1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
|
// 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=1 -mvscale-max=1 -O1 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-64
// RUN: %clang_cc1 -triple riscv64-none-linux-gnu -target-feature +f -target-feature +d -target-feature +zve64d -mvscale-min=4 -mvscale-max=4 -O1 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-256
// 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 __rvv_bool1_t vbool1_t;
typedef __rvv_bool4_t vbool4_t;
typedef __rvv_bool32_t vbool32_t;
typedef vint64m1_t fixed_int64m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vbool1_t fixed_bool1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vbool4_t fixed_bool4_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen/4)));
#if __riscv_v_fixed_vlen >= 256
typedef vbool32_t fixed_bool32_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen/32)));
#endif
fixed_int64m1_t global_i64;
fixed_bool1_t global_bool1;
fixed_bool4_t global_bool4;
#if __riscv_v_fixed_vlen >= 256
fixed_bool32_t global_bool32;
#endif
//===----------------------------------------------------------------------===//
// WRITES
//===----------------------------------------------------------------------===//
// CHECK-64-LABEL: @write_global_i64(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[CAST_FIXED:%.*]] = tail call <1 x i64> @llvm.vector.extract.v1i64.nxv1i64(<vscale x 1 x i64> [[V:%.*]], i64 0)
// CHECK-64-NEXT: store <1 x i64> [[CAST_FIXED]], ptr @global_i64, align 8, !tbaa [[TBAA4:![0-9]+]]
// CHECK-64-NEXT: ret void
//
// CHECK-256-LABEL: @write_global_i64(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[CAST_FIXED:%.*]] = tail call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[V:%.*]], i64 0)
// CHECK-256-NEXT: store <4 x i64> [[CAST_FIXED]], ptr @global_i64, align 8, !tbaa [[TBAA4:![0-9]+]]
// CHECK-256-NEXT: ret void
//
void write_global_i64(vint64m1_t v) { global_i64 = v; }
// CHECK-64-LABEL: @write_global_bool1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i1> [[V:%.*]] to <vscale x 8 x i8>
// CHECK-64-NEXT: [[CAST_FIXED:%.*]] = tail call <8 x i8> @llvm.vector.extract.v8i8.nxv8i8(<vscale x 8 x i8> [[TMP0]], i64 0)
// CHECK-64-NEXT: store <8 x i8> [[CAST_FIXED]], ptr @global_bool1, align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: ret void
//
// CHECK-256-LABEL: @write_global_bool1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i1> [[V:%.*]] to <vscale x 8 x i8>
// CHECK-256-NEXT: [[CAST_FIXED:%.*]] = tail call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[TMP0]], i64 0)
// CHECK-256-NEXT: store <32 x i8> [[CAST_FIXED]], ptr @global_bool1, align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret void
//
void write_global_bool1(vbool1_t v) { global_bool1 = v; }
// CHECK-64-LABEL: @write_global_bool4(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[TMP0:%.*]] = bitcast <vscale x 16 x i1> [[V:%.*]] to <vscale x 2 x i8>
// CHECK-64-NEXT: [[CAST_FIXED:%.*]] = tail call <2 x i8> @llvm.vector.extract.v2i8.nxv2i8(<vscale x 2 x i8> [[TMP0]], i64 0)
// CHECK-64-NEXT: store <2 x i8> [[CAST_FIXED]], ptr @global_bool4, align 2, !tbaa [[TBAA4]]
// CHECK-64-NEXT: ret void
//
// CHECK-256-LABEL: @write_global_bool4(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[TMP0:%.*]] = bitcast <vscale x 16 x i1> [[V:%.*]] to <vscale x 2 x i8>
// CHECK-256-NEXT: [[CAST_FIXED:%.*]] = tail call <8 x i8> @llvm.vector.extract.v8i8.nxv2i8(<vscale x 2 x i8> [[TMP0]], i64 0)
// CHECK-256-NEXT: store <8 x i8> [[CAST_FIXED]], ptr @global_bool4, align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret void
//
void write_global_bool4(vbool4_t v) { global_bool4 = v; }
#if __riscv_v_fixed_vlen >= 256
// CHECK-256-LABEL: @write_global_bool32(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[SAVED_VALUE:%.*]] = alloca <vscale x 2 x i1>, align 1
// CHECK-256-NEXT: store <vscale x 2 x i1> [[V:%.*]], ptr [[SAVED_VALUE]], align 1, !tbaa [[TBAA7:![0-9]+]]
// CHECK-256-NEXT: [[TMP0:%.*]] = load <1 x i8>, ptr [[SAVED_VALUE]], align 1, !tbaa [[TBAA4]]
// CHECK-256-NEXT: store <1 x i8> [[TMP0]], ptr @global_bool32, align 1, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret void
//
void write_global_bool32(vbool32_t v) { global_bool32 = v; }
#endif
//===----------------------------------------------------------------------===//
// READS
//===----------------------------------------------------------------------===//
// CHECK-64-LABEL: @read_global_i64(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[TMP0:%.*]] = load <1 x i64>, ptr @global_i64, align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v1i64(<vscale x 1 x i64> undef, <1 x i64> [[TMP0]], i64 0)
// CHECK-64-NEXT: ret <vscale x 1 x i64> [[CAST_SCALABLE]]
//
// CHECK-256-LABEL: @read_global_i64(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr @global_i64, align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[TMP0]], i64 0)
// CHECK-256-NEXT: ret <vscale x 1 x i64> [[CAST_SCALABLE]]
//
vint64m1_t read_global_i64() { return global_i64; }
// CHECK-64-LABEL: @read_global_bool1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[TMP0:%.*]] = load <8 x i8>, ptr @global_bool1, align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v8i8(<vscale x 8 x i8> undef, <8 x i8> [[TMP0]], i64 0)
// CHECK-64-NEXT: [[TMP1:%.*]] = bitcast <vscale x 8 x i8> [[CAST_SCALABLE]] to <vscale x 64 x i1>
// CHECK-64-NEXT: ret <vscale x 64 x i1> [[TMP1]]
//
// CHECK-256-LABEL: @read_global_bool1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[TMP0:%.*]] = load <32 x i8>, ptr @global_bool1, align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[TMP0]], i64 0)
// CHECK-256-NEXT: [[TMP1:%.*]] = bitcast <vscale x 8 x i8> [[CAST_SCALABLE]] to <vscale x 64 x i1>
// CHECK-256-NEXT: ret <vscale x 64 x i1> [[TMP1]]
//
vbool1_t read_global_bool1() { return global_bool1; }
// CHECK-64-LABEL: @read_global_bool4(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[TMP0:%.*]] = load <2 x i8>, ptr @global_bool4, align 2, !tbaa [[TBAA4]]
// CHECK-64-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 2 x i8> @llvm.vector.insert.nxv2i8.v2i8(<vscale x 2 x i8> undef, <2 x i8> [[TMP0]], i64 0)
// CHECK-64-NEXT: [[TMP1:%.*]] = bitcast <vscale x 2 x i8> [[CAST_SCALABLE]] to <vscale x 16 x i1>
// CHECK-64-NEXT: ret <vscale x 16 x i1> [[TMP1]]
//
// CHECK-256-LABEL: @read_global_bool4(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[TMP0:%.*]] = load <8 x i8>, ptr @global_bool4, align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 2 x i8> @llvm.vector.insert.nxv2i8.v8i8(<vscale x 2 x i8> undef, <8 x i8> [[TMP0]], i64 0)
// CHECK-256-NEXT: [[TMP1:%.*]] = bitcast <vscale x 2 x i8> [[CAST_SCALABLE]] to <vscale x 16 x i1>
// CHECK-256-NEXT: ret <vscale x 16 x i1> [[TMP1]]
//
vbool4_t read_global_bool4() { return global_bool4; }
#if __riscv_v_fixed_vlen >= 256
// CHECK-256-LABEL: @read_global_bool32(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[SAVED_VALUE:%.*]] = alloca <1 x i8>, align 1
// CHECK-256-NEXT: [[TMP0:%.*]] = load <1 x i8>, ptr @global_bool32, align 1, !tbaa [[TBAA4]]
// CHECK-256-NEXT: store <1 x i8> [[TMP0]], ptr [[SAVED_VALUE]], align 1, !tbaa [[TBAA4]]
// CHECK-256-NEXT: [[TMP1:%.*]] = load <vscale x 2 x i1>, ptr [[SAVED_VALUE]], align 1, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret <vscale x 2 x i1> [[TMP1]]
//
vbool32_t read_global_bool32() { return global_bool32; }
#endif
|