add a tutorial check_fp16_int8_support

README.md

@@ -21,6 +21,7 @@ All the models are implemented in pytorch or mxnet first, and export a weights f
 - [A guide for quickly getting started, taking lenet5 as a demo.](./tutorials/getting_started.md)
 - [Migrating from TensorRT 4 to 7](./tutorials/migrating_from_tensorrt_4_to_7.md)
 - [How to implement multi-GPU processing, taking YOLOv4 as example](./tutorials/multi_GPU_processing.md)
+- [Check if Your GPU support FP16/INT8](./tutorials/check_fp16_int8_support.md)
 - [Frequently Asked Questions (FAQ)](./tutorials/faq.md)
 
 ## Test Environment

tutorials/check_fp16_int8_support.md

@@ -0,0 +1,14 @@
+# Check if Your GPU Supports FP16/INT8
+
+## 1. check your GPU Compute Capability
+
+visit https://developer.nvidia.com/cuda-gpus#compute and check your GPU compute capability.
+
+For example, GTX1080 is 6.1, Tesla T4 is 7.5.
+
+## 2. check the hardware-precision-matrix
+
+visit https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html#hardware-precision-matrix and check the matrix.
+
+For example, compute capability 6.1 supports FP32 and INT8. 7.5 supports FP32, FP16, INT8, FP16 tensor core, etc.
+