Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
This generation of GPUs has seen some serious changes in the AMD–Nvidia arms race, next to the entrance of a third major player. Nvidia continued to be the leading GPU manufacturer thanks to its fantastic performance at all price levels, class-leading ray-tracing, and exceptional resolution technology through its GeForce RTX 40 series despite the high prices.
Meanwhile, rival AMD has continued to deliver the best bang-for-buck graphics cards with the Radeon RX 7000 series while spreading its technology across video game consoles and laptops.
After decades of dominating the CPU market, Intel also made its big entry into the discrete GPU market with its Intel Arc series. Although compatibility with older games and overall performance was not close to Nvidia and AMD at first, both A750 and A770 served as a respectable starting point for Intel.
As 2024 inches closer to the new year, much speculation has been made about the arrival of new cards from the new big three. According to rumors, Nvidia is expected to release its 50 series GPUs a few weeks later a potential CES 2025 reveal. On the other hand, Jack Huynh, senior vice president of AMD said in a recent interview that the chip maker’s current GPU focus is more mid-market and accessible areas. Most recently, Intel has announced and launched its new Intel Arc B580 to rave reviews (including TechRadar’s own review of the Intel Arc B580, which earned a coveted five stars). Even better, the Intel Arc B570 is scheduled for release in early 2025.
There are many features we expect with the new round of GPUs expected to drop next year, from increased VRAM to better enthusiast-level performance. However, here are some things I want to see from the next generation cards coming in 2025.
Better ray tracing
Real-time lighting, shadows, ambient occlusion, reflections, and global lighting completely revolutionized gaming once Nvidia released the first commercial graphics cards with ray tracing capabilities.
Introduced in 2018 through the Nvidia GeForce RTX 2080, the technology has become one of the most important visual effects in modern gaming. AMD later introduced the technology in its Radeon RX 6000 series in 2020, and since it made its debut in Battlefield V, ray tracing has become an option in many best pc games as well as Cyberpunk 2077 and Alan Wake II.
Intel’s Arc cards debuted in 2022, and despite their ray tracing capabilities that Nvidia or AMD lacked, it was at least present.
One of the problems with the technology, however, is how resource-intensive it is, which absolutely reduces performance. Although the current generation cards have done better, there is still a lot to do in this area.
Better AI upscaling
Nvidia’s AI dominance started with its Deep Learning Super Sampling (or DLSS) technology that was introduced in 2018 on its RTX 20 series GPUs.
It is allowed to render lower resolution images, then upgrade them to higher resolutions, greatly improving game framerates. It has also become a less resource-intensive way to achieve it 4K resolutions in modern game consoles.
AMD will introduce its competing upscaling technology, FidelityFX Super Resolution (or FSR), and Intel has also debuted Intel XeSS for its graphics cards as well as some competing graphics cards that can use DP4a instructions (which is a lot, but not all, modern). GPU).
Although all three versions of the AI upscaling look good, they still contain artifacts, blurring and ghosting among other issues that can disrupt immersion. For now, the performance gain makes it worth using, but here’s the hope that the technology will continue to improve with next-generation GPUs so that we don’t have to sacrifice so much visual quality for those extra frames.
The arrival of disaggregated GPU architectures
Intel’s upcoming “Celestial” GPUs It could use what is known as a “disaggregated GPU architecture,” according to an Intel patent. And while it’s unlikely to do so in Intel Battlemage GPUs, this modular design could offer flexibility and improved energy efficiency, especially valuable for high-performance graphics cards.
Similar chipset designs have been speculated for AMD’s RDNA 4 series and Nvidia’s RTX 50 series, although these rumors have largely died down in recent months.
However, there are potential challenges such as ensuring fast interconnections between chipsets to maintain performance. If done right, disintegrated chipsets could become as revolutionary as multi-core CPUs became in the mid-2000s, and we may see some in 2025.
Reduced energy consumption
As GPU chip sets become more powerful with each iteration, power consumption is also higher (at least on the enthusiast side). Nvidia’s next RTX 5090 card is rumored to have a thermal conception power (TDP) close to 600W, an increase from the RTX 4090’s 450W.
Corsair has confirmed that the 12V-2×6 connector will likely remain the standard for next-generation GPUs, and when it comes to AMD and Intel, it is unlikely that they will adopt similar high-power standards for their GPUs through continued use. of 8-pin. connectors. Hopefully the next generation chipsets will offer more performance without the huge power cost.
