TECH SUPPLIER Mar 2021 - Market Presentation - Doc # US47556821
Performance-Intensive Computing (PIC) Market Trends
This IDC Market Presentation highlights performance-intensive computing (PIC) market trends. The demand for computational power worldwide is driven by an insatiable appetite to reduce the time to value from data sets that are increasing in a nonlinear manner. Computational approaches are therefore constantly evolving so that the resulting architecture can get ahead of the data growth curve and deliver timely insights before the data expires or becomes stale.
IDC defines performance-intensive computing as the process of performing large-scale mathematically intensive computations, commonly used in artificial intelligence (AI), modeling and simulation (M&S), and big data and analytics (BDA) use cases. It is also used for processing large volumes of data or executing complex instruction sets in the fastest way possible.
Performance-intensive computing does not dictate specific computing and data management architecture, nor does it specify computational approaches. However, certain kinds of approaches such as accelerated computing and massively parallel computing have naturally gained prominence, given the inherent limitations of central processing units (CPUs). Even so, this has not stopped silicon vendors from making processors, CPUs, with features like high core counts or high I/O and memory bandwidth to make them suitable for performance-intensive use cases.
In this presentation, IDC has found that businesses are investing significantly in performance-intensive computing for a wide range of use cases; a major component of PIC is massively parallel computing (MPC). The presentation shows that:
- Acceleration is an important aspect of PIC, and it is moving to the cloud.
- Businesses are investing in massively parallel computing (MPC) for many use different cases.
- High-performance file storage and liquid cooling are becoming increasingly critical.