Saturday, August 8, 2026
DarkSubscribe
AI Infrastructure · News & Analysis
HomeChips & HardwareReport
Chips & Hardware · Report

AMD launches Vega GPU and Epyc CPU product lines targeting datacenters and AI workloads.

AMD's dual-architecture approach (CPU+GPU) offers integrated platform alternative to Nvidia-centric stacks, increasing AI infrastructure competition.
Trade pressSlicast · October 25, 2017 · Global · Source: fortune.com
importance 80

Advanced Micro Devices CEO Lisa Su showcased Project 47 at the SIGGRAPH conference in Los Angeles, demonstrating AMD's push into high-performance computing. The supercomputer, housed in a rack slightly taller than the MIT-trained Ph.D. CEO herself, crammed 20 of AMD's newest Epyc microprocessor chips inside along with 80 graphics processing units based on the company's new Vega design and 10 terabytes of memory. The system could perform 1 petaflop of calculations per second—a one followed by 15 zeros worth of calculations per second—at a price point substantially below traditional supercomputing systems.

This petaflop performance aligns with the fastest and priciest supercomputers in the world from 2009 and would rank just outside of the top 100 today, underscoring the rapid pace of progress in chip design over the past few years, particularly for graphics processors. GPU adoption has accelerated dramatically as the biggest cloud data center companies, including Amazon (AMZN) and Microsoft (MSFT), fill up more racks with GPUs to support the kinds of artificial intelligence and machine learning tasks that thrive on graphics processing architecture.

Nvidia's Jensen Huang, a fellow Taiwanese-born CEO like Su, has captured the bulk of the new cloud GPU market so far. However, AMD just started shipping its newest Vega graphics chips in volume in the third quarter, the company revealed on Tuesday in its third quarter results. Along with Epyc, the server CPU that started shipping earlier this year, these chips represent the results of Su's years-long effort to remake AMD's entire lineup with higher performing, modern designs. While Nvidia has a big head start and offers popular proprietary software tools alongside its chips, Su remains optimistic that AMD can win significant additional business in the data center market.

One strategic advantage for AMD is that while Nvidia pitches GPUs and Intel (INTC) is selling CPUs, only AMD has leading products in both segments. "We see them separately and together of some systems," Su said this week. "It's a fast growing segment of the market, and we're very underrepresented in share, so we see that continuing to grow." Some cloud servers will use Epyc and Vega together, just like in the Project 47 supercomputer, positioning AMD to capture share from customers seeking integrated solutions.

Read the original
AMD launches Vega GPU and Epyc CPU product… · Slicast