GPU-unlock: FP/BF16 instruction issue rate on Nvidia 3000's cards
- ID
- 39241
- Status
- summarized
- Published
- 24 Oct 2026, 5:58 PM
- Fetched
- 25 Oct 2026, 11:48 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://github.com/Zagitta/gpu-unlock
- Source URL
- https://hnrss.org/best
Summary
- Score
- 8.0
- Created
- 25 Oct 2026, 11:48 AM
- Tags
- Audience
- developersai_ml_learnersvibe_coders
What happened
gpu-unlock 1.0.0 is a Linux kernel module that raises the FP/BF16 instruction issue rate on Nvidia GA102/GA103/GA104/GA106 consumer cards to their professional-equivalent rates by writing speed selectors (SS0 0x88888888 for full BF16, 4-bit SS1 0x8 IMLA4) and doing an FLR before the unmodified NVIDIA driver binds the card. Because it runs pre-driver rather than as a patched driver or UEFI app, it survives driver updates without re-patching. On a 3090 Ti at 450 W the author reports BF16 87.50 → 157.41 TFLOPS, FP16 87.46 → 118.39 TFLOPS and TF32 42.58 → 82.61 TFLOPS; user reports show +25–81% BF16 GEMM gains on most 3090/3080/3070 variants, but one RTX 3080 Ti OEM card (10de:2205) completes the unlock and stays at half rate.
Why it matters
If you run local fine-tuning or inference on a used RTX 3090/3080/3070, this roughly doubles BF16 GEMM throughput for free, which changes the price-per-TFLOP maths against renting cloud GPUs — but you must check your exact PCI ID against the compatibility table first (at least one GA102 card reports no gain), budget for ~450 W board power, and accept that a kernel-level unlock of a consumer card is unsupported and may sit against the vendor's terms.
Discussion angle
Run the numbers live: at the reported BF16 jump on a 3090 Ti, how many months of rented cloud GPU time does a used 3090 plus this mod pay back — and would you risk an unsupported kernel module on the box that runs your training jobs?