| // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py |
| // REQUIRES: aarch64-registered-target |
| // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s |
| // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve2p1 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s |
| // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK |
| // RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s |
| // RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK |
| // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme2 -target-feature +sme-f64f64 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s |
| // RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve2p1 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s |
| |
| #include <arm_sve.h> |
| |
| #ifdef SVE_OVERLOADED_FORMS |
| // A simple used,unused... macro, long enough to represent any SVE builtin. |
| #define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED,A5) A1##A3##A5 |
| #else |
| #define SVE_ACLE_FUNC(A1,A2,A3,A4,A5) A1##A2##A3##A4##A5 |
| #endif |
| |
| |
| // SQRSHRN x 2 |
| |
| // CHECK-LABEL: @test_svqrshrn_s16_s32_x2( |
| // CHECK-NEXT: entry: |
| // CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN:%.*]], i64 0) |
| // CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN]], i64 4) |
| // CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshrn.x2.nxv4i32(<vscale x 4 x i32> [[TMP0]], <vscale x 4 x i32> [[TMP1]], i32 16) |
| // CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]] |
| // |
| // CPP-CHECK-LABEL: @_Z24test_svqrshrn_s16_s32_x211svint32x2_t( |
| // CPP-CHECK-NEXT: entry: |
| // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN:%.*]], i64 0) |
| // CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN]], i64 4) |
| // CPP-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshrn.x2.nxv4i32(<vscale x 4 x i32> [[TMP0]], <vscale x 4 x i32> [[TMP1]], i32 16) |
| // CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]] |
| // |
| svint16_t test_svqrshrn_s16_s32_x2(svint32x2_t zn) __arm_streaming_compatible { |
| return SVE_ACLE_FUNC(svqrshrn,_n,_s16,_s32_x2,)(zn, 16); |
| } |
| |
| // UQRSHRN x 2 |
| |
| // CHECK-LABEL: @test_svqrshrn_u16_u32_x2( |
| // CHECK-NEXT: entry: |
| // CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN:%.*]], i64 0) |
| // CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN]], i64 4) |
| // CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshrn.x2.nxv4i32(<vscale x 4 x i32> [[TMP0]], <vscale x 4 x i32> [[TMP1]], i32 16) |
| // CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]] |
| // |
| // CPP-CHECK-LABEL: @_Z24test_svqrshrn_u16_u32_x212svuint32x2_t( |
| // CPP-CHECK-NEXT: entry: |
| // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN:%.*]], i64 0) |
| // CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN]], i64 4) |
| // CPP-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshrn.x2.nxv4i32(<vscale x 4 x i32> [[TMP0]], <vscale x 4 x i32> [[TMP1]], i32 16) |
| // CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]] |
| // |
| svuint16_t test_svqrshrn_u16_u32_x2(svuint32x2_t zn) __arm_streaming_compatible { |
| return SVE_ACLE_FUNC(svqrshrn,_n,_u16,_u32_x2,)(zn, 16); |
| } |
| |
| // SQRSHRUN x 2 |
| |
| // CHECK-LABEL: @test_svqrshrun_u16_s32_x2( |
| // CHECK-NEXT: entry: |
| // CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN:%.*]], i64 0) |
| // CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN]], i64 4) |
| // CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshrun.x2.nxv4i32(<vscale x 4 x i32> [[TMP0]], <vscale x 4 x i32> [[TMP1]], i32 16) |
| // CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]] |
| // |
| // CPP-CHECK-LABEL: @_Z25test_svqrshrun_u16_s32_x211svint32x2_t( |
| // CPP-CHECK-NEXT: entry: |
| // CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN:%.*]], i64 0) |
| // CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv8i32(<vscale x 8 x i32> [[ZN]], i64 4) |
| // CPP-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshrun.x2.nxv4i32(<vscale x 4 x i32> [[TMP0]], <vscale x 4 x i32> [[TMP1]], i32 16) |
| // CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]] |
| // |
| svuint16_t test_svqrshrun_u16_s32_x2(svint32x2_t zn) __arm_streaming_compatible { |
| return SVE_ACLE_FUNC(svqrshrun,_n,_u16,_s32_x2,)(zn, 16); |
| } |
