Zynq UltraScale+ MPSoC
Heterogeneous Multiprocessing Platform for Broad Range of Embedded Applications
Scalable Portfolio of Adaptable MPSoCs
Zynq® UltraScale+™ MPSoC devices provide 64-bit processor scalability while combining real-time control with soft and hard engines for graphics, video, waveform, and packet processing. Built on a common real-time processor and programmable logic equipped platform, three distinct variants include dual application processor (CG) devices, quad application processor and GPU (EG) devices, and video codec (EV) devices, creating unlimited possibilities for applications such as 5G Wireless, Next-generation ADAS, and Industrial Internet-of-Things.
Zynq UltraScale+ CG
Dual-core Entry Point to Heterogeneous Processing
- Dual Arm® Cortex®-A53
- Dual Arm Cortex-R5F
- 16nm FinFET+ Programmable Logic
Zynq UltraScale+ EG
Broadest Device Range for Next-Generation Applications
- Quad Arm Cortex-A53
- Dual Arm Cortex-R5F
- 16nm FinFET+ Programmable Logic
- Arm Mali™-400MP2
Zynq UltraScale+ EV
Video Codec Enabled for Multimedia and Embedded Vision
- Quad Arm Cortex-A53
- Dual Arm Cortex-R5F
- 16nm FinFET+ Programmable Logic
- Arm Mali-400MP2
- H.264/H.265 Video Codec
Heterogeneous Processing for Whole Application Acceleration
Multiple processing engines enable the optimization of functions across an entire application, with programmable hardware providing further performance and safety handling
Ultra-Compact Packages for Unmatched Compute Density
InFO devices are 60% smaller, 70% thinner, with better thermal dissipation and higher signal integrity, all without sacrificing the processing power of the Zynq UltraScale+ MPSoC
Integrated H.264 / H.265 Video Codec
Zynq UltraScale+ EV devices include a video codec capable of low latency simultaneous encode and decode up to 4K resolution at 60 frames per second
Deep Learning Processing Unit for AI / ML
Free scalable computation engine optimized for convolutional neural networks, supporting common frameworks, leveraging large repositories of pre-trained AI models
Adaptable Memory Hierarchy Removes Memory Bottlenecks
Vast distributed on-chip memory: LUTRAM, Block RAM, UltraRAM, L3 Cache, minimizing memory access latency and allowing accelerators or co-processors to achieve maximum performance. Localized memory also allows full function isolation necessary for safety critical applications
Multiple Domains for Granular Power Management
Flexible architecture capable of reducing power consumption by eliminating static power of unused blocks, for up to 30% less static power consumption. Operate as low as 180nW in full Deep Sleep mode for maximum power savings when idle
Zynq UltraScale+ CG
Dual-core Entry Point to Heterogeneous Processing
Zynq UltraScale+ EG
Broadest Device Range for Next-Generation Applications
Zynq UltraScale+ EV
Video Codec Enabled for Multimedia and Embedded Vision
CG Devices
Processing System Features
| ZU1CG | ZU2CG | ZU3CG | ZU4CG | ZU5CG | ZU6CG | ZU7CG | ZU9CG | |
| Application Processing Unit | Dual-core Arm® Cortex®-A53 MPCore™ up to 1.3GHz | |||||||
| Real-Time Processing Unit | Dual-core Arm Cortex-R5F MPCore up to 533MHz | |||||||
| Dynamic Memory Interface | DDR4, LPDDR4, DDR3, DDR3L, LPDDR3 | |||||||
| High-Speed Peripherals | PCIe® Gen2, USB3.0, SATA 3.1, DisplayPort, Gigabit Ethernet | |||||||
Programmable Logic
| ZU1CG | ZU2CG | ZU3CG | ZU4CG | ZU5CG | ZU6CG | ZU7CG | ZU9CG | |
| System Logic Cells (K) | 81 | 103 | 154 | 192 | 256 | 469 | 504 | 600 |
| Memory (Mb) | 3.8 | 5.3 | 7.6 | 18.5 | 23.1 | 25.1 | 38.0 | 32.1 |
| DSP Slices | 216 | 240 | 360 | 728 | 1,248 | 1,973 | 1,728 | 2,520 |
| 16.3 Gb/s Transceiver Count | - | - | - | 16 |
16 | 24 |
24 | 24 |
| PCI Express Gen 3x16 | - | - | - | 2 | 2 | - | 2 | - |
| Maximum I/O Pins | 180 | 252 | 252 | 252 | 252 | 328 | 464 | 328 |
EG Devices
Processing System Features
| ZU1EG | ZU2EG | ZU3EG | ZU4EG | ZU5EG | ZU6EG | ZU7EG | ZU9EG | ZU11EG | ZU15EG | ZU17EG | ZU19EG | |
| Application Processing Unit | Quad-core Arm® Cortex®-A53 MPCore™ up to 1.5GHz | |||||||||||
| Real-Time Processing Unit | Dual-core Arm Cortex-R5F MPCore™ up to 600MHz | |||||||||||
| Graphics Processing Unit | Arm Mali™-400 MP2 up to 667MHz | |||||||||||
| Dynamic Memory Interface | DDR4, LPDDR4, DDR3, DDR3L, LPDDR3 | |||||||||||
| High-Speed Peripherals | PCIe® Gen2, USB3.0, SATA 3.1, DisplayPort, Gigabit Ethernet | |||||||||||
Programmable Logic
| ZU1EG | ZU2EG | ZU3EG | ZU4EG | ZU5EG | ZU6EG | ZU7EG | ZU9EG | ZU11EG | ZU15EG | ZU17EG | ZU19EG | |
| System Logic Cells (K) | 81 | 103 | 154 | 192 | 256 | 469 | 504 | 600 | 653 | 747 | 926 | 1,143 |
| Memory (Mb) | 3.8 | 5.3 | 7.6 | 18.5 | 23.1 | 25.1 | 38.0 | 32.1 | 43.6 | 57.7 | 56.7 | 70.6 |
| DSP Slices | 216 | 240 | 360 | 728 | 1,248 | 1,973 | 1,728 | 2,520 | 2,928 | 3,528 | 1,590 | 1,968 |
| 16.3 Gb/s Transceivers | - | - | - | 16 | 16 | 24 | 24 | 24 | 32 | 24 | 44 | 44 |
| 32.75 Gb/s Transceivers | - | - | - | - | - | - | - | - | 16 | - | 28 | 28 |
| PCI Express Gen 3x16 | - | - | - | 2 | 2 | - | 2 | - | 4 | - | 4 | 5 |
| Maximum I/O Pins | 180 | 252 | 252 | 252 | 252 | 328 | 464 | 328 | 512 | 328 | 668 | 668 |
EV Devices
Processing System Features
| ZU4EV | ZU5EV | ZU7EV | |
| Application Processing Unit | Quad-core Arm® Cortex®-A53 MPCore™ up to 1.5GHz | ||
| Real-Time Processing Unit | Dual-core Arm Cortex-R5F MPCore™ up to 600MHz | ||
| Graphics Processing Unit | Arm Mali™-400 MP2 up to 667MHz | ||
| Video Codec Unit | Supports H.264 / H.265 | ||
| Dynamic Memory Interface | DDR4, LPDDR4, DDR3, DDR3L, LPDDR3 | ||
| High-Speed Peripherals | PCIe® Gen2, USB3.0, SATA 3.1, DisplayPort, Gigabit Ethernet | ||
Programmable Logic
| ZU4EV | ZU5EV | ZU7EV | |
| System Logic Cells (K) | 192 | 256 | 504 |
| Memory (Mb) | 18.5 | 23.1 | 38.0 |
| DSP Slices | 728 | 1,248 | 1,728 |
| Video Code Unit (VCU) | 1 | 1 | 1 |
| Maximum I/O Pins | 252 | 252 | 464 |
Documentation
Featured Videos
All Videos
Adaptable Advantage Blog
-
- MicroZed Chronicles: Cocotb and AXI
- Sep 23, 2022
-
- MicroZed Chronicles: Getting Started with Cocotb
- Sep 09, 2022