NVIDIA (NVDA +1.73%) introduced TITAN V, what it calls "the world's most powerful graphics processing unit (GPU) for the PC," on Thursday evening at the annual NIPS (Neural Information Processing Systems) conference. This monster graphics card isn't targeted at gamers, however, but at developers working in the artificial intelligence and high-performance computing fields.
While NVIDIA's computer gaming business still accounts for the bulk of its revenue, it's been making strong inroads into artificial intelligence (AI) and high-performance computing (HPC) in recent years. Last week's surprise new product launch should help propel the GPU specialist further ahead in these spaces.
Here's what investors should know.
Image source: NVIDIA.
TITAN V turns "PC into AI supercomputer"
TITAN V is aimed at developers, including researchers and scientists, who want to use their PCs to do work in AI, deep learning, and HPC. (Deep learning is a category of AI that basically trains a machine to think like a human.) NVIDIA touts that the graphics card, which is driven by its newest GPU architecture, Volta, "transforms [the] PC into [an] AI supercomputer."
TITAN V's 21.1 billion transistors deliver 110 teraflops of raw horsepower, or more than 9 times that of its predecessor, Pascal-based TITAN Xp, and "extreme energy efficiency," according to the company's press release. TITAN Xp was also made as a compute card, though it's been adopted by some gamers as a high-end gaming card. It launched just eight months ago and the company's Pascal GPU architecture is only about one-and-a-half years old, making TITAN V's nine-fold jump in performance and doubling of energy efficiency particularly impressive.
"Our vision for Volta was to push the outer limits of high performance computing and AI. We broke new ground with its new processor architecture, instructions, numerical formats, memory architecture and processor links," said CEO Jensen Huang in the press release. "With TITAN V, we are putting Volta into the hands of researchers and scientists all over the world. I can't wait to see their breakthrough discoveries."
NVIDIA is a fabless chipmaker -– which means it subcontracts out all its manufacturing. Taiwan Semiconductor Manufacturing Company is fabricating TITAN V using its 12-nanometer FFN [FinFET NVIDIA] high-performance manufacturing process customized for NVIDIA.
Buyers of TITAN V get free access to GPU-optimized AI, deep learning, and HPC software on NVIDIA GPU Cloud. The $3,000 TITAN V is now available on NVIDIA's online store in participating countries. There's a limit of two graphics cards per customer.
TITAN V graphics card. Image source: NVIDIA.
TITAN V should tighten NVIDIA's grip on AI chip space
The TITAN V graphics card is the second product that NVIDIA has launched based on its Volta GPU architecture, which it unveiled last May and calls "the world's most advanced GPU architecture." Late in the second quarter, NVIDIA began shipping its Tesla V100 platform for data centers, and fully ramped production of this product in the third quarter.
NVIDIA's Tesla V100 has met with great success. All of the world's major internet companies and cloud-service providers are upgrading their data centers from NVIDIA Pascal-based systems to Volta-based ones. These companies include Amazon, Google, Facebook, IBM, and Microsoft, and the big Chinese players, Alibaba, Baidu, and Tencent. Major server makers are also incorporating Tesla V100 into their products.
NVIDIA's data center has been posting triple-digit year-over-year quarterly revenue growth over the last year-and-a-half, driven largely by the rapid adoption of the company's GPU-based approach to deep learning and high-performance computing. In the third quarter of fiscal 2018, NVIDIA's data center revenue jumped 109% from the year-ago quarter, driving the company's overall revenue and adjusted earnings per share (EPS) growth of 32% and 41%, respectively.
NVIDIA is riding high in AI, but investors need to keep their eyes on competitors, particularly Intel. The chip giant recently hired Advanced Micro Devices' former head of graphics and has said it plans to enter the discrete GPU space -- a market dominated by NVIDIA, with AMD currently the only other player in the space.
