This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 6653620075 [ROCm] Fix some ROCm codegen bugs (#15518)
6653620075 is described below
commit 665362007552268547526b78d20e2b304e9ef278
Author: llpan <[email protected]>
AuthorDate: Fri Feb 27 22:38:10 2026 +0800
[ROCm] Fix some ROCm codegen bugs (#15518)
## Problem
`CodeGenLLVM::AllocateSharedMemory` calls `llvm::Align(alignment)` (for
LLVM >= 10), but `llvm::Align` requires a non-zero, power-of-2 value and
will trigger an assertion failure if given `0`.
This crash can be triggered on ROCm when allocating dynamic shared
memory. In `codegen_amdgpu.cc`, the dynamic shared memory path calls:
```cpp
buf = AllocateSharedMemory(op->dtype, 0, 3, std::min(info.alignment, 16),
llvm::GlobalValue::ExternalLinkage);
```
`info.alignment` is looked up from `alloc_storage_info_`, which defaults
to `0` if no alignment annotation has been set on the buffer. So
`std::min(0, 16) = 0` is passed as the alignment argument, leading to:
```cpp
global->setAlignment(llvm::Align(0)); // assertion failure: alignment must
be non-zero
```
## Fix
Replace `llvm::Align(alignment)` with `llvm::MaybeAlign(alignment)`.
`llvm::MaybeAlign` treats `0` as "no explicit alignment specified"
(equivalent to `std::nullopt`), which is safe and correct — LLVM will
use the type's ABI alignment instead.
```cpp
// Before
global->setAlignment(llvm::Align(alignment));
// After
global->setAlignment(llvm::MaybeAlign(alignment));
```
---
src/target/llvm/codegen_llvm.cc | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/target/llvm/codegen_llvm.cc b/src/target/llvm/codegen_llvm.cc
index ccb9173cd1..93f0282015 100644
--- a/src/target/llvm/codegen_llvm.cc
+++ b/src/target/llvm/codegen_llvm.cc
@@ -757,7 +757,7 @@ llvm::GlobalVariable*
CodeGenLLVM::AllocateSharedMemory(DataType dtype, size_t s
new llvm::GlobalVariable(*module_, type, false, linkage,
llvm::UndefValue::get(type), "shmem",
nullptr, llvm::GlobalValue::NotThreadLocal,
shared_address_space);
#if TVM_LLVM_VERSION >= 100
- global->setAlignment(llvm::Align(alignment));
+ global->setAlignment(llvm::MaybeAlign(alignment));
#else
global->setAlignment(alignment);
#endif
