Package io.github.kirstenali.deepj.tensor

Interface GpuRuntime

public interface GpuRuntime

Abstraction over a GPU compute runtime (Metal, CUDA, Vulkan, etc.).

ComputeGraph delegates all native/driver calls through this interface, keeping the graph logic itself backend-agnostic.

Method Summary

Modifier and Type	Method	Description
void	allocBuffers(int[] ids, int[] sizes, int count)	Batch-allocate GPU buffers.
void	downloadBuffer(int bufId, float[] out)	Download GPU buffer contents into a CPU float array.
void	flushOps(int[] cmdStream, int cmdStreamLength)	Execute a batch of ops encoded as a flat int[] command stream, all in one command buffer submission.
void	releaseBuffers(int[] ids, int count)	Release multiple GPU buffers by id.
void	uploadBuffer(int bufId, float[] data)	Upload CPU float data into an existing GPU buffer.

Method Details

allocBuffers

void allocBuffers(int[] ids,
 int[] sizes,
 int count)

Batch-allocate GPU buffers. ids[i] gets sizes[i] floats.

uploadBuffer

void uploadBuffer(int bufId,
 float[] data)

Upload CPU float data into an existing GPU buffer.

downloadBuffer

void downloadBuffer(int bufId,
 float[] out)

Download GPU buffer contents into a CPU float array.

releaseBuffers

void releaseBuffers(int[] ids,
 int count)

Release multiple GPU buffers by id.

flushOps

void flushOps(int[] cmdStream,
 int cmdStreamLength)

Execute a batch of ops encoded as a flat int[] command stream, all in one command buffer submission.