Research2h ago
FLOPs Fail To Predict AI Execution Time
A new replication study on arXiv challenges the use of Floating Point Operations (FLOPs) as a proxy for computational cost. Researchers found that layers with identical FLOP counts vary in execution time due to differing parallelization efficiencies. This discrepancy renders traditional efficiency formulas unreliable on modern hardware. Practitioners should prioritize actual wall-clock time over theoretical FLOPs.