GoKawiilIndependent Tester Reports AMD Processors Never Output Zero From RNG Instructions
A Brazilian electronics engineer and assembly programmer named Jessé says he has tested two AMD processors extensively and found that the chips' hardware random number generator, accessed via instructions like rdrand and rdseed, has not produced a single zero value in over nine days of continuous testing. He has reported the issue to AMD, which has escalated it internally, though no technical explanation has been provided yet. Jessé also updated his testing application to benchmark RNG speed and support processors lacking the rdseed instruction, noting large performance differences across CPU generations.
GoKawiil's interpretation of the reporting above, not reported fact.
Hardware random number generators are foundational to cryptography, security keys, and secure communications, so any statistical bias—even something as simple as never returning zero—could weaken systems that assume true randomness. If confirmed, this could point to a design flaw or implementation bug in AMD's silicon that affects encryption strength across a wide range of chips. Until AMD issues an official technical response, the scope and real-world security impact of the anomaly remain unclear.
- A tester claims two AMD processors never returned a zero value from RNG instructions like rdrand/rdseed.
- AMD has internally escalated the report but has not yet provided a technical explanation.
- The tester's updated benchmarking tool also revealed large RNG performance differences between processor generations.
Source: board.flatassembler.net, 2026-09-22
Published there as: “AMD's random number generator can't generate a 0?”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.