# GPU utilization is low **URL:** \ **Category:** User discussions\ **Created:** [July 8, 2022, 6:28am UTC](https://gromacs.bioexcel.eu/t/gpu-utilization-is-low/4437 "2022-07-08T06:28:02Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![pd97](https://avatars.discourse-cdn.com/v4/letter/p/b9bd4f/32.png) [@pd97](https://gromacs.bioexcel.eu/u/pd97)\ **Post date:** [July 8, 2022, 6:28am UTC](https://gromacs.bioexcel.eu/t/gpu-utilization-is-low/4437/1 "2022-07-08T06:28:02Z")
GROMACS version: 2022.1 GROMACS modification: no Here post your question My GPU utilization is less in some simulations i.e around 6%. Gromacs has been integrated with Cuda even in single run the GPU utilization is low ---
**Author:** ![jalemkul](https://dub1.discourse-cdn.com/flex017/user_avatar/gromacs.bioexcel.eu/jalemkul/32/18_2.png) [@jalemkul](https://gromacs.bioexcel.eu/u/jalemkul)\ **Post date:** [July 8, 2022, 10:10am UTC](https://gromacs.bioexcel.eu/t/gpu-utilization-is-low/4437/2 "2022-07-08T10:10:00Z")
Not every simulation demands full use of a GPU. Low usage indicates your system is rather small and will not use all available resources. ---
**Author:** ![pd97](https://avatars.discourse-cdn.com/v4/letter/p/b9bd4f/32.png) [@pd97](https://gromacs.bioexcel.eu/u/pd97)\ **Post date:** [July 21, 2022, 9:43am UTC](https://gromacs.bioexcel.eu/t/gpu-utilization-is-low/4437/3 "2022-07-21T09:43:16Z")
The system contains about 47000 solvate atoms with protein containing about 10500 atoms which makes the system to a total of around 57000 atoms. Is this a small system? my gromacs version details are: GROMACS version: 2021.6 Precision: mixed Memory model: 64 bit MPI library: thread\_mpi OpenMP support: enabled (GMX\_OPENMP\_MAX\_THREADS = 64) GPU support: CUDA SIMD instructions: AVX2\_256 FFT library: fftw-3.3.8-sse2-avx-avx2-avx2\_128 RDTSCP usage: enabled TNG support: enabled Hwloc support: disabled Tracing support: disabled C compiler: /usr/bin/cc GNU 9.4.0 C compiler flags: -mavx2 -mfma -Wno-missing-field-initializers -fexcess-precision=fast -funroll-all-loops -O3 -DNDEBUG C++ compiler: /usr/bin/c++ GNU 9.4.0 C++ compiler flags: -mavx2 -mfma -Wno-missing-field-initializers -fexcess-precision=fast -funroll-all-loops -fopenmp -O3 -DNDEBUG CUDA compiler: /usr/local/cuda/bin/nvcc nvcc: NVIDIA (R) Cuda compiler driver;Copyright (c) 2005-2022 NVIDIA Corporation;Built on Tue\_May\_\_3\_18:49:52\_PDT\_2022;Cuda compilation tools, release 11.7, V11.7.64;Build cuda\_11.7.r11.7/compiler.31294372\_0 CUDA compiler flags:-std=c++17;-gencode;arch=compute\_35,code=sm\_35;-gencode;arch=compute\_37,code=sm\_37;-gencode;arch=compute\_50,code=sm\_50;-gencode;arch=compute\_52,code=sm\_52;-gencode;arch=compute\_60,code=sm\_60;-gencode;arch=compute\_61,code=sm\_61;-gencode;arch=compute\_70,code=sm\_70;-gencode;arch=compute\_75,code=sm\_75;-gencode;arch=compute\_80,code=sm\_80;-Wno-deprecated-gpu-targets;-gencode;arch=compute\_86,code=sm\_86;-gencode;arch=compute\_35,code=compute\_35;-gencode;arch=compute\_53,code=compute\_53;-gencode;arch=compute\_80,code=compute\_80;-use\_fast\_math;-D\_FORCE\_INLINES;-mavx2 -mfma -Wno-missing-field-initializers -fexcess-precision=fast -funroll-all-loops -fopenmp -O3 -DNDEBUG CUDA driver: 11.70 CUDA runtime: 11.70 I tried reinstalling another version but got the same result GPU: NVIDIA RTX A2000 12GB CPU: 11 gen core i7 with 16 cores on running nvidia-smi while running simulation Thu Jul 21 15:03:00 2022 ±----------------------------------------------------------------------------+ | NVIDIA-SMI 515.48.07 Driver Version: 515.48.07 CUDA Version: 11.7 | |-------------------------------±---------------------±---------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 NVIDIA RTX A200… On | 00000000:01:00.0 On | Off | | 33% 60C P2 26W / 70W | 651MiB / 12282MiB | 7% Default | | | | N/A | ±------------------------------±---------------------±---------------------+ ±----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 1358 G /usr/lib/xorg/Xorg 39MiB | | 0 N/A N/A 2038 G /usr/lib/xorg/Xorg 162MiB | | 0 N/A N/A 2167 G /usr/bin/gnome-shell 54MiB | | 0 N/A N/A 3470 G /usr/lib/firefox/firefox 182MiB | | 0 N/A N/A 72974 C gmx 201MiB | | 0 N/A N/A 72998 G /usr/bin/nvidia-settings 0MiB | ±----------------------------------------------------------------------------+ the speed of run Core t (s) Wall t (s) (%) Time: 43446.268 2715.392 1600.0 45:15 (ns/day) (hour/ns) Performance: 3.182 7.543 even if I give commands to take gpu it goes max to 8-9% of gpu usage and for a system of about 20000 atoms it does good usage of gpu (around 70 %) ---
**Author:** ![amarye23](https://avatars.discourse-cdn.com/v4/letter/a/b5e925/32.png) [@amarye23](https://gromacs.bioexcel.eu/u/amarye23)\ **Post date:** [August 11, 2023, 5:59am UTC](https://gromacs.bioexcel.eu/t/gpu-utilization-is-low/4437/4 "2023-08-11T05:59:49Z")
I have used your tutorial (Free Energy Calculations: Methane in Water). I have this problem too, when I ran mdrun… How to use full GPU @jalemkul ---
**Author:** ![XYT](https://dub1.discourse-cdn.com/flex017/user_avatar/gromacs.bioexcel.eu/xyt/32/3546_2.png) [@XYT](https://gromacs.bioexcel.eu/u/XYT)\ **Post date:** [July 18, 2024, 4:37am UTC](https://gromacs.bioexcel.eu/t/gpu-utilization-is-low/4437/5 "2024-07-18T04:37:03Z")
I am also experiencing this problem, have you solved your problem yet?