[hip] Implement asynchronous file reads in hip. (iree-org#19545)

This moves the blocking reads off the main thread, and so long as your PCI bandwidth outpaces your file IO bandwith, reduces the amount of time required to read files dramatically. Signed-off-by: Andrew Woloszyn <[email protected]> --------- Signed-off-by: Andrew Woloszyn <[email protected]>
nod-ai · Dec 20, 2024 · 47ccd93 · 47ccd93
1 parent d917e7d
commit 47ccd93
Show file tree

Hide file tree

Showing 3 changed files with 767 additions and 363 deletions.
diff --git a/runtime/src/iree/hal/drivers/hip/api.h b/runtime/src/iree/hal/drivers/hip/api.h
@@ -91,6 +91,14 @@ typedef struct iree_hal_hip_device_params_t {
   // device. Defaults to true when the device supports it.
   bool async_allocations;
 
+  // The reserved buffer size for asynchronous file transfers.
+  iree_device_size_t file_transfer_buffer_size;
+
+  // The maximum chunk size for any single asynchronous file transfer.
+  // This should be smaller than the full buffer size to allow overlapping
+  // cpu and gpu workloads.
+  iree_device_size_t file_transfer_chunk_size;
+
   // Parameters for each hipMemPool_t used for queue-ordered allocations.
   iree_hal_hip_memory_pooling_params_t memory_pools;