test/CodeGen/attr-riscv-rvv-vector-bits-codegen.c

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

// REQUIRES: riscv-registered-target

#include <riscv_vector.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 vint32m1_t fixed_int32m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));

fixed_int32m1_t global_vec;

// CHECK-LABEL: @test_ptr_to_global(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[RETVAL:%.*]] = alloca <8 x i32>, align 8
// CHECK-NEXT:    [[GLOBAL_VEC_PTR:%.*]] = alloca ptr, align 8
// CHECK-NEXT:    store ptr @global_vec, ptr [[GLOBAL_VEC_PTR]], align 8
// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[GLOBAL_VEC_PTR]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i32>, ptr [[TMP0]], align 8
// CHECK-NEXT:    store <8 x i32> [[TMP1]], ptr [[RETVAL]], align 8
// CHECK-NEXT:    [[TMP2:%.*]] = load <8 x i32>, ptr [[RETVAL]], align 8
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP2]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t test_ptr_to_global() {
  fixed_int32m1_t *global_vec_ptr;
  global_vec_ptr = &global_vec;
  return *global_vec_ptr;
}

//
// Test casting pointer from fixed-length array to scalable vector.
// CHECK-LABEL: @array_arg(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[RETVAL:%.*]] = alloca <8 x i32>, align 8
// CHECK-NEXT:    [[ARR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT:    store ptr [[ARR:%.*]], ptr [[ARR_ADDR]], align 8
// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ARR_ADDR]], align 8
// CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds <8 x i32>, ptr [[TMP0]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i32>, ptr [[ARRAYIDX]], align 8
// CHECK-NEXT:    store <8 x i32> [[TMP1]], ptr [[RETVAL]], align 8
// CHECK-NEXT:    [[TMP2:%.*]] = load <8 x i32>, ptr [[RETVAL]], align 8
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP2]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE]]
//
fixed_int32m1_t array_arg(fixed_int32m1_t arr[]) {
  return arr[0];
}

// CHECK-LABEL: @test_cast(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[RETVAL:%.*]] = alloca <8 x i32>, align 8
// CHECK-NEXT:    [[VEC_ADDR:%.*]] = alloca <vscale x 2 x i32>, align 4
// CHECK-NEXT:    store <vscale x 2 x i32> [[VEC:%.*]], ptr [[VEC_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <8 x i32>, ptr @global_vec, align 8
// CHECK-NEXT:    [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP0]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = load <vscale x 2 x i32>, ptr [[VEC_ADDR]], align 4
// CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> poison, <vscale x 2 x i32> [[CASTSCALABLESVE]], <vscale x 2 x i32> [[TMP1]], i64 8)
// CHECK-NEXT:    [[CASTFIXEDSVE:%.*]] = call <8 x i32> @llvm.vector.extract.v8i32.nxv2i32(<vscale x 2 x i32> [[TMP2]], i64 0)
// CHECK-NEXT:    store <8 x i32> [[CASTFIXEDSVE]], ptr [[RETVAL]], align 8
// CHECK-NEXT:    [[TMP3:%.*]] = load <8 x i32>, ptr [[RETVAL]], align 8
// CHECK-NEXT:    [[CASTSCALABLESVE1:%.*]] = call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP3]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i32> [[CASTSCALABLESVE1]]
//
fixed_int32m1_t test_cast(vint32m1_t vec) {
  return __riscv_vadd(global_vec, vec, __riscv_v_fixed_vlen/32);
}