Versatile, Ultra-Low-Power DSP for Audio, Voice, Vision, and AI
Smallest, ultra-low-energy DSP for always-on sensor fusion, always-listening voice trigger, and Bluetooth/BLE codecs The Cadence®…
Overview
Ultra-low-power always-on audio, voice, imaging, and AI inferencing
The Cadence Tensilica HiFi 1s DSP provides three benefits. First, it supports auto-vectorization by compiler to eliminate the need for hand-optimization, thereby opening it to every embedded programmer. Second, it enhances the always-on AI capability to allow higher-performance ML algorithms to run on an ultra-low power DSP. Third, it adds imaging ISA to support lightweight always-on vision processing.
Auto-vectorization support unburdens the programmer from expert-level hand-optimization, opening the HiFi 1s DSP to a vast pool of non-DSP programmers, lowering development costs, and accelerating time to market. The expanded AI and imaging ISA allow lightweight vision and machine learning applications to run at ultra-low power levels. Double-precision ISA helps modern audio programs run efficiently.
|
Feature |
HiFi 1s |
|
|---|---|---|
|
Load Units |
1 |
|
|
VLIW Slots |
2 |
|
|
Scalar Operations |
2 slots |
|
|
Accumulator Width |
64-bit |
|
|
Auto-Vectorization |
Yes |
|
|
Fixed Pt MACs per Cycle |
32x32 |
1 |
|
32x16 |
2 |
|
|
16x16 |
4 |
|
|
8x16 |
8 |
|
|
8x8 |
8 |
|
|
SP/HP FPU (integrated, optional) |
2x4-way/2x8-way |
|
|
DP FPU (integrated, optional) |
Scalar |
|
|
Imaging/Vision ISA |
Yes |
|
|
Expanded Instructions for NN |
Yes |
|
|
Arithmetic decoding |
Yes |
|
|
AVS (Huffman and bitstream operation) |
Yes |
|
|
Coremark |
5.25 |
|
Key features
Small Battery-Efficient DSP for Always-On Audio, Vision, and AI/ML
- AI acceleration with 8 8x8 and 8x16 MACs and dedicated ISA
- Imaging ISA and 8 8-bit (and 8x16) MACs for lightweight vision applications
- Double-precision acceleration hardware for audio and vision math functions
- Auto-vectorization support for porting efficiency and fast TTM
Block Diagram
Benefits
Auto-Vectorization
Enables the compiler to automatically vectorize data arrays to utilize the SIMD structure of HiFi 1s DSP, eliminates the need for hand-optimization
Expanded AI and Base Platform Performance
Dedicated MACs and ISA enhancing ML/AI and upgraded base platform to LX8, allowing richer applications to run at ultra-low power levels
Lightweight Imaging and Vision
Imaging targeted ISA and MACs for always-on lightweight vision applications to run standalone or in conjunction with a Vision DSP
Double-Precision Floating-Point
Greatly accelerates double-precision math functions found in audio and voice code, obviating the need to tradeoff precision with range
Specifications
Identity
Files
Note: some files may require an NDA depending on provider policy.
Provider
Learn more about DSP Core IP core
Wireless 5G BTS Need Super DSP core... CEVA XC-12
CEVA-X1 DSP Core Targets Cellular IoT Opportunities
Oxford Digital Offers Small Audio DSP Core With Graphical Programming
icyflex: an ultra-low power DSP core for portable applications
FPGA configures DSP core in imaging app
Frequently asked questions about DSP Core IP cores
What is Versatile, Ultra-Low-Power DSP for Audio, Voice, Vision, and AI?
Versatile, Ultra-Low-Power DSP for Audio, Voice, Vision, and AI is a DSP Core IP core from Cadence Design Systems, Inc. listed on Semi IP Hub.
How should engineers evaluate this DSP Core?
Engineers should review the overview, key features, supported foundries and nodes, maturity, deliverables, and provider information before shortlisting this DSP Core IP.
Can this semiconductor IP be compared with similar products?
Yes. Buyers can compare this product with similar semiconductor IP cores or IP families based on category, provider, process options, and structured technical specifications.