News Posts matching #AMD

Return to Keyword Browsing

AMD "Renoir" APU to Support LPDDR4X Memory and New Display Engine

AMD's next-generation "Renoir" APU, which succeeds the company's 12 nm "Picasso," will be the company's truly next-generation chip to feature an integrated graphics solution. It's unclear as of now, if the chip will be based on a monolithic die, or if it will be a multi-chip module of a 7 nm "Zen 2" chiplet paired with an enlarged I/O controller die that has the iGPU. We're getting confirmation on two key specs - one, that the iGPU will be based on the older "Vega" graphics architecture, albeit with an updated display engine to support the latest display standards; and two, that the processor's memory controller will support the latest LPDDR4X memory standard, at speeds of up to 4266 MHz DDR. In comparison, Intel's "Ice Lake-U" chip supports LPDDX4X up to 3733 MHz.

Code-lines pointing toward "Vega" graphics with an updated display controller mention the new DCN 2.1, found in AMD's new "Navi 10" GPU. This controller supports resolutions of up to 8K, DSC 1.2a, and new resolutions of 4K up to 240 Hz and 8K 60 Hz over a single cable, along with 30 bits per pixel color. The multimedia engine is also suitably updated to VCN 2.1 standard, and provides hardware-accelerated decoding for some of the newer video formats, such as VP9 and H.265 at up to 90 fps at 4K, and 8K up to 24 fps, and H.264 up to 150 fps at 4K. There's no word on when "Renoir" comes out, but a 2020 International CES unveil is likely.

ASRock Radeon RX 5700 XT Taichi OC+ Pictured

ASRock is ready with its flagship Radeon RX 5700 XT graphics card, which is among its first fully in-house graphics card designs. The Radeon RX 5700 XT Taichi features a board design that was teased at the 2019 Computex show as a high-end graphics card cooling solution concept. It's since been mated with a custom-design RX 5700 XT PCB. The card features a triple-slot cooling solution with an aluminium fin-stack heatsink, and a cooler shroud that holds three fans. The smaller central fan features an RGB LED embellishment. A tiny LED segment display along the top of the cooler appears to display real-time monitoring. ASRock's signature Taichi gearwheel aesthetic carries over not just to the cooler, but also its backplate.

The PCB is noticeably taller than the AMD reference PCB, pulls power from a pair of 8-pin PCIe power connectors, offers dual-BIOS with a toggle between an "OC BIOS" and a "Silent BIOS," an LED lighting master control switch, and possibly a strong VRM solution to keep the juices flowing to "Navi." The clock-speeds of the card are still under the wraps, but it's likely that only the OC BIOS features factory-overclocked speeds, while the Silent BIOS ticks at reference clock speeds to favor an aggressive fan-control. Both BIOSes could offer idle fan-stop. The display connectivity is particularly interesting - four DisplayPorts, and two HDMI connectors, all along the rear I/O. There's no word on the availability, but at least the box-art proves this card isn't a tradeshow unicorn.

Der8auer: Only Small Percentage of 3rd Gen Ryzen CPUs Hit Their Advertised Speeds

World famous overclocker Der8auer published his survey of boost clocks found on 3rd generation Ryzen CPUs. Collecting data from almost 3,000 entries from people around the world, he has found out that a majority of the 3000 series Ryzen CPUs are not hitting their advertised boost speeds. Perhaps one of the worst results from the entire survey are for the 12-core Ryzen 9 3900X, for which only 5.6% of entries reported have managed to reach the boost speeds AMD advertises. However, the situation is better for lower-end SKUs, with about half of the Ryzen 5 3600 results showing that their CPU is boosting correctly and within advertised numbers.

Der8auer carefully selected the results that went into the survey, where he discarded any numbers that used either specialized cooling like water chillers, Precision Boost Overdrive - PBO or the results which were submitted by "fanboys" who wanted to game the result. Testing was purely scientific using Cinebench R15 and clock speeds were recorded using HWinfo (which got recommendation from AMD), so he could get as precise data as possible.

AMD Makes Gains in GPU Shipments in Q2-2019: Jon Peddie Research

The PC GPU market sequentially increased by 0.6% in Q2'19, decreased year-to-year by -10.4% This is the latest report from Jon Peddie Research on the GPUs used in PCs. It is reporting on the results of Q2'19 GPU shipments world-wide. AMD shipments increased 9.8% NVIDIA was flat and Intel's shipments, decreased -1.4% as indicated in the following chart.

Even though there is uncertainty in the notebook supply chain, there has been a record number of new notebook announcements, and systems with amazing specifications in performance, battery life, and screen resolution. Specialized notebooks that sit somewhere between workstations and enthusiast PCs are arriving on the market for creative professionals. Strong graphics subsystems are an important selling point for these machines.

Yeston Reveal "CUTE PET" Pink AMD Radeon RX 580 Graphics Card - Straight out of Manga

Yeston have revealed an addition to their AMD graphics-card lineup in the form of the "CUTE PET" RX 580. The name implies exactly what this card is all about: a colorful, teenage theme in blue and pink with PCB cutouts that resemble a... well... Cute pet. There are RGB elements in the cut-outs for the eyes, ears and mouth of the "CUTE PET", the eyes are confused spirals built from the dual-fan cooling design, there's a blue backplate with cloudy cut-outs...

AMD Readies Three HEDT Chipsets: TRX40, TRX80, and WRX80

AMD is preparing to surprise Intel with its 3rd generation Ryzen Threadripper processors derived from the "Rome" MCM (codenamed "Castle Peak" for the client-platform), that features up to 64 CPU cores, a monolithic 8-channel DDR4 memory interface, and 128 PCIe gen 4.0 lanes. For the HEDT platform, AMD could reconfigure the I/O controller die for two distinct sub-platforms within HEDT - one targeting gamers/enthusiasts, and another targeting the demographic that buys Xeon W processors, including the W-3175X. The gamer/enthusiast-targeted processor line could feature a monolithic 4-channel DDR4 memory interface, and 64 PCI-Express gen 4.0 lanes from the processor socket, and additional lanes from the chipset; while the workstation-targeted processor line could essentially be EPYCs, with a wider memory bus width and more platform PCIe lanes; while retaining drop-in backwards-compatibility with AMD X399 (at the cost of physically narrower memory and PCIe I/O).

To support this diverse line of processors, AMD is coming up with not one, but three new chipsets: TRX40, TRX80, and WRX80. The TRX40 could have a lighter I/O feature-set (similar to the X570), and probably 4-channel memory on the motherboards. The TRX80 and WRX80 could leverage the full I/O of the "Rome" MCM, with 8-channel memory and more than 64 PCIe lanes. We're not sure what differentiates the TRX80 and WRX80, but we believe motherboards based on the latter will resemble proper workstation boards in form-factors such as SSI, and be made by enterprise motherboard manufacturers such as TYAN. The chipsets made their way to the USB-IF for certification, and were sniffed out by momomo_us. ASUS is ready with its first motherboards based on the TRX40, the Prime TRX40-Pro, and the ROG Strix TRX40-E Gaming.

The Coalition's Gears 5 Is Filled to the Brim With AMD DNA, System Requirements Outed

Gears 5, the next upcoming installment in the Gears of War series of video games, is launching this September 10th. In anticipation, developer The Coalition has announced the games' close partnership development with AMD, optimizing it for the company's cadre of GPU and CPU solutions. The game will make extensive use of Asynchronous Compute - one of AMD's most relevant technologies in gaining the upper hand against NVIDIA on performance terms. According to the developer, post-processing effects are being run exclusively on Asynchronous Compute, which means that the games' rendering is being run as close to a clockwork as possible. FidelityFX also makes an appearance again, as one of the latest AMD technologies for improving visual fidelity and sharpness. Multithreaded Command Buffering is the technical implementation for a system that improves AMD's Ryzen CPUs' processing of the game, specifically geared towards taking advantage of that CPU architecture's strong points.

The game seems to be a pretty scalable affair, with minimum requirements making do with just 2 GB of VRAM and an AMD RX 560 or NVIDIA GTX 1050. The ideal system requirements, however, call for a much beefier setup, with an AMD Radeon VII or NVIDIA RTX 2080 being called for, including 16 GB of system memory and a whopping 100 GB+ install footprint - preferably on an SSD. The game, like Gears of War 4, has been developed with the PC market in mind - there are more than 35 different graphical options for users to tweak. Here's hoping the games' writing is as much a technical achievement as its engine development seems to be.

Gearbox Reveals Minimum, Recommended Specs for Borderlands 3

Gearbox today revealed the minimum and recommended specs for their upcoming Borderlands 3, to be distributed digitally as an EPIC Games Store exclusive. Developed in close partnership with AMD, Borderlands 3 is being pitched by the company as playing best on AMD-based CPUs and GPUs. There's support for AMD's FidelityFX Sharpening, and graphics settings can be finely tuned for your desired level of performance and IQ, with plenty of options for users to play with - including resolution scale, where you can set your render resolution lower than your display resolution, or higher (with the resulting increase in IQ).

These are relatively standard requirements, as you can see in the image below. Nothing jumps to mind as being out of place: we've already seen 16 GB and a midrange RX 590 as the recommended specs before. Keep in mind Minimum Requirements are listed for 1080p resolution, whereas the Recommended specs are geared for a 1440p presentation. Borderlands 3 releases on September 13.

AMD to Cough Up $12.1 Million to Settle "Bulldozer" Core Count Class-Action Lawsuit

AMD reached a settlement in the Class Action Lawsuit filed against it, over alleged false-marketing of the core-counts of its eight-core FX-series processors based on the "Bulldozer" microarchitecture. Each member of the Class receives a one-time payout of USD $35 per chip, while the company takes a hit of $12.1 million. The lawsuit dates back to 2015, when Tony Dickey, representing himself in the U.S. District Court for the Northern District of California, accused AMD of false-marketing of its FX-series "Bulldozer" processor of having 8 CPU cores. Over the following four years, the case gained traction as a Class Action was built against AMD this January.

In the months that followed the January set-up of a 12-member Jury to examine the case, lawyers representing the Class and AMD argued over the underlying technology that makes "Bulldozer" a multi-core processor, and eventually discussed what a fair settlement would be for the Class. They eventually agreed on a number - $12.1 million, or roughly $35 per chip AMD sold, which they agreed was "fair," and yet significantly less than the "$60 million in premiums" consumers contended they paid for these processors. Sifting through these numbers, it's important to understand what the Class consists of. It consists of U.S. consumers who became interested to be part of the Class Action, and who bought an 8-core processor based on the "Bulldozer" microarchitecture. It excludes consumers of every other "Bulldozer" derivative (4-core, 6-core parts, APUs; and follow-ups to "Bulldozer" such as "Piledriver," "Excavator," etc.).
Image Credit: Taylor Alger

Ghost Recon Breakpoint PC System Requirements Revealed

Ubisoft's latest entry to its smash-hit open-world tactical combat sim "Ghost Recon" is getting its latest chapter "Breakpoint," bound for an October 4 release. Breakpoint builds on the open-world presentation of "Wildlands," and transports you to the fictional world of Auroa, across its diverse landscapes and drone-patrolled wilderness. Ubisoft today posted the system requirements for "Breakpoint." Nothing serious, the average gaming desktop should comfortably run it at 1080p thru 2K resolution, as detailed in the slide below.

Ghost Recon Breakpoint appears to be closely developed in collaboration with AMD, which means a high-level of optimization for AMD Ryzen processors and Radeon graphics cards. In particular, the game supports AMD FidelityFX image-quality enhancement introduced with "Navi." The PC version has texture-resolution suited for 4K Ultra HD, supports ultrawide monitors, has uncapped frame-rates, tobii eye-tracking support, and Discord integration. It's available for pre-order on UPlay and Epic Games Store.

AMD Releases Radeon Software Adrenalin 19.8.2 Beta

AMD Monday posted the latest version of Radeon Software Adrenalin 2019 Edition. Version 19.8.2 beta comes with optimization for the week's big AAA launch, "Control," with up to 10 percent higher frame-rates compared to the older 19.8.1 drivers. The new drivers also include optimization for the interactive novel "Man of Medan." The drivers add HDCP 2.3 support for Radeon RX 5700 series graphics cards.

Among the bugs fixed are a "Rocket League" application hang on task-switch, performance-drops with "League of Legends" when performing a task-switch; system instability seen with Radeon RX 5700-series when memory-overclocking while a 3D application is running; and minor stutter noticed with "Fortnite" in the first few minutes of gameplay. Grab the driver from the link below.

DOWNLOAD: AMD Radeon Software Adrenalin 19.8.2 beta
The change-log follows.

AMD Ryzen 5 3500 to Lack SMT, Takes on Core i5-9400

As AMD's Ryzen 5 3500 processor is inching closer to launch, we learn more possible specifications of the chip AMD is designing to take on Intel's popular Core i5-9400/9400F processor. Late July, we learned that the chip will be a 6-core model, breaking away from convention set by past generations, of the x500 Ryzen SKU being 4-core/8-thread. Thai PC enthusiast TUM_APISAK, who has a fairly high hit-rate on unreleased products, predicts that the 3500 will be six-core, but lack SMT (it will be 6-core/6-thread).

The Ryzen 5 3500 will be clocked at 3.60 GHz nominal, with a boost frequency of 4.10 GHz. There's no word on other specs, such as L3 cache amount. A single "Zen 2" chiplet normally has 32 MB of it (16 MB per CCX). The main competitor from the Intel stable is the Core i5-9400 / i5-9400F, which ticks at 2.90 GHz with 4.10 GHz boost. The i5-9400F in particular has had a big impact in the sub-$200 segment, as it's been aggressively priced under promotions by various DIY retailers. The chip lacks an iGPU, but has the specs to pull a fairly powerful gaming PC. With the Ryzen 5 3600 at $199, AMD could price the new chip around $169-179.

Intel Says AMD Did a Great Job (with Ryzen 3000), But Intel CPUs are Still Better

It is no secret that AMD has made a huge success with its long awaited "Zen" CPUs and returned to PC market stronger than ever. Intel however has neglected AMD's presence and only recently admitted what an impact AMD made. At this year's Gamescon, Intel started a new campaign against AMD with a point that Intel's CPUs are still better performers with "real world benchmarks" backing that claim.

"A year ago when we introduced the i9 9900K," says Intel's Troy Severson, "it was dubbed the fastest gaming CPU in the world. And I can honestly say nothing's changed. It's still the fastest gaming CPU in the world. I think you've heard a lot of press from the competition recently, but when we go out and actually do the real-world testing, not the synthetic benchmarks, but doing real-world testing of how these games perform on our platform, we stack the 9900K against the Ryzen 9 3900X. They're running a 12-core part and we're running an eight-core," he adds. "I'll be very honest, very blunt, say, hey, they've done a great job closing the gap, but we still have the highest performing CPUs in the industry for gaming, and we're going to maintain that edge."

AMD CEO Lisa Su: "CrossFire Isn't a Significant Focus"

AMD CEO Lisa Su at the Hot Chips conference answered some questions from the attending press. One of these regarded AMD's stance on CrossFire and whether or not it remains a focus for the company. Once the poster child for a scalable consumer graphics future, with AMD even going as far as enabling mixed-GPU support (with debatable merits). Lisa Su came out and said what we all have been seeing happening in the background: "To be honest, the software is going faster than the hardware, I would say that CrossFire isn't a significant focus".

There isn't anything really new here; we've all seen the consumer GPU trends as of late, with CrossFire barely being deserving of mention (and the NVIDIA camp does the same for their SLI technology, which has been cut from all but the higher-tier graphics cards). Support seems to be enabled as more of an afterthought than a "focus", and that's just the way things are. It seems that the old, old practice of buying a lower-tier GPU at launch and then buying an additional graphics processor further down the line to leapfrog performance of higher-performance, single GPU solutions is going the way of the proverbial dodo - at least until an MCM (Multi-Chip-Module) approach sees the light of day, paired with a hardware syncing solution that does away with the software side of things. A true, integrated, software-blind multi-GPU solution comprised of two or more smaller dies than a single monolithic solution seems to be the way to go. We'll see.

AMD Silently Pushes Out Radeon Software Adrenalin 19.8.1 WHQL Drivers

AMD late-Tuesday silently posted a WHQL-signed version of Radeon Software Adrenalin 19.8.1 drivers that it originally released as a Beta on August 12. The new 19.8.1 WHQL drivers, released on 20th August, are the first proper WHQL drivers since AMD's Radeon RX 5700-series launch. Besides WHQL, the underlying code is identical to 19.8.1 Beta, and hence the changelog is untouched. TechPowerUp confirmed with AMD that there are no underlying code changes, and that WHQL signing is the only change. Adrenalin 19.8.1 adds Microsoft PlayReady 3.0 DRM standard compliance to Radeon RX 5700-series GPUs. Grab the driver from the link below.

DOWNLOAD: AMD Radeon Software Adrenalin 19.8.1 WHQL

GIGABYTE Smashes 11 World Records with New AMD EPYC 7002 Processors

GIGABYTE, a leading server systems builder which recently released a total of 17 new AMD EPYC 7002 Series "Rome" server platforms simultaneously with AMD's own official launch of their next generation CPU, is proud to announce that our new systems have already broken 11 different SPEC benchmark world records. These new world records have not only been achieved against results from all alternative processor based systems but even against competing vendor solutions using the same 2nd Generation AMD EPYC 7002 Series "Rome" processor platform, illustrating that GIGABYTE's system design and engineering is perfectly optimized to deliver the maximum performance possible from the 2nd Generation AMD EPYC.

MSI Unveils Radeon RX 5700 MECH Series Graphics Cards

MSI unveiled its Radeon RX 5700-series MECH graphics cards. The lineup includes graphics cards based on both the Radeon RX 5700 XT and the Radeon RX 5700. MSI further differentiated them into a base variant that ticks at AMD-reference clock speeds out of the box, and OC Edition variants that come with factory-overclocked speeds. The MECH series is positioned slightly lower than the company's Evoke series, and the OC Edition variants come with clock speeds that are a notch lower than those of the Evoke OC. The RX 5700 XT MECH OC Edition ships with 1670/1815/1925 MHz (base/gaming/boost) clocks, while the RT 5700 XT MECH has reference clocks of 1605/1755/1905 MHz. The RX 5700 MECH OC Edition comes with 1515/1675/1750 MHz, while the standard RX 5700 MECH ships with reference clocks of 1465/1625/1725 MHz.

All four MECH series graphics cards are based on a common board design. The PCB is custom-design, and is similar to that of the RX 5700 Evoke series. The cooling solution uses the same exact aluminium fin-stack heatsink as the EVOKE, with the same pair of 90 mm TorX fans, but suspended onto a cost-effective plastic shroud, compared to the diamond-cut alloy shroud of the EVOKE. All four cards feature a backplate. The cards draw power from a combination of 6-pin and 8-pin PCIe power connectors. Display outputs include three DisplayPorts and an HDMI. The RX 5700 XT and RX 5700 MECH series from MSI are expected to be priced about $10-15 higher than the AMD baseline prices for the base variants, and about $15-20 higher for the OC Edition variants.

ASUS Launches its TUF Gaming X3 Radeon RX 5700-series Graphics Cards

ASUS today launched its TUF Gaming X3 Radeon RX 5700-series "Navi" graphics cards. The TUF Gaming series is positioned a notch below the company's premium ROG Strix RX 5700-series, and above its cost-effective custom-design Dual-series. A common board design is used for both the RX 5700 XT and the RX 5700. It features a macho-looking plastic cooler shroud with the TUF "urban camo" pattern. There's also a metal backplate with the same pattern. The card is based on a custom-design PCB that's shorter than that of the ROG Strix card.

The triple-slot cooling solution of the TUF Gaming X3 Radeon RX 5700-series features a compound aluminium fin-stack heatsink much like the ROG Strix, albeit slightly smaller. Three 80 mm fans ventilate it, although the cooler lacks idle fan-stop. The fans feature IP5X-certified dust-resistance and fluid-dynamic bearings with a "space-grade lubricant." Both cards come with factory-overclocked speeds. The TUF Gaming X3 RX 5700 XT ships with 1650 MHz base, 1795 MHz "gaming" clocks, and 1905 MHz boost; while the TUF Gaming X3 RX 5700 ships with 1565 MHz base, 1720 MHz "gaming" clocks, and 1750 MHz boost. Both cards feature software-based one-click "OC" modes that dial up clock speeds by around 4 percent, which require you to install the GPUTweak utility. The company didn't reveal pricing.

PowerColor Announces its Custom Navi Series Including Red Dragon and Red Devil Series

TUL Corporation, a leading and innovative manufacturer of AMD graphic cards since 1997, brings today the highly praised Red Devil and Red Dragon series to the RX 5700 line, engineered to provide the best hardware for the ultimate 1440p gaming experience.

To celebrate the new Red Devil branding as well the introduction of RGB lighting to the product line for the first time, PowerColor is having a special limited-edition RX 5700 XT Red Devil, to celebrate the new Red Devil series with an entire new cooling solution to bring the best of Navi as well a more neutral use of colors that will match any gaming rig color scheme. In addition, the Red Devil includes RGB lighting both on the side and on the back of the card for awesome tweaks.

AMD "Sharkstooth" Shows Up on Geekbench: Possible Zen 2 Threadripper

AMD is possibly testing its 3rd generation Ryzen Threadripper HEDT processors, with an interesting entry showing up on the Geekbench online database. The entry speaks of an "AMD Sharkstooth" processor with 32 cores and 64 threads, with a nominal clock speed of 3.60 GHz, and the long-form model number "AuthenticAMD Family 23 Model 49 Stepping 0." None of the 2nd generation EPYC processors correspond with these specs, and so we're almost certain this is a client-segment Ryzen Threadripper part.

The prototyping platform, which is a motherboard designed in-house by AMD to test the processor's various components and I/O capabilities, is codenamed "WhiteHavenOC-CP." In this Geekbench submission, the processor is paired with around 128 GB of memory, and tested on 64-bit Linux. The platform yields a multi-threaded score of 94,772 points, which is about 18.5 percent higher than what a Ryzen Threadripper 2990WX typically manages when tested on Linux. It is also within 5% of what the Xeon W-3175X manages (around 99,000 points). The production model could be clocked higher. AMD will also use the opportunity to launch a new motherboard chipset while maintaining backwards-compatibility with the AMD X399. This new chipset will enable PCI-Express gen 4.0 and come with stiffer CPU VRM and memory/PCIe wiring specifications to enable higher memory clocks and PCIe link stability. AMD is expected to launch its 3rd gen Ryzen Threadripper this October, to preempt Intel's next HEDT processor series.

MSI Radeon RX 5700 Mech OC Pictured

Another MSI interpretation of AMD's RX 5700 graphics card has been taken out of the bag. This time, on the form of the Mech OC series, which carries a dual-slot, dual-fan configuration not dissimilar to MSI's Ventus graphics cards, but with a darker color palette. The design is appealing, even if fully in plastic save for the backplate, which is full black and has some white strips to add a little more interest to the otherwise blank surface. The MSI Radeon RX 5700 Mech OC graphics card ships with 3x DisplayPort 1.4 and 1x HDMI 2.0 ports, and will join other MSI custom design mainstays in the company's portfolio for AMD-based hardware.

Caseking Adds Binned Ryzen 3000 CPUs to Its Offerings

Users that don't want to play the silicon lottery game have been using services that offer pre-binned and pre-overclocked chips for a while now. Silicon Lottery is one of the most well known players in this game, but German retailer Caseking is now offering the same for AMD's latest Ryzen 3000 processors. AMD's work on automatic overclocking and boost clocks for their Ryzen chips has rendered manual overclocking almost (read: almost) obsolete, and in some cases it may even be detrimental to the CPU's performance to set a manual overclock that overrides AMD's boost clock algorithm. This is because AMD's boost increases speed on a single core, with subsequent cores being clocked slightly lower according to their capabilities. In effect, this means that manually overclocking all cores to, say, 4.0 GHz can sometimes render lower performance in particular tasks, since the all-core overclock is, by necessity, handicapped by the least-overclockable core.

Caseking's offerings have been pre-overclocked, and are guaranteed to hit stable overclocks at the claimed frequency, thus saving users from getting a "bad" overclocker CPU from AMD. Caseking's offerings have been tested by their own King Mod team and overclocking superstar Roman "der8auer" Hartung, with Prime95 26.6 software being used to test the overclocked chips' stability with a FFT length of 1344 for at least one hour. This practice is backed by a two-year limited warranty on the CPU. Sadly, most CPUs are out of stock at the moment, so keep on checking availability, unless one of the offerings is exactly up your alley.

110°C Hotspot Temps "Expected and Within Spec", AMD on RX 5700-Series Thermals

AMD this Monday in a blog post demystified the boosting algorithm and thermal management of its new Radeon RX 5700 series "Navi" graphics cards. These cards are beginning to be available in custom-designs by AMD's board partners, but were only available as reference-design cards for over a month since their 7th July launch. The thermal management of these cards spooked many early adopters accustomed to seeing temperatures below 85 °C on competing NVIDIA graphics cards, with the Radeon RX 5700 XT posting GPU "hotspot" temperatures well above 100 °C, regularly hitting 110 °C, and sometimes even touching 113 °C with stress-testing application such as Furmark. In its blog post, AMD stated that 110 °C hotspot temperatures under "typical gaming usage" are "expected and within spec."

AMD also elaborated on what constitutes "GPU Hotspot" aka "junction temperature." Apparently, the "Navi 10" GPU is peppered with an array of temperature sensors spread across the die at different physical locations. The maximum temperature reported by any of those sensors becomes the Hotspot. In that sense, Hotspot isn't a fixed location in the GPU. Legacy "GPU temperature" measurements on past generations of AMD GPUs relied on a thermal diode at a fixed location on the GPU die which AMD predicted would become the hottest under load. Over the generations, and starting with "Polaris" and "Vega," AMD leaned toward an approach of picking the hottest temperature value from a network of diodes spread across the GPU, and reporting it as the Hotspot.

AMD Releases Radeon Software Adrenalin 19.8.1 Drivers

AMD today released Radeon Software Adrenalin 19.8.1 drivers as the first custom-design Radeon RX 5700-series graphics cards took to the shelves. The drivers add Microsoft PlayReady 3.0 DRM support for the RX 5700 series. The drivers also fix several issues but don't even acknowledge the elevated idle fan-speeds on reference RX 5700-series graphics cards, in what is shaping up to be a bait-and-switch tactic that's unbecoming of a company like AMD. Among the resolved bugs are color corruption noticed upon install of Radeon Software on Windows 10 May 2019 Update (1903) without Windows Update KB4505903 in place.

A black screen noticed on RX 5700 series with automatic memory overclocking enabled in games with full-screen display settings, has also been fixed. The drivers also fix Radeon Chill settings not being in sync with game profiles changed in-game using Radeon Overlay. Radeon AntiLag slightly impacting performance in some games has also been fixed. Uninstalling RX 5700 drivers on Windows 7 machines resulting in a black-screen has also been fixed. ReLive recording not working correctly on Windows 7 with RX 5700 series has also been fixed. Grab the drivers from the link below.
DOWNLOAD: AMD Radeon Software Adrenalin 19.8.1 Beta

The change-log follows.

AMD Patents new System and Method for Protecting GPU Memory Instructions Against Faults

With ever increasing number of exploits, processor manufacturers are finding new and improved ways to secure their system against such dangers. Exploits can be found on hardware and software level, but ones on hardware level are harder to patch and protect against. If you remember Spectre and Meltdown, they used CPU's branch speculation to enforce unwanted instruction stream. At software/firmware level we also got a fair number of exploits like recent "Screwed Drivers" incident, where drivers signed and approved by Microsoft are susceptible to privilege escalation.

However, AMD has patented a new way for protecting GPU memory instruction against faults by using a new system method. The proposed method uses system's "master and slave" devices and manipulates their instruction streams and check for any errors in the process. Firstly, the proposed system converts "slave" device request to dummy operations like NOP (No OPeration) is, and modifies the memory arbiter to issue N master and N slave global/shared memory instructions per cycle, sending master memory requests to memory system. Then it uses slave requests to check for errors and enter master requests in to memory FIFO aka First In First Out memory buffer. Slave request is stored in a register. Finally two values from register, where slave request was stored, and FIFO are compared to see if there are any differences.
Return to Keyword Browsing
Apr 2nd, 2025 02:51 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts