Computex 2019: AMD, Nvidia unveil new chipsets and more

American chipset-makers Nvidia and AMD made loads of announcements on the eve of the global PC technology fair Computex 2019 (May 28-June 1) in Taipei.

AMD unveiled a slew of chipsets for PCs and data center servers, which have set new performance benchmarks in respective fields.

Key announcements by AMD:

“Zen 2” – AMD is bringing new “Zen 2” core, which will power the new generation AMD Ryzen and EPYC processors. Internal tests showed the new processors outranking the historical generational performance, delivering 15% more IPC (Instructions Per Clock). It also features significant design improvements including larger cache sizes and a redesigned floating point engine.

3rd Gen AMD Ryzen desktop family – The new lineup of 3rd Gen Ryzen desktop processors introduces a new category of Ryzen 9 desktop processor with the flagship 12 core/24 thread Ryzen 9 3900X. The family has rounded out with 8 core Ryzen 7 models and 6 core Ryzen 5 models, and all 3rd Gen Ryzen desktop processors are supported by the world’s first PCIe 4.0 readiness (up to 5GB/s data transfer speed).

AMD X570 chipset – It comes with world’s first PCIe 4.0 supported for AM4 (microprocessor socket) offering the broadest ecosystem readiness in AMD to date, with over 50 new motherboard models as well as PCIe 4.0 storage solutions.

RDNA gaming architecture and AMD Radeon RX 5700-series: RDNA, the next foundational gaming architecture designed to drive the future of gaming, delivers incredible performance, power, and memory efficiency in a smaller package compared to the previous generation Graphics Core Next (GCN) architecture.

RDNA will power the upcoming Navi gaming GPU family Navi, based on 7nm Radeon RX 5700-series graphics cards, which feature high-speed GDDR6 memory and support for the PCIe 4.0 interface.

New Navi GPUs will be formally launched in a separate AMD event on June 10.

Datacenter updates – AMD also showcased 2nd Gen AMD EPYC server platform, outperformed two Intel Xeons by more than 2x on the NAMD benchmark.

Furthermore, AMD and Microsoft Azure announced they have achieved previously unobtainable levels of performance for computational fluid dynamics (CFD) using an Azure HB cloud instance running on a 1st Gen AMD EPYC-processor-based system.

Key announcement by Nvidia:
The company announced Nvidia EGX, a new an accelerated computing platform, which boasts low-latency AI that enables companies to perceive, understand and act in real time on continuous streaming data between 5G base stations, warehouses, retail stores, factories and beyond.

Picture credit: Nvidia

Nvidia EGX supports NVIDIA Jetson Nano, which will enable devices to perform one-half trillion operations per second (TOPS) of processing for tasks such as image recognition. It can go several notches up to 10,000 TOPS for real-time speech recognition and other real-time AI tasks via Nvidia T4 servers.

"EGX combines the full range of NVIDIA AI computing technologies with Red Hat OpenShift and NVIDIA Edge Stack together with Mellanox and Cisco security, networking, and storage technologies. This enables companies in the largest industries —telecom, manufacturing, retail, healthcare, and transportation —to quickly stand up state-of-the-art, secure, enterprise-grade AI infrastructures," the company added.

EGX servers are available from global enterprise computing providers ATOS, Cisco, Dell EMC, Fujitsu, Hewlett Packard Enterprise, Inspur, and Lenovo. They are also available from major server and IoT system makers Abaco, Acer, ADLINK, Advantech, ASRock Rack, Asus, and AverMedia.

Get the latest news on new launches, gadget reviews, apps and more on personal technology only on DH Tech.