// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple riscv64-none-linux-gnu -target-feature +zve64d \
// RUN: -target-feature +f -target-feature +d -disable-O0-optnone \
// RUN: -mvscale-min=4 -mvscale-max=4 -emit-llvm -o - %s | \
// RUN: opt -S -passes=sroa | FileCheck %s

// REQUIRES: riscv-registered-target

#include <stdint.h>

typedef __rvv_int8m1_t vint8m1_t;
typedef __rvv_uint8m1_t vuint8m1_t;
typedef __rvv_int16m1_t vint16m1_t;
typedef __rvv_uint16m1_t vuint16m1_t;
typedef __rvv_int32m1_t vint32m1_t;
typedef __rvv_uint32m1_t vuint32m1_t;
typedef __rvv_int64m1_t vint64m1_t;
typedef __rvv_uint64m1_t vuint64m1_t;
typedef __rvv_float32m1_t vfloat32m1_t;
typedef __rvv_float64m1_t vfloat64m1_t;

typedef vint8m1_t fixed_int8m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vint16m1_t fixed_int16m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vint32m1_t fixed_int32m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vint64m1_t fixed_int64m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));

typedef vuint8m1_t fixed_uint8m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vuint16m1_t fixed_uint16m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vuint32m1_t fixed_uint32m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vuint64m1_t fixed_uint64m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));

typedef vfloat32m1_t fixed_float32m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vfloat64m1_t fixed_float64m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));

// CHECK-LABEL: @lshift_i8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <32 x i8> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_int8m1_t lshift_i8(fixed_int8m1_t a, fixed_int8m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_i8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = ashr <32 x i8> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_int8m1_t rshift_i8(fixed_int8m1_t a, fixed_int8m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <32 x i8> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_uint8m1_t lshift_u8(fixed_uint8m1_t a, fixed_uint8m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = lshr <32 x i8> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_uint8m1_t rshift_u8(fixed_uint8m1_t a, fixed_uint8m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_i16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <16 x i16> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_int16m1_t lshift_i16(fixed_int16m1_t a, fixed_int16m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_i16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = ashr <16 x i16> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_int16m1_t rshift_i16(fixed_int16m1_t a, fixed_int16m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <16 x i16> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_uint16m1_t lshift_u16(fixed_uint16m1_t a, fixed_uint16m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = lshr <16 x i16> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_uint16m1_t rshift_u16(fixed_uint16m1_t a, fixed_uint16m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_i32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <8 x i32> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t lshift_i32(fixed_int32m1_t a, fixed_int32m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_i32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = ashr <8 x i32> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t rshift_i32(fixed_int32m1_t a, fixed_int32m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <8 x i32> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_uint32m1_t lshift_u32(fixed_uint32m1_t a, fixed_uint32m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = lshr <8 x i32> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_uint32m1_t rshift_u32(fixed_uint32m1_t a, fixed_uint32m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_i64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <4 x i64> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_int64m1_t lshift_i64(fixed_int64m1_t a, fixed_int64m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_i64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = ashr <4 x i64> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_int64m1_t rshift_i64(fixed_int64m1_t a, fixed_int64m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHL:%.*]] = shl <4 x i64> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_uint64m1_t lshift_u64(fixed_uint64m1_t a, fixed_uint64m1_t b) {
  return a << b;
}

// CHECK-LABEL: @rshift_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[B:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[B_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SHR:%.*]] = lshr <4 x i64> [[A]], [[B]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_uint64m1_t rshift_u64(fixed_uint64m1_t a, fixed_uint64m1_t b) {
  return a >> b;
}

// CHECK-LABEL: @lshift_i8_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = sext i8 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i32> [[SPLAT_SPLATINSERT]], <32 x i32> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <32 x i32> [[SPLAT_SPLAT]] to <32 x i8>
// CHECK-NEXT:    [[SHL:%.*]] = shl <32 x i8> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_int8m1_t lshift_i8_rsplat(fixed_int8m1_t a, int8_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_i8_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i8> poison, i8 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i8> [[SPLAT_SPLATINSERT]], <32 x i8> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <32 x i8> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_int8m1_t lshift_i8_lsplat(fixed_int8m1_t a, int8_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_i8_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = sext i8 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i32> [[SPLAT_SPLATINSERT]], <32 x i32> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <32 x i32> [[SPLAT_SPLAT]] to <32 x i8>
// CHECK-NEXT:    [[SHR:%.*]] = ashr <32 x i8> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_int8m1_t rshift_i8_rsplat(fixed_int8m1_t a, int8_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_i8_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i8> poison, i8 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i8> [[SPLAT_SPLATINSERT]], <32 x i8> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = ashr <32 x i8> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_int8m1_t rshift_i8_lsplat(fixed_int8m1_t a, int8_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_u8_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = zext i8 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i32> [[SPLAT_SPLATINSERT]], <32 x i32> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <32 x i32> [[SPLAT_SPLAT]] to <32 x i8>
// CHECK-NEXT:    [[SHL:%.*]] = shl <32 x i8> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_uint8m1_t lshift_u8_rsplat(fixed_uint8m1_t a, uint8_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_u8_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i8> poison, i8 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i8> [[SPLAT_SPLATINSERT]], <32 x i8> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <32 x i8> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_uint8m1_t lshift_u8_lsplat(fixed_uint8m1_t a, uint8_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_u8_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = zext i8 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i32> [[SPLAT_SPLATINSERT]], <32 x i32> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <32 x i32> [[SPLAT_SPLAT]] to <32 x i8>
// CHECK-NEXT:    [[SHR:%.*]] = lshr <32 x i8> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_uint8m1_t rshift_u8_rsplat(fixed_uint8m1_t a, uint8_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_u8_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <32 x i8> poison, i8 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <32 x i8> [[SPLAT_SPLATINSERT]], <32 x i8> poison, <32 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = lshr <32 x i8> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i8> [[CASTSCALABLESVE]]
//
fixed_uint8m1_t rshift_u8_lsplat(fixed_uint8m1_t a, uint8_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_i16_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i32> [[SPLAT_SPLATINSERT]], <16 x i32> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <16 x i32> [[SPLAT_SPLAT]] to <16 x i16>
// CHECK-NEXT:    [[SHL:%.*]] = shl <16 x i16> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_int16m1_t lshift_i16_rsplat(fixed_int16m1_t a, int16_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_i16_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i16> poison, i16 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i16> [[SPLAT_SPLATINSERT]], <16 x i16> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <16 x i16> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_int16m1_t lshift_i16_lsplat(fixed_int16m1_t a, int16_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_i16_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = sext i16 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i32> [[SPLAT_SPLATINSERT]], <16 x i32> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <16 x i32> [[SPLAT_SPLAT]] to <16 x i16>
// CHECK-NEXT:    [[SHR:%.*]] = ashr <16 x i16> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_int16m1_t rshift_i16_rsplat(fixed_int16m1_t a, int16_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_i16_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i16> poison, i16 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i16> [[SPLAT_SPLATINSERT]], <16 x i16> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = ashr <16 x i16> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_int16m1_t rshift_i16_lsplat(fixed_int16m1_t a, int16_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_u16_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = zext i16 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i32> [[SPLAT_SPLATINSERT]], <16 x i32> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <16 x i32> [[SPLAT_SPLAT]] to <16 x i16>
// CHECK-NEXT:    [[SHL:%.*]] = shl <16 x i16> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_uint16m1_t lshift_u16_rsplat(fixed_uint16m1_t a, uint16_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_u16_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i16> poison, i16 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i16> [[SPLAT_SPLATINSERT]], <16 x i16> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <16 x i16> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_uint16m1_t lshift_u16_lsplat(fixed_uint16m1_t a, uint16_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_u16_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[CONV:%.*]] = zext i16 [[B:%.*]] to i32
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i32> poison, i32 [[CONV]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i32> [[SPLAT_SPLATINSERT]], <16 x i32> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SH_PROM:%.*]] = trunc <16 x i32> [[SPLAT_SPLAT]] to <16 x i16>
// CHECK-NEXT:    [[SHR:%.*]] = lshr <16 x i16> [[A]], [[SH_PROM]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_uint16m1_t rshift_u16_rsplat(fixed_uint16m1_t a, uint16_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_u16_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <16 x i16> @llvm.vector.extract.v16i16.nxv4i16(<vscale x 4 x i16> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i16> poison, i16 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i16> [[SPLAT_SPLATINSERT]], <16 x i16> poison, <16 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = lshr <16 x i16> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 4 x i16> @llvm.vector.insert.nxv4i16.v16i16(<vscale x 4 x i16> undef, <16 x i16> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i16> [[CASTSCALABLESVE]]
//
fixed_uint16m1_t rshift_u16_lsplat(fixed_uint16m1_t a, uint16_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_i32_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <8 x i32> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t lshift_i32_rsplat(fixed_int32m1_t a, int32_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_i32_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <8 x i32> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t lshift_i32_lsplat(fixed_int32m1_t a, int32_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_i32_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = ashr <8 x i32> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t rshift_i32_rsplat(fixed_int32m1_t a, int32_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_i32_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = ashr <8 x i32> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t rshift_i32_lsplat(fixed_int32m1_t a, int32_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_u32_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <8 x i32> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_uint32m1_t lshift_u32_rsplat(fixed_uint32m1_t a, uint32_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_u32_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <8 x i32> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_uint32m1_t lshift_u32_lsplat(fixed_uint32m1_t a, uint32_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_u32_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = lshr <8 x i32> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_uint32m1_t rshift_u32_rsplat(fixed_uint32m1_t a, uint32_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_u32_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <8 x i32> poison, i32 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <8 x i32> [[SPLAT_SPLATINSERT]], <8 x i32> poison, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = lshr <8 x i32> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_uint32m1_t rshift_u32_lsplat(fixed_uint32m1_t a, uint32_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_i64_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <4 x i64> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_int64m1_t lshift_i64_rsplat(fixed_int64m1_t a, int64_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_i64_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <4 x i64> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_int64m1_t lshift_i64_lsplat(fixed_int64m1_t a, int64_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_i64_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = ashr <4 x i64> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_int64m1_t rshift_i64_rsplat(fixed_int64m1_t a, int64_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_i64_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = ashr <4 x i64> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_int64m1_t rshift_i64_lsplat(fixed_int64m1_t a, int64_t b) {
  return b >> a;
}

// CHECK-LABEL: @lshift_u64_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <4 x i64> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_uint64m1_t lshift_u64_rsplat(fixed_uint64m1_t a, uint64_t b) {
  return a << b;
}

// CHECK-LABEL: @lshift_u64_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHL:%.*]] = shl <4 x i64> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHL]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_uint64m1_t lshift_u64_lsplat(fixed_uint64m1_t a, uint64_t b) {
  return b << a;
}

// CHECK-LABEL: @rshift_u64_rsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = lshr <4 x i64> [[A]], [[SPLAT_SPLAT]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_uint64m1_t rshift_u64_rsplat(fixed_uint64m1_t a, uint64_t b) {
  return a >> b;
}

// CHECK-LABEL: @rshift_u64_lsplat(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[A:%.*]] = call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[A_COERCE:%.*]], i64 0)
// CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[B:%.*]], i64 0
// CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i64> [[SPLAT_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[SHR:%.*]] = lshr <4 x i64> [[SPLAT_SPLAT]], [[A]]
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[SHR]], i64 0)
// CHECK-NEXT:    ret <vscale x 1 x i64> [[CASTSCALABLESVE]]
//
fixed_uint64m1_t rshift_u64_lsplat(fixed_uint64m1_t a, uint64_t b) {
  return b >> a;
}