1 files changed, 31 insertions, 8 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
index ef46e53b7460..cb511e5e3483 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
@@ -29,6 +29,8 @@
 #include "SIMachineFunctionInfo.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
+#include "llvm/IR/GlobalAlias.h"
+#include "llvm/IR/GlobalValue.h"
 #include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
@@ -61,7 +63,8 @@ static const Function *getCalleeFunction(const MachineOperand &Op) {
     assert(Op.getImm() == 0);
     return nullptr;
   }
-
+  if (auto *GA = dyn_cast<GlobalAlias>(Op.getGlobal()))
+    return cast<Function>(GA->getOperand(0));
   return cast<Function>(Op.getGlobal());
 }
 
@@ -83,10 +86,15 @@ int32_t AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo::getTotalNumSGPRs(
 }
 
 int32_t AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo::getTotalNumVGPRs(
+    const GCNSubtarget &ST, int32_t ArgNumAGPR, int32_t ArgNumVGPR) const {
+  if (ST.hasGFX90AInsts() && ArgNumAGPR)
+    return alignTo(ArgNumVGPR, 4) + ArgNumAGPR;
+  return std::max(ArgNumVGPR, ArgNumAGPR);
+}
+
+int32_t AMDGPUResourceUsageAnalysis::SIFunctionResourceInfo::getTotalNumVGPRs(
     const GCNSubtarget &ST) const {
-  if (ST.hasGFX90AInsts() && NumAGPR)
-    return alignTo(NumVGPR, 4) + NumAGPR;
-  return std::max(NumVGPR, NumAGPR);
+  return getTotalNumVGPRs(ST, NumAGPR, NumVGPR);
 }
 
 bool AMDGPUResourceUsageAnalysis::runOnSCC(CallGraphSCC &SCC) {
@@ -444,6 +452,25 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage(
         if (!IsIndirect)
           I = CallGraphResourceInfo.find(Callee);
 
+        // FIXME: Call site could have norecurse on it
+        if (!Callee || !Callee->doesNotRecurse()) {
+          Info.HasRecursion = true;
+
+          // TODO: If we happen to know there is no stack usage in the
+          // callgraph, we don't need to assume an infinitely growing stack.
+          if (!MI.isReturn()) {
+            // We don't need to assume an unknown stack size for tail calls.
+
+            // FIXME: This only benefits in the case where the kernel does not
+            // directly call the tail called function. If a kernel directly
+            // calls a tail recursive function, we'll assume maximum stack size
+            // based on the regular call instruction.
+            CalleeFrameSize =
+              std::max(CalleeFrameSize,
+                       static_cast<uint64_t>(AssumedStackSizeForExternalCall));
+          }
+        }
+
         if (IsIndirect || I == CallGraphResourceInfo.end()) {
           CalleeFrameSize =
               std::max(CalleeFrameSize,
@@ -468,10 +495,6 @@ AMDGPUResourceUsageAnalysis::analyzeResourceUsage(
           Info.HasRecursion |= I->second.HasRecursion;
           Info.HasIndirectCall |= I->second.HasIndirectCall;
         }
-
-        // FIXME: Call site could have norecurse on it
-        if (!Callee || !Callee->doesNotRecurse())
-          Info.HasRecursion = true;
       }
     }
   }