[llvm] [AMDGPU][LowerModuleLDS] Refactor partially lowered module detection (PR #85793)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Pierre van Houtryve (Pierre-vh)

<details>
<summary>Changes</summary>

Refactor the logic that checks if a module contains mixed absolute/non-lowered LDS GVs.

The check now happens latter when the "worklists" are formed. This is because in some cases (OpenMP) we can have non-lowered GVs in a lowered module, and this is normal because those GVs are just unused and removed from the list at some point before the end of `getUsesOfLDSByFunction`.

Doing the check later ensures that if a mixed module is spotted, then it's a _real_ mixed module that needs rejection, not a module containing an intentionally ignored GV.

---
Full diff: https://github.com/llvm/llvm-project/pull/85793.diff


2 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp (+26-15) 
- (modified) llvm/test/CodeGen/AMDGPU/lds-reject-mixed-absolute-addresses.ll (+1-1) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
index b85cb26fdc9565..656f10e44c3bbc 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -340,26 +340,11 @@ class AMDGPULowerModuleLDS {
 
     // Get uses from the current function, excluding uses by called functions
     // Two output variables to avoid walking the globals list twice
-    std::optional<bool> HasAbsoluteGVs;
     for (auto &GV : M.globals()) {
       if (!AMDGPU::isLDSVariableToLower(GV)) {
         continue;
       }
 
-      // Check if the module is consistent: either all GVs are absolute (happens
-      // when we run the pass more than once), or none are.
-      const bool IsAbsolute = GV.isAbsoluteSymbolRef();
-      if (HasAbsoluteGVs.has_value()) {
-        if (*HasAbsoluteGVs != IsAbsolute) {
-          report_fatal_error(
-              "Module cannot mix absolute and non-absolute LDS GVs");
-        }
-      } else
-        HasAbsoluteGVs = IsAbsolute;
-
-      if (IsAbsolute)
-        continue;
-
       for (User *V : GV.users()) {
         if (auto *I = dyn_cast<Instruction>(V)) {
           Function *F = I->getFunction();
@@ -469,6 +454,31 @@ class AMDGPULowerModuleLDS {
       }
     }
 
+    // Verify that we fall into one of 2 cases:
+    //    - All variables are absolute: this is a re-run of the pass
+    //      so we don't have anything to do.
+    //    - No variables are absolute.
+    std::optional<bool> HasAbsoluteGVs;
+    for (auto Map : {direct_map_kernel, indirect_map_kernel}) {
+      for (auto [Fn, GVs] : Map) {
+        for (auto GV : GVs) {
+          bool IsAbsolute = GV->isAbsoluteSymbolRef();
+          if (HasAbsoluteGVs.has_value()) {
+            if (*HasAbsoluteGVs != IsAbsolute) {
+              report_fatal_error(
+                  "Module cannot mix absolute and non-absolute LDS GVs");
+            }
+          } else
+            HasAbsoluteGVs = IsAbsolute;
+        }
+      }
+    }
+
+    // If we only had absolute GVs, we have nothing to do, return an empty
+    // result.
+    if (HasAbsoluteGVs && *HasAbsoluteGVs)
+      return {FunctionVariableMap(), FunctionVariableMap()};
+
     return {std::move(direct_map_kernel), std::move(indirect_map_kernel)};
   }
 
@@ -1143,6 +1153,7 @@ class AMDGPULowerModuleLDS {
   }
 
   bool runOnModule(Module &M) {
+    dbgs() << "LowerModuleLDS: " << M.getName() << " (" << (void *)&M << ")\n";
     CallGraph CG = CallGraph(M);
     bool Changed = superAlignLDSGlobals(M);
 
diff --git a/llvm/test/CodeGen/AMDGPU/lds-reject-mixed-absolute-addresses.ll b/llvm/test/CodeGen/AMDGPU/lds-reject-mixed-absolute-addresses.ll
index b512a43aa10222..b1f4f2ef1ef535 100644
--- a/llvm/test/CodeGen/AMDGPU/lds-reject-mixed-absolute-addresses.ll
+++ b/llvm/test/CodeGen/AMDGPU/lds-reject-mixed-absolute-addresses.ll
@@ -8,7 +8,7 @@
 define amdgpu_kernel void @kern() {
   %val0 = load i32, ptr addrspace(3) @var1
   %val1 = add i32 %val0, 4
-  store i32 %val1, ptr addrspace(3) @var1
+  store i32 %val1, ptr addrspace(3) @var2
   ret void
 }
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/85793