Remove NEON vmull, vmlal, and vmlsl intrinsics, replacing them with multiply,

add, and subtract operations with zero-extended or sign-extended vectors.
Update tests.  Add auto-upgrade support for the old intrinsics.

llvm-svn: 112773

5 files changed, 191 insertions, 85 deletions

diff --git a/llvm/test/Bitcode/neon-intrinsics.ll b/llvm/test/Bitcode/neon-intrinsics.ll
index eafa94bc8ec..9dda745bc7e 100644
--- a/llvm/test/Bitcode/neon-intrinsics.ll
+++ b/llvm/test/Bitcode/neon-intrinsics.ll
@@ -52,7 +52,7 @@
 ; CHECK: zext <4 x i16>
 ; CHECK-NEXT: add <4 x i32>
 
-; vsubl/vsubw should be auto-upgraded to sub with sext/zext
+; vsubl/vsubw should be auto-upgraded to subtract with sext/zext
 
 ; CHECK: vsubls16
 ; CHECK-NOT: arm.neon.vsubls.v4i32
@@ -76,6 +76,56 @@
 ; CHECK: zext <4 x i16>
 ; CHECK-NEXT: sub <4 x i32>
 
+; vmull should be auto-upgraded to multiply with sext/zext
+; (but vmullp should remain an intrinsic)
+
+; CHECK: vmulls8
+; CHECK-NOT: arm.neon.vmulls.v8i16
+; CHECK: sext <8 x i8>
+; CHECK-NEXT: sext <8 x i8>
+; CHECK-NEXT: mul <8 x i16>
+
+; CHECK: vmullu16
+; CHECK-NOT: arm.neon.vmullu.v4i32
+; CHECK: zext <4 x i16>
+; CHECK-NEXT: zext <4 x i16>
+; CHECK-NEXT: mul <4 x i32>
+
+; CHECK: vmullp8
+; CHECK: arm.neon.vmullp.v8i16
+
+; vmlal should be auto-upgraded to multiply/add with sext/zext
+
+; CHECK: vmlals32
+; CHECK-NOT: arm.neon.vmlals.v2i64
+; CHECK: sext <2 x i32>
+; CHECK-NEXT: sext <2 x i32>
+; CHECK-NEXT: mul <2 x i64>
+; CHECK-NEXT: add <2 x i64>
+
+; CHECK: vmlalu8
+; CHECK-NOT: arm.neon.vmlalu.v8i16
+; CHECK: zext <8 x i8>
+; CHECK-NEXT: zext <8 x i8>
+; CHECK-NEXT: mul <8 x i16>
+; CHECK-NEXT: add <8 x i16>
+
+; vmlsl should be auto-upgraded to multiply/sub with sext/zext
+
+; CHECK: vmlsls16
+; CHECK-NOT: arm.neon.vmlsls.v4i32
+; CHECK: sext <4 x i16>
+; CHECK-NEXT: sext <4 x i16>
+; CHECK-NEXT: mul <4 x i32>
+; CHECK-NEXT: sub <4 x i32>
+
+; CHECK: vmlslu32
+; CHECK-NOT: arm.neon.vmlslu.v2i64
+; CHECK: zext <2 x i32>
+; CHECK-NEXT: zext <2 x i32>
+; CHECK-NEXT: mul <2 x i64>
+; CHECK-NEXT: sub <2 x i64>
+
 ; vmovn should be auto-upgraded to trunc
 
 ; CHECK: vmovni16
diff --git a/llvm/test/Bitcode/neon-intrinsics.ll.bc b/llvm/test/Bitcode/neon-intrinsics.ll.bc
index 0441aa16698..e925cea4de8 100644
--- a/llvm/test/Bitcode/neon-intrinsics.ll.bc
+++ b/llvm/test/Bitcode/neon-intrinsics.ll.bc
diff --git a/llvm/test/CodeGen/ARM/vmla.ll b/llvm/test/CodeGen/ARM/vmla.ll
index 77cf10ad3e6..9c6b210be79 100644
--- a/llvm/test/CodeGen/ARM/vmla.ll
+++ b/llvm/test/CodeGen/ARM/vmla.ll
@@ -94,8 +94,11 @@ define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
-	%tmp4 = call <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
-	ret <8 x i16> %tmp4
+	%tmp4 = sext <8 x i8> %tmp2 to <8 x i16>
+	%tmp5 = sext <8 x i8> %tmp3 to <8 x i16>
+	%tmp6 = mul <8 x i16> %tmp4, %tmp5
+	%tmp7 = add <8 x i16> %tmp1, %tmp6
+	ret <8 x i16> %tmp7
 }
 
 define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
@@ -104,8 +107,11 @@ define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
-	%tmp4 = call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
-	ret <4 x i32> %tmp4
+	%tmp4 = sext <4 x i16> %tmp2 to <4 x i32>
+	%tmp5 = sext <4 x i16> %tmp3 to <4 x i32>
+	%tmp6 = mul <4 x i32> %tmp4, %tmp5
+	%tmp7 = add <4 x i32> %tmp1, %tmp6
+	ret <4 x i32> %tmp7
 }
 
 define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
@@ -114,8 +120,11 @@ define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
-	%tmp4 = call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
-	ret <2 x i64> %tmp4
+	%tmp4 = sext <2 x i32> %tmp2 to <2 x i64>
+	%tmp5 = sext <2 x i32> %tmp3 to <2 x i64>
+	%tmp6 = mul <2 x i64> %tmp4, %tmp5
+	%tmp7 = add <2 x i64> %tmp1, %tmp6
+	ret <2 x i64> %tmp7
 }
 
 define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
@@ -124,8 +133,11 @@ define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
-	%tmp4 = call <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
-	ret <8 x i16> %tmp4
+	%tmp4 = zext <8 x i8> %tmp2 to <8 x i16>
+	%tmp5 = zext <8 x i8> %tmp3 to <8 x i16>
+	%tmp6 = mul <8 x i16> %tmp4, %tmp5
+	%tmp7 = add <8 x i16> %tmp1, %tmp6
+	ret <8 x i16> %tmp7
 }
 
 define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
@@ -134,8 +146,11 @@ define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
-	%tmp4 = call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
-	ret <4 x i32> %tmp4
+	%tmp4 = zext <4 x i16> %tmp2 to <4 x i32>
+	%tmp5 = zext <4 x i16> %tmp3 to <4 x i32>
+	%tmp6 = mul <4 x i32> %tmp4, %tmp5
+	%tmp7 = add <4 x i32> %tmp1, %tmp6
+	ret <4 x i32> %tmp7
 }
 
 define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
@@ -144,8 +159,11 @@ define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
-	%tmp4 = call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
-	ret <2 x i64> %tmp4
+	%tmp4 = zext <2 x i32> %tmp2 to <2 x i64>
+	%tmp5 = zext <2 x i32> %tmp3 to <2 x i64>
+	%tmp6 = mul <2 x i64> %tmp4, %tmp5
+	%tmp7 = add <2 x i64> %tmp1, %tmp6
+	ret <2 x i64> %tmp7
 }
 
 define arm_aapcs_vfpcc <4 x i32> @test_vmlal_lanes16(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %arg2_int16x4_t) nounwind readnone {
@@ -153,8 +171,11 @@ entry:
 ; CHECK: test_vmlal_lanes16
 ; CHECK: vmlal.s16 q0, d2, d3[1]
   %0 = shufflevector <4 x i16> %arg2_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
-  %1 = tail call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %1
+  %1 = sext <4 x i16> %arg1_int16x4_t to <4 x i32>
+  %2 = sext <4 x i16> %0 to <4 x i32>
+  %3 = mul <4 x i32> %1, %2
+  %4 = add <4 x i32> %arg0_int32x4_t, %3
+  ret <4 x i32> %4
 }
 
 define arm_aapcs_vfpcc <2 x i64> @test_vmlal_lanes32(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %arg2_int32x2_t) nounwind readnone {
@@ -162,8 +183,11 @@ entry:
 ; CHECK: test_vmlal_lanes32
 ; CHECK: vmlal.s32 q0, d2, d3[1]
   %0 = shufflevector <2 x i32> %arg2_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
-  %1 = tail call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %1
+  %1 = sext <2 x i32> %arg1_int32x2_t to <2 x i64>
+  %2 = sext <2 x i32> %0 to <2 x i64>
+  %3 = mul <2 x i64> %1, %2
+  %4 = add <2 x i64> %arg0_int64x2_t, %3
+  ret <2 x i64> %4
 }
 
 define arm_aapcs_vfpcc <4 x i32> @test_vmlal_laneu16(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %arg2_uint16x4_t) nounwind readnone {
@@ -171,8 +195,11 @@ entry:
 ; CHECK: test_vmlal_laneu16
 ; CHECK: vmlal.u16 q0, d2, d3[1]
   %0 = shufflevector <4 x i16> %arg2_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
-  %1 = tail call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %1
+  %1 = zext <4 x i16> %arg1_uint16x4_t to <4 x i32>
+  %2 = zext <4 x i16> %0 to <4 x i32>
+  %3 = mul <4 x i32> %1, %2
+  %4 = add <4 x i32> %arg0_uint32x4_t, %3
+  ret <4 x i32> %4
 }
 
 define arm_aapcs_vfpcc <2 x i64> @test_vmlal_laneu32(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %arg2_uint32x2_t) nounwind readnone {
@@ -180,14 +207,9 @@ entry:
 ; CHECK: test_vmlal_laneu32
 ; CHECK: vmlal.u32 q0, d2, d3[1]
   %0 = shufflevector <2 x i32> %arg2_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
-  %1 = tail call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %1
+  %1 = zext <2 x i32> %arg1_uint32x2_t to <2 x i64>
+  %2 = zext <2 x i32> %0 to <2 x i64>
+  %3 = mul <2 x i64> %1, %2
+  %4 = add <2 x i64> %arg0_uint64x2_t, %3
+  ret <2 x i64> %4
 }
-
-declare <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
-
-declare <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
diff --git a/llvm/test/CodeGen/ARM/vmls.ll b/llvm/test/CodeGen/ARM/vmls.ll
index 2b70a7878ce..65e7fe41bb3 100644
--- a/llvm/test/CodeGen/ARM/vmls.ll
+++ b/llvm/test/CodeGen/ARM/vmls.ll
@@ -94,8 +94,11 @@ define <8 x i16> @vmlsls8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
-	%tmp4 = call <8 x i16> @llvm.arm.neon.vmlsls.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
-	ret <8 x i16> %tmp4
+	%tmp4 = sext <8 x i8> %tmp2 to <8 x i16>
+	%tmp5 = sext <8 x i8> %tmp3 to <8 x i16>
+	%tmp6 = mul <8 x i16> %tmp4, %tmp5
+	%tmp7 = sub <8 x i16> %tmp1, %tmp6
+	ret <8 x i16> %tmp7
 }
 
 define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
@@ -104,8 +107,11 @@ define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
-	%tmp4 = call <4 x i32> @llvm.arm.neon.vmlsls.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
-	ret <4 x i32> %tmp4
+	%tmp4 = sext <4 x i16> %tmp2 to <4 x i32>
+	%tmp5 = sext <4 x i16> %tmp3 to <4 x i32>
+	%tmp6 = mul <4 x i32> %tmp4, %tmp5
+	%tmp7 = sub <4 x i32> %tmp1, %tmp6
+	ret <4 x i32> %tmp7
 }
 
 define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
@@ -114,8 +120,11 @@ define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
-	%tmp4 = call <2 x i64> @llvm.arm.neon.vmlsls.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
-	ret <2 x i64> %tmp4
+	%tmp4 = sext <2 x i32> %tmp2 to <2 x i64>
+	%tmp5 = sext <2 x i32> %tmp3 to <2 x i64>
+	%tmp6 = mul <2 x i64> %tmp4, %tmp5
+	%tmp7 = sub <2 x i64> %tmp1, %tmp6
+	ret <2 x i64> %tmp7
 }
 
 define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
@@ -124,8 +133,11 @@ define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
-	%tmp4 = call <8 x i16> @llvm.arm.neon.vmlslu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
-	ret <8 x i16> %tmp4
+	%tmp4 = zext <8 x i8> %tmp2 to <8 x i16>
+	%tmp5 = zext <8 x i8> %tmp3 to <8 x i16>
+	%tmp6 = mul <8 x i16> %tmp4, %tmp5
+	%tmp7 = sub <8 x i16> %tmp1, %tmp6
+	ret <8 x i16> %tmp7
 }
 
 define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
@@ -134,8 +146,11 @@ define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
-	%tmp4 = call <4 x i32> @llvm.arm.neon.vmlslu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
-	ret <4 x i32> %tmp4
+	%tmp4 = zext <4 x i16> %tmp2 to <4 x i32>
+	%tmp5 = zext <4 x i16> %tmp3 to <4 x i32>
+	%tmp6 = mul <4 x i32> %tmp4, %tmp5
+	%tmp7 = sub <4 x i32> %tmp1, %tmp6
+	ret <4 x i32> %tmp7
 }
 
 define <2 x i64> @vmlslu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
@@ -144,8 +159,11 @@ define <2 x i64> @vmlslu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
-	%tmp4 = call <2 x i64> @llvm.arm.neon.vmlslu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
-	ret <2 x i64> %tmp4
+	%tmp4 = zext <2 x i32> %tmp2 to <2 x i64>
+	%tmp5 = zext <2 x i32> %tmp3 to <2 x i64>
+	%tmp6 = mul <2 x i64> %tmp4, %tmp5
+	%tmp7 = sub <2 x i64> %tmp1, %tmp6
+	ret <2 x i64> %tmp7
 }
 
 define arm_aapcs_vfpcc <4 x i32> @test_vmlsl_lanes16(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %arg2_int16x4_t) nounwind readnone {
@@ -153,8 +171,11 @@ entry:
 ; CHECK: test_vmlsl_lanes16
 ; CHECK: vmlsl.s16 q0, d2, d3[1]
   %0 = shufflevector <4 x i16> %arg2_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
-  %1 = tail call <4 x i32> @llvm.arm.neon.vmlsls.v4i32(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %1
+  %1 = sext <4 x i16> %arg1_int16x4_t to <4 x i32>
+  %2 = sext <4 x i16> %0 to <4 x i32>
+  %3 = mul <4 x i32> %1, %2
+  %4 = sub <4 x i32> %arg0_int32x4_t, %3
+  ret <4 x i32> %4
 }
 
 define arm_aapcs_vfpcc <2 x i64> @test_vmlsl_lanes32(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %arg2_int32x2_t) nounwind readnone {
@@ -162,8 +183,11 @@ entry:
 ; CHECK: test_vmlsl_lanes32
 ; CHECK: vmlsl.s32 q0, d2, d3[1]
   %0 = shufflevector <2 x i32> %arg2_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
-  %1 = tail call <2 x i64> @llvm.arm.neon.vmlsls.v2i64(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %1
+  %1 = sext <2 x i32> %arg1_int32x2_t to <2 x i64>
+  %2 = sext <2 x i32> %0 to <2 x i64>
+  %3 = mul <2 x i64> %1, %2
+  %4 = sub <2 x i64> %arg0_int64x2_t, %3
+  ret <2 x i64> %4
 }
 
 define arm_aapcs_vfpcc <4 x i32> @test_vmlsl_laneu16(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %arg2_uint16x4_t) nounwind readnone {
@@ -171,8 +195,11 @@ entry:
 ; CHECK: test_vmlsl_laneu16
 ; CHECK: vmlsl.u16 q0, d2, d3[1]
   %0 = shufflevector <4 x i16> %arg2_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
-  %1 = tail call <4 x i32> @llvm.arm.neon.vmlslu.v4i32(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %1
+  %1 = zext <4 x i16> %arg1_uint16x4_t to <4 x i32>
+  %2 = zext <4 x i16> %0 to <4 x i32>
+  %3 = mul <4 x i32> %1, %2
+  %4 = sub <4 x i32> %arg0_uint32x4_t, %3
+  ret <4 x i32> %4
 }
 
 define arm_aapcs_vfpcc <2 x i64> @test_vmlsl_laneu32(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %arg2_uint32x2_t) nounwind readnone {
@@ -180,14 +207,9 @@ entry:
 ; CHECK: test_vmlsl_laneu32
 ; CHECK: vmlsl.u32 q0, d2, d3[1]
   %0 = shufflevector <2 x i32> %arg2_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
-  %1 = tail call <2 x i64> @llvm.arm.neon.vmlslu.v2i64(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %1
+  %1 = zext <2 x i32> %arg1_uint32x2_t to <2 x i64>
+  %2 = zext <2 x i32> %0 to <2 x i64>
+  %3 = mul <2 x i64> %1, %2
+  %4 = sub <2 x i64> %arg0_uint64x2_t, %3
+  ret <2 x i64> %4
 }
-
-declare <8 x i16> @llvm.arm.neon.vmlsls.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmlsls.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmlsls.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
-
-declare <8 x i16> @llvm.arm.neon.vmlslu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmlslu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmlslu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
diff --git a/llvm/test/CodeGen/ARM/vmul.ll b/llvm/test/CodeGen/ARM/vmul.ll
index 1d916802127..5383425018f 100644
--- a/llvm/test/CodeGen/ARM/vmul.ll
+++ b/llvm/test/CodeGen/ARM/vmul.ll
@@ -152,8 +152,10 @@ define <8 x i16> @vmulls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vmull.s8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
-	%tmp3 = call <8 x i16> @llvm.arm.neon.vmulls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
-	ret <8 x i16> %tmp3
+	%tmp3 = sext <8 x i8> %tmp1 to <8 x i16>
+	%tmp4 = sext <8 x i8> %tmp2 to <8 x i16>
+	%tmp5 = mul <8 x i16> %tmp3, %tmp4
+	ret <8 x i16> %tmp5
 }
 
 define <4 x i32> @vmulls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
@@ -161,8 +163,10 @@ define <4 x i32> @vmulls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vmull.s16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
-	%tmp3 = call <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
-	ret <4 x i32> %tmp3
+	%tmp3 = sext <4 x i16> %tmp1 to <4 x i32>
+	%tmp4 = sext <4 x i16> %tmp2 to <4 x i32>
+	%tmp5 = mul <4 x i32> %tmp3, %tmp4
+	ret <4 x i32> %tmp5
 }
 
 define <2 x i64> @vmulls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
@@ -170,8 +174,10 @@ define <2 x i64> @vmulls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vmull.s32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
-	%tmp3 = call <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
-	ret <2 x i64> %tmp3
+	%tmp3 = sext <2 x i32> %tmp1 to <2 x i64>
+	%tmp4 = sext <2 x i32> %tmp2 to <2 x i64>
+	%tmp5 = mul <2 x i64> %tmp3, %tmp4
+	ret <2 x i64> %tmp5
 }
 
 define <8 x i16> @vmullu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
@@ -179,8 +185,10 @@ define <8 x i16> @vmullu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vmull.u8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
-	%tmp3 = call <8 x i16> @llvm.arm.neon.vmullu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
-	ret <8 x i16> %tmp3
+	%tmp3 = zext <8 x i8> %tmp1 to <8 x i16>
+	%tmp4 = zext <8 x i8> %tmp2 to <8 x i16>
+	%tmp5 = mul <8 x i16> %tmp3, %tmp4
+	ret <8 x i16> %tmp5
 }
 
 define <4 x i32> @vmullu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
@@ -188,8 +196,10 @@ define <4 x i32> @vmullu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vmull.u16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
-	%tmp3 = call <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
-	ret <4 x i32> %tmp3
+	%tmp3 = zext <4 x i16> %tmp1 to <4 x i32>
+	%tmp4 = zext <4 x i16> %tmp2 to <4 x i32>
+	%tmp5 = mul <4 x i32> %tmp3, %tmp4
+	ret <4 x i32> %tmp5
 }
 
 define <2 x i64> @vmullu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
@@ -197,8 +207,10 @@ define <2 x i64> @vmullu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vmull.u32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
-	%tmp3 = call <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
-	ret <2 x i64> %tmp3
+	%tmp3 = zext <2 x i32> %tmp1 to <2 x i64>
+	%tmp4 = zext <2 x i32> %tmp2 to <2 x i64>
+	%tmp5 = mul <2 x i64> %tmp3, %tmp4
+	ret <2 x i64> %tmp5
 }
 
 define <8 x i16> @vmullp8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
@@ -215,8 +227,10 @@ entry:
 ; CHECK: test_vmull_lanes16
 ; CHECK: vmull.s16 q0, d0, d1[1]
   %0 = shufflevector <4 x i16> %arg1_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
-  %1 = tail call <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16> %arg0_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %1
+  %1 = sext <4 x i16> %arg0_int16x4_t to <4 x i32>
+  %2 = sext <4 x i16> %0 to <4 x i32>
+  %3 = mul <4 x i32> %1, %2
+  ret <4 x i32> %3
 }
 
 define arm_aapcs_vfpcc <2 x i64> @test_vmull_lanes32(<2 x i32> %arg0_int32x2_t, <2 x i32> %arg1_int32x2_t) nounwind readnone {
@@ -224,8 +238,10 @@ entry:
 ; CHECK: test_vmull_lanes32
 ; CHECK: vmull.s32 q0, d0, d1[1]
   %0 = shufflevector <2 x i32> %arg1_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
-  %1 = tail call <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32> %arg0_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %1
+  %1 = sext <2 x i32> %arg0_int32x2_t to <2 x i64>
+  %2 = sext <2 x i32> %0 to <2 x i64>
+  %3 = mul <2 x i64> %1, %2
+  ret <2 x i64> %3
 }
 
 define arm_aapcs_vfpcc <4 x i32> @test_vmull_laneu16(<4 x i16> %arg0_uint16x4_t, <4 x i16> %arg1_uint16x4_t) nounwind readnone {
@@ -233,8 +249,10 @@ entry:
 ; CHECK: test_vmull_laneu16
 ; CHECK: vmull.u16 q0, d0, d1[1]
   %0 = shufflevector <4 x i16> %arg1_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
-  %1 = tail call <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16> %arg0_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %1
+  %1 = zext <4 x i16> %arg0_uint16x4_t to <4 x i32>
+  %2 = zext <4 x i16> %0 to <4 x i32>
+  %3 = mul <4 x i32> %1, %2
+  ret <4 x i32> %3
 }
 
 define arm_aapcs_vfpcc <2 x i64> @test_vmull_laneu32(<2 x i32> %arg0_uint32x2_t, <2 x i32> %arg1_uint32x2_t) nounwind readnone {
@@ -242,16 +260,10 @@ entry:
 ; CHECK: test_vmull_laneu32
 ; CHECK: vmull.u32 q0, d0, d1[1]
   %0 = shufflevector <2 x i32> %arg1_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
-  %1 = tail call <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32> %arg0_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %1
+  %1 = zext <2 x i32> %arg0_uint32x2_t to <2 x i64>
+  %2 = zext <2 x i32> %0 to <2 x i64>
+  %3 = mul <2 x i64> %1, %2
+  ret <2 x i64> %3
 }
 
-declare <8 x i16> @llvm.arm.neon.vmulls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone
-
-declare <8 x i16> @llvm.arm.neon.vmullu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone
-declare <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone
-declare <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone
-
 declare <8 x i16>  @llvm.arm.neon.vmullp.v8i16(<8 x i8>, <8 x i8>) nounwind readnone