TVM 与 MLIR 有何不同？
[英]How TVM is different from MLIR?
问题描述
As per my understanding, both TVM and MLIR are used as compiler infrastructure for deep learning neural networks.
据我了解，TVM 和 MLIR 都用作深度学习神经网络的编译器基础设施。 Is my understanding correct?.我的理解正确吗？
And Which would be better if we are building a compiler for custom hardware that runs deep learning inferences?如果我们正在为运行深度学习推理的定制硬件构建编译器，哪个会更好？
1 个解决方案
解决方案1
0 已采纳 2021-09-07 12:37:12
I found this discussion helpful: https://discuss.tvm.apache.org/t/google-lasted-work-mlir-primer/1721我发现这个讨论很有帮助： https://discuss.tvm.apache.org/t/google-lasted-work-mlir-primer/1721
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
Tensorflow：没有启用任何 MLIR 优化通道（注册 1） - Tensorflow: None of the MLIR optimization passes are enabled (registered 1)
UNET 与简单的自动编码器有何不同？ - How UNET is different from simple autoencoders?
TVM库中relay.build_module.build()后图和库参数的差异 - Difference in graph and library parameters after relay.build_module.build() in the TVM library
如何从python中的不同文件夹和子文件夹加载图像 - how to load images from different folders and subfolders in python
如何从不同时期的 Mask R-CNN 开始训练？ - How to start training from different epoch Mask R-CNN?
如何根据来自不同数据集的变量预测数据？ - How to forecast data based on variables from different datasets?
如何使用image_summary在Tensorflow中查看来自不同批次的图像？ - How to use image_summary to view images from different batches in Tensorflow?
卷积结果与caffe不同 - convolution result different from that of caffe
从两种不同的输入模式连接两个不同形状的张量 - Concatenate two tensors of different shape from two different input modalities
Pytorch Batchnorm 层与 Keras Batchnorm 不同 - Pytorch Batchnorm layer different from Keras Batchnorm
相关标签