Unverified50% confidenceFactExact time
浮点运算不满足结合律，不同线程束的执行顺序差异会导致数值结果出现细微偏差
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
UnverifiedIn GPU parallel reduction, because floating-point operations do not satisfy the associative law, differences in the execution order of different warps cause deviations in numerical results, which is the root cause of non-determinism.78% similarUnverifiedFloating-point addition does not satisfy the associative law; (a+b)+c and a+(b+c) may yield different results under floating-point precision.76% similarUnverified实际部署中因并行计算的浮点非确定性可能产生细微差异并随链式生成放大74% similarUnverified引导过程若缺乏严格的数学保证，可能引入难以察觉的系统性误差72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/573238API
curl https://kongchang.com/api/v1/knowledge/claims/573238MCP
get_claim(id=573238)