Este é o driver nvidia padrão para WSL2?

noob@LAPTOP-DNCQ5AAC:/mnt/d/gatechFall2022/ihpc/lab1fa22/part2$ nvidia-smi
Thu Apr 20 00:04:03 2023       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.100      Driver Version: 528.76       CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  On   | 00000000:01:00.0 Off |                  N/A |
| N/A   41C    P8     2W /  50W |      0MiB /  4096MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A       227      G   /Xwayland                       N/A      |
+-----------------------------------------------------------------------------+

Diz algo como "tenha cuidado para não instalar outro que substitua o padrão" aqui https://docs.nvidia.com/cuda/wsl-user-guide/index.html

Este é meu padrão antes de começar a tentar instalar o cuda novamente em minha máquina com Windows 11? Alguém tem um link para uma boa resposta sobre como instalar o cuda no WSL2?
Talvez eu tenha que pesquisar minhas próprias perguntas, mas lembre-se de que nunca funcionou como esperado e tive que usar o Windows.

A tarefa que desejo executar com o Cuda está abaixo:

/*
My Chatgpt prompt:
"implement helman-jaja list rank where the function signature is "void cudaListRank (long head, const long* next, long* rank, size_t n)" where the first parameter head is the index into array representation of a linked list and points to its head,  the second parameter next is a "next array" that gives the index of the next node in the array representation of a linked list, the third parameter rank is an array holding the rank of each node in the array representation of a linked list and the fourth parameter n is the length of the array representation of a linked list."
The code written by ChatGPT below:
*/

#include <unistd.h>
#include "listutils.h"                        
#include <math.h>
#include <cuda.h>
#include <curand.h>

void cudaListRank(long head, const long* next, long* rank, size_t n) {
    // Allocate memory for the linked list nodes and next array on the device
    long* devNext;
    long* devRank;
    cudaMalloc((void**)&devNext, n * sizeof(long));
    cudaMalloc((void**)&devRank, n * sizeof(long));

    // Copy the input linked list next array from host to device
    cudaMemcpy(devNext, next, n * sizeof(long), cudaMemcpyHostToDevice);

    // Initialize rank array on the device to all 1's
    cudaMemset(devRank, 1, n * sizeof(long));

    // Launch a CUDA kernel that performs the scan phase of Helman-Jaja list rank
    int block_size = 256;
    int num_blocks = (n + block_size - 1) / block_size;
    helmanJajaScan<<<num_blocks, block_size>>>(head, devNext, devRank);

    // Launch another CUDA kernel that performs the increment phase of Helman-Jaja list rank
    helmanJajaIncrement<<<num_blocks, block_size>>>(devNext, devRank);

    // Copy the updated rank array from device to host
    cudaMemcpy(rank, devRank, n * sizeof(long), cudaMemcpyDeviceToHost);

    // Free the allocated memory on the device
    cudaFree(devNext);
    cudaFree(devRank);
}


//more kernels
/*
Note that in helmanJajaScan, we're traversing the linked list one node at a time and accumulating the ranks. In helmanJajaIncrement, we're traversing the list in reverse order and adding the accumulated ranks to each node's rank.

Also note that cudaMemcpyHostToDevice and cudaMemcpyDeviceToHost are used for transferring data between host and device memory. Finally, cudaMalloc and cudaFree are used to allocate and free device memory respectively.
*/
__global__ void helmanJajaScan(long head, const long* next, long* rank) {
    int tid = threadIdx.x + blockIdx.x * blockDim.x;

    // Traverse the linked list
    while (head != -1) {
        long curr = head;
        for (int i = 0; i < tid && curr != -1; i++) {
            curr = next[curr];
        }

        if (curr == -1 || next[curr] == -1) break;

        rank[next[curr]] += rank[curr];

        __syncthreads();
    }
}

__global__ void helmanJajaIncrement(const long* next, long* rank) {
    int tid = threadIdx.x + blockIdx.x * blockDim.x;

    // Traverse the linked list
    while (tid < gridDim.x * blockDim.x) {
        long curr = tid;
        for (int i = 0; i < blockDim.x && curr != -1; i++) {
            curr = next[curr];
        }

        if (curr == -1) break;

        rank[curr] += rank[next[curr]];

        tid += gridDim.x * blockDim.x;
    }
}

Agora, quando tento compilar com um arquivo Make, estou obtendo

noob@LAPTOP-DNCQ5AAC:/mnt/d/gatechFall2022/ihpc/lab1fa22/part2$ make correctness IMPL=hj
nvcc -Iutils -O0 -g -std=c++11 -o student/cuda_hj.o -c student/cuda_hj.cu
make: nvcc: Not a directory
make: *** [Makefile:8: student/cuda_hj.o] Error 127

Também estou vendo sublinhados ondulados em vermelho para as declarações de importação relacionadas a cuda no VSCode, mas não tenho certeza se isso indica se meu WSL-remote-VSCode e o Cuda padrão estão funcionando bem.

Também baixei e tentei instalar dois pacotes cuda diferentes (versões WSL) da Nvidia para instalar, mas nenhum deles deu certo (copiei e colei cada instrução de terminal da página de download):

cuda_12.1.0_530.30.02_linux.run
cuda-repo-wsl-ubuntu-12-1-local_12.1.0-1_amd64.deb