diff options
Diffstat (limited to 'test/CodeGen')
-rw-r--r-- | test/CodeGen/2007-04-14-FNoBuiltin.c | 1 | ||||
-rw-r--r-- | test/CodeGen/aarch64-v8.1a-neon-intrinsics.c | 156 | ||||
-rw-r--r-- | test/CodeGen/arm-target-features.c | 1 | ||||
-rw-r--r-- | test/CodeGen/arm-v8.1a-neon-intrinsics.c | 135 | ||||
-rw-r--r-- | test/CodeGen/libcalls-complex.c | 3 | ||||
-rw-r--r-- | test/CodeGen/libcalls-fno-builtin.c | 7 | ||||
-rw-r--r-- | test/CodeGen/nobuiltin.c | 9 | ||||
-rw-r--r-- | test/CodeGen/pku.c | 18 |
8 files changed, 252 insertions, 78 deletions
diff --git a/test/CodeGen/2007-04-14-FNoBuiltin.c b/test/CodeGen/2007-04-14-FNoBuiltin.c index 4d194b1..b95f41c 100644 --- a/test/CodeGen/2007-04-14-FNoBuiltin.c +++ b/test/CodeGen/2007-04-14-FNoBuiltin.c @@ -1,4 +1,5 @@ // RUN: %clang_cc1 -emit-llvm %s -O2 -fno-builtin -o - | FileCheck %s +// RUN: %clang_cc1 -emit-llvm %s -O2 -fno-builtin-printf -o - | FileCheck %s // Check that -fno-builtin is honored. extern int printf(const char*, ...); diff --git a/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c b/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c index 078b454..ad5d5dd 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 <arm_neon.h> -// 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> <i32 7, i32 7, i32 7, i32 7> +// 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> <i32 3, i32 3> +// 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> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7> +// 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> <i32 3, i32 3, i32 3, i32 3> +// 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> <i32 7, i32 7, i32 7, i32 7> +// 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> <i32 3, i32 3> +// 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> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7> +// 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> <i32 3, i32 3, i32 3, i32 3> +// 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-target-features.c b/test/CodeGen/arm-target-features.c index 35c0e04..7829edf 100644 --- a/test/CodeGen/arm-target-features.c +++ b/test/CodeGen/arm-target-features.c @@ -26,6 +26,7 @@ // RUN: %clang_cc1 -triple armv8-linux-gnueabi -target-cpu cortex-a53 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-BASIC-V8 // RUN: %clang_cc1 -triple thumbv8-linux-gnueabihf -target-cpu cortex-a57 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-BASIC-V8 // RUN: %clang_cc1 -triple thumbv8-linux-gnueabihf -target-cpu cortex-a72 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-BASIC-V8 +// RUN: %clang_cc1 -triple thumbv8-linux-gnueabihf -target-cpu exynos-m1 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-BASIC-V8 // CHECK-BASIC-V8: "target-features"="+crc,+crypto,+dsp,+fp-armv8,+hwdiv,+hwdiv-arm,+neon" diff --git a/test/CodeGen/arm-v8.1a-neon-intrinsics.c b/test/CodeGen/arm-v8.1a-neon-intrinsics.c index 5fe299a..7888831 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 <arm_neon.h> // 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> <i32 3, i32 3, i32 3, i32 3> +// 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> <i32 3, i32 3, i32 3, i32 3> +// 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> <i32 1, i32 1> +// 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> <i32 1, i32 1> +// 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> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3> +// 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> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3> +// 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> <i32 1, i32 1, i32 1, i32 1> +// 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> <i32 1, i32 1, i32 1, i32 1> +// 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> <i32 3, i32 3, i32 3, i32 3> +// 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> <i32 3, i32 3, i32 3, i32 3> +// 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> <i32 1, i32 1> +// 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> <i32 1, i32 1> +// 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> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3> +// 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> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3> +// 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> <i32 1, i32 1, i32 1, i32 1> +// 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> <i32 1, i32 1, i32 1, i32 1> +// 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); } - diff --git a/test/CodeGen/libcalls-complex.c b/test/CodeGen/libcalls-complex.c index 22c97b6..43b7055 100644 --- a/test/CodeGen/libcalls-complex.c +++ b/test/CodeGen/libcalls-complex.c @@ -1,4 +1,7 @@ // RUN: %clang_cc1 -fno-builtin -emit-llvm -o - %s -triple i386-unknown-unknown | FileCheck -check-prefix CHECK-YES %s +// RUN: %clang_cc1 -fno-builtin-crealf -fno-builtin-creal -fno-builtin-creall \ +// RUN: -fno-builtin-cimagf -fno-builtin-cimag -fno-builtin-cimagl -emit-llvm \ +// RUN: -o - %s -triple i386-unknown-unknown | FileCheck -check-prefix CHECK-YES %s // RUN: %clang_cc1 -emit-llvm -o - %s -triple i386-unknown-unknown | FileCheck -check-prefix CHECK-NO %s extern float crealf(float _Complex); diff --git a/test/CodeGen/libcalls-fno-builtin.c b/test/CodeGen/libcalls-fno-builtin.c index e7f3ef7..bc6a430 100644 --- a/test/CodeGen/libcalls-fno-builtin.c +++ b/test/CodeGen/libcalls-fno-builtin.c @@ -1,4 +1,11 @@ // RUN: %clang_cc1 -S -O3 -fno-builtin -o - %s | FileCheck %s +// RUN: %clang_cc1 -S -O3 -fno-builtin-ceil -fno-builtin-copysign -fno-builtin-cos \ +// RUN: -fno-builtin-fabs -fno-builtin-floor -fno-builtin-strcat -fno-builtin-strncat \ +// RUN: -fno-builtin-strchr -fno-builtin-strrchr -fno-builtin-strcmp -fno-builtin-strncmp \ +// RUN: -fno-builtin-strcpy -fno-builtin-stpcpy -fno-builtin-strncpy -fno-builtin-strlen \ +// RUN: -fno-builtin-strpbrk -fno-builtin-strspn -fno-builtin-strtod -fno-builtin-strtof \ +// RUN: -fno-builtin-strtold -fno-builtin-strtol -fno-builtin-strtoll -fno-builtin-strtoul \ +// RUN: -fno-builtin-strtoull -o - %s | FileCheck %s // rdar://10551066 typedef __SIZE_TYPE__ size_t; diff --git a/test/CodeGen/nobuiltin.c b/test/CodeGen/nobuiltin.c index 0a8e8bb..7cc8164 100644 --- a/test/CodeGen/nobuiltin.c +++ b/test/CodeGen/nobuiltin.c @@ -1,4 +1,5 @@ // RUN: %clang_cc1 -fno-builtin -O1 -S -o - %s | FileCheck %s +// RUN: %clang_cc1 -fno-builtin-memset -O1 -S -o - %s | FileCheck -check-prefix=MEMSET %s void PR13497() { char content[2]; @@ -6,3 +7,11 @@ void PR13497() { // CHECK: __strcpy_chk __builtin___strcpy_chk(content, "", 1); } + +void PR4941(char *s) { + // Make sure we don't optimize this loop to a memset(). + // MEMSET-LABEL: PR4941: + // MEMSET-NOT: memset + for (unsigned i = 0; i < 8192; ++i) + s[i] = 0; +} diff --git a/test/CodeGen/pku.c b/test/CodeGen/pku.c new file mode 100644 index 0000000..30565a8 --- /dev/null +++ b/test/CodeGen/pku.c @@ -0,0 +1,18 @@ +// RUN: %clang_cc1 %s -triple=x86_64-apple-darwin -target-feature +pku -emit-llvm -o - -Werror | FileCheck %s + +// Don't include mm_malloc.h, it's system specific. +#define __MM_MALLOC_H + +#include <immintrin.h> + +unsigned int test_rdpkru_u32() { + // CHECK-LABEL: @test_rdpkru_u32 + // CHECK: @llvm.x86.rdpkru + return _rdpkru_u32(); +} +void test_wrpkru(unsigned int __A) { + // CHECK-LABEL: @test_wrpkru + // CHECK: @llvm.x86.wrpkru + _wrpkru(__A); + return ; +} |