SANTA CLARA, Calif. – When the NVIDIA Titan RTX launched late last year, many dubbed it the "T-Rex" as it was essentially the most powerful graphics card on earth with 16.3 teraFLOPs of FP32 power. Notebookcheck reports. Continue reading original article
The Military & Aerospace Electronics take:
7 June 2019 -- With the launch of Apple's new Mac Pro yesterday, AMD announced two new graphics processing units (GPUs), the Radeon Pro Vega II and the Radeon Pro Vega II Duo. With a massive 28.3 teraFLOPs of FP32 performance, the Vega II Duo takes the crown from the Titan RTX to become the world's most powerful GPU.
It's been quite sometime since we've seen a dual-GPU card from AMD. The last consumer dual-GPU was the AMD Radeon R9 295X2 in 2014 while workstation users had the option of choosing a Radeon Pro Duo in 2016. The latest Radeon Pro Vega II is based on the same 7-nanometer architecture (Vega 20, GCN 5.1) as the Radeon VII but enables the four control units (CUs) that were disabled in the latter.
So, we now have a total of 64 CUs and 4096 SPs on the Radeon Pro Vega II along with 32 GB of HBM2 VRAM that offers 1 TB/s memory bandwidth. The whole GPU runs at a peak engine clock of 1.7 GHz. Combine two such GPUs on a single PCB and you get the Radeon Pro Vega II Duo.
Related: New Nvidia computing architecture taps GPU, speeds data-intensive processing
Related: Rugged embedded computer that combines CPU and GPU processing introduced by MEN Micro
John Keller, chief editor
Military & Aerospace Electronics
