Samsung quietly posts exynos 2600 details with major cpu and artificial intelligence upgrades

Samsung has quietly published full specifications for its exynos 2600 mobile chip, confirming a new cpu cluster, upgraded xclipse 960 gpu, and a dedicated artificial intelligence engine. The 2 nm design also brings faster memory, storage, camera, and display support while introducing new security and video features.

Samsung has quietly unveiled its exynos 2600 system on chip on its website, confirming most of the details that had leaked a day earlier. The mobile processor is built around a heterogeneous cpu cluster that includes a 3.8 GHz C1-Ultra prime core, three C1-Prox3 3.25 GHz performance cores and six power efficient C1-Prox6 2.75 GHz cores, all based on the arm v9.3 architecture. The exynos 2600 will be fabricated using Samsung foundry’s 2 nm GAA process and its low power design and the package will use something Samsung calls heat path block which is using a High-k EMC material which is said to improve heat dissipation. The exynos 2600 should deliver 39 percent better CPU performance compared to its predecessor according to Samsung.

Graphics are handled by Samsung’s xclipse 960 gpu, which the company says supports ray tracing and an exynos neural super sampling feature for artificial intelligence powered frame generation and upscaling, and Samsung claims twice the compute performance of its predecessor here. In addition to the gpu capabilities, there will also be a separate artificial intelligence engine with a 32K MAC NPU and post-quantum cryptography support, positioning the chip for both on-device machine learning workloads and enhanced security. Samsung is not promoting the launch with its usual marketing push, but the specification sheet signals a flagship-class part aimed at future premium devices.

On the platform side, the exynos 2600 includes support for LPDDR5X memory and UFS 4.1 storage, aligning it with current high end smartphones. The display controller can drive up to 4K or WQUXGA resolutions with a refresh rate of up to 120 Hz, and the media engine supports native 8K 30p video encoding and 8K 60p video decoding. The image signal processor can handle up to 320 MP single camera resolution and the ability to shoot pictures at 108 MP at 30 FPS, with additional artificial intelligence features that Samsung calls DVNR or deep learning video noise reduction. Codec support covers AV1, VP9 and Samsung’s own APV, but there is no mention of H.266, and Samsung hints that more details about the exynos 2600 will likely be shared at CES early next year.

56

Impact Score

Firefox 148 adds artificial intelligence killswitch after user backlash

Mozilla is adding a persistent artificial intelligence killswitch to Firefox 148 after strong community backlash against plans for an artificial intelligence first browser experience. Users will be able to disable individual artificial intelligence features or shut them all off with a single control.

Western Digital unveils high bandwidth hard drives with 4x I/O performance

Western Digital is introducing new high bandwidth hard drives that combine multi-head read and write techniques with a dual actuator design to significantly boost I/O performance while preserving capacity. The roadmap targets up to 100 TB HDDs with throughput that aims to rival traditional QLC SSDs on price and density.

Nvidia and Dassault deepen partnership to build industrial virtual twins

Nvidia and Dassault Systèmes are expanding their long-running partnership to build shared industrial Artificial Intelligence world models that merge physics-based virtual twins with accelerated computing. The companies aim to shift engineering, manufacturing and scientific work into real-time, simulation-driven workflows powered by Artificial Intelligence companions.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.