summaryrefslogtreecommitdiff
path: root/test/CodeGen/ARM/vabd.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/ARM/vabd.ll')
-rw-r--r--test/CodeGen/ARM/vabd.ll107
1 files changed, 95 insertions, 12 deletions
diff --git a/test/CodeGen/ARM/vabd.ll b/test/CodeGen/ARM/vabd.ll
index 0fe5ddb94ba4..2b4539361459 100644
--- a/test/CodeGen/ARM/vabd.ll
+++ b/test/CodeGen/ARM/vabd.ll
@@ -1,13 +1,8 @@
-; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
-; RUN: grep {vabd\\.s8} %t | count 2
-; RUN: grep {vabd\\.s16} %t | count 2
-; RUN: grep {vabd\\.s32} %t | count 2
-; RUN: grep {vabd\\.u8} %t | count 2
-; RUN: grep {vabd\\.u16} %t | count 2
-; RUN: grep {vabd\\.u32} %t | count 2
-; RUN: grep {vabd\\.f32} %t | count 2
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @vabds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vabds8:
+;CHECK: vabd.s8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -15,6 +10,8 @@ define <8 x i8> @vabds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
}
define <4 x i16> @vabds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vabds16:
+;CHECK: vabd.s16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -22,6 +19,8 @@ define <4 x i16> @vabds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
}
define <2 x i32> @vabds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vabds32:
+;CHECK: vabd.s32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -29,6 +28,8 @@ define <2 x i32> @vabds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
}
define <8 x i8> @vabdu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vabdu8:
+;CHECK: vabd.u8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -36,6 +37,8 @@ define <8 x i8> @vabdu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
}
define <4 x i16> @vabdu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vabdu16:
+;CHECK: vabd.u16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -43,6 +46,8 @@ define <4 x i16> @vabdu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
}
define <2 x i32> @vabdu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vabdu32:
+;CHECK: vabd.u32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -50,13 +55,17 @@ define <2 x i32> @vabdu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
}
define <2 x float> @vabdf32(<2 x float>* %A, <2 x float>* %B) nounwind {
+;CHECK: vabdf32:
+;CHECK: vabd.f32
%tmp1 = load <2 x float>* %A
%tmp2 = load <2 x float>* %B
- %tmp3 = call <2 x float> @llvm.arm.neon.vabdf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
+ %tmp3 = call <2 x float> @llvm.arm.neon.vabds.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
ret <2 x float> %tmp3
}
define <16 x i8> @vabdQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vabdQs8:
+;CHECK: vabd.s8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = call <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@@ -64,6 +73,8 @@ define <16 x i8> @vabdQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
}
define <8 x i16> @vabdQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vabdQs16:
+;CHECK: vabd.s16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = call <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@@ -71,6 +82,8 @@ define <8 x i16> @vabdQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
}
define <4 x i32> @vabdQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vabdQs32:
+;CHECK: vabd.s32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = call <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@@ -78,6 +91,8 @@ define <4 x i32> @vabdQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
}
define <16 x i8> @vabdQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vabdQu8:
+;CHECK: vabd.u8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = call <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@@ -85,6 +100,8 @@ define <16 x i8> @vabdQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
}
define <8 x i16> @vabdQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vabdQu16:
+;CHECK: vabd.u16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = call <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@@ -92,6 +109,8 @@ define <8 x i16> @vabdQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
}
define <4 x i32> @vabdQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vabdQu32:
+;CHECK: vabd.u32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = call <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@@ -99,9 +118,11 @@ define <4 x i32> @vabdQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
}
define <4 x float> @vabdQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
+;CHECK: vabdQf32:
+;CHECK: vabd.f32
%tmp1 = load <4 x float>* %A
%tmp2 = load <4 x float>* %B
- %tmp3 = call <4 x float> @llvm.arm.neon.vabdf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
+ %tmp3 = call <4 x float> @llvm.arm.neon.vabds.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
ret <4 x float> %tmp3
}
@@ -113,7 +134,7 @@ declare <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8>, <8 x i8>) nounwind readnon
declare <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
-declare <2 x float> @llvm.arm.neon.vabdf.v2f32(<2 x float>, <2 x float>) nounwind readnone
+declare <2 x float> @llvm.arm.neon.vabds.v2f32(<2 x float>, <2 x float>) nounwind readnone
declare <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
declare <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
@@ -123,4 +144,66 @@ declare <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8>, <16 x i8>) nounwind read
declare <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
declare <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
-declare <4 x float> @llvm.arm.neon.vabdf.v4f32(<4 x float>, <4 x float>) nounwind readnone
+declare <4 x float> @llvm.arm.neon.vabds.v4f32(<4 x float>, <4 x float>) nounwind readnone
+
+define <8 x i16> @vabdls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vabdls8:
+;CHECK: vabdl.s8
+ %tmp1 = load <8 x i8>* %A
+ %tmp2 = load <8 x i8>* %B
+ %tmp3 = call <8 x i16> @llvm.arm.neon.vabdls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
+ ret <8 x i16> %tmp3
+}
+
+define <4 x i32> @vabdls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vabdls16:
+;CHECK: vabdl.s16
+ %tmp1 = load <4 x i16>* %A
+ %tmp2 = load <4 x i16>* %B
+ %tmp3 = call <4 x i32> @llvm.arm.neon.vabdls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
+ ret <4 x i32> %tmp3
+}
+
+define <2 x i64> @vabdls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vabdls32:
+;CHECK: vabdl.s32
+ %tmp1 = load <2 x i32>* %A
+ %tmp2 = load <2 x i32>* %B
+ %tmp3 = call <2 x i64> @llvm.arm.neon.vabdls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
+ ret <2 x i64> %tmp3
+}
+
+define <8 x i16> @vabdlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vabdlu8:
+;CHECK: vabdl.u8
+ %tmp1 = load <8 x i8>* %A
+ %tmp2 = load <8 x i8>* %B
+ %tmp3 = call <8 x i16> @llvm.arm.neon.vabdlu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
+ ret <8 x i16> %tmp3
+}
+
+define <4 x i32> @vabdlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vabdlu16:
+;CHECK: vabdl.u16
+ %tmp1 = load <4 x i16>* %A
+ %tmp2 = load <4 x i16>* %B
+ %tmp3 = call <4 x i32> @llvm.arm.neon.vabdlu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
+ ret <4 x i32> %tmp3
+}
+
+define <2 x i64> @vabdlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vabdlu32:
+;CHECK: vabdl.u32
+ %tmp1 = load <2 x i32>* %A
+ %tmp2 = load <2 x i32>* %B
+ %tmp3 = call <2 x i64> @llvm.arm.neon.vabdlu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
+ ret <2 x i64> %tmp3
+}
+
+declare <8 x i16> @llvm.arm.neon.vabdls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vabdls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i64> @llvm.arm.neon.vabdls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <8 x i16> @llvm.arm.neon.vabdlu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vabdlu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i64> @llvm.arm.neon.vabdlu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-02 11:36:29 +0000