cudnn

问题 By default, the kernel will use all available SMs of the device (if enough blocks). However, now I have 2 stream with one computational-intense and one memory-intense, and I want to limit the maximal SMs used for 2 stream respectively (after setting the maximal SMs, the kernel in one stream will use up to maximal SMs, like 20SMs for computational-intense and 4SMs for memory-intense), is it possible to do so? (if possible, which API should I use) 回答1: In short, no there is no way to do what

问题 By default, the kernel will use all available SMs of the device (if enough blocks). However, now I have 2 stream with one computational-intense and one memory-intense, and I want to limit the maximal SMs used for 2 stream respectively (after setting the maximal SMs, the kernel in one stream will use up to maximal SMs, like 20SMs for computational-intense and 4SMs for memory-intense), is it possible to do so? (if possible, which API should I use) 回答1: In short, no there is no way to do what

来源： https://stackoverflow.com/questions/55098742/tensorflow-gpu-is-not-identifying-my-gpus

来源： https://stackoverflow.com/questions/64422489/what-are-current-version-compatibility-between-keras-gpu-tensorflow-cudatoolki

来源： https://stackoverflow.com/questions/64422489/what-are-current-version-compatibility-between-keras-gpu-tensorflow-cudatoolki

来源： https://stackoverflow.com/questions/60849474/how-to-download-the-cudnn-straight-from-nvidia-website-to-my-linux-instance-on-g

来源： https://stackoverflow.com/questions/60849474/how-to-download-the-cudnn-straight-from-nvidia-website-to-my-linux-instance-on-g

来源： https://stackoverflow.com/questions/61533291/is-it-still-necessary-to-install-cuda-before-using-the-conda-tensorflow-gpu-pack

来源： https://stackoverflow.com/questions/61533291/is-it-still-necessary-to-install-cuda-before-using-the-conda-tensorflow-gpu-pack

来源： https://stackoverflow.com/questions/63179991/why-does-conda-list-cudnn-have-no-output-after-conda-install-pytorch-torchvis