diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vmullbq.c b/clang/test/CodeGen/arm-mve-intrinsics/vmullbq.c
@@ -0,0 +1,125 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vmullbq_int_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vmull.v8i16.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 0)
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vmullbq_int_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_int(a, b);
+#else /* POLYMORPHIC */
+    return vmullbq_int_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_int_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vmull.v4i32.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 0)
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+int32x4_t test_vmullbq_int_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_int(a, b);
+#else /* POLYMORPHIC */
+    return vmullbq_int_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_int_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vmull.v2i64.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 0)
+// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
+//
+uint64x2_t test_vmullbq_int_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_int(a, b);
+#else /* POLYMORPHIC */
+    return vmullbq_int_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_poly_p16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vmull.poly.v4i32.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 0)
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vmullbq_poly_p16(uint16x8_t a, uint16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_poly(a, b);
+#else /* POLYMORPHIC */
+    return vmullbq_poly_p16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_int_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.mull.int.predicated.v8i16.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 0, <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+int16x8_t test_vmullbq_int_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_int_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmullbq_int_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_int_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.mull.int.predicated.v4i32.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 0, <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+uint32x4_t test_vmullbq_int_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_int_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmullbq_int_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_int_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.mull.int.predicated.v2i64.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 0, <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
+//
+int64x2_t test_vmullbq_int_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_int_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmullbq_int_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmullbq_poly_m_p8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.mull.poly.predicated.v8i16.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 0, <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vmullbq_poly_m_p8(uint8x16_t inactive, uint8x16_t a, uint8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmullbq_poly_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmullbq_poly_m_p8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vmulltq.c b/clang/test/CodeGen/arm-mve-intrinsics/vmulltq.c
@@ -0,0 +1,125 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vmulltq_int_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vmull.v8i16.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 1)
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vmulltq_int_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_int(a, b);
+#else /* POLYMORPHIC */
+    return vmulltq_int_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_int_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vmull.v4i32.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1)
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+int32x4_t test_vmulltq_int_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_int(a, b);
+#else /* POLYMORPHIC */
+    return vmulltq_int_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_int_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vmull.v2i64.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1)
+// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
+//
+uint64x2_t test_vmulltq_int_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_int(a, b);
+#else /* POLYMORPHIC */
+    return vmulltq_int_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_poly_p16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vmull.poly.v4i32.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1)
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vmulltq_poly_p16(uint16x8_t a, uint16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_poly(a, b);
+#else /* POLYMORPHIC */
+    return vmulltq_poly_p16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_int_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.mull.int.predicated.v8i16.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 1, <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+int16x8_t test_vmulltq_int_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_int_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmulltq_int_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_int_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.mull.int.predicated.v4i32.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+uint32x4_t test_vmulltq_int_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_int_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmulltq_int_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_int_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.mull.int.predicated.v2i64.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1, <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
+//
+int64x2_t test_vmulltq_int_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_int_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmulltq_int_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vmulltq_poly_m_p8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.mull.poly.predicated.v8i16.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 1, <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vmulltq_poly_m_p8(uint8x16_t inactive, uint8x16_t a, uint8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vmulltq_poly_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vmulltq_poly_m_p8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vqaddq.c b/clang/test/CodeGen/arm-mve-intrinsics/vqaddq.c
@@ -0,0 +1,95 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vqaddq_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
+//
+uint8x16_t test_vqaddq_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vqaddq(a, b);
+#else /* POLYMORPHIC */
+    return vqaddq_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqaddq_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vqaddq_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vqaddq(a, b);
+#else /* POLYMORPHIC */
+    return vqaddq_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqaddq_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vqaddq_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vqaddq(a, b);
+#else /* POLYMORPHIC */
+    return vqaddq_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqaddq_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.qadd.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
+//
+int8x16_t test_vqaddq_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqaddq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqaddq_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqaddq_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.qadd.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vqaddq_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqaddq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqaddq_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqaddq_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.qadd.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+int32x4_t test_vqaddq_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqaddq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqaddq_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vqdmulhq.c b/clang/test/CodeGen/arm-mve-intrinsics/vqdmulhq.c
@@ -0,0 +1,95 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vqdmulhq_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vqdmulh.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
+//
+uint8x16_t test_vqdmulhq_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vqdmulhq(a, b);
+#else /* POLYMORPHIC */
+    return vqdmulhq_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqdmulhq_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vqdmulh.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vqdmulhq_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vqdmulhq(a, b);
+#else /* POLYMORPHIC */
+    return vqdmulhq_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqdmulhq_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vqdmulh.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vqdmulhq_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vqdmulhq(a, b);
+#else /* POLYMORPHIC */
+    return vqdmulhq_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqdmulhq_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.qdmulh.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
+//
+int8x16_t test_vqdmulhq_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqdmulhq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqdmulhq_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqdmulhq_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.qdmulh.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vqdmulhq_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqdmulhq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqdmulhq_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqdmulhq_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.qdmulh.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+int32x4_t test_vqdmulhq_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqdmulhq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqdmulhq_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vqrdmulhq.c b/clang/test/CodeGen/arm-mve-intrinsics/vqrdmulhq.c
@@ -0,0 +1,95 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vqrdmulhq_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vqrdmulh.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
+//
+uint8x16_t test_vqrdmulhq_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vqrdmulhq(a, b);
+#else /* POLYMORPHIC */
+    return vqrdmulhq_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqrdmulhq_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vqrdmulh.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vqrdmulhq_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vqrdmulhq(a, b);
+#else /* POLYMORPHIC */
+    return vqrdmulhq_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqrdmulhq_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vqrdmulh.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vqrdmulhq_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vqrdmulhq(a, b);
+#else /* POLYMORPHIC */
+    return vqrdmulhq_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqrdmulhq_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.qrdmulh.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
+//
+int8x16_t test_vqrdmulhq_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqrdmulhq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqrdmulhq_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqrdmulhq_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.qrdmulh.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vqrdmulhq_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqrdmulhq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqrdmulhq_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqrdmulhq_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.qrdmulh.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+int32x4_t test_vqrdmulhq_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqrdmulhq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqrdmulhq_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vqsubq.c b/clang/test/CodeGen/arm-mve-intrinsics/vqsubq.c
@@ -0,0 +1,95 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vqsubq_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
+//
+uint8x16_t test_vqsubq_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vqsubq(a, b);
+#else /* POLYMORPHIC */
+    return vqsubq_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqsubq_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vqsubq_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vqsubq(a, b);
+#else /* POLYMORPHIC */
+    return vqsubq_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqsubq_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vqsubq_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vqsubq(a, b);
+#else /* POLYMORPHIC */
+    return vqsubq_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqsubq_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.qsub.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
+//
+int8x16_t test_vqsubq_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqsubq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqsubq_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqsubq_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.qsub.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vqsubq_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqsubq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqsubq_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vqsubq_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.qsub.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+int32x4_t test_vqsubq_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vqsubq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vqsubq_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/test/CodeGen/arm-mve-intrinsics/vrhaddq.c b/clang/test/CodeGen/arm-mve-intrinsics/vrhaddq.c
@@ -0,0 +1,95 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @test_vrhaddq_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vrhadd.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
+//
+uint8x16_t test_vrhaddq_u8(uint8x16_t a, uint8x16_t b)
+{
+#ifdef POLYMORPHIC
+    return vrhaddq(a, b);
+#else /* POLYMORPHIC */
+    return vrhaddq_u8(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vrhaddq_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vrhadd.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vrhaddq_s16(int16x8_t a, int16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vrhaddq(a, b);
+#else /* POLYMORPHIC */
+    return vrhaddq_s16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vrhaddq_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vrhadd.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vrhaddq_u32(uint32x4_t a, uint32x4_t b)
+{
+#ifdef POLYMORPHIC
+    return vrhaddq(a, b);
+#else /* POLYMORPHIC */
+    return vrhaddq_u32(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vrhaddq_m_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.rhadd.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
+//
+int8x16_t test_vrhaddq_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vrhaddq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vrhaddq_m_s8(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vrhaddq_m_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.rhadd.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
+//
+uint16x8_t test_vrhaddq_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vrhaddq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vrhaddq_m_u16(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @test_vrhaddq_m_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
+// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.rhadd.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
+// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
+//
+int32x4_t test_vrhaddq_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    return vrhaddq_m(inactive, a, b, p);
+#else /* POLYMORPHIC */
+    return vrhaddq_m_s32(inactive, a, b, p);
+#endif /* POLYMORPHIC */
+}
diff --git a/clang/utils/TableGen/MveEmitter.cpp b/clang/utils/TableGen/MveEmitter.cpp
@@ -143,7 +143,7 @@ class Type {
   virtual std::string llvmName() const {
     PrintFatalError("no LLVM type name available for type " + cName());
   }
-  virtual std::string acleSuffix() const {
+  virtual std::string acleSuffix(std::string) const {
     PrintFatalError("no ACLE suffix available for this type");
   }
 };
@@ -180,7 +180,7 @@ class VoidType : public Type {
   std::string cName() const override { return "void"; }
 
   static bool classof(const Type *T) { return T->typeKind() == TypeKind::Void; }
-  std::string acleSuffix() const override { return ""; }
+  std::string acleSuffix(std::string) const override { return ""; }
 };
 
 class PointerType : public Type {
@@ -266,8 +266,9 @@ class ScalarType : public CRegularNamedType {
     }
     return "Int" + utostr(Bits) + "Ty";
   }
-  std::string acleSuffix() const override {
-    return "_" + toLetter(Kind) + utostr(Bits);
+  std::string acleSuffix(std::string overrideLetter) const override {
+    return "_" + (overrideLetter.size() ? overrideLetter : toLetter(Kind))
+               + utostr(Bits);
   }
   bool isInteger() const { return Kind != ScalarTypeKind::Float; }
   bool requiresFloat() const override { return !isInteger(); }
@@ -1093,6 +1094,16 @@ const Type *MveEmitter::getType(DagInit *D, const Type *Param) {
     PrintFatalError("Cannot find a type to satisfy CopyKind");
   }
 
+  if (Op->getName() == "CTO_DoubleSize") {
+    const ScalarType *STKind = cast<ScalarType>(getType(D->getArg(0), Param));
+    for (const auto &kv : ScalarTypes) {
+      const ScalarType *RT = kv.second.get();
+      if (RT->kind() == STKind->kind() && RT->sizeInBits() == 2*STKind->sizeInBits())
+        return RT;
+    }
+    PrintFatalError("Cannot find a type to satisfy DoubleSize");
+  }
+
   PrintFatalError("Bad operator in type dag expression");
 }
 
@@ -1251,7 +1262,8 @@ ACLEIntrinsic::ACLEIntrinsic(MveEmitter &ME, Record *R, const Type *Param)
   StringRef BaseName =
       (R->isSubClassOf("NameOverride") ? R->getValueAsString("basename")
                                        : R->getName());
-  FullName = (Twine(BaseName) + Param->acleSuffix()).str();
+  StringRef overrideLetter = R->getValueAsString("overrideKindLetter");
+  FullName = (Twine(BaseName) + Param->acleSuffix(overrideLetter)).str();
 
   // Derive the intrinsic's polymorphic name, by removing components from the
   // full name as specified by its 'pnt' member ('polymorphic name type'),

diff --git a/llvm/include/llvm/IR/IntrinsicsARM.td b/llvm/include/llvm/IR/IntrinsicsARM.td
@@ -837,9 +837,38 @@ def int_arm_mve_mul_predicated: Intrinsic<[llvm_anyvector_ty],
 def int_arm_mve_mulh_predicated: Intrinsic<[llvm_anyvector_ty],
    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
    [IntrNoMem]>;
+def int_arm_mve_qdmulh_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
 def int_arm_mve_rmulh_predicated: Intrinsic<[llvm_anyvector_ty],
    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
    [IntrNoMem]>;
+def int_arm_mve_qrdmulh_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
+def int_arm_mve_mull_int_predicated: Intrinsic<[llvm_anyvector_ty],
+   [llvm_anyvector_ty, LLVMMatchType<1>, llvm_i32_ty, llvm_anyvector_ty,
+    LLVMMatchType<1>],
+   [IntrNoMem]>;
+def int_arm_mve_mull_poly_predicated: Intrinsic<[llvm_anyvector_ty],
+   [llvm_anyvector_ty, LLVMMatchType<1>, llvm_i32_ty, llvm_anyvector_ty,
+    LLVMMatchType<1>],
+   [IntrNoMem]>;
+def int_arm_mve_qadd_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
+def int_arm_mve_hadd_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
+def int_arm_mve_rhadd_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
+def int_arm_mve_qsub_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
+def int_arm_mve_hsub_predicated: Intrinsic<[llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyvector_ty, LLVMMatchType<0>],
+   [IntrNoMem]>;
 
 defm int_arm_mve_minv: IntrinsicSignSuffix<[llvm_i32_ty],
    [llvm_i32_ty, llvm_anyvector_ty], [IntrNoMem]>;
@@ -925,9 +954,30 @@ def int_arm_mve_vadc_predicated: Intrinsic<
 def int_arm_mve_vmulh: Intrinsic<
    [llvm_anyvector_ty],
    [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
+def int_arm_mve_vqdmulh: Intrinsic<
+   [llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
+def int_arm_mve_vhadd: Intrinsic<
+   [llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
+def int_arm_mve_vrhadd: Intrinsic<
+   [llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
+def int_arm_mve_vhsub: Intrinsic<
+   [llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
 def int_arm_mve_vrmulh: Intrinsic<
    [llvm_anyvector_ty],
    [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
+def int_arm_mve_vqrdmulh: Intrinsic<
+   [llvm_anyvector_ty],
+   [LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
+def int_arm_mve_vmull: Intrinsic<
+   [llvm_anyvector_ty],
+   [llvm_anyvector_ty, LLVMMatchType<1>, llvm_i32_ty], [IntrNoMem]>;
+def int_arm_mve_vmull_poly: Intrinsic<
+   [llvm_anyvector_ty],
+   [llvm_anyvector_ty, LLVMMatchType<1>, llvm_i32_ty], [IntrNoMem]>;
 
 // Intrinsic with a predicated and a non-predicated case. The predicated case
 // has two additional parameters: inactive (the value for inactive lanes, can

diff --git a/llvm/lib/Target/ARM/ARMInstrMVE.td b/llvm/lib/Target/ARM/ARMInstrMVE.td
diff --git a/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp b/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
@@ -7895,10 +7895,10 @@ bool ARMAsmParser::validateInstruction(MCInst &Inst,
   case ARM::MVE_VQDMULLs32bh:
   case ARM::MVE_VQDMULLs32th:
   case ARM::MVE_VCMULf32:
-  case ARM::MVE_VMULLs32bh:
-  case ARM::MVE_VMULLs32th:
-  case ARM::MVE_VMULLu32bh:
-  case ARM::MVE_VMULLu32th: {
+  case ARM::MVE_VMULLBs32:
+  case ARM::MVE_VMULLTs32:
+  case ARM::MVE_VMULLBu32:
+  case ARM::MVE_VMULLTu32: {
     if (Operands[3]->getReg() == Operands[4]->getReg()) {
       return Error (Operands[3]->getStartLoc(),
                     "Qd register and Qn register can't be identical");

diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vhaddq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vhaddq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vhaddq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhaddq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vhadd.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.arm.mve.vhadd.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.arm.mve.vhadd.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vhaddq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhaddq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vhadd.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vhadd.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vhadd.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vhaddq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhaddq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vhadd.s32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vhadd.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vhadd.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vhaddq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhaddq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vhaddt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.hadd.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <16 x i8> @llvm.arm.mve.hadd.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vhaddq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhaddq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vhaddt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.hadd.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.hadd.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vhaddq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhaddq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vhaddt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.hadd.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.hadd.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #1
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vhsubq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vhsubq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vhsubq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhsubq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vhsub.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.arm.mve.vhsub.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.arm.mve.vhsub.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vhsubq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhsubq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vhsub.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vhsub.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vhsub.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vhsubq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhsubq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vhsub.s32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vhsub.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vhsub.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vhsubq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhsubq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vhsubt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.hsub.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <16 x i8> @llvm.arm.mve.hsub.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vhsubq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhsubq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vhsubt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.hsub.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.hsub.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vhsubq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vhsubq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vhsubt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.hsub.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.hsub.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #1
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vmullbq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vmullbq.ll
@@ -0,0 +1,121 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <8 x i16> @test_vmullbq_int_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_int_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullb.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vmull.v8i16.v16i8(<16 x i8> %a, <16 x i8> %b, i32 0)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vmull.v8i16.v16i8(<16 x i8>, <16 x i8>, i32) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmullbq_int_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_int_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullb.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vmull.v4i32.v8i16(<8 x i16> %a, <8 x i16> %b, i32 0)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vmull.v4i32.v8i16(<8 x i16>, <8 x i16>, i32) #1
+
+define arm_aapcs_vfpcc <2 x i64> @test_vmullbq_int_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_int_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullb.s32 q2, q0, q1
+; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <2 x i64> @llvm.arm.mve.vmull.v2i64.v4i32(<4 x i32> %a, <4 x i32> %b, i32 0)
+  ret <2 x i64> %0
+}
+
+declare <2 x i64> @llvm.arm.mve.vmull.v2i64.v4i32(<4 x i32>, <4 x i32>, i32) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmullbq_poly_p16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_poly_p16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullb.p16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vmull.poly.v4i32.v8i16(<8 x i16> %a, <8 x i16> %b, i32 0)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vmull.poly.v4i32.v8i16(<8 x i16>, <8 x i16>, i32) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vmullbq_int_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_int_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmullbt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.mull.int.predicated.v8i16.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, i32 0, <16 x i1> %1, <16 x i8> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.mull.int.predicated.v8i16.v16i8.v16i1(<16 x i8>, <16 x i8>, i32, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmullbq_int_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_int_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmullbt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.mull.int.predicated.v4i32.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, i32 0, <8 x i1> %1, <8 x i16> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.mull.int.predicated.v4i32.v8i16.v8i1(<8 x i16>, <8 x i16>, i32, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <2 x i64> @test_vmullbq_int_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_int_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmullbt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <2 x i64> @llvm.arm.mve.mull.int.predicated.v2i64.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, i32 0, <4 x i1> %1, <4 x i32> %inactive)
+  ret <2 x i64> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <2 x i64> @llvm.arm.mve.mull.int.predicated.v2i64.v4i32.v4i1(<4 x i32>, <4 x i32>, i32, <4 x i1>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vmullbq_poly_m_p8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmullbq_poly_m_p8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmullbt.p8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.mull.poly.predicated.v8i16.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, i32 0, <16 x i1> %1, <16 x i8> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i16> @llvm.arm.mve.mull.poly.predicated.v8i16.v16i8.v16i1(<16 x i8>, <16 x i8>, i32, <16 x i1>, <16 x i8>) #1
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vmulltq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vmulltq.ll
@@ -0,0 +1,121 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <8 x i16> @test_vmulltq_int_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_int_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullt.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vmull.v8i16.v16i8(<16 x i8> %a, <16 x i8> %b, i32 1)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vmull.v8i16.v16i8(<16 x i8>, <16 x i8>, i32) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmulltq_int_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_int_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullt.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vmull.v4i32.v8i16(<8 x i16> %a, <8 x i16> %b, i32 1)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vmull.v4i32.v8i16(<8 x i16>, <8 x i16>, i32) #1
+
+define arm_aapcs_vfpcc <2 x i64> @test_vmulltq_int_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_int_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullt.s32 q2, q0, q1
+; CHECK-NEXT:    vmov q0, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <2 x i64> @llvm.arm.mve.vmull.v2i64.v4i32(<4 x i32> %a, <4 x i32> %b, i32 1)
+  ret <2 x i64> %0
+}
+
+declare <2 x i64> @llvm.arm.mve.vmull.v2i64.v4i32(<4 x i32>, <4 x i32>, i32) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmulltq_poly_p16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_poly_p16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmullt.p16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vmull.poly.v4i32.v8i16(<8 x i16> %a, <8 x i16> %b, i32 1)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vmull.poly.v4i32.v8i16(<8 x i16>, <8 x i16>, i32) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vmulltq_int_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_int_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmulltt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.mull.int.predicated.v8i16.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, i32 1, <16 x i1> %1, <16 x i8> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.mull.int.predicated.v8i16.v16i8.v16i1(<16 x i8>, <16 x i8>, i32, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmulltq_int_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_int_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmulltt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.mull.int.predicated.v4i32.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, i32 1, <8 x i1> %1, <8 x i16> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.mull.int.predicated.v4i32.v8i16.v8i1(<8 x i16>, <8 x i16>, i32, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <2 x i64> @test_vmulltq_int_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_int_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmulltt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <2 x i64> @llvm.arm.mve.mull.int.predicated.v2i64.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, i32 1, <4 x i1> %1, <4 x i32> %inactive)
+  ret <2 x i64> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <2 x i64> @llvm.arm.mve.mull.int.predicated.v2i64.v4i32.v4i1(<4 x i32>, <4 x i32>, i32, <4 x i1>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vmulltq_poly_m_p8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vmulltq_poly_m_p8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vmulltt.p8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.mull.poly.predicated.v8i16.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, i32 1, <16 x i1> %1, <16 x i8> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i16> @llvm.arm.mve.mull.poly.predicated.v8i16.v16i8.v16i1(<16 x i8>, <16 x i8>, i32, <16 x i1>, <16 x i8>) #1
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqaddq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqaddq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqaddq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqaddq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqadd.u8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqaddq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqaddq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqadd.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqaddq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqaddq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqadd.u32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqaddq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqaddq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqaddt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.qadd.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #2
+
+declare <16 x i8> @llvm.arm.mve.qadd.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #2
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqaddq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqaddq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqaddt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.qadd.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #2
+
+declare <8 x i16> @llvm.arm.mve.qadd.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #2
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqaddq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqaddq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqaddt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.qadd.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #2
+
+declare <4 x i32> @llvm.arm.mve.qadd.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #2
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqdmulhq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqdmulhq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqdmulhq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqdmulhq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqdmulh.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.arm.mve.vqdmulh.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.arm.mve.vqdmulh.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqdmulhq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqdmulhq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqdmulh.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vqdmulh.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vqdmulh.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqdmulhq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqdmulhq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqdmulh.s32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vqdmulh.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vqdmulh.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqdmulhq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqdmulhq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqdmulht.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.qdmulh.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <16 x i8> @llvm.arm.mve.qdmulh.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqdmulhq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqdmulhq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqdmulht.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.qdmulh.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.qdmulh.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqdmulhq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqdmulhq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqdmulht.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.qdmulh.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.qdmulh.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #1
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqrdmulhq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqrdmulhq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqrdmulhq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqrdmulhq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqrdmulh.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.arm.mve.vqrdmulh.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.arm.mve.vqrdmulh.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqrdmulhq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqrdmulhq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqrdmulh.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vqrdmulh.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vqrdmulh.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqrdmulhq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqrdmulhq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqrdmulh.s32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vqrdmulh.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vqrdmulh.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqrdmulhq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqrdmulhq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqrdmulht.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.qrdmulh.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <16 x i8> @llvm.arm.mve.qrdmulh.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqrdmulhq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqrdmulhq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqrdmulht.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.qrdmulh.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.qrdmulh.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqrdmulhq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqrdmulhq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqrdmulht.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.qrdmulh.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.qrdmulh.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #1
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqsubq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vqsubq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqsubq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqsubq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqsub.u8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.usub.sat.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqsubq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqsubq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqsub.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqsubq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqsubq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vqsub.u32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.usub.sat.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vqsubq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqsubq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqsubt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.qsub.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #2
+
+declare <16 x i8> @llvm.arm.mve.qsub.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #2
+
+define arm_aapcs_vfpcc <8 x i16> @test_vqsubq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqsubq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqsubt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.qsub.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #2
+
+declare <8 x i16> @llvm.arm.mve.qsub.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #2
+
+define arm_aapcs_vfpcc <4 x i32> @test_vqsubq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vqsubq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vqsubt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.qsub.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #2
+
+declare <4 x i32> @llvm.arm.mve.qsub.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #2
diff --git a/llvm/test/CodeGen/Thumb2/mve-intrinsics/vrhaddq.ll b/llvm/test/CodeGen/Thumb2/mve-intrinsics/vrhaddq.ll
@@ -0,0 +1,92 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
+
+define arm_aapcs_vfpcc <16 x i8> @test_vrhaddq_u8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vrhaddq_u8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vrhadd.s8 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <16 x i8> @llvm.arm.mve.vrhadd.v16i8(<16 x i8> %a, <16 x i8> %b)
+  ret <16 x i8> %0
+}
+
+declare <16 x i8> @llvm.arm.mve.vrhadd.v16i8(<16 x i8>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vrhaddq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vrhaddq_s16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vrhadd.s16 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <8 x i16> @llvm.arm.mve.vrhadd.v8i16(<8 x i16> %a, <8 x i16> %b)
+  ret <8 x i16> %0
+}
+
+declare <8 x i16> @llvm.arm.mve.vrhadd.v8i16(<8 x i16>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vrhaddq_u32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vrhaddq_u32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vrhadd.s32 q0, q0, q1
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call <4 x i32> @llvm.arm.mve.vrhadd.v4i32(<4 x i32> %a, <4 x i32> %b)
+  ret <4 x i32> %0
+}
+
+declare <4 x i32> @llvm.arm.mve.vrhadd.v4i32(<4 x i32>, <4 x i32>) #1
+
+define arm_aapcs_vfpcc <16 x i8> @test_vrhaddq_m_s8(<16 x i8> %inactive, <16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vrhaddq_m_s8:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vrhaddt.s8 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
+  %2 = tail call <16 x i8> @llvm.arm.mve.rhadd.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1, <16 x i8> %inactive)
+  ret <16 x i8> %2
+}
+
+declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #1
+
+declare <16 x i8> @llvm.arm.mve.rhadd.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>, <16 x i8>) #1
+
+define arm_aapcs_vfpcc <8 x i16> @test_vrhaddq_m_u16(<8 x i16> %inactive, <8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vrhaddq_m_u16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vrhaddt.s16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
+  %2 = tail call <8 x i16> @llvm.arm.mve.rhadd.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1, <8 x i16> %inactive)
+  ret <8 x i16> %2
+}
+
+declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #1
+
+declare <8 x i16> @llvm.arm.mve.rhadd.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>, <8 x i16>) #1
+
+define arm_aapcs_vfpcc <4 x i32> @test_vrhaddq_m_s32(<4 x i32> %inactive, <4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #0 {
+; CHECK-LABEL: test_vrhaddq_m_s32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vmsr p0, r0
+; CHECK-NEXT:    vpst
+; CHECK-NEXT:    vrhaddt.s32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = zext i16 %p to i32
+  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
+  %2 = tail call <4 x i32> @llvm.arm.mve.rhadd.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1, <4 x i32> %inactive)
+  ret <4 x i32> %2
+}
+
+declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #1
+
+declare <4 x i32> @llvm.arm.mve.rhadd.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>, <4 x i32>) #1