1 files changed, 23 insertions, 4 deletions
diff --git a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp
index 07cf08c..6596ec0 100644
--- a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp
+++ b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp
@@ -192,9 +192,17 @@ static Value *emitFPIntBuiltin(CodeGenFunction &CGF,
   return CGF.Builder.CreateCall(F, {Src0, Src1});
 }
 
+static inline StringRef mapScopeToSPIRV(StringRef AMDGCNScope) {
+  if (AMDGCNScope == "agent")
+    return "device";
+  if (AMDGCNScope == "wavefront")
+    return "subgroup";
+  return AMDGCNScope;
+}
+
 // For processing memory ordering and memory scope arguments of various
 // amdgcn builtins.
-// \p Order takes a C++11 comptabile memory-ordering specifier and converts
+// \p Order takes a C++11 compatible memory-ordering specifier and converts
 // it into LLVM's memory ordering specifier using atomic C ABI, and writes
 // to \p AO. \p Scope takes a const char * and converts it into AMDGCN
 // specific SyncScopeID and writes it to \p SSID.
@@ -227,6 +235,8 @@ void CodeGenFunction::ProcessOrderScopeAMDGCN(Value *Order, Value *Scope,
   // Some of the atomic builtins take the scope as a string name.
   StringRef scp;
   if (llvm::getConstantStringInfo(Scope, scp)) {
+    if (getTarget().getTriple().isSPIRV())
+      scp = mapScopeToSPIRV(scp);
     SSID = getLLVMContext().getOrInsertSyncScopeID(scp);
     return;
   }
@@ -238,13 +248,19 @@ void CodeGenFunction::ProcessOrderScopeAMDGCN(Value *Order, Value *Scope,
     SSID = llvm::SyncScope::System;
     break;
   case 1: // __MEMORY_SCOPE_DEVICE
-    SSID = getLLVMContext().getOrInsertSyncScopeID("agent");
+    if (getTarget().getTriple().isSPIRV())
+      SSID = getLLVMContext().getOrInsertSyncScopeID("device");
+    else
+      SSID = getLLVMContext().getOrInsertSyncScopeID("agent");
     break;
   case 2: // __MEMORY_SCOPE_WRKGRP
     SSID = getLLVMContext().getOrInsertSyncScopeID("workgroup");
     break;
   case 3: // __MEMORY_SCOPE_WVFRNT
-    SSID = getLLVMContext().getOrInsertSyncScopeID("wavefront");
+    if (getTarget().getTriple().isSPIRV())
+      SSID = getLLVMContext().getOrInsertSyncScopeID("subgroup");
+    else
+      SSID = getLLVMContext().getOrInsertSyncScopeID("wavefront");
     break;
   case 4: // __MEMORY_SCOPE_SINGLE
     SSID = llvm::SyncScope::SingleThread;
@@ -1510,7 +1526,10 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
       //
       // The global/flat cases need to use agent scope to consistently produce
       // the native instruction instead of a cmpxchg expansion.
-      SSID = getLLVMContext().getOrInsertSyncScopeID("agent");
+      if (getTarget().getTriple().isSPIRV())
+        SSID = getLLVMContext().getOrInsertSyncScopeID("device");
+      else
+        SSID = getLLVMContext().getOrInsertSyncScopeID("agent");
       AO = AtomicOrdering::Monotonic;
 
       // The v2bf16 builtin uses i16 instead of a natural bfloat type.