[ARM] Do not use vtrn for vectorshuffle if the order is reversed

The tests in isVTRNMask and isVTRN_v_undef_Mask should also check that the elements of the upper and lower half of the vectorshuffle occur in the correct order when both halves are used. Without this test the code assumes that it is correct to use vector transpose (vtrn) for the masks <1, 1, 0, 0> and <1, 3, 0, 2>, among others, but the transpose actually incorrectly generates shuffles for <0, 0, 1, 1> and <0, 2, 1, 3> in this case.

Patch by Jeroen Ketema!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@247254 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/ARM/ARMISelLowering.cpp

@@ -5050,10 +5050,16 @@ static bool isVTRNMask(ArrayRef<int> M, EVT VT, unsigned &WhichResult) {
   if (M.size() != NumElts && M.size() != NumElts*2)
     return false;
 
-  // If the mask is twice as long as the result then we need to check the upper
-  // and lower parts of the mask
+  // If the mask is twice as long as the input vector then we need to check the
+  // upper and lower parts of the mask with a matching value for WhichResult
+  // FIXME: A mask with only even values will be rejected in case the first
+  // element is undefined, e.g. [-1, 4, 2, 6] will be rejected, because only
+  // M[0] is used to determine WhichResult
   for (unsigned i = 0; i < M.size(); i += NumElts) {
-    WhichResult = M[i] == 0 ? 0 : 1;
+    if (M.size() == NumElts * 2)
+      WhichResult = i / NumElts;
+    else
+      WhichResult = M[i] == 0 ? 0 : 1;
     for (unsigned j = 0; j < NumElts; j += 2) {
       if ((M[i+j] >= 0 && (unsigned) M[i+j] != j + WhichResult) ||
           (M[i+j+1] >= 0 && (unsigned) M[i+j+1] != j + NumElts + WhichResult))
@@ -5080,7 +5086,10 @@ static bool isVTRN_v_undef_Mask(ArrayRef<int> M, EVT VT, unsigned &WhichResult){
     return false;
 
   for (unsigned i = 0; i < M.size(); i += NumElts) {
-    WhichResult = M[i] == 0 ? 0 : 1;
+    if (M.size() == NumElts * 2)
+      WhichResult = i / NumElts;
+    else
+      WhichResult = M[i] == 0 ? 0 : 1;
     for (unsigned j = 0; j < NumElts; j += 2) {
       if ((M[i+j] >= 0 && (unsigned) M[i+j] != j + WhichResult) ||
           (M[i+j+1] >= 0 && (unsigned) M[i+j+1] != j + WhichResult))

test/CodeGen/ARM/vtrn.ll

@@ -371,3 +371,31 @@ define <8 x i8> @vtrn_mismatched_builvector1(<8 x i8> %tr0, <8 x i8> %tr1,
   %rv = select <8 x i1> %c, <8 x i8> %tr0, <8 x i8> %tr1
   ret <8 x i8> %rv
 }
+
+; Negative test that should not generate a vtrn
+define void @lower_twice_no_vtrn(<4 x i16>* %A, <4 x i16>* %B, <8 x i16>* %C) {
+entry:
+  ; CHECK-LABEL: lower_twice_no_vtrn
+  ; CHECK: @ BB#0:
+  ; CHECK-NOT: vtrn
+  ; CHECK: mov pc, lr
+  %tmp1 = load <4 x i16>, <4 x i16>* %A
+  %tmp2 = load <4 x i16>, <4 x i16>* %B
+  %0 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 undef, i32 5, i32 3, i32 7, i32 1, i32 5, i32 3, i32 7>
+  store <8 x i16> %0, <8 x i16>* %C
+  ret void
+}
+
+; Negative test that should not generate a vtrn
+define void @upper_twice_no_vtrn(<4 x i16>* %A, <4 x i16>* %B, <8 x i16>* %C) {
+entry:
+  ; CHECK-LABEL: upper_twice_no_vtrn
+  ; CHECK: @ BB#0:
+  ; CHECK-NOT: vtrn
+  ; CHECK: mov pc, lr
+  %tmp1 = load <4 x i16>, <4 x i16>* %A
+  %tmp2 = load <4 x i16>, <4 x i16>* %B
+  %0 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 0, i32 undef, i32 2, i32 6, i32 0, i32 4, i32 2, i32 6>
+  store <8 x i16> %0, <8 x i16>* %C
+  ret void
+}

test/CodeGen/ARM/vuzp.ll

@@ -286,6 +286,18 @@ entry:
   ret <4 x i32> %0
 }
 
+define void @vuzp_rev_shufflemask_vtrn(<2 x i32>* %A, <2 x i32>* %B, <4 x i32>* %C) {
+entry:
+  ; CHECK-LABEL: vuzp_rev_shufflemask_vtrn
+  ; CHECK-NOT: vtrn
+  ; CHECK: vuzp
+  %tmp1 = load <2 x i32>, <2 x i32>* %A
+  %tmp2 = load <2 x i32>, <2 x i32>* %B
+  %0 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <4 x i32> <i32 1, i32 3, i32 0, i32 2>
+  store <4 x i32> %0, <4 x i32>* %C
+  ret void
+}
+
 define <8 x i8> @vuzp_trunc(<8 x i8> %in0, <8 x i8> %in1, <8 x i32> %cmp0, <8 x i32> %cmp1) {
 ; In order to create the select we need to truncate the vcgt result from a vector of i32 to a vector of i8.
 ; This results in a build_vector with mismatched types. We will generate two vmovn.i32 instructions to

test/CodeGen/ARM/vzip.ll

@@ -295,3 +295,13 @@ entry:
   ret <4 x i32> %0
 }
 
+define void @vzip_undef_rev_shufflemask_vtrn(<2 x i32>* %A, <4 x i32>* %B) {
+entry:
+  ; CHECK-LABEL: vzip_undef_rev_shufflemask_vtrn
+  ; CHECK-NOT: vtrn
+  ; CHECK: vzip
+  %tmp1 = load <2 x i32>, <2 x i32>* %A
+  %0 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
+  store <4 x i32> %0, <4 x i32>* %B
+  ret void
+}