Many readers will be familiar with Stan Lee’s oft-quoted dictum from Marvel’s Spider-Man series: “With great power comes great responsibility.”
Now consider, from the perspective of a defense and aerospace high-performance system designer, this extrapolation of Lee’s platitude:
“Power cannot simply be enjoyed for its privileges alone, but necessarily makes its holders responsible both for what they choose to do with it, and for what they fail to do with it.”
In the context of 100Gbps technology for the VPX ecosystem, simply stating that a module or system supports 100Gbps is, by itself, insufficient for ensuring the full benefits of the claim. If a vendor’s datasheet for a VPX plug-in card (PIC) or system states 100Gbps support but is unable to fully utilize the potential of this high-speed connectivity, that claim, while perhaps technically accurate at some sub-level, overstates the product’s ability to deliver the full benefits, without system bottlenecks, that 100Gbps promises.
At face value, a vendor’s claim to support 100Gbps technology implies 2.5x faster <something> compared to 40Gbps technology and 10x faster <something> compared to 10Gbps technology. In an ideal world, the mathematical relationship between the numbers 100 and 40 will result in 2.5x better performance. Likewise, 100 to 10 should yield a 10x performance increase. Unfortunately, the real world does not work like that.
A 16-core laptop processor does not make a person able to work 4x faster when editing documents compared to their previous 4-core laptop. Increasing one’s home Internet speed from 50 Mbps to 150 Mbps will not result in Amazon web pages loading 3x quicker. Neither will connecting a computer at 10Gbps to a corporate network result in application file saves that are 10x quicker than a 1Gbps connection.
High-performance embedded module and system designers must understand the technical considerations required to fully realize the true benefits of 100G technology.
Log in and download the white paper.
