GPU for molecular dynamics (Desmond)

chrhsths1 · October 18, 2021, 7:31am

Description

Hello, i would like to know which GPU can be suitable for running molecular dynamics with Desmond (Supported Platforms | Schrödinger) as a researcher. Some graphics cards are suggested, but they are too expensive and i would like to buy a RTX 3000 series graphics card. Could i use a Ti graphics card (for example GeForce RTX 3060 Ti) or a LHR graphics card?
*Forgive me if this post is not in the correct category, it’s my first post and i am not sure where it should be posted.

Environment

TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

NVES · October 18, 2021, 12:33pm

Hi ,
We recommend you to check the supported features from the below link.

You can refer below link for all the supported operators list.
For unsupported operators, you need to create a custom plugin to support the operation

github.com

onnx/onnx-tensorrt/blob/main/docs/operators.md

<!--- SPDX-License-Identifier: Apache-2.0 -->

# Supported ONNX Operators

TensorRT 8.4 supports operators up to Opset 17. Latest information of ONNX operators can be found [here](https://github.com/onnx/onnx/blob/master/docs/Operators.md)

TensorRT supports the following ONNX data types: DOUBLE, FLOAT32, FLOAT16, INT8, and BOOL

> Note: There is limited support for INT32, INT64, and DOUBLE types. TensorRT will attempt to cast down INT64 to INT32 and DOUBLE down to FLOAT, clamping values to `+-INT_MAX` or `+-FLT_MAX` if necessary.

See below for the support matrix of ONNX operators in ONNX-TensorRT.

## Operator Support Matrix

| Operator                  | Supported  | Supported Types | Restrictions                                                                                                           |
|---------------------------|------------|-----------------|------------------------------------------------------------------------------------------------------------------------|
| Abs                       | Y          | FP32, FP16, INT32 |
| Acos                      | Y          | FP32, FP16 |
| Acosh                     | Y          | FP32, FP16 |
| Add                       | Y          | FP32, FP16, INT32 |

This file has been truncated. show original

Thanks!

chrhsths1 · October 18, 2021, 2:02pm

Actually, to be honest i don’t understand a thing!

spolisetty · October 18, 2021, 5:30pm

Hi @chrhsths1,

This forum talks more abouts updates and issues related TensorRT, we recommend you to please post your concern on related platform to get better help. May be following will be helpful, if it is relevant.
https://www.nvidia.com/en-us/geforce/forums/discover/

Thank you.

Topic		Replies	Views
Does TensorRT support GeForce and Quadro boards TensorRT	1	605	April 6, 2023
nVidia release versions compatibility TensorRT	4	915	September 20, 2023
What Nvidia GPUs can I use for TensorRT execution provider in ONNX runtime? TensorRT	6	1146	October 12, 2021
Comaptibility Of TensorRT with Windows 11 Professional TensorRT	2	2273	December 6, 2021
TensorRT mix precision with supported hard drives TensorRT tensorrt	3	622	April 19, 2021
Tensor Flow with GPU support for GTX 1650 max Q TensorRT	1	813	April 10, 2023
How to monitor tensor cores utilization? TensorRT	5	4454	August 5, 2021
GPU Utilization TensorRT tensorrt	3	700	August 29, 2023
Android for NX module TensorRT board-design	1	350	September 15, 2021
Does tensorrt suport op like "expand_as" or "tile" for dynamic shape input? TensorRT	2	882	November 11, 2021

GPU for molecular dynamics (Desmond)

Description

Environment

Related topics