Stratix® IV FPGAs leverage the 40-nm process node to deliver the highest performance AND the lowest power.
At 40 nm, Stratix IV FPGAs have transistor gate lengths that are 38.5 percent and 11 percent smaller than the 65-nm and 45-nm transistors, respectively. Stratix IV FPGAs further improve performance through the use of strained silicon, which increases electron and hole mobility by up to 30 percent.
35 Percent Faster Than the Nearest Competing FPGAs
Integrating optimal processing techniques and a highly efficient logic structure, Stratix IV FPGAs are, on average, 35 percent faster than the nearest competing devices when comparing the fastest speed grades.
Figure 1 and Table 1 show how you can use this speed advantage to meet your high-performance requirements in slower speed grades while lowering your system costs.
Figure 1. Performance Comparison by Speed Grade
| Table 1. Performance Comparison by Speed Grade | |
| Speed Grade | Stratix IV FPGA Performance Advantage Over Competition |
|---|---|
| Fast | 35 percent faster than nearest competitor |
| Medium | 24 percent faster than nearest competitor |
| Slow | 28 percent faster than nearest competitor |
Complementing the high-performance core, Stratix IV FPGAs provide an unprecedented level of system bandwidth, as shown in Figure 2.
Figure 2. Stratix IV FPGA System Bandwidth
- High-speed transceivers rated up to 8.5 Gbps
- 1,067 Mbps (533 MHz) DDR3 memory interfaces
- 600-MHz digital signal processing (DSP) performance through parallelism with optimal DSP/memory/logic ratio
- 600-MHz TriMatrix memory blocks
- 1.6-Gbps LVDS channels
- 600-MHz core clock speeds
Benchmarking Methodology
All benchmarking data on this page is based on comparing an Altera® FPGA to the equivalent, nearest competing FPGA and using the latest available version of software at the time of analysis.
Altera has a third-party, industry-expert-endorsed performance benchmarking methodology that is used to compare FPGA performance between families from a single FPGA vendor to those of competitive solutions. This ensures a consistent benchmarking environment when testing Altera FPGAs and when comparing them to competitor FPGAs.
- Benchmarking Methodology White Paper (PDF)
- Guidance to Accurately Benchmarking FPGAs White Paper (PDF)
Related Links
- Stratix IV FPGAs: Think AND, not OR
- Stratix IV FPGA Core Fabric Architecture
- Stratix IV vs. Virtex-5 Logic Efficiency
- Stratix IV FPGA ALM Logic Structure's 8-input Fracturable LUT
- Stratix IV: The World's Biggest 40-nm FPGAs
- Stratix IV: The Lowest Power High-End 40-nm FPGA
- OpenCore designs validate increased Stratix III FPGA advantages on performance, utilization, and compile time
