Nvidia ditches Intel, cozies up to AMD with its new DGX A100

Nvidia’s first Ampere hardware is headed for the data center, not the game room.

This morning, everybody found out what CEO Jensen Huang was cooking—an Ampere-powered successor to the Volta-powered DGX-2 deep learning system.

Yesterday, we described mysterious hardware in Huang's kitchen as likely "packing a few Xeon CPUs" in addition to the new successor to the Tesla v100 GPU. Egg's on our face for that one—the new system packs a pair of AMD Epyc 7742 64-core, 128-thread CPUs, along with 1TiB of RAM, a pair of 1.9TiB NVMe SSDs in RAID1 for a boot drive, and up to four 3.8TiB PCIe4.0 NVMe drives in RAID 0 as secondary storage.

Goodbye Intel, hello AMD

Technically, it shouldn't come as too much of a surprise that Nvidia would tap AMD for the CPUs in its flagship machine-learning nodes—Epyc Rome has been kicking Intel's Xeon server CPU line up and down the block for quite a while now. Staying on the technical side of things, Epyc 7742's support for PCIe 4.0 may have been even more important than its high CPU speed and massive core/thread count.

Read 7 remaining paragraphs | Comments

Corona und Videostreaming: Netflix beendet Drosselung der Bitrate, Amazon nicht

Alle Netflix-Abonnenten in Deutschland werden bald wieder alle Inhalte mit voller Bitrate erhalten. Bei Prime Video bleibt es bei der reduzierten Bitrate. Von Ingo Pakalski (Netflix, Apple)

Alle Netflix-Abonnenten in Deutschland werden bald wieder alle Inhalte mit voller Bitrate erhalten. Bei Prime Video bleibt es bei der reduzierten Bitrate. Von Ingo Pakalski (Netflix, Apple)

Zur Aussagekraft von Massentests bei COVID-19

Das Problem zur Aussagekraft von Massentests liegt in der Prävalenz (Krankheitshäufigkeit), die immer noch verhältnismäßig gering ist

Das Problem zur Aussagekraft von Massentests liegt in der Prävalenz (Krankheitshäufigkeit), die immer noch verhältnismäßig gering ist