NVIDIA graphics cards can be accelerated by almost twofold - enthusiasts found hidden potential in RTX 30, RTX 40, and RTX 20 - iXBT.games
Enthusiasts have found a way to almost double the performance of matrix computations on NVIDIA RTX 20, RTX 30, and RTX 40 graphics cards without changing drivers.
The modifications affect matrix computations, which are important for AI, and work with standard drivers while passing CUDA tests.
For the RTX 3090 Ti, accelerated processing of FP/BF16 FMA instructions with FP32 accumulation increased performance from 87.5 to 157.4 TFLOPS, approximately 80%.
A similar trick worked on Ada Lovelace: for the RTX 4090, FP16 tensor core performance increased from 165.6 to 331.6 TFLOPS.
The modification also covers the RTX 20: the RTX 2080 Ti's result increased from 59.9 to 111 TFLOPS.
For local language models, this can speed up work by approximately 33–36%.
How to activate
Activation requires startup at system boot, and the warranty may be voided.
The changes accelerate AI tasks and complex matrix computations, not games.
Related
