We still do not know if Nvidia will finally be able to buy ARM, but what we do know is that today the English company announced its new ARMv9 architecture, promising a 30 percent performance improvement over ARMv8. In addition, security improvements are added, to which is added evolution of the Mali graphics that will integrate RayTracing and Variable Rate Shading to improve mobile gameplay.
Today, ARM introduced the ARMv9 architecture in response to the global demand for ubiquitous specialized processing with increasingly capable security and artificial intelligence (AI). ARMv9 is the first new ARM architecture in a decade, building on the success of ARMv8, which today drives the best performance per watt anywhere computing occurs.
"As we look to a future that will be defined by AI, we must lay the foundation for cutting-edge computing that is ready to address the unique challenges to come," said Simon Segars, CEO of ARM.
"ARMv9 is the answer. It will be at the forefront of the next 300 billion ARM-based chips driven by demand for pervasive, powerful, and specialized processing based on the economics, design freedom, and accessibility of computing. general-purpose."
The number of ARM-based chips continues to accelerate, with more than 100 billion devices distributed in the last five years. At the current rate, 100% of the world's shared data will soon be processed in ARM, whether at the endpoint, on data networks or in the cloud. This ubiquity comes with ARM's responsibility to deliver more security and performance, along with other new features in ARMv9. ARMv9's new capabilities will accelerate the shift from general-purpose to more specialized computing across all applications, as AI, the Internet of Things (IoT) and 5G gain momentum globally.
Over the past five years, ARM designs have increased CPU performance annually at a faster rate than the industry. ARM will continue this momentum in the ARMv9 generation, with expected CPU performance increases of more than 30% in the next two generations of infrastructure and mobile CPUs.
However, as the industry moves from general-purpose computing to ubiquitous specialized processing, the annual performance gains of double-digit CPUs are not enough. In addition to enhancing specialized processing, ARM's Total Compute design methodology will accelerate overall computing performance through system-level hardware and software-focused optimizations and performance increases for use cases.
By applying Total Compute's design principles across its entire IP portfolio of automotive, customer, infrastructure, and IoT solutions, ARMv9's system-level technologies will encompass the entire IP solution, as well as enhancing individual IPs. Additionally, ARM is developing several technologies to increase cache frequency, bandwidth, and size, and reduce memory latency to maximize the performance of ARMv9-based CPUs.
Many ARM partners spoke out on this announcement, but unsurprisingly, we're only interested in what Nvidia says :
"Nvidia sees tremendous opportunities to bring the transformative power of AI deeper into games, autonomous vehicles, enterprise data centers, and embedded devices. Through our ongoing collaboration with ARM, we look forward to using ARMv9 to deliver a broad range of previously unimaginable computing possibilities, "said Brian Kelleher, senior vice president of hardware engineering at Nvidia.
0 Comments