ARM v8.1a adds Advanced SIMD instructions for Rounding Double Multiply

Add/Subtract.

Add missing tests that accidentally were not committed in rL254250.

Differential Revision: http://reviews.llvm.org/D14982

llvm-svn: 254251

2 files changed, 249 insertions, 0 deletions

diff --git a/clang/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c b/clang/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c
new file mode 100644
index 00000000000..078b454b397
--- /dev/null
+++ b/clang/test/CodeGen/aarch64-v8.1a-neon-intrinsics.c
@@ -0,0 +1,128 @@
+// 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
+
+ #include <arm_neon.h>
+
+// CHECK-AARCH64-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]
+  return vqrdmlah_laneq_s16(a, b, v, 7);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlah_laneq_s32(a, b, v, 3);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlahq_laneq_s16(a, b, v, 7);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlahq_laneq_s32(a, b, v, 3);
+}
+
+// CHECK-AARCH64-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}}
+  return vqrdmlahh_s16(a, b, c);
+}
+
+// CHECK-AARCH64-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]+}}
+  return vqrdmlahs_s32(a, b, c);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlahh_lane_s16(a, b, c, 3);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlahs_lane_s32(a, b, c, 1);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlahh_laneq_s16(a, b, c, 7);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlahs_laneq_s32(a, b, c, 3);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlsh_laneq_s16(a, b, v, 7);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlsh_laneq_s32(a, b, v, 3);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlshq_laneq_s16(a, b, v, 7);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlshq_laneq_s32(a, b, v, 3);
+}
+
+// CHECK-AARCH64-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}}
+  return vqrdmlshh_s16(a, b, c);
+}
+
+// CHECK-AARCH64-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]+}}
+  return vqrdmlshs_s32(a, b, c);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlshh_lane_s16(a, b, c, 3);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlshs_lane_s32(a, b, c, 1);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlshh_laneq_s16(a, b, c, 7);
+}
+
+// CHECK-AARCH64-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]
+  return vqrdmlshs_laneq_s32(a, b, c, 3);
+}
+
diff --git a/clang/test/CodeGen/arm-v8.1a-neon-intrinsics.c b/clang/test/CodeGen/arm-v8.1a-neon-intrinsics.c
new file mode 100644
index 00000000000..f826e3166a5
--- /dev/null
+++ b/clang/test/CodeGen/arm-v8.1a-neon-intrinsics.c
@@ -0,0 +1,121 @@
+// RUN: %clang_cc1 -triple armv8.1a-linux-gnu -target-feature +neon \
+// RUN:  -O3 -S -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:  | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AARCH64
+
+#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
+  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
+  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
+  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
+  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]
+  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]
+  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]
+  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]
+  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
+  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
+  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
+  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
+  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]
+  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]
+  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]
+  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]
+  return vqrdmlshq_lane_s32(a, b, c, 1);
+}
+