Microsoft preparing its own AI chips to compete with Nvidia’s GPUs

The development of artificial intelligence has gained mainstream awareness in recent months with news around ChatGPT and OpenAI and similar projects. These advanced neural networks and AI models have large hardware requirements, benefiting Nvidia, whose GPUs are used to train and run these neural networks. But this interest may also bring new competitors. Among them is reportedly Microsoft, which is preparing its own chips for AI. Read more “Microsoft preparing its own AI chips to compete with Nvidia’s GPUs” »

Kioxia trying HLC NAND with 7 bits per cell, LN2 cooling required

A few years ago, we used to look down on TLC NAND flash that stores 3 bits in a single cell and ask for SSDs with SLC (just 1-bit) flash memory. Since then, TLC has become the norm, and the lower-quality tier was taken over by QLC chips with 4 bits per cell and even worse endurance and performance. And it seems this trend could continue, as Kioxia and WD are preparing “hepta-level cell” NAND that would store 7 bits at once. Read more “Kioxia trying HLC NAND with 7 bits per cell, LN2 cooling required” »

First AMD FSR 3.0 sneak peek, technology is similar to DLSS 3

Few months ago, AMD has announced ongoing work on the third generation of FidelityFX Super Resolution (FSR) upscaling, which should bring a similar feature to DLSS 3 – interpolating of intermediate frames inserted between legitimate game frames, much like TVs do with video and movies. AMD has now formally confirmed this and presented FSR 3.0, which will offer frame interpolation and will again be open technology (including source code). Read more “First AMD FSR 3.0 sneak peek, technology is similar to DLSS 3” »

WD introduces Dual Actuator HDDs reaching SATA SSDs speeds

Hard drives are often considered obsolete or plain bad technology, but they still serve an important role when vast storage space is needed without breaking the bank. Fortunately, this technology is still continuing to evolve. We’ve seen HAMR from Seagate recently and now it’s Western Digital’s turn with a performance-enhancing innovation for a change. Performance is chief weakness of HDDs, but there are ways to improve it. Read more “WD introduces Dual Actuator HDDs reaching SATA SSDs speeds” »

FSR 2.0 is no eyesore now. AMD upscaler analysis in Deathloop

The second version of FidelityFX Super Resolution is officially released. This upscaler premiered in Deathloop, the first and so far the only supported game. We compared FSR 2.0 with FSR 1.0 in our tests, both visually and performance-wise. While FSR 1.0 couldn’t compete visually with Nvidia’s DLSS, and the result was significantly worse, AMD pulled the thorn out of its heel with FSR 2.0. A full-featured alternative is now available. Read more “FSR 2.0 is no eyesore now. AMD upscaler analysis in Deathloop” »

PWM vs. DC control. Why do fans work better with impulses?

We avoid it like the plague when it comes to backlighting LCD monitors, but we can’t imagine the best fans without it. We’re talking about pulse-width modulation for voltage regulation. In this article, we will explain in the simplest possible terms the reason why PWM regulation is gradually replacing linear regulation. Related to this in computers is the strong disproportion of 3-pin to 4-pin fans, of which there are considerably more. Read more “PWM vs. DC control. Why do fans work better with impulses?” »

N4X: TSMC unveils special processes for high performance chips

Five to ten years ago, Intel had been the undisputed king of silicon processes, but the delay of 10nm node has ended that and TSMC has been the clear leader since. It is often said that its processes are specialised for mobile use, still remaining inferior to Intel in terms of the maximum achieved clock frequency. But this might change soon. The company will now focus on this very area and high performance chips for PCs. Read more “N4X: TSMC unveils special processes for high performance chips” »

First OptiNAND-based WD HDDs go on sale. 20 TB without SMR

HDD capacities have been rising slowly lately and new larger HDDs often take very long to ship after being announced. But it looks like we are finally getting somewhere: the first 20 TB capacity HDDs (without SMR) are coming, from Western Digital. They’re actually coming to the market with general availability. What’s more, they are interesting because they are the first drives with the recently introduced OptiNAND technology. Read more “First OptiNAND-based WD HDDs go on sale. 20 TB without SMR” »

Samsung will start 2nm chip production 3 years after 3nm node

Samsung’s semiconductor production has been a center of negative news lately. Apart form delays, Samsung processes are believed to be inferior to TSMC node-for-node. But despite this Samsung is still the number two in leading edge process nodes out of the Foundry producers. Now the company has announced 2nm node, which should go into production in four years, two to three years after the volume ramp of the 3nm technology. Read more “Samsung will start 2nm chip production 3 years after 3nm node” »

Nvidia shares experimental new DLSS models for public testing

The version of Nvidia DLSS integrated in games can be upgraded manually by replacing DLL files by newer and better ones from another game. TPU has an archive for various versions extracted from games, but there’s an even better opportunity to tweak the upscaling quality in games now: Nvidia will offer development DLSS models for testing directly, this will allow you to try even the newest pre-release experimental versions. Read more “Nvidia shares experimental new DLSS models for public testing” »

OptiNAND: WD adds flash memory to HDDs, but not in the SSHD way

Lately (actually for several years now) we’ve seldom had news about hard disks. An opportunity to write about a new innovation in this area has come now though. Western Digital has introduced OptiNAND technology, which improves the performance of mechanical drives by integrating NAND Flash memory – but not in the way of SSHDs, which only used it for caching. OptiNAND serves other purposes, and it could be much more useful. Read more “OptiNAND: WD adds flash memory to HDDs, but not in the SSHD way” »

TSMC keeps rocking. 4nm process to be ready a quarter earlier

When release dates get rescheduled in computer industry, it’s usually to later. Obstacles in development happen and it is not always possible to meet the plans, so delays are common. But there’s a good news of this sort now, for a change. TSMC actually managed to push the development of ab upcoming future process noe forward. The company has now announced that the production of 4nm chips will start earlier than originally planned. Read more “TSMC keeps rocking. 4nm process to be ready a quarter earlier” »

AMD redies 3D chiplets: demo of Zen 3 with 192MB 3D V-Cache

After Intel, AMD has now presented its new products. These include the Ryzen 5000G APU, Radeon RX 6000M graphics for laptops and FSR upscaling intended as a competition for DLSS from Nvidia. But the processor news was the most interesting thing: 3D silicon chiplets layered on top of each other may come into Ryzen processors, and AMD has shown a prototype, which has 3× larger L3 cache, bringing nice gaming performance boosts. Read more “AMD redies 3D chiplets: demo of Zen 3 with 192MB 3D V-Cache” »

A look at Nvidia DXR, Broadcast App and DLSS visual quality

We are introducing a new testing methodology for graphics cards. One of the reviewed cards will be the GeForce RTX 3070 and we have an interesting one: Aorus GeForce RTX 3070 Master 8G with six video outputs. Before the review comes out, we’ve use it for a visual comparison to see the impact of ray tracing and how the different DLSS settings in the latest Cyberpunk 2077 patch will affect the quality of the game graphics. Read more “A look at Nvidia DXR, Broadcast App and DLSS visual quality” »

Ampere deep dive: what’s new in GeForce RTX 3000 architecture

In terms of hardware, September was a green month with the release of the new generation of Nvidia GPUs, GeForce RTX 3000. They are based on the new Ampere architecture. In this article we are going to discuss what’s new compared to Turing: the new SM architecture doubling the number of shaders, the manufacturing process and the characteristics of the two chips that have been unveiled so far. Read more “Ampere deep dive: what’s new in GeForce RTX 3000 architecture” »