[llvm] [AMDGPU] Infer amdgpu-no-flat-scratch-init attribute in AMDGPUAttributor (PR #94647)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Thu Jun 27 12:13:23 PDT 2024


================
@@ -677,6 +693,33 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
     return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
                                               UsedAssumedInformation);
   }
+
+  // Returns true if FlatScratchInit is needed, i.e., no-flat-scratch-init is
+  // not to be set.
+  bool needFlatScratchInit(Attributor &A) {
+    // This is called on each callee; false means callee shouldn't have
+    // no-flat-scratch-init.
+    auto CheckForNoFlatScratchInit = [&](Instruction &I) {
+      const auto &CB = cast<CallBase>(I);
+      const Value *CalleeOp = CB.getCalledOperand();
+      const Function *Callee = dyn_cast<Function>(CalleeOp);
+      if (!Callee) // indirect call
+        return CB.isInlineAsm();
----------------
arsenm wrote:

Instead of checking for the call instructions with checkForAllCallLikeInstructions, you instead use checkForAllCallees for all direct and possible indirect call candidates (not 100% sure how this interacts with asm). That way you don't have to concern yourself with indirect calls, since any possible call targets should also appear in the callees 

https://github.com/llvm/llvm-project/pull/94647


More information about the llvm-commits mailing list