From dc92be522b5e628f1c29d38a8184dde8ec018ede Mon Sep 17 00:00:00 2001 From: Alexandros Lamprineas Date: Tue, 5 Jan 2016 09:58:29 +0000 Subject: [PATCH] [ARM] [AARCH64] Add CodeGen IR tests for {VS}QRDML{AS}H v8.1a intrinsics. Differential Revision: http://reviews.llvm.org/D15223 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@256822 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/aarch64-v8.1a-neon-intrinsics.c | 156 ++++++++++++++----- test/CodeGen/arm-v8.1a-neon-intrinsics.c | 135 +++++++++++----- 2 files changed, 213 insertions(+), 78 deletions(-) diff --git a/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c b/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c index 078b454b39..ad5d5dd438 100644 --- a/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c +++ b/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c @@ -1,128 +1,198 @@ // REQUIRES: aarch64-registered-target // RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon \ -// RUN: -target-feature +v8.1a -O3 -S -o - %s \ -// RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AARCH64 +// RUN: -target-feature +v8.1a -S -emit-llvm -o - %s | FileCheck %s #include -// CHECK-AARCH64-LABEL: test_vqrdmlah_laneq_s16 +// CHECK-LABEL: test_vqrdmlah_laneq_s16 int16x4_t test_vqrdmlah_laneq_s16(int16x4_t a, int16x4_t b, int16x8_t v) { -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.h[7] +// CHECK: shufflevector <8 x i16> {{%.*}}, <8 x i16> {{%.*}}, <4 x i32> +// CHECK: call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK: call <4 x i16> @llvm.aarch64.neon.sqadd.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) return vqrdmlah_laneq_s16(a, b, v, 7); } -// CHECK-AARCH64-LABEL: test_vqrdmlah_laneq_s32 +// CHECK-LABEL: test_vqrdmlah_laneq_s32 int32x2_t test_vqrdmlah_laneq_s32(int32x2_t a, int32x2_t b, int32x4_t v) { -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[3] +// CHECK: shufflevector <4 x i32> {{%.*}}, <4 x i32> {{%.*}}, <2 x i32> +// CHECK: call <2 x i32> @llvm.aarch64.neon.sqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK: call <2 x i32> @llvm.aarch64.neon.sqadd.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) return vqrdmlah_laneq_s32(a, b, v, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlahq_laneq_s16 +// CHECK-LABEL: test_vqrdmlahq_laneq_s16 int16x8_t test_vqrdmlahq_laneq_s16(int16x8_t a, int16x8_t b, int16x8_t v) { -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.h[7] +// CHECK: shufflevector <8 x i16> {{%.*}}, <8 x i16> {{%.*}}, <8 x i32> +// CHECK: call <8 x i16> @llvm.aarch64.neon.sqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK: call <8 x i16> @llvm.aarch64.neon.sqadd.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) return vqrdmlahq_laneq_s16(a, b, v, 7); } -// CHECK-AARCH64-LABEL: test_vqrdmlahq_laneq_s32 +// CHECK-LABEL: test_vqrdmlahq_laneq_s32 int32x4_t test_vqrdmlahq_laneq_s32(int32x4_t a, int32x4_t b, int32x4_t v) { -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[3] +// CHECK: shufflevector <4 x i32> {{%.*}}, <4 x i32> {{%.*}}, <4 x i32> +// CHECK: call <4 x i32> @llvm.aarch64.neon.sqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK: call <4 x i32> @llvm.aarch64.neon.sqadd.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) return vqrdmlahq_laneq_s32(a, b, v, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlahh_s16 +// CHECK-LABEL: test_vqrdmlahh_s16 int16_t test_vqrdmlahh_s16(int16_t a, int16_t b, int16_t c) { -// CHECK-AARCH64: sqrdmlah {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}} +// CHECK: [[insb:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insc:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[mul:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> [[insb]], <4 x i16> [[insc]]) +// CHECK: extractelement <4 x i16> [[mul]], i64 0 +// CHECK: [[insa:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insmul:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[add:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqadd.v4i16(<4 x i16> [[insa]], <4 x i16> [[insmul]]) +// CHECK: extractelement <4 x i16> [[add]], i64 0 return vqrdmlahh_s16(a, b, c); } -// CHECK-AARCH64-LABEL: test_vqrdmlahs_s32 +// CHECK-LABEL: test_vqrdmlahs_s32 int32_t test_vqrdmlahs_s32(int32_t a, int32_t b, int32_t c) { -// CHECK-AARCH64: sqrdmlah {{s[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}} +// CHECK: call i32 @llvm.aarch64.neon.sqrdmulh.i32(i32 {{%.*}}, i32 {{%.*}}) +// CHECK: call i32 @llvm.aarch64.neon.sqadd.i32(i32 {{%.*}}, i32 {{%.*}}) return vqrdmlahs_s32(a, b, c); } -// CHECK-AARCH64-LABEL: test_vqrdmlahh_lane_s16 +// CHECK-LABEL: test_vqrdmlahh_lane_s16 int16_t test_vqrdmlahh_lane_s16(int16_t a, int16_t b, int16x4_t c) { -// CHECK-AARCH64: sqrdmlah {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}}, {{v[0-9]+}}.h[3] +// CHECK: extractelement <4 x i16> {{%.*}}, i32 3 +// CHECK: [[insb:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insc:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[mul:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> [[insb]], <4 x i16> [[insc]]) +// CHECK: extractelement <4 x i16> [[mul]], i64 0 +// CHECK: [[insa:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insmul:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[add:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqadd.v4i16(<4 x i16> [[insa]], <4 x i16> [[insmul]]) +// CHECK: extractelement <4 x i16> [[add]], i64 0 return vqrdmlahh_lane_s16(a, b, c, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlahs_lane_s32 +// CHECK-LABEL: test_vqrdmlahs_lane_s32 int32_t test_vqrdmlahs_lane_s32(int32_t a, int32_t b, int32x2_t c) { -// CHECK-AARCH64: sqrdmlah {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[1] +// CHECK: extractelement <2 x i32> {{%.*}}, i32 1 +// CHECK: call i32 @llvm.aarch64.neon.sqrdmulh.i32(i32 {{%.*}}, i32 {{%.*}}) +// CHECK: call i32 @llvm.aarch64.neon.sqadd.i32(i32 {{%.*}}, i32 {{%.*}}) return vqrdmlahs_lane_s32(a, b, c, 1); } -// CHECK-AARCH64-LABEL: test_vqrdmlahh_laneq_s16 +// CHECK-LABEL: test_vqrdmlahh_laneq_s16 int16_t test_vqrdmlahh_laneq_s16(int16_t a, int16_t b, int16x8_t c) { -// CHECK-AARCH64: sqrdmlah {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}}, {{v[0-9]+}}.h[7] +// CHECK: extractelement <8 x i16> {{%.*}}, i32 7 +// CHECK: [[insb:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insc:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[mul:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> [[insb]], <4 x i16> [[insc]]) +// CHECK: extractelement <4 x i16> [[mul]], i64 0 +// CHECK: [[insa:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insmul:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[add:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqadd.v4i16(<4 x i16> [[insa]], <4 x i16> [[insmul]]) +// CHECK: extractelement <4 x i16> [[add]], i64 0 return vqrdmlahh_laneq_s16(a, b, c, 7); } -// CHECK-AARCH64-LABEL: test_vqrdmlahs_laneq_s32 +// CHECK-LABEL: test_vqrdmlahs_laneq_s32 int32_t test_vqrdmlahs_laneq_s32(int32_t a, int32_t b, int32x4_t c) { -// CHECK-AARCH64: sqrdmlah {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[3] +// CHECK: extractelement <4 x i32> {{%.*}}, i32 3 +// CHECK: call i32 @llvm.aarch64.neon.sqrdmulh.i32(i32 {{%.*}}, i32 {{%.*}}) +// CHECK: call i32 @llvm.aarch64.neon.sqadd.i32(i32 {{%.*}}, i32 {{%.*}}) return vqrdmlahs_laneq_s32(a, b, c, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlsh_laneq_s16 +// CHECK-LABEL: test_vqrdmlsh_laneq_s16 int16x4_t test_vqrdmlsh_laneq_s16(int16x4_t a, int16x4_t b, int16x8_t v) { -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.h[7] +// CHECK: shufflevector <8 x i16> {{%.*}}, <8 x i16> {{%.*}}, <4 x i32> +// CHECK: call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK: call <4 x i16> @llvm.aarch64.neon.sqsub.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) return vqrdmlsh_laneq_s16(a, b, v, 7); } -// CHECK-AARCH64-LABEL: test_vqrdmlsh_laneq_s32 +// CHECK-LABEL: test_vqrdmlsh_laneq_s32 int32x2_t test_vqrdmlsh_laneq_s32(int32x2_t a, int32x2_t b, int32x4_t v) { -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[3] +// CHECK: shufflevector <4 x i32> {{%.*}}, <4 x i32> {{%.*}}, <2 x i32> +// CHECK: call <2 x i32> @llvm.aarch64.neon.sqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK: call <2 x i32> @llvm.aarch64.neon.sqsub.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) return vqrdmlsh_laneq_s32(a, b, v, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlshq_laneq_s16 +// CHECK-LABEL: test_vqrdmlshq_laneq_s16 int16x8_t test_vqrdmlshq_laneq_s16(int16x8_t a, int16x8_t b, int16x8_t v) { -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.h[7] +// CHECK: shufflevector <8 x i16> {{%.*}}, <8 x i16> {{%.*}}, <8 x i32> +// CHECK: call <8 x i16> @llvm.aarch64.neon.sqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK: call <8 x i16> @llvm.aarch64.neon.sqsub.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) return vqrdmlshq_laneq_s16(a, b, v, 7); } -// CHECK-AARCH64-LABEL: test_vqrdmlshq_laneq_s32 +// CHECK-LABEL: test_vqrdmlshq_laneq_s32 int32x4_t test_vqrdmlshq_laneq_s32(int32x4_t a, int32x4_t b, int32x4_t v) { -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[3] +// CHECK: shufflevector <4 x i32> {{%.*}}, <4 x i32> {{%.*}}, <4 x i32> +// CHECK: call <4 x i32> @llvm.aarch64.neon.sqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK: call <4 x i32> @llvm.aarch64.neon.sqsub.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) return vqrdmlshq_laneq_s32(a, b, v, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlshh_s16 +// CHECK-LABEL: test_vqrdmlshh_s16 int16_t test_vqrdmlshh_s16(int16_t a, int16_t b, int16_t c) { -// CHECK-AARCH64: sqrdmlsh {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}} +// CHECK: [[insb:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insc:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[mul:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> [[insb]], <4 x i16> [[insc]]) +// CHECK: extractelement <4 x i16> [[mul]], i64 0 +// CHECK: [[insa:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insmul:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[sub:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqsub.v4i16(<4 x i16> [[insa]], <4 x i16> [[insmul]]) +// CHECK: extractelement <4 x i16> [[sub]], i64 0 return vqrdmlshh_s16(a, b, c); } -// CHECK-AARCH64-LABEL: test_vqrdmlshs_s32 +// CHECK-LABEL: test_vqrdmlshs_s32 int32_t test_vqrdmlshs_s32(int32_t a, int32_t b, int32_t c) { -// CHECK-AARCH64: sqrdmlsh {{s[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}} +// CHECK: call i32 @llvm.aarch64.neon.sqrdmulh.i32(i32 {{%.*}}, i32 {{%.*}}) +// CHECK: call i32 @llvm.aarch64.neon.sqsub.i32(i32 {{%.*}}, i32 {{%.*}}) return vqrdmlshs_s32(a, b, c); } -// CHECK-AARCH64-LABEL: test_vqrdmlshh_lane_s16 +// CHECK-LABEL: test_vqrdmlshh_lane_s16 int16_t test_vqrdmlshh_lane_s16(int16_t a, int16_t b, int16x4_t c) { -// CHECK-AARCH64: sqrdmlsh {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}}, {{v[0-9]+}}.h[3] +// CHECK: extractelement <4 x i16> {{%.*}}, i32 3 +// CHECK: [[insb:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insc:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[mul:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> [[insb]], <4 x i16> [[insc]]) +// CHECK: extractelement <4 x i16> [[mul]], i64 0 +// CHECK: [[insa:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insmul:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[sub:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqsub.v4i16(<4 x i16> [[insa]], <4 x i16> [[insmul]]) +// CHECK: extractelement <4 x i16> [[sub]], i64 0 return vqrdmlshh_lane_s16(a, b, c, 3); } -// CHECK-AARCH64-LABEL: test_vqrdmlshs_lane_s32 +// CHECK-LABEL: test_vqrdmlshs_lane_s32 int32_t test_vqrdmlshs_lane_s32(int32_t a, int32_t b, int32x2_t c) { -// CHECK-AARCH64: sqrdmlsh {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[1] +// CHECK: extractelement <2 x i32> {{%.*}}, i32 1 +// CHECK: call i32 @llvm.aarch64.neon.sqrdmulh.i32(i32 {{%.*}}, i32 {{%.*}}) +// CHECK: call i32 @llvm.aarch64.neon.sqsub.i32(i32 {{%.*}}, i32 {{%.*}}) return vqrdmlshs_lane_s32(a, b, c, 1); } -// CHECK-AARCH64-LABEL: test_vqrdmlshh_laneq_s16 +// CHECK-LABEL: test_vqrdmlshh_laneq_s16 int16_t test_vqrdmlshh_laneq_s16(int16_t a, int16_t b, int16x8_t c) { -// CHECK-AARCH64: sqrdmlsh {{h[0-9]+|v[0-9]+.4h}}, {{h[0-9]+|v[0-9]+.4h}}, {{v[0-9]+}}.h[7] +// CHECK: extractelement <8 x i16> {{%.*}}, i32 7 +// CHECK: [[insb:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insc:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[mul:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> [[insb]], <4 x i16> [[insc]]) +// CHECK: extractelement <4 x i16> [[mul]], i64 0 +// CHECK: [[insa:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[insmul:%.*]] = insertelement <4 x i16> undef, i16 {{%.*}}, i64 0 +// CHECK: [[sub:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqsub.v4i16(<4 x i16> [[insa]], <4 x i16> [[insmul]]) +// CHECK: extractelement <4 x i16> [[sub]], i64 0 return vqrdmlshh_laneq_s16(a, b, c, 7); } -// CHECK-AARCH64-LABEL: test_vqrdmlshs_laneq_s32 +// CHECK-LABEL: test_vqrdmlshs_laneq_s32 int32_t test_vqrdmlshs_laneq_s32(int32_t a, int32_t b, int32x4_t c) { -// CHECK-AARCH64: sqrdmlsh {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[3] +// CHECK: extractelement <4 x i32> {{%.*}}, i32 3 +// CHECK: call i32 @llvm.aarch64.neon.sqrdmulh.i32(i32 {{%.*}}, i32 {{%.*}}) +// CHECK: call i32 @llvm.aarch64.neon.sqsub.i32(i32 {{%.*}}, i32 {{%.*}}) return vqrdmlshs_laneq_s32(a, b, c, 3); } - diff --git a/test/CodeGen/arm-v8.1a-neon-intrinsics.c b/test/CodeGen/arm-v8.1a-neon-intrinsics.c index 5fe299af5f..7888831004 100644 --- a/test/CodeGen/arm-v8.1a-neon-intrinsics.c +++ b/test/CodeGen/arm-v8.1a-neon-intrinsics.c @@ -1,122 +1,187 @@ // RUN: %clang_cc1 -triple armv8.1a-linux-gnu -target-feature +neon \ -// RUN: -O3 -S -o - %s \ +// RUN: -S -emit-llvm -o - %s \ // RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-ARM + // RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon \ -// RUN: -target-feature +v8.1a -O3 -S -o - %s \ +// RUN: -target-feature +v8.1a -S -emit-llvm -o - %s \ // RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AARCH64 + // REQUIRES: arm-registered-target,aarch64-registered-target #include // CHECK-LABEL: test_vqrdmlah_s16 int16x4_t test_vqrdmlah_s16(int16x4_t a, int16x4_t b, int16x4_t c) { -// CHECK-ARM: vqrdmlah.s16 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}} -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.4h +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqadds.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) + +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqadd.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) return vqrdmlah_s16(a, b, c); } // CHECK-LABEL: test_vqrdmlah_s32 int32x2_t test_vqrdmlah_s32(int32x2_t a, int32x2_t b, int32x2_t c) { -// CHECK-ARM: vqrdmlah.s32 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}} -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqadds.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) + +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqadd.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) return vqrdmlah_s32(a, b, c); } // CHECK-LABEL: test_vqrdmlahq_s16 int16x8_t test_vqrdmlahq_s16(int16x8_t a, int16x8_t b, int16x8_t c) { -// CHECK-ARM: vqrdmlah.s16 q{{[0-9]+}}, q{{[0-9]+}}, q{{[0-9]+}} -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.8h +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqadds.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) + +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqadd.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) return vqrdmlahq_s16(a, b, c); } // CHECK-LABEL: test_vqrdmlahq_s32 int32x4_t test_vqrdmlahq_s32(int32x4_t a, int32x4_t b, int32x4_t c) { -// CHECK-ARM: vqrdmlah.s32 q{{[0-9]+}}, q{{[0-9]+}}, q{{[0-9]+}} -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqadds.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) + +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqadd.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) return vqrdmlahq_s32(a, b, c); } // CHECK-LABEL: test_vqrdmlah_lane_s16 int16x4_t test_vqrdmlah_lane_s16(int16x4_t a, int16x4_t b, int16x4_t c) { -// CHECK-ARM: vqrdmlah.s16 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}[3] -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.h[3] +// CHECK-ARM: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <4 x i32> +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqadds.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) + +// CHECK-AARCH64: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <4 x i32> +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqadd.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) return vqrdmlah_lane_s16(a, b, c, 3); } // CHECK-LABEL: test_vqrdmlah_lane_s32 int32x2_t test_vqrdmlah_lane_s32(int32x2_t a, int32x2_t b, int32x2_t c) { -// CHECK-ARM: vqrdmlah.s32 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}[1] -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[1] +// CHECK-ARM: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <2 x i32> +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqadds.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) + +// CHECK-AARCH64: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <2 x i32> +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqadd.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) return vqrdmlah_lane_s32(a, b, c, 1); } // CHECK-LABEL: test_vqrdmlahq_lane_s16 int16x8_t test_vqrdmlahq_lane_s16(int16x8_t a, int16x8_t b, int16x4_t c) { -// CHECK-ARM: vqrdmlah.s16 q{{[0-9]+}}, q{{[0-9]+}}, d{{[0-9]+}}[3] -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.h[3] +// CHECK-ARM: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <8 x i32> +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqadds.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) + +// CHECK-AARCH64: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <8 x i32> +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqadd.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) return vqrdmlahq_lane_s16(a, b, c, 3); } // CHECK-LABEL: test_vqrdmlahq_lane_s32 int32x4_t test_vqrdmlahq_lane_s32(int32x4_t a, int32x4_t b, int32x2_t c) { -// CHECK-ARM: vqrdmlah.s32 q{{[0-9]+}}, q{{[0-9]+}}, d{{[0-9]+}}[1] -// CHECK-AARCH64: sqrdmlah {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[1] +// CHECK-ARM: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <4 x i32> +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqadds.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) + +// CHECK-AARCH64: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <4 x i32> +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqadd.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) return vqrdmlahq_lane_s32(a, b, c, 1); } // CHECK-LABEL: test_vqrdmlsh_s16 int16x4_t test_vqrdmlsh_s16(int16x4_t a, int16x4_t b, int16x4_t c) { -// CHECK-ARM: vqrdmlsh.s16 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}} -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.4h +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqsubs.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) + +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqsub.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) return vqrdmlsh_s16(a, b, c); } // CHECK-LABEL: test_vqrdmlsh_s32 int32x2_t test_vqrdmlsh_s32(int32x2_t a, int32x2_t b, int32x2_t c) { -// CHECK-ARM: vqrdmlsh.s32 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}} -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqsubs.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) + +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqsub.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) return vqrdmlsh_s32(a, b, c); } // CHECK-LABEL: test_vqrdmlshq_s16 int16x8_t test_vqrdmlshq_s16(int16x8_t a, int16x8_t b, int16x8_t c) { -// CHECK-ARM: vqrdmlsh.s16 q{{[0-9]+}}, q{{[0-9]+}}, q{{[0-9]+}} -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.8h +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqsubs.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) + +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqsub.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) return vqrdmlshq_s16(a, b, c); } // CHECK-LABEL: test_vqrdmlshq_s32 int32x4_t test_vqrdmlshq_s32(int32x4_t a, int32x4_t b, int32x4_t c) { -// CHECK-ARM: vqrdmlsh.s32 q{{[0-9]+}}, q{{[0-9]+}}, q{{[0-9]+}} -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqsubs.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) + +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqsub.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) return vqrdmlshq_s32(a, b, c); } // CHECK-LABEL: test_vqrdmlsh_lane_s16 int16x4_t test_vqrdmlsh_lane_s16(int16x4_t a, int16x4_t b, int16x4_t c) { -// CHECK-ARM: vqrdmlsh.s16 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}[3] -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.h[3] +// CHECK-ARM: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <4 x i32> +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-ARM: call <4 x i16> @llvm.arm.neon.vqsubs.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) + +// CHECK-AARCH64: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <4 x i32> +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqrdmulh.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) +// CHECK-AARCH64: call <4 x i16> @llvm.aarch64.neon.sqsub.v4i16(<4 x i16> {{%.*}}, <4 x i16> {{%.*}}) return vqrdmlsh_lane_s16(a, b, c, 3); } // CHECK-LABEL: test_vqrdmlsh_lane_s32 int32x2_t test_vqrdmlsh_lane_s32(int32x2_t a, int32x2_t b, int32x2_t c) { -// CHECK-ARM: vqrdmlsh.s32 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}[1] -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[1] +// CHECK-ARM: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <2 x i32> +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-ARM: call <2 x i32> @llvm.arm.neon.vqsubs.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) + +// CHECK-AARCH64: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <2 x i32> +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqrdmulh.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) +// CHECK-AARCH64: call <2 x i32> @llvm.aarch64.neon.sqsub.v2i32(<2 x i32> {{%.*}}, <2 x i32> {{%.*}}) return vqrdmlsh_lane_s32(a, b, c, 1); } // CHECK-LABEL: test_vqrdmlshq_lane_s16 int16x8_t test_vqrdmlshq_lane_s16(int16x8_t a, int16x8_t b, int16x4_t c) { -// CHECK-ARM: vqrdmlsh.s16 q{{[0-9]+}}, q{{[0-9]+}}, d{{[0-9]+}}[3] -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.h[3] +// CHECK-ARM: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <8 x i32> +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-ARM: call <8 x i16> @llvm.arm.neon.vqsubs.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) + +// CHECK-AARCH64: shufflevector <4 x i16> {{%.*}}, <4 x i16> {{%.*}}, <8 x i32> +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqrdmulh.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) +// CHECK-AARCH64: call <8 x i16> @llvm.aarch64.neon.sqsub.v8i16(<8 x i16> {{%.*}}, <8 x i16> {{%.*}}) return vqrdmlshq_lane_s16(a, b, c, 3); } // CHECK-LABEL: test_vqrdmlshq_lane_s32 int32x4_t test_vqrdmlshq_lane_s32(int32x4_t a, int32x4_t b, int32x2_t c) { -// CHECK-ARM: vqrdmlsh.s32 q{{[0-9]+}}, q{{[0-9]+}}, d{{[0-9]+}}[1] -// CHECK-AARCH64: sqrdmlsh {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[1] +// CHECK-ARM: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <4 x i32> +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-ARM: call <4 x i32> @llvm.arm.neon.vqsubs.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) + +// CHECK-AARCH64: shufflevector <2 x i32> {{%.*}}, <2 x i32> {{%.*}}, <4 x i32> +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqrdmulh.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) +// CHECK-AARCH64: call <4 x i32> @llvm.aarch64.neon.sqsub.v4i32(<4 x i32> {{%.*}}, <4 x i32> {{%.*}}) return vqrdmlshq_lane_s32(a, b, c, 1); } - -- 2.40.0