The data centers of today have shifted from a focus on single thread performance to performance at rack scale with performance/watt, performance/$ and overall TCO being the key drivers to deployment. These data centers are making use of servers that are customized for specific workloads. The applications running on these servers are either based on open source software or controlled by the customers who deploy them. Marvell’s ThunderX2® server processor is a leading example of this evolution in the server market with deployments spanning across the cloud and HPC market segments with major customers like Microsoft Azure and the Astra Top 500 Supercomputer installation at Sandia National Laboratories.
We continue to make progress on our roadmap with our third generation Arm® based server processor, ThunderX3™. ThunderX3 is purpose-built for the most demanding workloads in today’s cloud and HPC markets. Utilizing a small die size, ThunderX3 delivers high performance, power efficiency, memory bandwidth and the low memory latency for target cloud and HPC workloads.
Fabricated using the TSMC 7P process, the ThunderX3 processor features up to 96-cores with 4-threads/core delivering a total compute power of 384 threads/socket. The memory interface supports 8-channels of DDR4-3200 with 2 DIMMs/channel. The IO expansion offers 64 lanes of PCIe Gen 4.0 with 16 controllers. The processor supports both single and dual socket configurations. For floating point operations, ThunderX3 features four 128-bit SIMD (Neon) units per core. The device is fully SBSA/SBBR compliant and provides enterprise class RAS and virtualization capabilities. Platforms based on ThunderX3 will sample to customers in mid-year calendar 2020.
Microarchitectural improvements in ThunderX3 provide an overall IPC performance improvement greater than 25% over ThunderX2. This increase along with the increase in the core and DDR frequencies provide an overall gain over 60% in single thread performance versus the previous generation. At the socket level, ThunderX3 provides over 3x higher socket level integer performance and over 5x socket level floating point performance over ThunderX2.
ThunderX3 target markets continue to be specific workloads within the cloud computing and high-performance computing markets where our differentiation delivers strong performance per $ and performance per watt benefits to end customers. In addition, we also enable native Arm workloads such as Android gaming in the cloud. The segments we are focused on constitute approximately 30% of the overall server processor market.
Our target cloud workloads such as big data, databases, media streaming, web tier, elastic search and cloud storage are highly parallel in nature. ThunderX3 features 4 thread simultaneous multithreading (SMT) which enables significant throughput improvements for these workloads. HPC workloads such as EDA and CAE also benefit from multithreading. ThunderX3 is highly power efficient and can maintain higher frequency while operating in floating point-intensive workloads. This capability combined with multiple single instruction, multiple data (SIMD) units and best-in-class memory bandwidth provides a very good performance advantage for target HPC workloads in the areas of quantum physics, quantum chemistry, computational fluid dynamics, genomics, and oil and gas workloads.
The ThunderX3 device is also ideally suited for running native Arm applications that currently deploy on mobile phones and Arm end points as containers or virtual machines in the cloud or at the edge. This enables a variety of emerging use cases such as Android gaming in the cloud, Android and Arm software/application development in the cloud. Marvell has collaborated with NVIDIA in integrating industry-leading GPUs for both HPC and gaming.
Marvell has established a leadership role in the Arm-based server segment with proven performance, large scale production deployments in some of the most demanding environments and a vibrant partner ecosystem that continues to grow. ThunderX3 is another exciting chapter in this journey and we look forward to sharing more details in the coming months.