8e800cedaf
cudaPackages.cuda_compat: ignore missing libs provided at runtime cudaPackages.gpus: Jetson should never build by default cudaPackages.flags: don't build Jetson capabilities by default cudaPackages: re-introduce filter for pre-existing CUDA redist packages in overrides cudaPackages: only recurseIntoAttrs for the latest of each major version cudaPackages.nvccCompatabilities: use GCC 10 through CUDA 11.5 to avoid a GLIBC incompatability cudaPackages.cutensor: acquire libcublas through cudatoolkit prior to 11.4 cudaPackages.cuda_compat: mark as broken on aarch64-linux if not targeting Jetson cudaPackages.cutensor_1_4: fix build cudaPackages: adjust use of autoPatchelfIgnoreMissingDeps cudaPackages.cuda_nvprof: remove unecessary override to add addOpenGLRunpath cudaPackages: use getExe' to avoid patchelf warning about missing meta.mainProgram cudaPackages: fix evaluation with Nix 2.3 cudaPackages: fix platform detection for Jetson/non-Jetson aarch64-linux python3Packages.tensorrt: mark as broken if required packages are missing Note: evaluating the name of the derivation will fail if tensorrt is not present, which is why we wrap the value in `lib.optionalString`. cudaPackages.flags.getNixSystem: add guard based on jetsonTargets cudaPackages.cudnn: use explicit path to patchelf cudaPackages.tensorrt: use explicit path to patchelf
69 lines
1.9 KiB
Plaintext
69 lines
1.9 KiB
Plaintext
#include <cublas_v2.h>
|
|
#include <cuda_runtime.h>
|
|
#include <vector>
|
|
|
|
#include <stdio.h>
|
|
|
|
static inline void check(cudaError_t err, const char *context) {
|
|
if (err != cudaSuccess) {
|
|
fprintf(stderr, "CUDA error at %s: %s\n", context, cudaGetErrorString(err));
|
|
std::exit(EXIT_FAILURE);
|
|
}
|
|
}
|
|
|
|
#define CHECK(x) check(x, #x)
|
|
|
|
__global__ void saxpy(int n, float a, float *x, float *y) {
|
|
int i = blockIdx.x * blockDim.x + threadIdx.x;
|
|
if (i < n)
|
|
y[i] = a * x[i] + y[i];
|
|
}
|
|
|
|
int main(void) {
|
|
setbuf(stderr, NULL);
|
|
fprintf(stderr, "Start\n");
|
|
|
|
int rtVersion, driverVersion;
|
|
CHECK(cudaRuntimeGetVersion(&rtVersion));
|
|
CHECK(cudaDriverGetVersion(&driverVersion));
|
|
|
|
fprintf(stderr, "Runtime version: %d\n", rtVersion);
|
|
fprintf(stderr, "Driver version: %d\n", driverVersion);
|
|
|
|
constexpr int N = 1 << 10;
|
|
|
|
std::vector<float> xHost(N), yHost(N);
|
|
for (int i = 0; i < N; i++) {
|
|
xHost[i] = 1.0f;
|
|
yHost[i] = 2.0f;
|
|
}
|
|
|
|
fprintf(stderr, "Host memory initialized, copying to the device\n");
|
|
fflush(stderr);
|
|
|
|
float *xDevice, *yDevice;
|
|
CHECK(cudaMalloc(&xDevice, N * sizeof(float)));
|
|
CHECK(cudaMalloc(&yDevice, N * sizeof(float)));
|
|
|
|
CHECK(cudaMemcpy(xDevice, xHost.data(), N * sizeof(float),
|
|
cudaMemcpyHostToDevice));
|
|
CHECK(cudaMemcpy(yDevice, yHost.data(), N * sizeof(float),
|
|
cudaMemcpyHostToDevice));
|
|
fprintf(stderr, "Scheduled a cudaMemcpy, calling the kernel\n");
|
|
|
|
saxpy<<<(N + 255) / 256, 256>>>(N, 2.0f, xDevice, yDevice);
|
|
fprintf(stderr, "Scheduled a kernel call\n");
|
|
CHECK(cudaGetLastError());
|
|
|
|
CHECK(cudaMemcpy(yHost.data(), yDevice, N * sizeof(float),
|
|
cudaMemcpyDeviceToHost));
|
|
|
|
float maxError = 0.0f;
|
|
for (int i = 0; i < N; i++)
|
|
maxError = max(maxError, abs(yHost[i] - 4.0f));
|
|
fprintf(stderr, "Max error: %f\n", maxError);
|
|
|
|
CHECK(cudaFree(xDevice));
|
|
CHECK(cudaFree(yDevice));
|
|
}
|