diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -2688,6 +2688,27 @@
         break;
       }
 
+      // VLST arguments are coerced to VLATs at the function boundary for
+      // ABI consistency. If this is a VLST that was coerced to
+      // a VLAT at the function boundary and the types match up, use
+      // llvm.experimental.vector.extract to convert back to the original
+      // VLST.
+      if (auto *VecTyTo = dyn_cast<llvm::FixedVectorType>(ConvertType(Ty))) {
+        auto *Coerced = Fn->getArg(FirstIRArg);
+        if (auto *VecTyFrom =
+                dyn_cast<llvm::ScalableVectorType>(Coerced->getType())) {
+          if (VecTyFrom->getElementType() == VecTyTo->getElementType()) {
+            llvm::Value *Zero = llvm::Constant::getNullValue(CGM.Int64Ty);
+
+            assert(NumIRArgs == 1);
+            Coerced->setName(Arg->getName() + ".coerce");
+            ArgVals.push_back(ParamValue::forDirect(Builder.CreateExtractVector(
+                VecTyTo, Coerced, Zero, "castFixedSve")));
+            break;
+          }
+        }
+      }
+
       Address Alloca = CreateMemTemp(Ty, getContext().getDeclAlign(Arg),
                                      Arg->getName());
 
diff --git a/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.c b/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.c
--- a/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.c
+++ b/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.c
@@ -59,14 +59,14 @@
 
 // CHECK-LABEL: define{{.*}} void @f2(
 // CHECK-SAME:   <[[#div(VBITS,8)]] x i8>* noalias nocapture sret(<[[#div(VBITS,8)]] x i8>) align 16 %agg.result, <[[#div(VBITS,8)]] x i8>* nocapture readonly %0)
-// CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[X:%.*]] = load <[[#div(VBITS,8)]] x i8>, <[[#div(VBITS,8)]] x i8>* [[TMP0:%.*]], align 16, [[TBAA6:!tbaa !.*]]
-// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v[[#div(VBITS,8)]]i8(<vscale x 16 x i8> undef, <[[#div(VBITS,8)]] x i8> [[X]], i64 0)
-// CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asrd.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[CASTSCALABLESVE]], i32 1)
-// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <[[#div(VBITS,8)]] x i8> @llvm.experimental.vector.extract.v[[#div(VBITS,8)]]i8.nxv16i8(<vscale x 16 x i8> [[TMP2]], i64 0)
-// CHECK-NEXT:    store <[[#div(VBITS,8)]] x i8> [[CASTFIXEDSVE]], <[[#div(VBITS,8)]] x i8>* [[AGG_RESULT:%.*]], align 16, [[TBAA6]]
-// CHECK-NEXT:    ret void
+// CHECK-NEXT: entry:
+// CHECK-NEXT:   [[X:%.*]] = load <[[#div(VBITS,8)]] x i8>, <[[#div(VBITS,8)]] x i8>* [[TMP0:%.*]], align 16, [[TBAA6:!tbaa !.*]]
+// CHECK-NEXT:   [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
+// CHECK-NEXT:   [[CASTSCALABLESVE:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v[[#div(VBITS,8)]]i8(<vscale x 16 x i8> undef, <[[#div(VBITS,8)]] x i8> [[X]], i64 0)
+// CHECK-NEXT:   [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asrd.nxv16i8(<vscale x 16 x i1> [[TMP1]], <vscale x 16 x i8> [[CASTSCALABLESVE]], i32 1)
+// CHECK-NEXT:   [[CASTFIXEDSVE:%.*]] = call <[[#div(VBITS,8)]] x i8> @llvm.experimental.vector.extract.v[[#div(VBITS,8)]]i8.nxv16i8(<vscale x 16 x i8> [[TMP2]], i64 0)
+// CHECK-NEXT:   store <[[#div(VBITS,8)]] x i8> [[CASTFIXEDSVE]], <[[#div(VBITS,8)]] x i8>* [[AGG_RESULT:%.*]], align 16, [[TBAA6]]
+// CHECK-NEXT:   ret void
 vec_int8 f2(vec_int8 x) { return svasrd_x(svptrue_b8(), x, 1); }
 #endif
 
@@ -78,24 +78,18 @@
 typedef svint8_t vec2 __attribute__((arm_sve_vector_bits(N)));
 
 // CHECK128-LABEL: define{{.*}} void @g(<vscale x 16 x i8> %x.coerce)
-// CHECK128-NEXT:  entry:
-// CHECK128-NEXT:    [[X:%.*]] = alloca <16 x i8>, align 16
-// CHECK128-NEXT:    [[TMP0:%.*]] = bitcast <16 x i8>* [[X]] to <vscale x 16 x i8>*
-// CHECK128-NEXT:    store <vscale x 16 x i8> [[X_COERCE:%.*]], <vscale x 16 x i8>* [[TMP0]], align 16
-// CHECK128-NEXT:    [[X1:%.*]] = load <16 x i8>, <16 x i8>* [[X]], align 16, [[TBAA6:!tbaa !.*]]
-// CHECK128-NEXT:    call void @f3(<16 x i8> [[X1]]) [[ATTR5:#.*]]
+// CHECK128-NEXT: entry:
+// CHECK128-NEXT:  [[X:%.*]] = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> [[X_COERCE:%.*]], i64 0)
+// CHECK128-NEXT:    call void @f3(<16 x i8> [[X]]) [[ATTR5:#.*]]
 // CHECK128-NEXT:    ret void
 
 // CHECK-LABEL: define{{.*}} void @g(<vscale x 16 x i8> %x.coerce)
-// CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[X:%.*]] = alloca <[[#div(VBITS,8)]] x i8>, align 16
-// CHECK-NEXT:    [[INDIRECT_ARG_TEMP:%.*]] = alloca <[[#div(VBITS,8)]] x i8>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <[[#div(VBITS,8)]] x i8>* [[X]] to <vscale x 16 x i8>*
-// CHECK-NEXT:    store <vscale x 16 x i8> [[X_COERCE:%.*]], <vscale x 16 x i8>* [[TMP0]], align 16
-// CHECK-NEXT:    [[X1:%.*]] = load <[[#div(VBITS,8)]] x i8>, <[[#div(VBITS,8)]] x i8>* [[X]], align 16, [[TBAA6]]
-// CHECK-NEXT:    store <[[#div(VBITS,8)]] x i8> [[X1]], <[[#div(VBITS,8)]] x i8>* [[INDIRECT_ARG_TEMP]], align 16, [[TBAA6]]
-// CHECK-NEXT:    call void @f3(<[[#div(VBITS,8)]] x i8>* nonnull [[INDIRECT_ARG_TEMP]]) [[ATTR5:#.*]]
-// CHECK-NEXT:    ret void
+// CHECK-NEXT: entry:
+// CHECK-NEXT:   [[INDIRECT_ARG_TEMP:%.*]] = alloca <[[#div(VBITS,8)]] x i8>, align 16
+// CHECK-NEXT:   [[X:%.*]] = call <[[#div(VBITS,8)]] x i8> @llvm.experimental.vector.extract.v[[#div(VBITS,8)]]i8.nxv16i8(<vscale x 16 x i8> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:   store <[[#div(VBITS,8)]] x i8> [[X]], <[[#div(VBITS,8)]] x i8>* [[INDIRECT_ARG_TEMP]], align 16, [[TBAA6]]
+// CHECK-NEXT:   call void @f3(<[[#div(VBITS,8)]] x i8>* nonnull [[INDIRECT_ARG_TEMP]]) [[ATTR5:#.*]]
+// CHECK-NEXT:   ret void
 
 // CHECK128-LABEL: declare void @f3(<16 x i8>)
 
diff --git a/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.cpp b/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.cpp
--- a/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.cpp
+++ b/clang/test/CodeGen/aarch64-sve-acle-__ARM_FEATURE_SVE_VECTOR_OPERATORS.cpp
@@ -48,20 +48,14 @@
 // CHECK-SAME:    [[#VBITS]]
 // CHECK-SAME:    EES_(<vscale x 4 x i32> %x.coerce, <vscale x 4 x i32> %y.coerce)
 // CHECK-NEXT: entry:
-// CHECK-NEXT:   %x = alloca <[[#div(VBITS,32)]] x i32>, align 16
-// CHECK-NEXT:   %y = alloca <[[#div(VBITS,32)]] x i32>, align 16
-// CHECK-NEXT:   %retval.coerce = alloca <vscale x 4 x i32>, align 16
-// CHECK-NEXT:   %0 = bitcast <[[#div(VBITS,32)]] x i32>* %x to <vscale x 4 x i32>*
-// CHECK-NEXT:   store <vscale x 4 x i32> %x.coerce, <vscale x 4 x i32>* %0, align 16
-// CHECK-NEXT:   %x1 = load <[[#div(VBITS,32)]] x i32>, <[[#div(VBITS,32)]] x i32>* %x, align 16
-// CHECK-NEXT:   %1 = bitcast <[[#div(VBITS,32)]] x i32>* %y to <vscale x 4 x i32>*
-// CHECK-NEXT:   store <vscale x 4 x i32> %y.coerce, <vscale x 4 x i32>* %1, align 16
-// CHECK-NEXT:   %y2 = load <[[#div(VBITS,32)]] x i32>, <[[#div(VBITS,32)]] x i32>* %y, align 16
-// CHECK-NEXT:   %add = add <[[#div(VBITS,32)]] x i32> %y2, %x1
-// CHECK-NEXT:   %retval.0..sroa_cast = bitcast <vscale x 4 x i32>* %retval.coerce to <[[#div(VBITS,32)]] x i32>*
-// CHECK-NEXT:   store <[[#div(VBITS,32)]] x i32> %add, <[[#div(VBITS,32)]] x i32>* %retval.0..sroa_cast, align 16
-// CHECK-NEXT:   %2 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %retval.coerce, align 16
-// CHECK-NEXT:   ret <vscale x 4 x i32> %2
+// CHECK-NEXT:   [[RETVAL_COERCE:%.*]] = alloca <vscale x 4 x i32>, align 16
+// CHECK-NEXT:   [[X:%.*]] = call <[[#div(VBITS, 32)]] x i32> @llvm.experimental.vector.extract.v[[#div(VBITS, 32)]]i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:   [[Y:%.*]] = call <[[#div(VBITS, 32)]] x i32> @llvm.experimental.vector.extract.v[[#div(VBITS, 32)]]i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE1:%.*]], i64 0)
+// CHECK-NEXT:   [[ADD:%.*]] = add <[[#div(VBITS, 32)]] x i32> [[Y]], [[X]]
+// CHECK-NEXT:   [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 4 x i32>* [[RETVAL_COERCE]] to <[[#div(VBITS, 32)]] x i32>*
+// CHECK-NEXT:   store <[[#div(VBITS, 32)]] x i32> [[ADD]], <[[#div(VBITS, 32)]] x i32>* [[RETVAL_0__SROA_CAST]], align 16
+// CHECK-NEXT:   [[TMP0:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:   ret <vscale x 4 x i32> [[TMP0]]
 typedef svint32_t vec __attribute__((arm_sve_vector_bits(N)));
 auto f(vec x, vec y) { return x + y; } // Returns a vec.
 #endif
@@ -76,19 +70,13 @@
 // CHECK-SAME:    [[#VBITS]]
 // CHECK-SAME:    EE(<vscale x 8 x i16> %x.coerce)
 // CHECK-NEXT: entry:
-// CHECK128-NEXT:   %x = alloca <[[#div(VBITS,16)]] x i16>, align 16
-// CHECK128-NEXT:   %0 = bitcast <[[#div(VBITS,16)]] x i16>* %x to <vscale x 8 x i16>*
-// CHECK128-NEXT:   store <vscale x 8 x i16> %x.coerce, <vscale x 8 x i16>* %0, align 16
-// CHECK128-NEXT:   %x1 = load <[[#div(VBITS,16)]] x i16>, <[[#div(VBITS,16)]] x i16>* %x, align 16
-// CHECK128-NEXT:   call void @_Z1fDv[[#div(VBITS,16)]]_s(<[[#div(VBITS,16)]] x i16> %x1)
+// CHECK128-NEXT:   [[X:%.*]] = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> [[X_COERCE:%.*]], i64 0)
+// CHECK128-NEXT:   call void @_Z1fDv8_s(<8 x i16> [[X]]) [[ATTR5:#.*]]
 // CHECK128-NEXT:   ret void
-// CHECKWIDE-NEXT:   %x = alloca <[[#div(VBITS,16)]] x i16>, align 16
-// CHECKWIDE-NEXT:   %indirect-arg-temp = alloca <[[#div(VBITS,16)]] x i16>, align 16
-// CHECKWIDE-NEXT:   %0 = bitcast <[[#div(VBITS,16)]] x i16>* %x to <vscale x 8 x i16>*
-// CHECKWIDE-NEXT:   store <vscale x 8 x i16> %x.coerce, <vscale x 8 x i16>* %0, align 16
-// CHECKWIDE-NEXT:   %x1 = load <[[#div(VBITS,16)]] x i16>, <[[#div(VBITS,16)]] x i16>* %x, align 16
-// CHECKWIDE-NEXT:   store <[[#div(VBITS,16)]] x i16> %x1, <[[#div(VBITS,16)]] x i16>* %indirect-arg-temp, align 16
-// CHECKWIDE-NEXT:   call void @_Z1fDv[[#div(VBITS,16)]]_s(<[[#div(VBITS,16)]] x i16>* nonnull %indirect-arg-temp)
+// CHECKWIDE-NEXT:   [[INDIRECT_ARG_TEMP:%.*]] = alloca <[[#div(VBITS, 16)]] x i16>, align 16
+// CHECKWIDE-NEXT:   [[X:%.*]] = call <[[#div(VBITS, 16)]] x i16> @llvm.experimental.vector.extract.v[[#div(VBITS, 16)]]i16.nxv8i16(<vscale x 8 x i16> [[X_COERCE:%.*]], i64 0)
+// CHECKWIDE-NEXT:   store <[[#div(VBITS, 16)]] x i16> [[X]], <[[#div(VBITS, 16)]] x i16>* [[INDIRECT_ARG_TEMP]], align 16, [[TBAA6:!tbaa !.*]]
+// CHECKWIDE-NEXT:   call void @_Z1fDv[[#div(VBITS, 16)]]_s(<[[#div(VBITS, 16)]] x i16>* nonnull [[INDIRECT_ARG_TEMP]]) [[ATTR5:#.*]]
 // CHECKWIDE-NEXT:   ret void
 void g(vec2 x) { f(x); } // OK
 #endif
diff --git a/clang/test/CodeGen/attr-arm-sve-vector-bits-call.c b/clang/test/CodeGen/attr-arm-sve-vector-bits-call.c
--- a/clang/test/CodeGen/attr-arm-sve-vector-bits-call.c
+++ b/clang/test/CodeGen/attr-arm-sve-vector-bits-call.c
@@ -24,17 +24,14 @@
 
 // CHECK-LABEL: @fixed_caller(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[X:%.*]] = alloca <16 x i32>, align 16
 // CHECK-NEXT:    [[RETVAL_COERCE:%.*]] = alloca <vscale x 4 x i32>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <16 x i32>* [[X]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[X_COERCE:%.*]], <vscale x 4 x i32>* [[TMP0]], align 16
-// CHECK-NEXT:    [[X1:%.*]] = load <16 x i32>, <16 x i32>* [[X]], align 16, [[TBAA6:!tbaa !.*]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[X1]], i64 0)
+// CHECK-NEXT:    [[X:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[X]], i64 0)
 // CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[CASTSCALABLESVE]], i64 0)
 // CHECK-NEXT:    [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 4 x i32>* [[RETVAL_COERCE]] to <16 x i32>*
 // CHECK-NEXT:    store <16 x i32> [[CASTFIXEDSVE]], <16 x i32>* [[RETVAL_0__SROA_CAST]], align 16
-// CHECK-NEXT:    [[TMP1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
-// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 fixed_int32_t fixed_caller(fixed_int32_t x) {
   return sizeless_callee(x);
@@ -42,15 +39,12 @@
 
 // CHECK-LABEL: @fixed_callee(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[X:%.*]] = alloca <16 x i32>, align 16
 // CHECK-NEXT:    [[RETVAL_COERCE:%.*]] = alloca <vscale x 4 x i32>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <16 x i32>* [[X]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[X_COERCE:%.*]], <vscale x 4 x i32>* [[TMP0]], align 16
-// CHECK-NEXT:    [[X1:%.*]] = load <16 x i32>, <16 x i32>* [[X]], align 16, [[TBAA6]]
+// CHECK-NEXT:    [[X:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
 // CHECK-NEXT:    [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 4 x i32>* [[RETVAL_COERCE]] to <16 x i32>*
-// CHECK-NEXT:    store <16 x i32> [[X1]], <16 x i32>* [[RETVAL_0__SROA_CAST]], align 16
-// CHECK-NEXT:    [[TMP1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
-// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+// CHECK-NEXT:    store <16 x i32> [[X]], <16 x i32>* [[RETVAL_0__SROA_CAST]], align 16
+// CHECK-NEXT:    [[TMP0:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 fixed_int32_t fixed_callee(fixed_int32_t x) {
   return x;
@@ -67,7 +61,7 @@
 // CHECK-NEXT:    [[CALL:%.*]] = call <vscale x 4 x i32> @fixed_callee(<vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i32>* [[COERCE1]] to <vscale x 4 x i32>*
 // CHECK-NEXT:    store <vscale x 4 x i32> [[CALL]], <vscale x 4 x i32>* [[TMP1]], align 16
-// CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i32>, <16 x i32>* [[COERCE1]], align 16, [[TBAA6]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i32>, <16 x i32>* [[COERCE1]], align 16, [[TBAA6:!tbaa !.*]]
 // CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TMP2]], i64 0)
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[CASTSCALABLESVE]]
 //
@@ -81,24 +75,18 @@
 
 // CHECK-LABEL: @call_int32_ff(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[OP1:%.*]] = alloca <16 x i32>, align 16
-// CHECK-NEXT:    [[OP2:%.*]] = alloca <16 x i32>, align 16
 // CHECK-NEXT:    [[RETVAL_COERCE:%.*]] = alloca <vscale x 4 x i32>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <16 x i32>* [[OP1]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[OP1_COERCE:%.*]], <vscale x 4 x i32>* [[TMP0]], align 16
-// CHECK-NEXT:    [[OP11:%.*]] = load <16 x i32>, <16 x i32>* [[OP1]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i32>* [[OP2]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[OP2_COERCE:%.*]], <vscale x 4 x i32>* [[TMP1]], align 16
-// CHECK-NEXT:    [[OP22:%.*]] = load <16 x i32>, <16 x i32>* [[OP2]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[OP11]], i64 0)
-// CHECK-NEXT:    [[CASTSCALABLESVE3:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[OP22]], i64 0)
-// CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP2]], <vscale x 4 x i32> [[CASTSCALABLESVE]], <vscale x 4 x i32> [[CASTSCALABLESVE3]])
-// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[TMP3]], i64 0)
+// CHECK-NEXT:    [[OP1:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[OP2:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE1:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[OP1]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE3:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[OP2]], i64 0)
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[CASTSCALABLESVE]], <vscale x 4 x i32> [[CASTSCALABLESVE3]])
+// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[TMP1]], i64 0)
 // CHECK-NEXT:    [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 4 x i32>* [[RETVAL_COERCE]] to <16 x i32>*
 // CHECK-NEXT:    store <16 x i32> [[CASTFIXEDSVE]], <16 x i32>* [[RETVAL_0__SROA_CAST]], align 16
-// CHECK-NEXT:    [[TMP4:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
-// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP4]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 fixed_int32_t call_int32_ff(svbool_t pg, fixed_int32_t op1, fixed_int32_t op2) {
   return svsel(pg, op1, op2);
@@ -106,24 +94,18 @@
 
 // CHECK-LABEL: @call_float64_ff(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[OP1:%.*]] = alloca <8 x double>, align 16
-// CHECK-NEXT:    [[OP2:%.*]] = alloca <8 x double>, align 16
 // CHECK-NEXT:    [[RETVAL_COERCE:%.*]] = alloca <vscale x 2 x double>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <8 x double>* [[OP1]] to <vscale x 2 x double>*
-// CHECK-NEXT:    store <vscale x 2 x double> [[OP1_COERCE:%.*]], <vscale x 2 x double>* [[TMP0]], align 16
-// CHECK-NEXT:    [[OP11:%.*]] = load <8 x double>, <8 x double>* [[OP1]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x double>* [[OP2]] to <vscale x 2 x double>*
-// CHECK-NEXT:    store <vscale x 2 x double> [[OP2_COERCE:%.*]], <vscale x 2 x double>* [[TMP1]], align 16
-// CHECK-NEXT:    [[OP22:%.*]] = load <8 x double>, <8 x double>* [[OP2]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[OP11]], i64 0)
-// CHECK-NEXT:    [[CASTSCALABLESVE3:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[OP22]], i64 0)
-// CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP2]], <vscale x 2 x double> [[CASTSCALABLESVE]], <vscale x 2 x double> [[CASTSCALABLESVE3]])
-// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[TMP3]], i64 0)
+// CHECK-NEXT:    [[OP1:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[OP2:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[X_COERCE1:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[OP1]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE3:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[OP2]], i64 0)
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[CASTSCALABLESVE]], <vscale x 2 x double> [[CASTSCALABLESVE3]])
+// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[TMP1]], i64 0)
 // CHECK-NEXT:    [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 2 x double>* [[RETVAL_COERCE]] to <8 x double>*
 // CHECK-NEXT:    store <8 x double> [[CASTFIXEDSVE]], <8 x double>* [[RETVAL_0__SROA_CAST]], align 16
-// CHECK-NEXT:    [[TMP4:%.*]] = load <vscale x 2 x double>, <vscale x 2 x double>* [[RETVAL_COERCE]], align 16
-// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP4]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load <vscale x 2 x double>, <vscale x 2 x double>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 fixed_float64_t call_float64_ff(svbool_t pg, fixed_float64_t op1, fixed_float64_t op2) {
   return svsel(pg, op1, op2);
@@ -168,19 +150,16 @@
 
 // CHECK-LABEL: @call_int32_fs(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[OP1:%.*]] = alloca <16 x i32>, align 16
 // CHECK-NEXT:    [[RETVAL_COERCE:%.*]] = alloca <vscale x 4 x i32>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <16 x i32>* [[OP1]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[OP1_COERCE:%.*]], <vscale x 4 x i32>* [[TMP0]], align 16
-// CHECK-NEXT:    [[OP11:%.*]] = load <16 x i32>, <16 x i32>* [[OP1]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[OP11]], i64 0)
-// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP1]], <vscale x 4 x i32> [[CASTSCALABLESVE]], <vscale x 4 x i32> [[OP2:%.*]])
-// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[TMP2]], i64 0)
+// CHECK-NEXT:    [[OP1:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[OP1]], i64 0)
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[CASTSCALABLESVE]], <vscale x 4 x i32> [[OP2:%.*]])
+// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[TMP1]], i64 0)
 // CHECK-NEXT:    [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 4 x i32>* [[RETVAL_COERCE]] to <16 x i32>*
 // CHECK-NEXT:    store <16 x i32> [[CASTFIXEDSVE]], <16 x i32>* [[RETVAL_0__SROA_CAST]], align 16
-// CHECK-NEXT:    [[TMP3:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
-// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 fixed_int32_t call_int32_fs(svbool_t pg, fixed_int32_t op1, svint32_t op2) {
   return svsel(pg, op1, op2);
@@ -188,19 +167,16 @@
 
 // CHECK-LABEL: @call_float64_fs(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[OP1:%.*]] = alloca <8 x double>, align 16
 // CHECK-NEXT:    [[RETVAL_COERCE:%.*]] = alloca <vscale x 2 x double>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <8 x double>* [[OP1]] to <vscale x 2 x double>*
-// CHECK-NEXT:    store <vscale x 2 x double> [[OP1_COERCE:%.*]], <vscale x 2 x double>* [[TMP0]], align 16
-// CHECK-NEXT:    [[OP11:%.*]] = load <8 x double>, <8 x double>* [[OP1]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[OP11]], i64 0)
-// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP1]], <vscale x 2 x double> [[CASTSCALABLESVE]], <vscale x 2 x double> [[OP2:%.*]])
-// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[TMP2]], i64 0)
+// CHECK-NEXT:    [[OP1:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[OP1]], i64 0)
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[CASTSCALABLESVE]], <vscale x 2 x double> [[OP2:%.*]])
+// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[TMP1]], i64 0)
 // CHECK-NEXT:    [[RETVAL_0__SROA_CAST:%.*]] = bitcast <vscale x 2 x double>* [[RETVAL_COERCE]] to <8 x double>*
 // CHECK-NEXT:    store <8 x double> [[CASTFIXEDSVE]], <8 x double>* [[RETVAL_0__SROA_CAST]], align 16
-// CHECK-NEXT:    [[TMP3:%.*]] = load <vscale x 2 x double>, <vscale x 2 x double>* [[RETVAL_COERCE]], align 16
-// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load <vscale x 2 x double>, <vscale x 2 x double>* [[RETVAL_COERCE]], align 16
+// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 fixed_float64_t call_float64_fs(svbool_t pg, fixed_float64_t op1, svfloat64_t op2) {
   return svsel(pg, op1, op2);
diff --git a/clang/test/CodeGen/attr-arm-sve-vector-bits-cast.c b/clang/test/CodeGen/attr-arm-sve-vector-bits-cast.c
--- a/clang/test/CodeGen/attr-arm-sve-vector-bits-cast.c
+++ b/clang/test/CodeGen/attr-arm-sve-vector-bits-cast.c
@@ -13,11 +13,8 @@
 
 // CHECK-LABEL: @to_svint32_t(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TYPE:%.*]] = alloca <16 x i32>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <16 x i32>* [[TYPE]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[TYPE_COERCE:%.*]], <vscale x 4 x i32>* [[TMP0]], align 16
-// CHECK-NEXT:    [[TYPE1:%.*]] = load <16 x i32>, <16 x i32>* [[TYPE]], align 16, [[TBAA6:!tbaa !.*]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TYPE1]], i64 0)
+// CHECK-NEXT:    [[TYPE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TYPE]], i64 0)
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[CASTSCALABLESVE]]
 //
 svint32_t to_svint32_t(fixed_int32_t type) {
@@ -39,11 +36,8 @@
 
 // CHECK-LABEL: @to_svfloat64_t(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TYPE:%.*]] = alloca <8 x double>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <8 x double>* [[TYPE]] to <vscale x 2 x double>*
-// CHECK-NEXT:    store <vscale x 2 x double> [[TYPE_COERCE:%.*]], <vscale x 2 x double>* [[TMP0]], align 16
-// CHECK-NEXT:    [[TYPE1:%.*]] = load <8 x double>, <8 x double>* [[TYPE]], align 16, [[TBAA6]]
-// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[TYPE1]], i64 0)
+// CHECK-NEXT:    [[TYPE:%.*]] = call <8 x double> @llvm.experimental.vector.extract.v8f64.nxv2f64(<vscale x 2 x double> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> [[TYPE]], i64 0)
 // CHECK-NEXT:    ret <vscale x 2 x double> [[CASTSCALABLESVE]]
 //
 svfloat64_t to_svfloat64_t(fixed_float64_t type) {
@@ -69,7 +63,7 @@
 // CHECK-NEXT:    [[TYPE_ADDR:%.*]] = alloca <8 x i8>, align 16
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <8 x i8>* [[TYPE]] to <vscale x 16 x i1>*
 // CHECK-NEXT:    store <vscale x 16 x i1> [[TYPE_COERCE:%.*]], <vscale x 16 x i1>* [[TMP0]], align 16
-// CHECK-NEXT:    [[TYPE1:%.*]] = load <8 x i8>, <8 x i8>* [[TYPE]], align 16, [[TBAA6]]
+// CHECK-NEXT:    [[TYPE1:%.*]] = load <8 x i8>, <8 x i8>* [[TYPE]], align 16, [[TBAA6:!tbaa !.*]]
 // CHECK-NEXT:    store <8 x i8> [[TYPE1]], <8 x i8>* [[TYPE_ADDR]], align 16, [[TBAA6]]
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8>* [[TYPE_ADDR]] to <vscale x 16 x i1>*
 // CHECK-NEXT:    [[TMP2:%.*]] = load <vscale x 16 x i1>, <vscale x 16 x i1>* [[TMP1]], align 16, [[TBAA6]]
@@ -130,11 +124,8 @@
 
 // CHECK-LABEL: @from_fixed_int32_t__to_gnu_int32_t(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[TYPE:%.*]] = alloca <16 x i32>, align 16
-// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <16 x i32>* [[TYPE]] to <vscale x 4 x i32>*
-// CHECK-NEXT:    store <vscale x 4 x i32> [[TYPE_COERCE:%.*]], <vscale x 4 x i32>* [[TMP0]], align 16
-// CHECK-NEXT:    [[TYPE1:%.*]] = load <16 x i32>, <16 x i32>* [[TYPE]], align 16, [[TBAA6]]
-// CHECK-NEXT:    store <16 x i32> [[TYPE1]], <16 x i32>* [[AGG_RESULT:%.*]], align 16, [[TBAA6]]
+// CHECK-NEXT:    [[TYPE:%.*]] = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> [[X_COERCE:%.*]], i64 0)
+// CHECK-NEXT:    store <16 x i32> [[TYPE]], <16 x i32>* [[AGG_RESULT:%.*]], align 16, [[TBAA6]]
 // CHECK-NEXT:    ret void
 //
 gnu_int32_t from_fixed_int32_t__to_gnu_int32_t(fixed_int32_t type) {