Deep Learning is a dataflow application that demands a dataflow processor. By uniquely applying technology to modeling dataflow applications, Wave eliminates the need for a host and co-processor in the calculations of a neural network, yielding an architecture that scales for any application: from the Edge to the Datacenter.
AI-Native Dataflow Technology
Deep Learning is a Dataflow Application
16K PEs per DPU
Wave’s DPUs (Dataflow Processor Units) pack 16,000 Processor Elements (PEs), to accelerate even the most complex neural network models.
0 CPUs/GPUs REQUIRED
Wave DPUs eliminate the need for CPUs, GPUs, or other co-processors.
An Order of Magnitude Performance over GPUs
Wave DPUs deliver an order of magnitude performance improvement over GPU implementations.
Wave Aquires MIPS Technology
MIPS is an intellectual property licensing business within Wave Computing, providing processor architecture and core IP.
Widely used and backed by an active ecosystem of hardware and software partners.
The latest family of MIPS CPUs offer best-in-class performance, power and area efficiency.
Widely licensed and cost-effective solutions for embedded and multimedia applications.
Highest levels of performance together with clean elegant design.
Want to accelerate your AI project with Wave innovation? Let us help you discover the power of scalable, dataflow technology.LET’S CONNECT
Sign Me Up for Early Access
At Wave, we’re always working on what’s next. Sign up to be the first to learn about, and test, our next generation designs.SIGN UP