![]()  | 
  
    ONNX Runtime
    
   | 
 
ROCM Provider Options. More...
#include <onnxruntime_c_api.h>
Public Member Functions | |
| OrtROCMProviderOptions () | |
Public Attributes | |
| int | device_id | 
| ROCM device Id Defaults to 0.   | |
| int | miopen_conv_exhaustive_search | 
| ROCM MIOpen Convolution algorithm exaustive search option. Defaults to 0 (false).   | |
| size_t | gpu_mem_limit | 
| ROCM memory limit (To use all possible memory pass in maximum size_t) Defaults to SIZE_MAX.   | |
| int | arena_extend_strategy | 
| Strategy used to grow the memory arena 0 = kNextPowerOfTwo 1 = kSameAsRequested Defaults to 0.  | |
| 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.   | |
| int | has_user_compute_stream | 
| Flag indicating if there is a user provided compute stream Defaults to 0.   | |
| void * | user_compute_stream | 
User provided compute stream. If provided, please set has_user_compute_stream to 1.   | |
| OrtArenaCfg * | default_memory_arena_cfg | 
| ROCM memory arena configuration parameters.   | |
| int | enable_hip_graph | 
| int | tunable_op_enable | 
| Enable TunableOp for using. Set it to 1/0 to enable/disable TunableOp. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_ROCM_TUNABLE_OP_ENABLE.   | |
| int | tunable_op_tuning_enable | 
| Enable TunableOp for tuning. Set it to 1/0 to enable/disable TunableOp tuning. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_ROCM_TUNABLE_OP_TUNING_ENABLE.   | |
| int | tunable_op_max_tuning_duration_ms | 
| Max tuning duration time limit for each instance of TunableOp. Defaults to 0 to disable the limit.   | |
ROCM Provider Options.
      
  | 
  inline | 
| int OrtROCMProviderOptions::arena_extend_strategy | 
Strategy used to grow the memory arena 0 = kNextPowerOfTwo
 1 = kSameAsRequested
 Defaults to 0. 
| OrtArenaCfg* OrtROCMProviderOptions::default_memory_arena_cfg | 
ROCM memory arena configuration parameters.
| int OrtROCMProviderOptions::device_id | 
ROCM device Id Defaults to 0.
| 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.
| int OrtROCMProviderOptions::enable_hip_graph | 
| size_t OrtROCMProviderOptions::gpu_mem_limit | 
ROCM memory limit (To use all possible memory pass in maximum size_t) Defaults to SIZE_MAX.
| int OrtROCMProviderOptions::has_user_compute_stream | 
Flag indicating if there is a user provided compute stream Defaults to 0.
| int OrtROCMProviderOptions::miopen_conv_exhaustive_search | 
ROCM MIOpen Convolution algorithm exaustive search option. Defaults to 0 (false).
| int OrtROCMProviderOptions::tunable_op_enable | 
Enable TunableOp for using. Set it to 1/0 to enable/disable TunableOp. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_ROCM_TUNABLE_OP_ENABLE.
| int OrtROCMProviderOptions::tunable_op_max_tuning_duration_ms | 
Max tuning duration time limit for each instance of TunableOp. Defaults to 0 to disable the limit.
| int OrtROCMProviderOptions::tunable_op_tuning_enable | 
Enable TunableOp for tuning. Set it to 1/0 to enable/disable TunableOp tuning. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_ROCM_TUNABLE_OP_TUNING_ENABLE.
| void* OrtROCMProviderOptions::user_compute_stream | 
User provided compute stream. If provided, please set has_user_compute_stream to 1.