Hi，I run the following code ：
... target = "llvm -mcpu=core-avx2" with tvm.transform.PassContext(opt_level=3): lib = relay.build(mod, target=target, params=params) lib.export_library(args.output_file) ... lib = tvm.runtime.load_module(args.output_file) dev = tvm.device(str(target), 0) module = graph_executor.GraphModule(lib["default"](dev))
I want to know if my machine supports avx512, tvm use avx2 or avx512 when I load avx2 module using above code and run model benchmark, thank you !