Intel offers Gaudi
Product
Intel Gaudi is a data-center AI accelerator product family.
- Currently Offered
Intel Gaudi is a data-center AI accelerator product family.
Intel Gaudi accelerators are designed for deep learning training and inference in data-center environments.
They are positioned as alternatives to NVIDIA AI accelerators for large-scale generative AI and computer vision workloads.
NVIDIA Blackwell is a data-center GPU architecture for generative AI and accelerated computing.
Purpose-built AI supercomputers integrating GPUs, CPUs, networking, and software for enterprise training and inference.
Modular reference platform letting server makers build NVLink-connected GPU systems for hyperscale AI and HPC.
NVIDIA Hopper is a data-center GPU architecture for AI and high-performance computing workloads.
NVIDIA B200 GPU for high-performance AI training and inference.
NVIDIA H100 is a data-center GPU for large AI model training and inference.
AMD Instinct is a family of data-center accelerators for AI and high-performance computing.
Trainium is AWS's purpose-built AI accelerator chip family for training and inference of large generative models.
World's largest AI chip: 4T transistors, 125 petaflops on one wafer.
Rack-mounted AI inference system integrating proven compute IP with photonic interconnect and large, high-bandwidth memory.
Maverick-2 is NextSilicon's runtime-reconfigurable dataflow accelerator for high-performance computing and AI workloads.
IBM Power Systems are enterprise servers built on POWER processors for mission-critical Linux, AIX, and IBM i workloads.
Tenstorrent scale-out server family for production AI training and inference.
Wafer-scale AI supercomputer in mini-fridge form with cluster-scale power.
PowerEdge XE9680 is Dell's 6U GPU-dense server for AI/ML supporting up to eight NVIDIA, AMD, or Intel accelerators.
AMD Instinct is a family of data-center accelerators for AI and high-performance computing.
Arm-based data-center CPU paired with NVIDIA GPUs for AI, scientific computing, and accelerated workloads.
AMD Pensando is a data-center infrastructure acceleration platform.
Trainium is AWS's purpose-built AI accelerator chip family for training and inference of large generative models.
TPU is Google's custom AI accelerator ASIC family delivered through Google Cloud TPU Pods for ML training and inference.
World's largest AI chip: 4T transistors, 125 petaflops on one wafer.
Rack-mounted AI inference system integrating proven compute IP with photonic interconnect and large, high-bandwidth memory.
Maverick-2 is NextSilicon's runtime-reconfigurable dataflow accelerator for high-performance computing and AI workloads.
MatX One is a high-throughput chip for large language model training and inference.
IBM Power Systems are enterprise servers built on POWER processors for mission-critical Linux, AIX, and IBM i workloads.
Tenstorrent scale-out server family for production AI training and inference.
Wafer-scale AI supercomputer in mini-fridge form with cluster-scale power.
PowerEdge XE9680 is Dell's 6U GPU-dense server for AI/ML supporting up to eight NVIDIA, AMD, or Intel accelerators.