Asus First to Confirm Clock Speeds of Custom Radeon RX 7900 GPUs

Anticipation is starting to build for AMD’s next-gen graphics cards. The company is deploying an unusual, month-long delay between the announcement and the on-sale date next week. With cards starting to be shipped to retailers, Asus has become the first company to announce specs for its offerings. It’ll be using its The Ultimate Force (TUF) series for AMD’s latest GPUs, which is one rung below its ROG Strix flagship series typically. In preparation for the launch, it’s posted the cards’ clock speeds, and they’re naturally a bit higher than the AMD reference boards. Whether that’ll translate into a much higher price remains to be seen.

News of the impending pixel pushers’ clocks comes via the Asus website via Videocardz. The company has specs listed for both the XTX and XT cards. For context, AMD’s reference design for the Radeon RX 7900 XTX has a 2.3GHz “game clock.” That’s the sustained clock speed it utilizes during gaming applications. In addition, it can boost temporarily to 2.4GHz when needed.

The Asus version, which is called the TUF Gaming OC Edition, has both a default and an OC mode, likely switched via an onboard toggle. In its default mode, its game clock is 2,395MHz, which is a mild four percent boost over reference. It can also boost to 2,565MHz, compared with the reference card’s 2,500MHz boost clock. That’s a meager 2.6 percent over stock.

However, who would spend all this money and not use OC mode? In that setting, things get a bit more interesting.

In OC mode, the TUF card’s game clock is 2,455MHz; a 6.7 percent improvement over reference. Its boost clock is 2,615MHz, which is 4.6 percent higher than stock. Although AMD defines the boost clock as something that can only be achieved for bursty workloads, the prodigious cooling of the Asus card might allow it to swap its game clock for the boost clock. After all, as shown above, it’s a monster GPU. This tracks with the company’s Nvidia boards as well, which are all gargantuan.

When it comes to the Asus XT version, uplift over reference is similar. The AMD XT card’s game clock is 2GHz, with a 2.4GHz boost clock. Asus ups the game clock in default mode to 2,130MHz. That’s a 6.5 percent improvement over reference. It can also boost to 2.5GHz, which is 4.1 percent higher than stock. In OC mode, game clock goes up to 2,175MHz and boost becomes 2,535MHz. That represents an 8.7 and 5.6 percent improvement over AMD’s design.

An interesting twist is that AMD championed how small its new GPUs were at the launch event. It bragged that, unlike the Nvidia 40-series, you don’t need a new case to buy an RDNA3 card. That might not be the case, pardon the pun, with these Asus boards. Both GPUs are 13.9 inches long, which might be too big for some cases. For reference, pardon the pun again [You’re killing me. -Ed], the AMD cards are only 10.86 inches long. That’s relatively tiny compared with the 40-series partner boards, which can reach up to 14 inches. Asus also added a power connector, with the reference board only requiring two PCIe cables. Theoretically, they are probably rocking slightly higher TDPs than AMD’s cards.

AMD is poised to do some heavy battle with the beleaguered RTX 4080. Nvidia’s GPU is rated at 320W TDP, with both AMD cards landing on either side of that number. The flagship XTX is 355W, while the XT is 300W. Naturally, you can’t draw a straight line between that number and frame rate in games, but it’ll likely be a close call. AMD already has a pricing advantage, which could lead Nvidia to drop the 4080’s price to compete more heavily. Either way, it’s going to be a fantastic holiday for gamers, especially those running 4K panels. That is, assuming one will be able to buy an AMD card at launch.

Continue reading

Intel Launches New Xe Max Mobile GPUs for Entry-Level Content Creators

Intel has launched a new consumer, mobile GPU — but it's got a very specific use-case, at least for now.

MIT Creates Battery-Free Underwater GPS

GPS radio signals dissipate quickly when they hit water, causing a headache for scientific research at sea. The only alternative is to use acoustic systems that chew through batteries. A team from MIT has devised a battery-free tracking technology that could end this annoyance.

Intel Details XPU Strategy, Launches New Server GPU, OneAPI Gold

Intel made a pair of announcements today regarding its OneAPI initiative and the launch of its first server GPU based on Xe graphics.

Nvidia Unveils Ampere A100 80GB GPU With 2TB/s of Memory Bandwidth

Nvidia announced an 80GB Ampere A100 GPU this week, for AI software developers who really need some room to stretch their legs.