MIG enables several use cases to improve GPU utilization.
It enables multiple clients such as VMs, containers, or processes to run simultaneously while providing error isolation and advanced quality of service (QoS) between these programs.Ī100 is the first GPU that can either scale up to a full GPU with NVLink or scale out with MIG for many users by lowering the per-GPU instance cost. The MIG feature can physically divide a single A100 GPU into multiple GPUs. For more information about the NVIDIA Ampere GPU microarchitecture, see the NVIDIA Ampere Architecture In Depth post.
CUDA 11 offers something for everyone, whether you’re a platform DevOps engineer managing clusters or a software developer writing GPU-accelerated applications. The next few sections discuss the major innovations introduced in NVIDIA A100 and how CUDA 11 enables you to make the most of these capabilities. All of these are used by various CUDA libraries to accelerate HPC and AI applications. The A100 comes equipped with specialized hardware units including third-generation Tensor Cores, more video decoder (NVDEC) units, JPEG decoder and optical flow accelerators.
The SMs in A100 include a larger and faster combined L1 cache and shared memory unit (at 192 KB per SM) to provide 1.5x the aggregate capacity of the Volta V100 GPU. CUDA 11 provides new specialized L2 cache management and residency control APIs on the A100. The 40 MB L2 cache on A100 is almost 7x larger than that of Tesla V100 and provides over 2x the L2 cache-read bandwidth. The A100’s 40 GB (5-site) high-speed, HBM2 memory has a bandwidth of 1.6 TB/sec, which is over 1.7x faster than V100.
CUDA and NVIDIA Ampere microarchitecture GPUsįabricated on the TSMC 7nm N7 manufacturing process, the NVIDIA Ampere GPU microarchitecture includes more streaming multiprocessors (SMs), larger and faster memory, and interconnect bandwidth with third-generation NVLink to deliver massive computational throughput. At the end of this post, there are links to GTC Digital sessions that offer deeper dives into the new CUDA features.
Support for the NVIDIA Ampere GPU architecture, including the new NVIDIA A100 GPU for accelerated scale-up and scale-out of AI and HPC data centers multi-GPU systems with the NVSwitch fabric such as the DGX A100 and HGX A100.
This post offers an overview of the major software features in this release: The A100 GPU has revolutionary hardware capabilities and we’re excited to announce CUDA 11 in conjunction with A100.ĬUDA 11 enables you to leverage the new hardware capabilities to accelerate HPC, genomics, 5G, rendering, deep learning, data analytics, data science, robotics, and many more diverse workloads.ĬUDA 11 is packed full of features-from platform system software to everything that you need to get started and develop GPU-accelerated applications. The new NVIDIA A100 GPU based on the NVIDIA Ampere GPU architecture delivers the greatest generational leap in accelerated computing.