ROCM Provider Options. More...

#include <onnxruntime_c_api.h>

Public Attributes
int	device_id
	ROCM device Id Defaults to 0. More...

int	miopen_conv_exhaustive_search
	ROCM MIOpen Convolution algorithm exaustive search option. Defaults to 0 (false). More...

size_t	gpu_mem_limit
	ROCM memory limit (To use all possible memory pass in maximum size_t) Defaults to SIZE_MAX. More...

int	arena_extend_strategy
	Strategy used to grow the memory arena 0 = kNextPowerOfTwo 1 = kSameAsRequested Defaults to 0. More...

int	do_copy_in_default_stream
	Flag indicating if copying needs to take place on the same stream as the compute stream in the ROCM EP 0 = Use separate streams for copying and compute. 1 = Use the same stream for copying and compute. Defaults to 1. WARNING: Setting this to 0 may result in data races for some models. Please see issue #4829 for more details. More...

int	has_user_compute_stream
	Flag indicating if there is a user provided compute stream Defaults to 0. More...

void *	user_compute_stream
	User provided compute stream. If provided, please set `has_user_compute_stream` to 1. More...

OrtArenaCfg *	default_memory_arena_cfg
	ROCM memory arena configuration parameters. More...

int	tunable_op_enabled
	Enable TunableOp. Set it to 1 to enable TunableOp. Otherwise, it is disabled by default. This option can be superseded by environment variable ORT_ROCM_TUNABLE_OP_ENABLED. More...

Detailed Description

ROCM Provider Options.

See Also: OrtApi::SessionOptionsAppendExecutionProvider_ROCM

Definition at line 444 of file onnxruntime_c_api.h.

Member Data Documentation

int OrtROCMProviderOptions::arena_extend_strategy

Strategy used to grow the memory arena 0 = kNextPowerOfTwo
1 = kSameAsRequested
Defaults to 0.

Note: If a OrtArenaCfg has been applied, it will override this field

Definition at line 480 of file onnxruntime_c_api.h.

OrtArenaCfg* OrtROCMProviderOptions::default_memory_arena_cfg

ROCM memory arena configuration parameters.

Definition at line 503 of file onnxruntime_c_api.h.

int OrtROCMProviderOptions::device_id

ROCM device Id Defaults to 0.

Definition at line 461 of file onnxruntime_c_api.h.

int OrtROCMProviderOptions::do_copy_in_default_stream

Flag indicating if copying needs to take place on the same stream as the compute stream in the ROCM EP 0 = Use separate streams for copying and compute. 1 = Use the same stream for copying and compute. Defaults to 1. WARNING: Setting this to 0 may result in data races for some models. Please see issue #4829 for more details.

Definition at line 489 of file onnxruntime_c_api.h.

size_t OrtROCMProviderOptions::gpu_mem_limit

ROCM memory limit (To use all possible memory pass in maximum size_t) Defaults to SIZE_MAX.

Note: If a OrtArenaCfg has been applied, it will override this field

Definition at line 472 of file onnxruntime_c_api.h.

int OrtROCMProviderOptions::has_user_compute_stream

Flag indicating if there is a user provided compute stream Defaults to 0.

Definition at line 494 of file onnxruntime_c_api.h.

int OrtROCMProviderOptions::miopen_conv_exhaustive_search

ROCM MIOpen Convolution algorithm exaustive search option. Defaults to 0 (false).

Definition at line 466 of file onnxruntime_c_api.h.

int OrtROCMProviderOptions::tunable_op_enabled

Enable TunableOp. Set it to 1 to enable TunableOp. Otherwise, it is disabled by default. This option can be superseded by environment variable ORT_ROCM_TUNABLE_OP_ENABLED.

Definition at line 509 of file onnxruntime_c_api.h.

void* OrtROCMProviderOptions::user_compute_stream

User provided compute stream. If provided, please set has_user_compute_stream to 1.

Definition at line 499 of file onnxruntime_c_api.h.

The documentation for this struct was generated from the following file:

onnxruntime/core/session/onnxruntime_c_api.h

Public Attributes

Detailed Description

Member Data Documentation