* [LLVM] Fix generation of LLVM intrinsics The type list in the call to llvm::Intrinsic::getDeclaration is not the intrinsic's signature, it's the list of overloaded types. Without this fix, the updated unit test would cause the following error: TVMError: LLVM module verification failed with the following errors: Intrinsic name not mangled correctly for type arguments! Should be: llvm.ctlz.i32 i32 (i32, i1)* @llvm.ctlz.i32.i1 Special handling for llvm.prefetch, sig matching for overloaded ints only The prefetch intrinsic returns void in LLVM, while it returns i32 in TVM. This case needs to be handled specially, because rule-based intrinsic translation would cause invalid LLVM type to be created. Do the signature matching only for overloaded intrinsics. It's not needed for non-overloaded ones, so this can save a bit of compile-time. * Include intrinsic name in the error message * Fix number of arguments for llvm.fmuladd and llvm.pow
Name |
Last commit
|
Last update |
---|---|---|
.. | ||
codegen_amdgpu.cc | Loading commit data... | |
codegen_arm.cc | Loading commit data... | |
codegen_blob.cc | Loading commit data... | |
codegen_blob.h | Loading commit data... | |
codegen_cpu.cc | Loading commit data... | |
codegen_cpu.h | Loading commit data... | |
codegen_llvm.cc | Loading commit data... | |
codegen_llvm.h | Loading commit data... | |
codegen_nvptx.cc | Loading commit data... | |
codegen_x86_64.cc | Loading commit data... | |
intrin_rule_llvm.cc | Loading commit data... | |
intrin_rule_llvm.h | Loading commit data... | |
intrin_rule_nvptx.cc | Loading commit data... | |
intrin_rule_rocm.cc | Loading commit data... | |
llvm_common.cc | Loading commit data... | |
llvm_common.h | Loading commit data... | |
llvm_module.cc | Loading commit data... |