Benchmarks: stock versus unlocked

Every same-card stock-vs-unlocked measurement published by the GPU Unlock Ada fork, including the tensor modes that did not change and the FP8 CUTLASS pair that measured 1.0029×.

How these were taken

The RTX 4090 rows come from a register-resident MMA issue-rate loop run at 20,000 iterations and three repetitions per mode, best-of-three reported. The RTX 4070 Ti SUPER rows come from the fork's tensor-modes-comparison.json, 66 SMs, driver 580.178.04, 240 W cap, 20,000 iterations and three repetitions, with all-one inputs across eight independent chains. The FP8 pair is a separate CUTLASS 4.8.1 profiler run on one sm_89 kernel.

GeForce RTX 4090

AD102 · 128 SMs · driver unrecorded in the evidence file

Mode	Stock	Unlocked	Gain
`f16/f16`	325.70 TF/s	331.60 TF/s	1.02×
`f16/f32`	165.60 TF/s	330.80 TF/s	2.00×
`bf16/f32`	165.50 TF/s	330.30 TF/s	2.00×
`s8/s32`	661.60 TF/s	659.50 TF/s	1.00×
`dp4a`	164.50 TF/s	164.10 TF/s	1.00×
`ffma`	79.10 TF/s	79.10 TF/s	1.00×

f16/f16: stock run includes one slow sample (306.3); best-of-three
s8/s32: already at full rate before the unlock
ffma: FP32 was never rate-limited

Source files for this run

GeForce RTX 4070 Ti SUPER

AD103 · 66 SMs · driver 580.178.04

Mode	Stock	Unlocked	Gain
`f16/f32`	94.96 TFLOP/s	188.97 TFLOP/s	1.99×
`tf32`	47.49 TFLOP/s	94.51 TFLOP/s	1.99×
`u4/s32`	754.81 TOP/s	754.68 TOP/s	1.00×

u4/s32: integer path, unaffected

Source files for this run

GeForce RTX 2080 Ti

TU102 · 68 SMs · driver 575.51.03

Mode	Stock	Unlocked	Gain
`f16/f32`	50.30 TFLOP/s	68.30 TFLOP/s	1.36×
`f16/f32`	55.70 TFLOP/s	91.40 TFLOP/s	1.64×
`f16/f32`	53.70 TFLOP/s	81.70 TFLOP/s	1.52×
`f16/f32`	52.80 TFLOP/s	77.90 TFLOP/s	1.48×

f16/f32: M.N.K 1024: 88.4% to 120.0% of the 56.9 TFLOP/s peak
f16/f32: M.N.K 2048: 97.9% to 160.6% of peak
f16/f32: M.N.K 4096: 94.4% to 143.6% of peak
f16/f32: M.N.K 8192: 92.8% to 136.9% of peak

Source files for this run

The FP8 pair that did not move

The fork measured a matched E4M3 FP8 input, FP32 accumulate 4096³ GEMM on the 4070 Ti SUPER with the same CUTLASS profiler binary, one kernel, 10 warmups and 20 profiling iterations, requiring device-reference verification. Both runs passed their reference checks.

Run	ms	GFLOP/s
stock	2.31724	59325.8
unlocked	2.31066	59495.0

RTX 4070 Ti SUPER · cutlass_tensorop_s16832gemm_e4m3_128x128_64x3_tn_align16 · 1.0029×

How to read a ratio of 1.00×

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.