Marvell OCTEON 10 DPU is a family of data processing units for cloud and carrier data centers.
The Marvell OCTEON 10 DPU is a family of data processing units built for hyperscale cloud, carrier, and enterprise data-center infrastructure. Each device combines Arm server-class cores with in-line hardware accelerators for packet processing, cryptography, and machine-learning inference, so networking and security work runs on the DPU instead of consuming host CPU cycles.
The family includes an integrated high-capacity switch and support for high-speed DDR5, PCIe, and SerDes interfaces. It is aimed at operators building cloud and carrier infrastructure, and it is sold alongside Marvell's unified software development kit.
NVIDIA
BlueField
nvidia.com
Intel
Infrastructure Processing Unit
intel.com
Broadcom
Semiconductor Solutions
broadcom.com
Adds products that compete with one of Marvell OCTEON 10 DPU’s direct competitors but not with Marvell OCTEON 10 DPU itself. They are shaded, and Linked Through names the direct competitor each one competes with.
| Attribute | Marvell OCTEON 10 DPU | BlueField | Infrastructure Processing Unit | Semiconductor Solutions | |
|---|---|---|---|---|---|
| Provider | | | | | |
| Founded | 1995 | 1993 | 1968 | 1961 | |
| Sells To | Enterprise | Consumers, Enterprise | Enterprise | Enterprise | |
| Pricing Model | Recurring, Transactional | Licensing, Product Sales, Subscription | Hardware Sales | Recurring, Transactional | |
| Ownership | Public | Public | Public | Public |
Provider
Founded 1995
Sells To Enterprise
Pricing Model Recurring, Transactional
Ownership Public
Provider
Founded 1993
Sells To Consumers, Enterprise
Pricing Model Licensing, Product Sales, Subscription
Ownership Public
Provider
Founded 1968
Sells To Enterprise
Pricing Model Hardware Sales
Ownership Public
Provider
Founded 1961
Sells To Enterprise
Pricing Model Recurring, Transactional
Ownership Public
AMD Instinct is a family of data-center accelerators for AI and high-performance computing.
AMD Pensando is a data-center infrastructure acceleration platform.
NVIDIA Blackwell is a data-center GPU architecture for generative AI and accelerated computing.
AMD Instinct is a family of data-center accelerators for AI and high-performance computing.
TPU is Google's custom AI accelerator ASIC family delivered through Google Cloud TPU Pods for ML training and inference.
NVIDIA Hopper is a data-center GPU architecture for AI and high-performance computing workloads.