[llvm] Remove an incorrect assert in MFMASmallGemmSingleWaveOpt. (PR #130131)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: None (anjenner)

<details>
<summary>Changes</summary>

This assert was failing in a fuzzing test. I consulted with @<!-- -->jrbyrnes who said:

The MFMASmallGemmSingleWaveOpt::apply() method is invoked if and only if the user has inserted an intrinsic llvm.amdgcn.iglp.opt(i32 1) into their source code. This intrinsic applies a highly specialized DAG mutation to result in specific scheduling for a specific set of kernels. These assertions are really just confirming that the characteristics of the kernel match what is expected (i.e. The kernels are similar to the ones this DAG mutation strategy were designed against).

However, if we apply this DAG mutation to kernels for which is was not designed, then we may not find the types of instructions we are looking for, and may end up with empty caches.

I think it should be fine to just return false if the cache is empty instead of the assert.

---
Full diff: https://github.com/llvm/llvm-project/pull/130131.diff


1 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.cpp (-1) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.cpp b/llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.cpp
index bbd262748d680..a284cc0e5af51 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.cpp
@@ -1891,7 +1891,6 @@ class MFMASmallGemmSingleWaveOpt final : public IGLPStrategy {
         }
       }
 
-      assert(Cache->size());
       auto *DAG = SyncPipe[0].DAG;
       for (auto &Elt : *Cache) {
         if (DAG->IsReachable(Elt, const_cast<SUnit *>(SU)))

``````````

</details>


https://github.com/llvm/llvm-project/pull/130131