DSP
A fast and economical platform for the intelligent IoT, which delivers on flexibility without sacrificing performance. Enjoy high performance AI, DSP, I/O and control in a single device.
PERIPHERALS
THEATRE / AUDIO
Key features
Feature packed
Feature packedxcore.ai is a unique programmable processor array which features:
- 16 hardware threads (HART) split between 2 multi-threaded processor ‘tiles’
- Each tile is equipped with 512kB of SRAM and an integer vector unit capable of efficient block floating point, enabling every HART to execute a common set of control, DSP, AI and IO instructions.
- A powerful inter‑processor communication infrastructure provides high speed communication between any number of xcore.ai chips.
XMOS provide a comprehensive set of high-level functions such as: PDM interfaces, acoustic echo cancellation, noise suppression, asynchronous sample rate conversion, automatic gain control and many others. These are packaged as reference applications that can be readily modified and extended to match unique system functionality and interface requirements all within a single, cost-effective device.
Flexibility
xcore enables whole DSP systems to be built with the lowest system bill of materials, including significant DSP workloads in both fixed- and floating-point formats.
The platform’s flexibility enables solutions that integrate other key components, for example IO protocols, control algorithms and even AI. Uniquely with xcore, these entire DSP systems can be built using software alone.
Programmability
xcore delivers world‑leading predictable programmability, essential for DSP applications requiring hard real‑time performance.
xcore’s unique architecture ensures that different parts of the system do not interfere with each other, delivering the robustness, low‑latency and guaranteed execution time required by DSP systems, especially those supporting multiple sample rates.
Scalability
Dedicated XMOS links can be used to connect multi-chip systems and seamlessly extend performance.
Performance
xcore.ai 800MHz
- 800 MFLOPS sustained | 1,600 MFLOPS peak
- 98,561 FFTs/s | 11,300 float FFT/s
1,024-Pt Complex FFT (Radix 2)/s - 957M FIR filter taps/s
- 251M IIR filter (per biquad)/s
Our ready made solutions
DSP for Audio Applications
Our Audio DSP platform brings powerful, real-time signal processing to your audio products. From noise suppression and echo cancellation to custom EQ and effects, our flexible DSP solutions let you shape sound with precision. Designed for seamless integration and easy customisation, Audio DSP gives you the tools to deliver clearer calls, richer music, and smarter voice interfaces — all while reducing complexity and accelerating development.
See our audio dsp platformDSP for Voice Applications
- 2-microphone front-end
- Audio pipeline including echo cancelation, interference cancelling and noise suppression
- I2S to USB interface supporting asynchronous sampling rates between 44.1 kHz – 192 kHz
- Bidirectional signal path
See our xcore-voice platformTechnical
| Part Number | Package | IO voltage | IO | External Interfaces | Datasheet | Buy |
|---|---|---|---|---|---|---|
| XU316-1024-QF60A | 60pin QFN (7x7mm) | 1v8 | 34 | USB | DATASHEET | |
| XU316-1024-QF60B | 60pin QFN (7x7mm) | 3v3 | 34 | USB | DATASHEET | |
| XU316-1024-FB265 | 265pin FBGA (14x14mm) | 1V8 / 3V3 | 128 | USB, Single or Dual lane MIPI D-PHY receiver, LPDDR1 | DATASHEET | |
| XU316-1024-TQ128 | 128pin TQFP (14x14mm) | 1V8 / 3V3 | 78 | USB, Single or Dual lane MIPI D-PHY receiver | DATASHEET |
Start your development with the
XCORE.AI MULTICHANNEL
AUDIO BOARD
The xcore.ai multichannel audio board includes support for full and high-speed USB operation, USB Audio Class 2.0 & 1.0, MIDI, HID & DFU classes.
The board integrates four stereo audio DACs and two quad channel audio ADCs supporting eight simultaneous bi-directional audio streams. It also includes electrical and optical interfaces for S/PDIF and MIDI In and Out ports.
An integrated XTAG4 enables debug with JTAG and XTC tools.
Our kit features:
- Eight-channel audio line input: 24 bit, up to 192 kHz sampling
- Eight-channel audio line output: 24 bit, up to 384 kHz sampling
- High-speed USB 2.0 compliant device with low latency
- USB Audio Class 2.0 compliant.
- High-resolution stereo audio playback delivered through PCM up to 384 kHz, 32 bits
- Single ADAT, S/PDIF, and MIDI interface connectors
- Local clocking, asynchronous USB audio transfer and PLL clock recovery for low jitter, high-quality audio capture and playback
- Simultaneous quad stereo record and playback through eight-channel streaming to and from host
- Self-powered or USB bus powered operation
- Integrated XTAG4 debug adaptor
- Source code reference software and integrated suite of development tools
Start your development with the
2-MIC VOICE
DEVELOPMENT KIT
The voice reference design evaluation kit can be used as a Raspberry Pi HAT for integration with example AVS client or used standalone as a USB accessory to a host system.
Our kit features:
- XU316-1024-QF60A-C24 xcore.ai processor
- Raspberry Pi HAT connector
- 2 x Infineon IM69D130 MEMS mics
- 71mm inter-mic spacing
- Microphone mute switch
- Speaker output (Line level)
- USB / I2S host interface support
Developer Resources
| Title | Version | Date | Download |
|---|---|---|---|
| USB Audio Driver Support | 2025-10-03 | HTML | |
| USB Audio User Guide | 9.1.0 | 2025-07-08 | html |
| XU316-1024-TQ128 Datasheet | 2.0.0 | 2025-01-13 | html |
| xcore for DSP One Pager | 1.0 | 2023-10-17 |