Google Cloud
• Microsoft
• Massachusetts Institute of Technology
• Rensselaer Polytechnic Institute
• The National Science Foundation
• Argonne, Lawrence Livermore, Los Alamos, Oak Ridge and Sandia National laboratories.
• National Center for Atmospheric Research's Wyoming Supercomputing Center
• AMD
• NVIDIA
• Dell Technologies. ("The company is now donating cycles from the Zenith supercomputer and other resources.")

"Linux creator Linus Torvalds had some choice words today on Advanced Vector Extensions 512 (AVX-512) found on select Intel processors," reports Phoronix: In a mailing list discussion stemming from the Phoronix article this week on the compiler instructions Intel is enabling for Alder Lake (and Sapphire Rapids), Linus Torvalds chimed in. The Alder Lake instructions being flipped on in GCC right now make no mention of AVX-512 but only AVX2 and others, likely due to Intel pursuing the subset supported by both the small and large cores in this new hybrid design being pursued.

The lack of seeing AVX512 for Alder Lake led Torvalds to comment:

I hope AVX512 dies a painful death, and that Intel starts fixing real problems instead of trying to create magic instructions to then create benchmarks that they can look good on.

I hope Intel gets back to basics: gets their process working again, and concentrate more on regular code that isn't HPC or some other pointless special case.

I've said this before, and I'll say it again: in the heyday of x86, when Intel was laughing all the way to the bank and killing all their competition, absolutely everybody else did better than Intel on FP loads. Intel's FP performance sucked (relatively speaking), and it matter not one iota.

Because absolutely nobody cares outside of benchmarks.

The same is largely true of AVX512 now - and in the future...
After several more paragraphs, Torvalds reaches his conclusion. "Stop with the special-case garbage, and make all the core common stuff that everybody cares about run as well as you humanly can."

Phoronix notes that Torvalds' comments came "just weeks after he switched to AMD Ryzen Threadripper for his primary development rig."

Intel unveiled Thunderbolt 4 on Wednesday, the next iteration of the I/O specification that provides a high-speed peripheral bus to docks, displays, external storage and eGPUs for PCs. Rather than increase the available bandwidth, however, Thunderbolt 4 provides more clarity and helps create new categories of products. From a report: Thunderbolt 4 will debut later this year as part of Intel's "Tiger Lake" CPU platform, as Intel originally announced during CES in January. We now know it will support 40Gbps throughput, but with tighter minimum specs. Thunderbolt 4 will guarantee that a pair of 4K displays will work with a Thunderbolt dock, and require Thunderbolt 4-equipped PCs to charge on at least one Thunderbolt port. Thunderbolt PCs will be able to connect to either "compact" or "full" docks with up to four Thunderbolt ports. Longer Thunderbolt cables will be possible, too. One thing that doesn't seem to be changing is Thunderbolt's exclusivity. Intel developed Thunderbolt, and perhaps not coincidentally, OEM systems based on rival AMD's CPUs have never had this technology. While AMD has officially dismissed the need for Thunderbolt, with generation 4 Intel appears to have made it even harder for AMD to get it, even if it wanted to. Intel's still pitching Thunderbolt as a single standard to rule them all, but the reality up to now has been complicated. You still have to squint hard at that USB-C-shaped port to determine which of the multitude of USB specifications it meets, including whether it's a USB4 connection that happens to support Thunderbolt. To muddy things further, Thunderbolt also encompasses PCIe, DisplayPort, and USB Power Delivery standards.

MojoKid writes: Last month, AMD made its Ryzen 3000XT series processors official, after weeks of leaks and speculation. Ryzen 3000XT series processors are tweaked versions of the original 3000X series products, but with higher clocks and the ability to maintain turbo frequencies longer. Launching today, AMD's new Ryzen 5 3600XT is a 6 core/12-thread processor, with a 3.8GHz base clock and a 4.5GHz max boost clock. That's a 100MHz increase over the 3600X. The Ryzen 7 3800XT is an 8-core/16-thread processor with a base clock of 3.9GHz and a max boost clock of 4.7GHz, which is 200MHz higher than the original 3800X. Finally, the Ryzen 9 3900XT is a 12-core/24-thread processor with a base clock of 3.8GHz with a max boost clock of 4.7GHz, which is a 100MHz increase over the original Ryzen 9 3900X.

AMD also notes these new processors can maintain boost frequencies for somewhat longer durations as well, which should offer an additional performance uplift, based on refinements made to the chip's 7nm manufacturing process. In testing, the new CPUs offer small performance gains over their "non-XT" namesakes, with 100MHz - 200MHz increases in boost clocks resulting in roughly 2% - 5% increases to both their single and multi-threaded performance in most workloads. Those frequency increases come at the expense of slightly higher peak power consumption as well of course. The best news may be that AMD's original Ryzen 5 3600X, Ryzen 7 3800X, and the Ryzen 9 3900X will remain in the line-up for the time being, but their prices will be slashed a bit, with the new Ryzen 5 3600XT, Ryzen 7 3800XT, and Ryzen 9 3900XT arriving with the same $249, $399, and $499 introductory prices as the originals.

This week Linus Torvalds and Dirk Hohndel re-created their keynote conversation for a special all-virtual edition of the Open Source Summit and Embedded Linux Conference North America. ZDNet reports: While COVID-19 has slowed down many technologies, while speeding up other tech developments, it hasn't affected Linux development much at all. "None of my co-developers have been hugely impacted either. I was worried for a while because one of our developers was offline for a month or two.... [But,] it turned out that it was just RSI [repetitive strain injury], and RSI is kind of an occupational hazard to deal with." He added. "One of the things that is so interesting about the Linux community is how much it has always been email-based and remote, how rarely we get together in person...."

Torvalds trusts this new build. Indeed, he ran his end of the videoconference from his new developer machine running the first release candidate of 5.8.

Thinking of his new AMD Threadripper 3970x-based processor-powered developer desktop, Torvalds later added that, although he had been concerned about its fan noise it actually works well for him. Torvalds moved to this new homebrew computer because he needed the speed. "My 'allmodconfig' test builds are now three times faster than they used to be." That's important because Torvalds "strives to do about 20 to 30 [pull requests] a day, which is above my limit, ... [but] in order to do that, [he needs] a lot of computing power.

AMD has exceeded its goal to improve the energy efficiency of its mobile processors by 25 times by 2020. According to Thurrott, " The new AMD Ryzen 7 4800H mobile processor improves on the energy efficiency of the 2014 baseline measurement by 31.7 times, the firm says, while offering 'leadership performance' for portable PCs." From the report: "We have always focused on energy efficiency in our processors, but in 2014 we decided to put even greater emphasis on this capability," AMD CTO Mark Papermaster says in a prepared statement. "Our engineering team rallied around the challenge and charted a path to reach our stretch goal of 25 times greater energy efficiency by 2020. We were able to far surpass our objective, achieving 31.7 times improvement leading to gaming and ultrathin laptops with unmatched performance, graphics and long battery life. I could not be prouder of our engineering and business teams."

As AMD notes, greater energy efficiency leads to significant real-world benefits, including improved battery life, better performance, lower energy costs, and reduced environmental impact from computing. And with the focus in mobile computing hardware switching to performance-per-watt these days, AMD is trying to position itself as the traditional PC chipmaker that can rise to the ARM challenge.

Nvidia, Intel and AMD have announced their support for Microsoft's new effort to bring graphics processor support to the Windows 10 Windows Subsystem for Linux to enhance machine-learning training. From a report: GPU support for WSL arrived on Wednesday in the Dev Channel preview of Windows 10 build 20150 under Microsoft's reorganized testing structure, which lets it test Windows 10 builds that aren't tied to a specific future feature release. Microsoft announced upcoming GPU support for WSL a few weeks ago at Build 2020, along with support for running Linux GUI apps. The move on GPU access for WSL is intended to bring the performance of applications running in WSL2 up to par with those running on Windows. GPU compute support is the feature most requested by WSL users, according to Microsoft. The 20150 update includes support for Nvidia's CUDA parallel computing platform and GPUs, as well as GPUs from AMD and Intel. It also supports DirectML (Direct Machine Learning), Microsoft's Windows 10 API for hardware-accelerated machine learning.

AMD has announced three new additions to its desktop Ryzen CPU line: Ryzen 9 3900XT, Ryzen 7 3800XT, and Ryzen 5 3600XT. Ars Technica reports on the technical details: The new CPU designs take advantage of newly optimized 7nm process technology to offer higher performance at the same TDPs as Ryzen 3000 designs. The new 3000XT CPUs are drop-in replacements on AM4 motherboards that supported Ryzen 3000 CPUs and offer small (up to 4 percent) single-threaded performance improvements over their Ryzen 3000 counterparts. Although the single-threaded performance improvements are small, the margins between CPUs in that stat tend to be razor-thin, and AMD says they're enough to take the coveted single-thread performance crown away from Intel. A 4 percent improvement to the Ryzen 9 3900X score shown on the CGDirector leaderboard would come out to 531 -- a few points higher than CGDirector's posted score for the i9-10900K, although a few points lower than our own Cinebench R20 result for that processor, using an NZXT fluid-cooler and Primochill Praxis open-air bench.

AMD has determined that most consumers are discarding the free Wraith Spire coolers in favor of higher-performance third-party cooling systems -- so in the 3000XT line, only the Ryzen 5 3600XT retains the included OEM cooler. Ryzen 9 3900XT and Ryzen 7 3800XT will require the consumer to supply their own cooling solution, and AMD recommends "a minimum 280mm radiator or equivalent air cooling." The company offers the existing 3950X compatibility list for those who aren't sure what to buy. AMD also announced a new motherboard chipset for Ryzen 3000 desktop processors: the A520. A new version of AMD's StoreMI software will also be coming soon.

AMD's press release can be read here.

Intel has published a news release on its website stating that Jim Keller has resigned from the company, effective immediately, due to personal reasons. From a report: Jim Keller was hired by Intel two years ago to the role as Senior Vice President of Intel's Silicon Engineering Group, after a string of successes at Tesla, AMD, Apple, AMD (again), and PA Semiconductor. As far as we understand, Jim's goal inside Intel was to streamline a lot of the product development process on the silicon side, as well as providing strategic platforms though which future products can be developed and optimized to market. We also believe that Jim Keller has had a hand in looking at Intel's manufacturing processes, as well as a number of future products. Intel's press release states that Jim Keller is leaving the position on June 11th due to personal reasons. However, he will remain with the company as a consultant for six months in order to assist with the transition.

Linux computer maker/seller System76 has been offering AMD processors in its Thelio desktop computers, but believe it or not, the company has never offered an AMD-powered laptop -- until now, that is. From a report: You see, starting today, you can buy a "Serval WS" powered by AMD. No, System76 is not offering mobile Ryzen chips in this laptop, but instead, desktop-class processors. As you can expect, this 15-inch portable Linux workstation is quite chunky and heavy as a result. With that said, it is simply impossible to cram this much power into a thin and light notebook. "The Serval WS comes with either the 3rd Gen Ryzen 3600, 3700X, or 3900 CPU. The latter is equipped with 12 Cores and 24 Threads, making this laptop perfect for taking on heavy computational loads. Having this kind of desktop-caliber power in a laptop body helps if you need to run complex simulations at your desk or quickly render 3D scenes while on the road. AMD CPUs are also known for having the an extremely high price per performance, which means you get maximum bang-for-buck," says System76. The laptop starts at $1,300 -- and BetaNews has all the specs.

AMD "has a potent combination of both CPU and GPU technologies," writes Slashdot reader MojoKid, that "can play well in the laptop market especially, where a tight coupling of the two processing engines can mean both performance and cost efficiencies." One of the first all-AMD laptops to hit the market powered by the company's new Ryzen 4000 mobile processors is the Dell G5 15 SE, it's a 5.5 pound, 14.4-inch machine [with a 15.6-inch display] that sports an understated design for a gaming notebook but with an interesting glittery finish that resists fingerprints well. With a retail price of $1199 (starting at $879), the model tested at HotHardware is powered by an AMD Ryzen 4800H 8-core processor that boosts to 4.2GHz and an AMD Radeon RX 5600M mobile GPU with 6GB of GDDR6 memory...

In the benchmarks, AMD's SmartShift technology load-balances CPU and GPU power supply for optimal performance and very respectable numbers that are competitive with any similar Intel/NVIDIA powered machine. The Dell G5 15 SE put up north of 60 FPS frame rates at maximum image quality in current-gen game titles, but with a significantly better price point, relatively speaking.
The GPU also has 2,304 stream processors across 36 compute units, and "Overall, we think Dell hit it out of the park with the new G5 15 SE," the review concludes.

"This all-AMD budget blockbuster has all of the gaming essentials: a fast processor, a powerful GPU, and a 144 Hz display."

Linus Torvalds released Linux 5.7 rc7 today, saying it "looks very normal... none of the fixes look like there's anything particularly scary going on."

But then he added something else: [T]he biggest excitement this week for me was just that I upgraded my main machine, and for the first time in about 15 years, my desktop isn't Intel-based. No, I didn't switch to ARM yet, but I'm now rocking an AMD Threadripper 3970x. My 'allmodconfig' test builds are now three times faster than they used to be, which doesn't matter so much right now during the calming down period, but I will most definitely notice the upgrade during the next merge window.
The Register writes: Torvalds didn't divulge any further details about his new rig, but the 3970x is quite the beast, boasting 32 cores and 64 threads at 3.7GHz with the ability to burst up to 4.5GHz, all built on TSMC's 7nm FinFET process... Torvalds has probably acquired a whole new PC, as the Threadripper range requires a sTRX4 socket and those debuted on motherboards from late 2019.

Whatever he's running, it has more cores than Intel currently offers in a CPU designed for PCs. Even Chipzilla's high-end CoreX range tops out at 18 cores. AMD will be over the moon that such a high profile IT pro has adopted their kit and pointed to its performance.
Or, as long-time Slashdot reader williamyf puts it, "Good endorsement for AMD, a PR blow for Intel."

MojoKid writes: A couple of weeks back, Intel announced its 10th Gen Core desktop processors but today the embargo has been lifted on performance data. Intel's new 10th Gen Core series desktop chips are still based on the same architecture and leverage the same 14nm++ manufacturing process as their 9th Gen predecessors, but the company made numerous changes with Comet Lake-S in an attempt to deliver even more performance, efficiency, and value. A review of the new chips at HotHardware details features and performance of a couple of the stand-outs in Intel's initial 10th Gen Core series line-up -- the flagship Core i9-10900K and mid-range Core i5-10600K.

The Core i9-10900K features a monolithic, 10-core (20-thread) die that boosts to 5.3GHz, while the Core i5-10600K offers 6 cores / 12-threads at a 4.8GHz boost clock. Although the architecture is the same as the previous-gen, Intel has tuned its 10th Gen's frequency and voltage curves to boost performance and optimize power. The Core i9-10900K ends up being a significant upgrade over its predecessor, but more-so for multi-threaded tasks. The Core i5-10600K, however, is a decent upgrade over the previous-gen Core i5-9600K, in terms of both single- and multi-threaded performance. Both CPUs deliver competitive performance versus similarly-priced Ryzen 3000 series chips from AMD, though Intel retains an edge in gaming, while AMD delivers better overall multithreaded performance.

New submitter FallOutBoyTonto shares a reprot from AnandTech: AMD today is reversing its decision to limit the BIOSes on the 400-series chipsets. To cut a long story short, the TL;DR mantra from AMD is: "We've heard our audience, and we understand the concerns. We are going to work out a way to support Zen 3 on our 400-series chipsets between now and launch -- we're still working out the what and the how, but we will update you closer to Zen 3 launch. [...]

1. We will develop and enable our motherboard partners with the code to support 'Zen 3'-based processors in select beta BIOSes for AMD B450 and X470 motherboards.
2. These optional BIOS updates will disable support for many existing AMD Ryzen Desktop Processor models to make the necessary ROM space available.
3. The select beta BIOSes will enable a one-way upgrade path for AMD Ryzen Processors with 'Zen 3,' coming later this year. Flashing back to an older BIOS version will not be supported.
4. To reduce the potential for confusion, our intent is to offer BIOS download only to verified customers of 400 Series motherboards who have purchased a new desktop processor with 'Zen 3' inside. This will help us ensure that customers have a bootable processor on-hand after the BIOS flash, minimizing the risk a user could get caught in a no-boot situation.
5. Timing and availability of the BIOS updates will vary and may not immediately coincide with the availability of the first 'Zen 3'-based processors.
6. This is the final pathway AMD can enable for 400 Series motherboards to add new CPU support. CPU releases beyond 'Zen 3' will require a newer motherboard.
7. AMD continues to recommend that customers choose an AMD 500 Series motherboard for the best performance and features with our new CPUs."

New submitter xhonza writes: New OpenBSD version. String of good news. Some of the new changes, as highlighted by Phoronix, include:
- FFS2 file-system improvements including using 64-bit timestamps and block numbers by default for new installs.
- Support for the Raspberry Pi 4 on ARM64 while improving the Raspberry Pi 3 support too. Raspberry Pi 2/3 support has also improved for OpenBSD ARMv7.
- Better support for Rockchip systems like the Pinebook Pro.
- Various SMP improvements including better AMD SMT/Core/Package detection.
- A wide variety of different hardware driver improvements, including Intel AX200 WiFi device support.
- A FIDO driver introduced for FIDO/U2F security keys support.
- Fixed handling of USB 2.0 devices when in use on different USB 3.0 controllers.
- The PowerPC OpenBSD build switched over to Clang as its default code compiler.
- Various dhclient fixes.
- Various security improvements.

The changelog, announcement, and list of mirrors can be found at their respective links.

Long-time Slashdot reader UnknowingFool writes: As NVidia and AMD battle it out with their GPUs in consumer gaming, behind the scenes both manufacturers were competing against each for manufacturing capacity with TSMC's lines. It appears that early on in the 7nm line, NVidia lost out as it is rumored their strategy was to use Samsung more only to go back to TSMC when that failed By then TSMC had sold out their capacity to AMD. For their next generation GPUs it appears both NVidia is securing both 5nm early while grabbing as much 7nm as possible.

MojoKid writes: AMD unveiled two new Ryzen 3 processors recently, designed to drive its Zen 2 CPU microarchitecture into more affordable price points. The new Ryzen 3 3100 and Ryzen 3 3300X are entry-level 3rd gen Ryzen CPUs that will run in any socket AM4 motherboard, with price points of only $99 (Ryzen 3 3100) and $120 (Ryzen 3 3300X). They are both quad-core/eight-thread chips, with similar cache configurations (2MB L2 + 16MB L3), and they both include basic Wraith Stealth coolers in their retail boxes. Internally, however, these two processors are somewhat different. The Ryzen 3 3100 is setup in a 2+2 configuration with two cores active per CCX (CPU Core Complex). The Ryzen 3 3300X, however, has a 4+0 configuration, with all of its active cores residing on a single CCX. These differences should result in better overall performance for the Ryzen 3 3300X, over and above just having a higher peek clock speed of 4.3GHz, versus 3.90Ghz for the Ryzen 3 3100. In the benchmarks, these new AMD quad-core chips offer similar or better performance versus competitive Intel Core i5 chips, but at significantly lower price points.

UnknowingFool writes: Intel released more information about their next generation CPUs, codenamed Comet Lake. Overall, CPUs will get more cores and threads and slight speed boosts. Price wise, Intel is cutting prices to be more competitive with AMD's Rzyen processors. Some of the downsides include requiring new socket (thus new MBs), LGA 1200 and lack of PCIE 4.0 compatibility. No specific benchmarks were released, however Intel claims to have the fastest gaming CPUs. "[T]he top Comet Lake chip is the same price as the top Coffee Lake at $488, and the cheapest Core i3 is $122," reports PC Gamer. They expect the release date to be sometime in May, though no official date has been confirmed.

An anonymous reader quote Hot Hardware: If you're looking for the best gaming CPU or the best CPU for desktop applications, there are only two choices to pick from: AMD and Intel. That fact has spawned an almost religious following for both camps, and the resulting flamewars, that make it tricky to get unbiased advice about the best choice for your next processor.

But in many cases, the answer is actually very clear. In fact, for most users, it's a blowout win in AMD's favor. That's an amazing reversal of fortunes for the chipmaker after it teetered on the edge of bankruptcy a mere three years ago, making its turnaround all the more impressive as it continues to upset the entrenched Intel that enjoyed a decade of dominance... Pricing is the most important consideration for almost everyone, and AMD is hard to beat in the value department. The company offers a plethora of advantages, like bundled coolers and full overclockability on all models, not to mention complimentary software that includes the innovative Precision Boost Overdrive auto-overclocking feature.

You also benefit from the broad compatibility of Socket AM4 motherboards that support both forward and backward compatibility, ensuring that not only do you get the most bang for your processor buck, but also your motherboard investment. AMD also allows overclocking on all but its A-Series motherboards (see our article on how to overclock AMD Ryzen), which is another boon for users. And, in this battle of AMD vs Intel CPUs, we haven't even discussed the actual silicon yet. AMD's modern processors tend to offer either more cores or threads and faster PCIe 4.0 connectivity at every single price point.
"We're not covering laptop or server chips," the article notes, adding "There's a clear winner overall, but which brand of CPU you should buy depends most on what kind of features, price and performance are important to you."

Still, it's noteworthy that AMD beats Intel in 7 out of 10 comparisons. The three in which Intel won were gaming performance ("only because we measure strictly by the absolute top performance possible"), drivers and software ("the company has an army of software developers [and] a decade of dominance also finds most software developers optimizing almost exclusively for Intel architectures"), and overclocking, where Intel "has far more headroom and much higher attainable frequencies.

"Just be prepared to pay for the privilege."