Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minutePC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11In Intel’s 2021-era 5G O-RU benchmark, the tested Agilex FPGA closed timing 15% to 20% faster on average than the tested Xilinx Versal device, while using an average 5% smaller logic footprint, according to Intel. Agilex met the benchmark’s 614.40 MHz targets for FFT & CP− and IFFT & CP+, and its 491.52 MHz targets for the other tested modules. The tested Versal missed 614.40 MHz across the functions and missed 491.52 MHz for DUC & CFR. These are vendor-reported results for a specific design suite, devices, and 2021 tool flow—not a universal performance ranking or a power-efficiency verdict.
What did Intel’s benchmark measure?
Intel compared FPGA implementations of 5G radio-unit (O-RU) signal-processing designs. The study included almost 60 finite impulse response (FIR) designs spanning channel and half-band filters, plus a broader set of modules: FFT & CP−, IFFT & CP+, DDC, DUC & CFR, and PRACH. Intel’s headline figures describe average timing closure and average logic footprint across the comparison; they should not be read as results for every module or every Agilex and Versal product.
Timing closure indicates whether a design can meet its target clock frequency after implementation. A higher achieved frequency can matter when a design has a demanding timing requirement, but it does not alone capture power, system-level throughput, resource use across all device resources, or total cost.
What were the reported performance results?
Average timing and logic footprint
Intel reports that Agilex closed timing 15% to 20% faster on average than the tested Versal device. Intel also reports an average 5% smaller logic footprint for Agilex. Both are Intel’s results from its own benchmark suite; the figures are not an independent industry-wide comparison.
#1 Best Overall
- FPGA Evaluation Platform: DE25-Standard Development Kit designed for evaluation of Intel Agilex 5E FPGA (A5ED013BB32AE4SR1) for advanced programmable logic applications
- Development and Education Focus: Comprehensive development board from Terasic's DE Series, ideal for learning, prototyping, and testing FPGA-based designs and SoC implementations
- Rich Connectivity Options: Features multiple USB ports, Ethernet, audio jacks (pink, blue, green), GPIO expansion headers, and various interfaces for versatile project development
- Interactive Components: Equipped with onboard buttons, switches, LED displays, and indicators enabling hands-on experimentation and debugging of digital logic designs
- Professional Grade Hardware: Robust construction weighing 2.425 pounds with high-quality PCB design, providing a stable platform for complex FPGA development projects
5G timing targets and module results
Intel used two target frequencies: 614.40 MHz and 491.52 MHz. In the benchmark summary, Agilex met 614.40 MHz for FFT & CP− and IFFT & CP+, and met 491.52 MHz for the other tested modules. Intel says the tested Versal failed to reach 614.40 MHz for all functions and also missed 491.52 MHz for DUC & CFR.
The targets reflect sampling relationships cited for the 5G designs: 491.52 MHz is four times 122.88 MHz, and 614.40 MHz is five times 122.88 MHz. They are benchmark requirements, not guaranteed operating frequencies for every design built on either product family.
Rank #2
- FPGA Development Platform: Atum A5 Agilex 5 E-Series SoC FPGA development board featuring the A5ED065B chip for advanced programmable logic applications
- Complete Kit: Includes development board, USB and power cables, power supply adapter, and accessories for immediate setup and evaluation
- Connectivity Options: Equipped with FMC+ and MIPI (CSI/CSI-2/DSI/DSI-2) interconnect systems for flexible peripheral and camera interface integration
- Compact Design: Board measures 6.3 inches x 6.1 inches (160 mm x 155 mm), providing a space-efficient platform for FPGA and MCU/MPU SoC development
- USB Interface: Features USB connectivity for easy programming, debugging, and communication with host computer systems
Versal DUC & CFR optimization results
For the Versal DUC & CFR module, Intel reports these maximum frequencies (FMAX) at optimization levels 0 through 3:
| Optimization level | Intel-reported Versal FMAX | Compared with 491.52 MHz target |
|---|---|---|
| 0 | 343 MHz | Below target |
| 1 | 445 MHz | Below target |
| 2 | 474 MHz | Below target |
| 3 | 482 MHz | Below target |
Intel also reports 372.2 MHz for Versal in its complete O-RU design after optimization. A separate attempt using a mid-speed-grade device reached 499.62 MHz. That latter result is a distinct configuration and should not be substituted for the complete-design figure or treated as the result for every Versal device.
Rank #3
- Arty A7 comes in two FPGA variants: Arty A7-35T features Xilinx XC7A35TICSG324-1L. Arty A7-100T features the larger Xilinx XC7A100TCSG324-1.
- Internal clock speeds exceeding 450MHz, On-chip analog-to-digital converter (XADC), Programmable over JTAG and Quad-SPI Flash
- 256MB DDR3L with a 16-bit bus @ 667MHz, 16MB Quad-SPI Flash, USB-JTAG Programming circuitry, Powered from USB or any 7V-15V source
- 10/100 Mbps Ethernet, USB-UART Bridge
- 4 Switches, 4 Buttons, 1 Reset Button, 4 LEDs, 4 RGB LEDs, 4 Pmod connectors, shield connector
How controlled was the comparison?
The vendors used separate FPGA toolchains on the same stated server and operating-system setup. A shared host helps control the computing environment, but the comparison remains a vendor benchmark using each vendor’s tools and flows; it is not an independent laboratory test.
| Benchmark element | Agilex flow | Versal flow |
|---|---|---|
| FPGA design tools | Quartus Prime 21.3, DSP Builder 21.3, and Quartus IP | Vivado 2021.1, Model Composer 2021.1, and Vivado IP |
| MATLAB | MATLAB R2020b, 64-bit | |
| Host system | Dell PowerEdge R630; Intel Xeon E5-2699 v4 family processor; 256 GB RAM | |
| Operating system | CentOS Linux 7 | |
Because timing closure depends on design details, implementation settings, tool versions, device selection, and speed grade, the published averages are best treated as evidence about this particular 2021-era flow. They do not establish how a current tool release or a different design will perform.
Rank #4
- Altera Cyclone IV FPGA includes 6,000 Logic Elements with two clock multipliers. The Cyclone IV FPGA is the perfect balance of inexpensive cost versus plentiful logic cells, 20KBytes of SRAM, and General Purpose Input/Output pins. This is a great board to learn how to program FPGA's.
- Built in programmer cable allows configuring the FPGA with a single USB-C cable. The DPL can be powered from the USB cable or from the Barrel Connector. A separate JTAG header can also be used to program the FPGA using a compatible USB Blaster cable.
- 6x6 LED Array allows character and animations to be displayed at ultra fast speed. LED blocks can be individually turned on/off to allow LED signals to be used as I/O's
- 70 Inputs/Outputs originating at the FPGA are available at Stackable Headers organized around the edge of the board. The user can configure these I/O's using the FPGA project code.
- The DPL contains two oscillators, 66MHz and 100MHz. The 66MHz oscillator is used to provide clocking for the EPT ActiveHost USB communications core. The 100MHz oscillator can be used by the user clocked up using one of the onboard Clock-DLL modules.
Does the result mean Agilex is always faster than Versal?
No. It supports a narrower conclusion: in Intel’s tested 5G O-RU suite and stated tool flow, Agilex had the reported average timing and logic-footprint advantages, and the tested Versal missed several listed timing targets. It does not prove that every Agilex part beats every Versal part, or that Agilex is the better choice for a workload that uses different device features.
AMD’s counterpoint addresses a different problem: a projected 7 nm Versal VC1902 versus a 10 nm Intel Agilex AGF027 for a 64-transmit/receive, 200 MHz-plus massive-MIMO beamformer. AMD attributes the comparison’s compute-density and power case to Versal AI Engines, and its analysis uses power-estimation assumptions. Its metric and workload differ from Intel’s FIR and IP-module timing study, so the two sets of vendor claims cannot be combined into one direct winner or a conclusion about performance per watt for Intel’s benchmark.
Best Value
- Designed for students and beginners looking to understand Digital Logic, fundamentals of FPGAs
- Features the Xilinx Artix 7 FPGA compatible with Vivado Design Suite WebPACK Edition (free download available from Xilinx)
- On board user interfaces include 16 user switches, 16 LEDs, 5 user pushbuttons, and a
- Expansion opportunities with four Pmod ports including 3 standard 12-pin Pmod ports and 1 dual
- Does NOT ship with micro USB cable
Versal is a heterogeneous architecture that can combine programmable fabric with features such as hard IP, AI Engines, RF converters, expanded DSP, and HBM options. Whether those resources help depends on the design and how it uses them; the Intel O-RU timing results do not evaluate every such use case.
How should a design team compare the families?
Use the Intel results as a reason to test the exact workload, not as a substitute for that test. For a decision tied to a clock target, begin with the same functions, target frequencies, and implementation goals you expect in production, then compare results on the candidate devices and speed grades.
Quick Recap
- Timing closure and FMAX: Check each critical module against its actual target, rather than relying only on a suite-wide average.
- Resource use: Compare logic and DSP utilization, memory needs, and routing pressure for the complete design—not just the reported logic-footprint average.
- Architecture fit: Determine whether the workload benefits from FPGA fabric, hard IP, AI Engines, RF converters, or HBM, and include the supporting system components in the evaluation.
- Power: Measure or estimate both devices for the same workload, operating conditions, and system boundary. Intel’s timing benchmark does not establish which option consumes less power.
- Tool flow and speed grade: Record tool versions, optimization settings, device variant, and speed grade. These are part of the result, not incidental details.
- System economics: Compare current availability, total implementation effort, and full system cost for the intended region and schedule; the benchmark does not establish current prices or availability.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
