
Intel
Intel’s slow and steady leak of information about its upcoming Arc GPUs continued last week when the company released final specs for its four A-series desktop graphics cards. As with the laptop GPUs the company announced earlier this year, desktop Arc cards are split between entry-level Arc 3, mid-range Arc 5, and high-end Arc 7 tiers.
The only Arc GPU that has been extensively vetted by independent testers is the entry-level A380, which is also the only one to have had an official US launch (this $140 ASRock Challenger model sold out listed on Newegg, not counting the more expensive cards imported from China). It’s by far the weakest GPU in the line, with just eight Xe cores and ray tracing units from Intel and 6GB of GDDR6 memory on a 96-bit memory bus. Reviews generally show the A380’s business hits with older, budget-focused GPUs like Nvidia’s GTX 1650 or AMD’s RX 6400, depending on the game.

Intel
The other three GPUs are all much more similar. The A580, A750, and A770 have 24, 28, and 32 Xe cores respectively, which increase in clock speed as you go higher. But they all share a 256-bit memory bus and 8GB of GDDR6 RAM (with a 16GB option available for the A770). Intel introduced its own “Limited Edition” versions of the A770 and A750; they share the same basic board and fan design and 225W board power, but the A770 has built-in LEDs, unlike the A750. Intel is presumably leaving the low-end A580 and A380 cards to its edge partners, rather than creating its own versions.
Intel’s tests show the A750 GPU competes with the Nvidia RTX 3060 in DirectX12 and Vulkan games; Going only from the specs on paper, this suggests that the A770 will land somewhere between an RTX 3060 and 3070, while the A580 will perform worse than a 3060 but better than a 3050.
It’s a fairly narrow performance range, with a big gap between low-end and mid-range cards and no offerings for high-end gaming PCs, but it makes sense given that the Alchemist family is said to be based on a pair of GPU dies, with one maxing out at eight Xe cores (the A380) and the other at 32 Xe cores (the 28- and 24-core versions being “binned” versions which shut down faulty or underperforming cores so that the chip itself can still be used). Current GPU lines from Nvidia and AMD typically use at least three or four different GPU dies.

Intel
Making performance comparisons with established Nvidia and AMD GPUs is difficult for Arc GPUs due to driver issues. The company recognized that the performance of older DirectX11 games would not be on par with the performance of games using the low-overhead DirectX12 and Vulkan APIs, and the company relies on code translation for older DirectX9 games rather than to allow GPUs. to run these games natively. And Arc GPU performance suffers significantly if the Resizable BAR feature (also known as ReBar or Smart Access Memory) is not enabled or supported by your motherboard, making Arc GPUs a poor choice for upgrading. from an older PC.
To compound Intel’s launch issues, AMD and Nvidia are already gearing up for next-gen GPU launches. AMD briefly showcased an RDNA3-based GPU at its Ryzen 7000 announcement event last month, while Nvidia’s RTX 4000-series GPUs are expected to be announced from next week. Intel’s next-gen Battlemage GPUs won’t be released until 2023 at the earliest, so these Alchemist GPUs will likely find themselves competing with the RTX 4060 and RX 7600 GPUs soon enough.
Intel said it will price Arc GPUs based on its DirectX11 gaming performance, making its cards more appealing to bargain hunters looking to put together an inexpensive but capable gaming PC. The company just has to launch them first.
List image by Intel
#Intel #releases #Arc #GPU #specs #launch #draws #closer