At Computex, AMD introduced RDNA architecture, which would begin with Navi GPUs. It was said that Vega is here to stay, and yes, they meant it.
AMD Radeon Vega II Duo with two Vega 20 GPUs
This is worlds first dual 7nm GPU graphics card. It features two Vega 20 processors, each with full 64 Compute Units (unlike Radeon VII which only has 60 enabled). The GPUs can carry four stacks of HBM2 memory with up to 32 GB of capacity. This means that the Duo variant will be equipped with 128 CUs (8192 Stream Processors) and 64 GB of HBM2 memory.
AMD and Apple developed a new PCI-Express connector, which supports up to 475W of power. Alongside the new PCI-e connector Radeon Pro Vega II Duo features Infinity Fabric Link capable of carrying 84 GB/s of data between the GPUs. More importantly, the Radeon Vega II Duo features onboard Thunderbolt 3 connector.
This new form factor, which does not require any conventional external power connectors known from desktop PCs such as PEG (PCIe power cable), is called the MPX module.
AMD Radeon Pro Vega II Duo has a maximum theoretical 32-bit floating point computing power of 14.1 TFLOPS per GPU, this means Duo can offer up to 28.2 TFLOPs. This gives us an estimated boost clock of 1.72 GHz.
The new Radeon Pro Vega II will be offered with the new Apple Mac Pro, which will retail for around $35,000 (this is an estimation because pricing for higher-end models has not been confirmed by Apple).
| AMD Radeon Vega 20 Graphics | |||
|---|---|---|---|
| Radeon VII | Radeon Pro Vega II | Radeon Pro Vega II | |
| GPU | 7nm Vega 20 | 7nm Vega 20 | 2x 7nm Vega 20 |
| Stream Processors | |||
| Max FP32 Compute | |||
| Boost Clock | |||
| Bandwidth | |||
| Memory | |||
| Memory Bus | |||
Press Release
New supercharged 7nm AMD Radeon™ Pro Vega II GPUs with high-speed HBM2 memory and AMD Infinity Fabric Link GPU interconnect technology power demanding content creation applications.
AMD (NASDAQ: AMD) today announced that its new AMD Radeon™ Pro Vega II GPUs will be included in the all-new Mac Pro. Built on industry-leading 7nm process technology, AMD Radeon™ Pro Vega II GPUs provide groundbreaking levels of graphics performance for computation-intensive tasks, including rendering, 8K video, video effects, and other high-end content creation workloads.
AMD Radeon™ Pro Vega II GPUs provide exceptional computational performance by harnessing 7nm AMD Radeon Vega family GPUs, ultra-fast High Bandwidth Memory (HBM2), and AMD Infinity Fabric Link GPU interconnect technology that dramatically enhances data-transfer speeds between GPUs. Providing up to 14 TFLOPS of single-precision floating-point (FP32) performance and up to 28 TFLOPS of half-precision floating-point (FP16) performance, AMD Radeon™ Pro Vega II GPUs are optimized for powering demanding professional applications.
“Today’s high-end professional content creation applications are driving an insatiable need for ever increasing levels of processing power and memory,” said Scott Herkelman, corporate vice president and general manager, Radeon Technologies Group at AMD. “Equipped with Radeon™ Pro Vega II GPUs, the new Mac Pro delivers the computational horsepower and memory bandwidth to power ultra-high screen resolutions and help dramatically accelerate compute and content creation workloads, enabling creative professionals to focus on unleashing their creativity and delivering amazing results.”
“AMD continues to develop amazing graphics technologies to accelerate workflows for professionals who rely on DaVinci Resolve for faster color correction and editing,” said Dan May, president, Blackmagic Design. “Radeon Pro Vega II delivers outstanding performance, especially when DaVinci Resolve is put to work with 8K video footage combined with various filters.”
Key capabilities and features of AMD Radeon™ Pro Vega II GPUs include:
Leading-edge compute performance – The AMD Radeon™ Pro Vega II GPU delivers up to 14 TFLOPS of single-precision FP32 performance and up to 28 TFLOPS of half-precision FP16 performance.
Support for Infinity Fabric Link GPU interconnect technology – With up to 84GB/s per direction low-latency peer-to-peer memory access1, the scalable GPU interconnect technology enables GPU-to-GPU communications up to 5X faster than PCIe® Gen 3 interconnect speeds2.
Ultra-fast HBM2 memory – 32GB of high-speed HBM2 memory delivers 1TB/s memory bandwidth, providing the memory capacity and data transfer speeds required by today’s high-resolution, multi-display setups, 8K video, and other demanding content creation workloads.
Source: AMD
