Unlock FP/BF16 instruction issue rate on Nvidia 3000's cards to their professional equivalents
This Linux kernel module combines the CMP unlocker's V67/PLM technique with the pre-driver timing of the UEFI approach. It runs the unlock, writes the speed selectors (SS0 0x88888888, which selects the full BF16 rate, and the 4-bit SS1 0x8 IMLA4) and performs FLR before the unmodified NVIDIA driver binds the card. It is neither a UEFI application nor a patched NVIDIA driver.
The benefit of this early kmod driver is that it does not require manual patching each time nvidia releases a new driver version.
The effect of this unlock is that it doubles the instruction issuing speed of FP/BF16 FMA into FP32 operations on GA102, GA103, GA104 and GA106 cards.
3090 Ti dense 8192³ GEMM at 450 W, five-sample medians with FP32 accumulation:
| Input | Before | After |
|---|---|---|
| FP16 | 87.46 TFLOPS | 118.39 TFLOPS |
| BF16 | 87.50 TFLOPS | 157.41 TFLOPS |
| TF32 | 42.58 TFLOPS | 82.61 TFLOPS |
Results reported by users. The module accepts every GeForce ID listed in
kernel/gpu_unlock/main.c, but the cards below are the ones someone has
reported on. Please add yours with a
compatibility report,
whether it worked or not.
| Chip | Card | PCI ID | Result | BF16 GEMM gain | Reports |
|---|---|---|---|---|---|
| GA102 | RTX 3090 Ti | 10de:2203 |
Unlocked | +68–80% | #1 |
| GA102 | RTX 3090 | 10de:2204 |
Unlocked | +25–67% | #5, #9, #10, #17, #25, #27, #33 |
| GA102 | RTX 3080 Ti 20 GB (OEM, GA102-250) | 10de:2205 |
Unlock completes, BF16 stays at half rate | — | #28 |
| GA102 | RTX 3080 10 GB | 10de:2206 |
Unlocked | +70–73% | #14 |
| GA102 | RTX 3080 20 GB (memory upgrade) | 10de:2206 |
Unlocked | +56–59% | #10, #15 |
| GA104 | RTX 3070 | 10de:2484 |
Unlocked | +73–81% | #10, #12 |
| GA104 | RTX 3070 Ti | 10de:2482 |
Not tested with this module (the same unlock worked from a UEFI port on Windows) | — | #32 |
| GA106 | RTX 3060 12 GB | 10de:2504 |
Unlocked | about +80% | #13, #31 |
| GA103 | any | 10de:2414 |
No reports yet | — | — |
The gains are dense GEMM throughput from each report's own benchmark, so they are not directly comparable. The power limit matters a lot: the lowest figure (+25%) is from cards capped at 225 W.