Replace the arm.neon.vmovls and vmovlu intrinsics with vector sign-extend and

zero-extend operations.

llvm-svn: 111614

4 files changed, 35 insertions, 21 deletions

diff --git a/llvm/test/Bitcode/neon-intrinsics.ll b/llvm/test/Bitcode/neon-intrinsics.ll
new file mode 100644
index 00000000000..73ca7075d80
--- /dev/null
+++ b/llvm/test/Bitcode/neon-intrinsics.ll
@@ -0,0 +1,29 @@
+; RUN: llvm-dis < %s.bc | FileCheck %s
+
+; vmovls should be auto-upgraded to sext
+
+; CHECK: vmovls8
+; CHECK-NOT: arm.neon.vmovls.v8i16
+; CHECK: sext <8 x i8>
+
+; CHECK: vmovls16
+; CHECK-NOT: arm.neon.vmovls.v4i32
+; CHECK: sext <4 x i16>
+
+; CHECK: vmovls32
+; CHECK-NOT: arm.neon.vmovls.v2i64
+; CHECK: sext <2 x i32>
+
+; vmovlu should be auto-upgraded to zext
+
+; CHECK: vmovlu8
+; CHECK-NOT: arm.neon.vmovlu.v8i16
+; CHECK: zext <8 x i8>
+
+; CHECK: vmovlu16
+; CHECK-NOT: arm.neon.vmovlu.v4i32
+; CHECK: zext <4 x i16>
+
+; CHECK: vmovlu32
+; CHECK-NOT: arm.neon.vmovlu.v2i64
+; CHECK: zext <2 x i32>
diff --git a/llvm/test/Bitcode/neon-intrinsics.ll.bc b/llvm/test/Bitcode/neon-intrinsics.ll.bc
new file mode 100644
index 00000000000..93eeabc8223
--- /dev/null
+++ b/llvm/test/Bitcode/neon-intrinsics.ll.bc
diff --git a/llvm/test/CodeGen/ARM/neon-ops.ll b/llvm/test/CodeGen/ARM/neon-ops.ll
deleted file mode 100644
index d7e893f64f9..00000000000
--- a/llvm/test/CodeGen/ARM/neon-ops.ll
+++ /dev/null
@@ -1,7 +0,0 @@
-; RUN: llc -march=arm -mattr=+neon -O2 -o /dev/null
-
-; This used to crash.
-define <4 x i32> @test1(<4 x i16> %a) {
-  %A = zext <4 x i16> %a to <4 x i32>
-  ret <4 x i32> %A
-}
diff --git a/llvm/test/CodeGen/ARM/vmov.ll b/llvm/test/CodeGen/ARM/vmov.ll
index 5e872ab6d0b..f863bf8a092 100644
--- a/llvm/test/CodeGen/ARM/vmov.ll
+++ b/llvm/test/CodeGen/ARM/vmov.ll
@@ -192,7 +192,7 @@ define <8 x i16> @vmovls8(<8 x i8>* %A) nounwind {
 ;CHECK: vmovls8:
 ;CHECK: vmovl.s8
 	%tmp1 = load <8 x i8>* %A
-	%tmp2 = call <8 x i16> @llvm.arm.neon.vmovls.v8i16(<8 x i8> %tmp1)
+	%tmp2 = sext <8 x i8> %tmp1 to <8 x i16>
 	ret <8 x i16> %tmp2
 }
 
@@ -200,7 +200,7 @@ define <4 x i32> @vmovls16(<4 x i16>* %A) nounwind {
 ;CHECK: vmovls16:
 ;CHECK: vmovl.s16
 	%tmp1 = load <4 x i16>* %A
-	%tmp2 = call <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16> %tmp1)
+	%tmp2 = sext <4 x i16> %tmp1 to <4 x i32>
 	ret <4 x i32> %tmp2
 }
 
@@ -208,7 +208,7 @@ define <2 x i64> @vmovls32(<2 x i32>* %A) nounwind {
 ;CHECK: vmovls32:
 ;CHECK: vmovl.s32
 	%tmp1 = load <2 x i32>* %A
-	%tmp2 = call <2 x i64> @llvm.arm.neon.vmovls.v2i64(<2 x i32> %tmp1)
+	%tmp2 = sext <2 x i32> %tmp1 to <2 x i64>
 	ret <2 x i64> %tmp2
 }
 
@@ -216,7 +216,7 @@ define <8 x i16> @vmovlu8(<8 x i8>* %A) nounwind {
 ;CHECK: vmovlu8:
 ;CHECK: vmovl.u8
 	%tmp1 = load <8 x i8>* %A
-	%tmp2 = call <8 x i16> @llvm.arm.neon.vmovlu.v8i16(<8 x i8> %tmp1)
+	%tmp2 = zext <8 x i8> %tmp1 to <8 x i16>
 	ret <8 x i16> %tmp2
 }
 
@@ -224,7 +224,7 @@ define <4 x i32> @vmovlu16(<4 x i16>* %A) nounwind {
 ;CHECK: vmovlu16:
 ;CHECK: vmovl.u16
 	%tmp1 = load <4 x i16>* %A
-	%tmp2 = call <4 x i32> @llvm.arm.neon.vmovlu.v4i32(<4 x i16> %tmp1)
+	%tmp2 = zext <4 x i16> %tmp1 to <4 x i32>
 	ret <4 x i32> %tmp2
 }
 
@@ -232,18 +232,10 @@ define <2 x i64> @vmovlu32(<2 x i32>* %A) nounwind {
 ;CHECK: vmovlu32:
 ;CHECK: vmovl.u32
 	%tmp1 = load <2 x i32>* %A
-	%tmp2 = call <2 x i64> @llvm.arm.neon.vmovlu.v2i64(<2 x i32> %tmp1)
+	%tmp2 = zext <2 x i32> %tmp1 to <2 x i64>
 	ret <2 x i64> %tmp2
 }
 
-declare <8 x i16> @llvm.arm.neon.vmovls.v8i16(<8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmovls.v2i64(<2 x i32>) nounwind readnone
-
-declare <8 x i16> @llvm.arm.neon.vmovlu.v8i16(<8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmovlu.v4i32(<4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmovlu.v2i64(<2 x i32>) nounwind readnone
-
 define <8 x i8> @vmovni16(<8 x i16>* %A) nounwind {
 ;CHECK: vmovni16:
 ;CHECK: vmovn.i16