Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/NVIDIA/TensorRT
/ deviceToHost
Method
deviceToHost
samples/common/sampleDevice.h:416–419 ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
414
}
415
416
void deviceToHost(TrtCudaStream& stream) override
417
{
418
cudaCheck(cudaMemcpyAsync(mHostBuffer.get(), mDeviceBuffer.get(), mSize, cudaMemcpyDeviceToHost, stream.get()));
419
}
420
421
size_t getSize() const override
422
{
Callers
nothing calls this directly
Calls
2
cudaCheck
Function · 0.85
get
Method · 0.45
Tested by
no test coverage detected