我在并发 CUDA 方面遇到了一些问题。看一下附加的图像。内核在标记点启动，即 0.395 秒。然后是一些绿色的 CpuWork。最后，调用了 cudaDeviceSynchronize。在 CpuWork 之前启动的内核不会在同步调用之前启动。理想情况下，它应该与 CPU 工作并行运行。
void KdTreeGpu::traceRaysOnGpuAsync(int firstRayIndex, int numRays, int rank, int buffer)
{
int per_block = 128;
int num_blocks = numRays/per_block + (numRays%per_block==0?0:1);
Ray* rays = &this->deviceRayPtr[firstRayIndex];
int* outputHitPanelIds = &this->deviceHitPanelIdPtr[firstRayIndex];
kdTreeTraversal<<<num_blocks, per_block, 0>>>(sceneBoundingBox, rays, deviceNodesPtr, deviceTrianglesListPtr,
firstRayIndex, numRays, rank, rootNodeIndex,
deviceTHitPtr, outputHitPanelIds, deviceReflectionPtr);
CUDA_VALIDATE(cudaMemcpyAsync(resultHitDistances[buffer], deviceTHitPtr, numRays*sizeof(double), cudaMemcpyDeviceToHost));
CUDA_VALIDATE(cudaMemcpyAsync(resultHitPanelIds[buffer], outputHitPanelIds, numRays*sizeof(int), cudaMemcpyDeviceToHost));
CUDA_VALIDATE(cudaMemcpyAsync(resultReflections[buffer], deviceReflectionPtr, numRays*sizeof(Vector3), cudaMemcpyDeviceToHost));
}
内存副本是异步的。结果缓冲区是这样分配的
unsigned int flag = cudaHostAllocPortable;
CUDA_VALIDATE(cudaHostAlloc(&resultHitPanelIds[0], MAX_RAYS_PER_ITERATION*sizeof(int), flag));
CUDA_VALIDATE(cudaHostAlloc(&resultHitPanelIds[1], MAX_RAYS_PER_ITERATION*sizeof(int), flag));
希望对此有解决方案。尝试了很多事情，包括不在默认流中运行。当我添加 cudaHostAlloc 时，我意识到异步方法返回到 CPU。但是，当内核在稍后调用 deviceSynchronize 之前没有启动时，这无济于事。
resultHitDistances[2]包含两个分配的内存区域，因此当 CPU 读取 0 时，GPU 应该将结果放入 1。
谢谢！
编辑：这是调用 traceRaysAsync 的代码。
int numIterations = ceil(float(this->numPrimaryRays) / MAX_RAYS_PER_ITERATION);
int numRaysPrevious = min(MAX_RAYS_PER_ITERATION, this->numPrimaryRays);
nvtxRangePushA("traceRaysOnGpuAsync First");
traceRaysOnGpuAsync(0, numRaysPrevious, rank, 0);
nvtxRangePop();
for(int iteration = 0; iteration < numIterations; iteration++)
{
int rayFrom = (iteration+1)*MAX_RAYS_PER_ITERATION;
int rayTo = min((iteration+2)*MAX_RAYS_PER_ITERATION, this->numPrimaryRays) - 1;
int numRaysIteration = rayTo-rayFrom+1;
// Wait for results to finish and get them
waitForGpu();
// Trace the next iteration asynchronously. This will have data prepared for next iteration
if(numRaysIteration > 0)
{
int nextBuffer = (iteration+1) % 2;
nvtxRangePushA("traceRaysOnGpuAsync Interior");
traceRaysOnGpuAsync(rayFrom, numRaysIteration, rank, nextBuffer);
nvtxRangePop();
}
nvtxRangePushA("CpuWork");
// Store results for current iteration
int rayOffset = iteration*MAX_RAYS_PER_ITERATION;
int buffer = iteration % 2;
for(int i = 0; i < numRaysPrevious; i++)
{
if(this->activeRays[rayOffset+i] && resultHitPanelIds[buffer][i] >= 0)
{
this->activeRays[rayOffset+i] = false;
const TrianglePanelPair & t = this->getTriangle(resultHitPanelIds[buffer][i]);
double hitT = resultHitDistances[buffer][i];
Vector3 reflectedDirection = resultReflections[buffer][i];
Result res = Result(rays[rayOffset+i], hitT, t.panel);
results[rank].push_back(res);
t.panel->incrementIntensity(1.0);
if (t.panel->getParent().absorbtion < 1)
{
numberOfRaysGenerated++;
Ray reflected (res.endPoint() + 0.00001*reflectedDirection, reflectedDirection);
this->newRays[rayOffset+i] = reflected;
this->activeRays[rayOffset+i] = true;
numNewRays++;
}
}
}
numRaysPrevious = numRaysIteration;
nvtxRangePop();
}