[RISCV][AArch64][IRGen] Add a special case to CodeGenFunction::EmitCa…

…ll for scalable vector return being coerced to fixed vector.

Before falling back to CreateCoercedStore, detect a scalable vector
return being coerced to fixed vector. Handle it using a vector.extract
intrinsic without going through memory.

Reviewed By: c-rhodes

Differential Revision: https://reviews.llvm.org/D155495

clang/lib/CodeGen/CGCall.cpp

@@ -5743,6 +5743,20 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
         llvm_unreachable("bad evaluation kind");
       }
 
+      // If coercing a fixed vector from a scalable vector for ABI
+      // compatibility, and the types match, use the llvm.vector.extract
+      // intrinsic to perform the conversion.
+      if (auto *FixedDst = dyn_cast<llvm::FixedVectorType>(RetIRTy)) {
+        llvm::Value *V = CI;
+        if (auto *ScalableSrc = dyn_cast<llvm::ScalableVectorType>(V->getType())) {
+          if (FixedDst->getElementType() == ScalableSrc->getElementType()) {
+            llvm::Value *Zero = llvm::Constant::getNullValue(CGM.Int64Ty);
+            V = Builder.CreateExtractVector(FixedDst, V, Zero, "cast.fixed");
+            return RValue::get(V);
+          }
+        }
+      }
+
       Address DestPtr = ReturnValue.getValue();
       bool DestIsVolatile = ReturnValue.isVolatile();
 

clang/test/CodeGen/attr-arm-sve-vector-bits-call.c

@@ -41,11 +41,7 @@ fixed_int32_t fixed_callee(fixed_int32_t x) {
 
 // CHECK-LABEL: @sizeless_caller(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[COERCE1:%.*]] = alloca <16 x i32>, align 16
-// CHECK-NEXT:    store <vscale x 4 x i32> [[X:%.*]], ptr [[COERCE1]], align 16
-// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i32>, ptr [[COERCE1]], align 16, !tbaa [[TBAA6:![0-9]+]]
-// CHECK-NEXT:    [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TMP1]], i64 0)
-// CHECK-NEXT:    ret <vscale x 4 x i32> [[CASTSCALABLESVE2]]
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[X:%.*]]
 //
 svint32_t sizeless_caller(svint32_t x) {
   return fixed_callee(x);

clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c

@@ -38,11 +38,7 @@ fixed_int32m1_t fixed_callee(fixed_int32m1_t x) {
 
 // CHECK-LABEL: @sizeless_caller(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[COERCE1:%.*]] = alloca <8 x i32>, align 8
-// CHECK-NEXT:    store <vscale x 2 x i32> [[X:%.*]], ptr [[COERCE1]], align 8
-// CHECK-NEXT:    [[TMP0:%.*]] = load <8 x i32>, ptr [[COERCE1]], align 8, !tbaa [[TBAA4:![0-9]+]]
-// CHECK-NEXT:    [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP0]], i64 0)
-// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE2]]
+// CHECK-NEXT:    ret <vscale x 2 x i32> [[X:%.*]]
 //
 vint32m1_t sizeless_caller(vint32m1_t x) {
   return fixed_callee(x);