A naukri.com initiative
VentureBeat
1M
204
Going beyond GPUs: The evolving landscape of AI chips and accelerators
- As the focus of enterprises shifts toward advanced AI workloads, data centers’ traditional CPU-centric servers are being buffed with the integration of new specialized chips or “co-processors.”
- Over the last few years, GPUs, led by Nvidia, have been the go-to choice for co-processors due to their ability to process large volumes of data at unmatched speeds.
- The dominance of GPUs is only expected to grow, with revenues from the category surging 30% annually to $102 billion by 2028.
- Specialized AI processors and accelerators like ASICs, FPGAs, and Neural Processing Units (NPUs) are being built by chipmakers, startups and cloud providers to support select low- to medium-intensive AI workloads.
- AI processors are chips that sit within servers’ CPU ecosystem and focus on specific AI functions. They can prove more efficient than GPUs in terms of cost and power use.
- The selection of AI processors should be based upon the scale and type of the workload to be processed, the data, the likelihood of continued iteration/change and cost and availability needs.
- Globally, with inference jobs on track to grow, the total market of AI hardware, including AI chips, accelerators and GPUs, is estimated to grow 30% annually to touch $138 billion by 2028.
- IBM and Google for instance use multiple GPUs and AI accelerators to provide enterprises with choices to meet the needs of their unique workloads and applications.
- Other AI accelerators are also drawing attention in the market. This includes custom chips built for and by public cloud providers such as Google, AWS and Microsoft but also dedicated products (NPUs in some cases) from startups such as Groq, Graphcore, SambaNova Systems and Cerebras Systems.
- According to experts, it is also important for enterprises to run benchmarks to test for price-performance benefits and ensure that their teams are familiar with the broader software ecosystem that supports the respective AI accelerators.
Read Full Article
12 Likes
For uninterrupted reading, download the app