17 a0[0].
data = placeholder;
18 a1[0].
data = placeholder1;
19 a2[0].
data = T_multiply;
23 #ifdef BAMBU_PROFILING 29 #ifdef BAMBU_PROFILING
void __builtin_bambu_time_start()
Union type of values being passed through API and function calls.
int32_t fused_multiply(void *args, void *arg_type_ids, int32_t num_args)
void * data
The opaque data pointer points to the allocated data. This will be CUDA device pointer or cl_mem hand...
int32_t fused_multiply_wrapper(float *placeholder, float *placeholder1, float *T_multiply)
Plain C Tensor object, does not manage memory.
void __builtin_bambu_time_stop()