执行程序时提示cuBLAS Error: cublasGemmStridedBatchedEx failed.

【操作步骤&问题现象】

在使用Mindspore-GPU跑程序的时候出现报错：

[CRITICAL] KERNEL(1084,7f5e5ffff700,python3):2022-06-22-19:46:23.385.199 [mindspore/ccsrc/plugin/device/gpu/kernel/math/matmul_gpu_kernel.h:88] Launch] cuBLAS Error: cublasGemmStridedBatchedEx failed. Possible reasons: the GPU is occupied by other processes. | Error Number: 15 CUBLAS_STATUS_NOT_SUPPORTED: The functionality requested is not supported.
The function call stack:
In file /mnt/d/Anaconda3/envs/mindspore/lib/python3.9/site-packages/mindspore/ops/_grad/grad_math_ops.py(277)/            dw = mul2(x, dout)/
Corresponding forward node candidate:
 - In file /mnt/e/课题/dockerfile/alchemy/cybertron/base.py(386)/            context = self.bmm(attention_probs, V)/
   In file /mnt/e/课题/dockerfile/alchemy/cybertron/interaction.py(378)/        v = self.multi_head_attention(/
   In file /mnt/e/课题/dockerfile/alchemy/cybertron/interaction.py(475)/                    xx = self._encoder(xx, neighbours, g_ii,/
   In file /mnt/e/课题/dockerfile/alchemy/cybertron/interaction.py(475)/                    xx = self._encoder(xx, neighbours, g_ii,/
   In file /mnt/e/课题/dockerfile/alchemy/cybertron/model.py(431)/        n_interaction = len(self.interactions)/
   In file /mnt/e/课题/dockerfile/alchemy/cybertron/cybertron.py(568)/        x, xlist = self.model(distances, atom_types, atom_mask,/
   In file /mnt/e/课题/dockerfile/alchemy/cybertron/train.py(468)/        out = self._network(/
   In file /mnt/d/Anaconda3/envs/mindspore/lib/python3.9/site-packages/mindspore/nn/wrap/cell_wrapper.py(373)/        loss = self.network(*inputs)/

【截图信息】

 是cuda版本太低了，换成11.1就可以了