Overview
The Akeana 1000 Series of processors is highly configurable and customizable, supporting applications from smart homes and wearables, to automotive ADAS applications.
These processors can be configured with support for 1-, 2-, or 4-way Multi-threading.
The Akeana 1000 Series is optimized for a broad range of applications, available with either an In-Order or Out-of-Order microarchitecture and from single-issue to quad-issue instruction issue width, to provide customers with the range needed for a variety of computation requirements.
The Akeana 1000 Series is the midrange of Akeana’s three processor product lines, offering customers one of the broadest available processor IP portfolios. Start your journey today with one or more of these Akeana processors.
Add On Options Include
- L1 Instruction cache, up to 128 KB
- L1 Data cache, up to 64 KB
- L2 cache, up to 1 MB
- Physical Address width 32 to 39 bits
- Virtual Address width 39, 48, or 57 bits
- Shared, unified Last-Level Cache (LLC), up to 16 MB
- Scalar Cryptographic (Zk) extension
- Hypervisor (H) extension
- Vector (V) extension (64 to 512 bits)
- Vector Cryptographic (Zvk) extension
- Physical Memory Protection (PMP) , up to 64 regions
- TLB up to 2048 entries, 8 ways
- Custom instructions
- Support for 2-way or 4-way multithreaded microarchitecture
Learn more about CPU IP core
Today we present to you the Akeana 1000 Series Processors, a series of High Performance processors IP which is optimized for AI applications and workloads, thus providing a quick AND efficient processing solution for your AI needs.
The demand for high-performance AI computation is reshaping the semiconductor industry, requiring innovative solutions that optimize performance, power efficiency, and flexibility. RISC-V, an open-source instruction set architecture (ISA), has emerged as a key enabler for next-generation AI chips by providing a unified framework for both hardware and software. This open and extensible architecture allows companies to develop customized solutions tailored to specific AI workloads, making it a compelling choice for heterogeneous computing, for lower cost, and power consumption.
This article shares our experience using Google’s FlatBuffers library as a memory subsystem stress test on the Andes AX46MPV RISC-V core.
For the first time in our more than 35-year history, Arm is delivering its own silicon products – extending the Arm Neoverse platform beyond IP and Arm Compute Subsystems (CSS) to give customers greater choice in how they deploy Arm compute – from building custom silicon to integrating platform-level solutions or deploying Arm-designed processors.
The ChiPy DSL is Quadric's Python framework for building complete on-chip pipelines. Using YOLOX-M as a case study, we show how backbone inference, box decoding, and NMS run entirely on the Chimera GPNPU — no host CPU intervention, no DDR round-trips, just Python compiled to silicon.
As part of the new Arm Lumex compute subsystem (CSS) platform, the Arm C1 CPU cluster – the first built on the Armv9.3 architecture – is the next evolution of our highest performing CPU cluster for consumer devices, designed to unleash the full potential of on-device AI and elevate the user experience.
