Zynq-7000 AP SoC Performance & Benchmarks
Zynq-7000 AP SoC Performance & Benchmarks
Xilinx Zynq®-7000 SoC devices fuse a fast processor system (PS) based on two 1GHz ARM Cortex™-A9 MPCore processors with the industry’s fastest and most advanced 28nm programmable logic (PL) fabric, a large on-chip memory, multiple high-speed serial transceivers, numerous hardened peripheral IP cores including DDR and Flash memory controllers, and an on-chip analog-processing block that incorporates two 1Msamples/sec A/D converters. Xilinx’s use of the TSMC 28nm HPL process technology has resulted in a product family that offers unmatched performance with low operating power. The ARM Cortex-A9 microprocessors operate 25% faster than the ARM Cortex-A9 MPCore processor cores in competing devices.
Resources
Zynq-7000 SoC Performance Page
Xilinx.com page provides a performance overview and competitive analysis
Software Acceleration for DSP Functions with Zynq-7000 SoC
Video showcases Zynq-7000 SoC and its capability to accelerate software using NEON engines or hardware acceleration
Dhrystone is a synthetic computing benchmark program intended to be representative of system (integer) programming.
The Whetstone benchmark is a synthetic benchmark for evaluating the performance of computers and primarily measures the floating-point arithmetic performance.
The LINPACK benchmarks are a measure of a system's floating point computing power.
Zynq Training
Xilinx Zynq-7000 SoC Solution Center
User Guides
UltraFast Emebedded Design Methodology Guide
Zynq-7000 SoC Technical Reference Manual
Xilinx Software Development Kit (SDK) User Guide
App Notes & Reference Designs & White Papers
Zynq 7000 Partial Reconfiguration Reference Design
Zynq PL Ethernet
Partial Reconfiguration of a Hardware Accelerator on Zynq-7000 SoC Devices
PS and PL Ethernet Performance and Jumbo Frame Support with PL Ethernet in the Zynq-7000 SoC
System Performance Analysis of Zynq-7000 SoC
Boost Software Performance on Zynq-7000 SoC with NEON Application Note
App Note explains how to use NEON to improve software performance and cache efficiency
Zynq-7000 SoC ZC702 Base Targeted Reference Design
The Base TRD showcases various features and capabilities of the Zynq-7000 SoC, including how video image 100X via a Programmable Logic accelerator processing done in software may be accelerated
Zynq-7000 SoC Accelerator for Floating-Point Matrix Multiplication using Vivado HLS
App note describes how to use Vivado High Level Synthesis (HLS) to develop a floating-point matrix multiplication accelerator, demonstrating 20X software acceleration
Zynq-7000 SoC- Where can I find Data Mover examples?
Overview of Zynq-7000 SoC resources for data mover examples
Tech Tips
Zynq-7000 SoC Spectrum Analyzer: Ready to Run Demonstration with 45% acceleration and 6.4x FFT acceleration
Zynq-7000 SoC Spectrum Analyzer part 2 - Accelerating Software - Building ARM NEON Library Tech Tip
Building ARM NEON Library Tech Tip
Zynq-7000 SoC Spectrum Analyzer part 3 - Accelerating Sfotware - Running ARM Library Tests Tech Tip
Running ARM Library Tests Tech Tip
Building and Running an FFT Tech Tip with 45% acceleration
A design example, including source code, showing how an FFT can be accelerated by 6.4X using a Programmable Logic accelerator
Shows the use of multiple DMA blocks and the AXI interconnect multiple funnel processes into the ACP port of the PS
Zynq-7000 SoC - Performance - Ethernet Packet Inspection - Bare Metal - Redirecting Packets to PL Tech Tip
Zynq-7000 SoC - Performance - Ethernet Packet Inspection - Bare Metal - Redirecting Headers to PL and Cache Tech Tip
Zynq-7000 SoC - Performance - Ethernet Packet Inspection - Linux - Redirecting Packets to PL and Cache Tech Tip
Zynq-7000 SoC Benchmark - LMBench Tech Tip
Zynq-7000 SoC Benchmark - SPEC CPU 2000 Tech Tip
Windows Embedded Compact
Related Links
Exclusive Resources
Please contact your local Xilinx sales representative for the following competitive benchmark information:
LMbench
SPEC CPU2000
CoreMark
Netperf
SoC System Performance Zynq®‐7000 SoC vs. Cyclone V SoC FPGA