Comments (6)
Hi @avilella - no GPU memory utilisation rate depends on Model, chunk size and batch size but not on read length.
The reason it does not depend on read length is that reads are "chunked" into fixed length segments before being processed by the GPU for performance reasons.
from dorado.
from dorado.
@avilella at the moment (until Multi GPU is fully working) for assigning tasks to GPUs I suggest you use --device "cuda:0"
and export CUDA_VISIBLE_DEVICES=ID
where ID
is the GPU you want to use.
from dorado.
Closing this issue as I believe it's resolved. @avilella please reopen it if you have any more queries.
from dorado.
I kicked of dorado on a simulated [email protected] dataset using an NVIDIA RTX A4000 (16GB VRAM) GPU.
The memory usage with the different --batchsize N
options is shown below:
1 = 1664MiB / 16117MiB
100 = 2466MiB / 16117MiB
1000 = 9615MiB / 16117MiB
1984 (2*(2^10)-(2^6)) = 15930MiB / 16117MiB
So --batchsize 1984
is the optimal for a 16Gb VRAM Nvidia GPU. Full command-line:
dorado basecaller --device cuda:0 --batchsize 2000 --remora-threads 1 /data/ONT/dorado/[email protected] . > calls.sam
On a smaller NVIDIA T1000 GPU with 4GB VRAM, the optimal batchsize was 384 (updated on @vellamike 's comments):
384 (2^9)/2+(2^7) = 3828MiB / 3911MiB
from dorado.
Maximising the utilised VRAM with the biggest possible batch size to increase performance is a good rule of thumb, but not necessarily something which always works. For example it is often the case that good batch sizes are powers of two or integer multiples of powers of two.
from dorado.
Related Issues (20)
- How to apply the 5K 6mA model under a 4K data sampling frequency? HOT 1
- Cannot get Dorado to work on a Jetson AGX HOT 10
- Can a Linux server without a GPU and only a CPU install and run Dorado? HOT 1
- Install error in M1 mac HOT 2
- Inconsistencies in '--no-trim' results HOT 1
- Basecalling speed on M2 pro HOT 1
- A few duplex questions HOT 1
- Call standalone Dorado from minKNOW installation HOT 1
- C++ warnings being treated as errors with GCC 12.3.0 HOT 1
- samplesheet.csv contains invalid column experiment_id HOT 4
- Sample sheet error HOT 4
- Regarding modified basecalling for m6A HOT 4
- Dorado duplex stand alone v 0.6.0 : when the models are in a different location. How to configure dorado to look for models elsewhere? HOT 2
- I have failed to install pod5 HOT 2
- Installation Issue in Nvidia Jetson AGX Orin Developer kit HOT 1
- Using bam files demuxed by Dorado with NanoPlot? HOT 2
- Support for Standalone 5mC and/or 5mCG in Basecalling Model Version 4.3.0 HOT 1
- pod5 files in multiple directories HOT 3
- poly-A estimation and adapter trimming on direct RNAseq data HOT 2
- demultiplex HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dorado.