SK hynix Debuts Accelerator Card Prototype for Generative AI

SK hynix unveiled and demonstrated a prototype of AiMX1, a generative AI accelerator2 card based on GDDR6-AiM. This happened at the AI Hardware & Edge AI Summit 2023 held Sept. 12–14 at the Santa Clara Marriott, California.

1Accelerator-in-Memory based Accelerator (AiMX): SK hynix’s accelerator card product that specializes in large language models (AI that learns with large amounts of text data such as ChatGPT) using GDDR6-AiM chips.

2Accelerator: A special-purpose hardware device that uses a chip designed specifically for processing and computing information.

Figure 1. SK hynix’s exhibition booth at the AI Hardware & Edge AI Summit 2023

Specifically, the AI Hardware & Edge AI Summit brings together global IT companies and high-profile startups. They shared their developments in artificial intelligence and machine learning. The UK marketing firm Kisaco Research annually hosts the event. This year is SK hynix’s third time participating in the summit.

At the event, the company showcased the prototype of AiMX, an accelerator card that combines multiple GDDR6-AiMs to further enhance performance along with the GDDR6-AIM itself under the slogan of “Boost Your AI: Discover the Power of PIM3 with SK hynix’s AiM4.”

3Processing-In-Memory (PIM): A next-generation technology that adds computational capabilities to semiconductor memories to solve the problem of data movement congestion in AI and big data processing.

4Accelerator in Memory (AiM): SK hynix’s PIM semiconductor product name, which includes GDDR6-AiM.

Figure 2. The prototype AiMX card utilizes multiple GDDR6-AiM chips for enhanced performance

Mainly, AiMX is a low-power, high-speed memory solution capable of handling large amounts of data. It sets to play a key role in the advancement of data-intensive generative AI5 systems. The performance of generative AI improves as it is trained on more data. Thus, it highlights the need for high-performance products that can be applied to an array of generative AI systems.

5Generative AI: AI that learns from large amounts of data to actively generate results based on a user’s specific needs.

Figure 3. Demonstrating a large AI language model with AiMX that utilizes GDDR6-AiM

Moreover, SK hynix demonstrated Meta’s generative AI Open Pretrained Transformer (OPT) 13B model on a server system equipped with the AiMX prototype. Specifically, the AiMX system featuring GDDR6-AiM chips reduces data processing time by more than 10 times compared to systems with GPUs. Meanwhile, it consumes only one-fifth the power. The company’s demonstration piqued the interest of global companies providing AI services by showing that it can deliver higher performance6 than the most recent accelerators.

6Performance is based on the condition that the AiM Control Hub inside the AiMX card is developed as an application-specific integrated circuit (ASIC).

In addition, the company held a session outlining the benefits of AiMX. In a presentation titled “Cost-Effective Generative AI Inference Acceleration using AiM,” Eui-cheol Lim, vice president of the Solution Development division, compared the performance of GPUs and AiMX. Also, Lim discussed the future of next-generation intelligent semiconductor memories.

Figure 4. Eui-cheol Lim, vice president of SK hynix’s Solution Development division, delivers a presentation on AiMX

“SK hynix’s AiMX is a solution that delivers higher performance while consuming less power, and costing less than conventional GPUs,” Lim explained. “We will continue to develop memory technologies that will lead the way in the era of artificial intelligence.”