BF16 → FP32 tensor rate
BF16 multiply with an FP32 accumulator, the shape used by bf16 training stacks.
How this path is measured
Register-resident mma.sync issue rate: all-one inputs, eight independent accumulator chains per warp, 20,000 iterations and three timed repetitions, best of three reported.
What the unlock changes on this path
8 rows over 8 cards. 8 improved by more than 5%, 0 did not; the largest gain is GeForce RTX 4070 SUPER at 2.00×.
| Mode | Stock | Unlocked | Gain | Card |
|---|---|---|---|---|
bf16/f32 | 76.7 | 153.6 TF/s | 2.00× | GeForce RTX 4070 SUPER |
bf16/f32 | 106.9 | 213.6 TF/s | 2.00× | GeForce RTX 4080 |
bf16/f32 | 66.9 | 133.7 TF/s | 2.00× | GeForce RTX 4070 (Gigabyte) |
bf16/f32 | 104.8 | 209.3 TF/s | 2.00× | GeForce RTX 4080 SUPER |
bf16/f32 | 165.5 | 330.3 TF/s | 2.00× | GeForce RTX 4090 |
bf16/f32 | 84.7 | 168.9 TF/s | 1.99× | GeForce RTX 4070 Ti |
bf16/f32 | 18.2 | 36.3 TF/s | 1.99× | GeForce RTX 3050 6GB |
bf16/f32 | 66.3 | 132.0 TF/s | 1.99× | GeForce RTX 4070 (AD103) |
Reading the numbers
A 1.00× row is not a failed unlock. It says that particular path was never rate-limited, so the override had nothing to restore. If you benchmark your own card and see 1.00× on the mode you care about, the unlock may well have applied correctly and simply does not help that workload.