printf("\033[2J\033[1;1H");

printf("\nHello gpu.cpp!\n");

printf("--------------\n\n");

Context ctx = createContext();

static constexpr size_t N = 10000;

std::array<float, N> inputArr, outputArr;

for (int i = 0; i < N; ++i) {

inputArr[i] = static_cast<float>(i) / 10.0; // dummy input data

}

Tensor input = createTensor(ctx, Shape{N}, kf32, inputArr.data());

Tensor output = createTensor(ctx, Shape{N}, kf32);

std::promise<void> promise;

std::future<void> future = promise.get_future();

Kernel op = createKernel(ctx, {kGelu, 256, kf32},

Bindings{input, output},

/* nWorkgroups */ {cdiv(N, 256), 1, 1});

dispatchKernel(ctx, op, promise);

wait(ctx, future);

toCPU(ctx, output, outputArr.data(), sizeof(outputArr));

for (int i = 0; i < 12; ++i) {

printf(" gelu(%.2f) = %.2f\n", inputArr[i], outputArr[i]);

}

printf(" ...\n\n");

printf("Computed %zu values of GELU(x)\n\n", N);

return 0;