Also set addrmode6 alignment when align==size.

Previously, we were only setting the alignment bits on over-aligned
loads and stores.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@143160 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/ARMISelDAGToDAG.cpp b/lib/Target/ARM/ARMISelDAGToDAG.cpp
index 39d4d39c9044bc336d30908fbf324496ef252cb9..7c67e0a1e35a5e2e3ee885a1370790fd862f5441 100644 (file)
--- a/lib/Target/ARM/ARMISelDAGToDAG.cpp
+++ b/lib/Target/ARM/ARMISelDAGToDAG.cpp
@@ -923,7 +923,7 @@ bool ARMDAGToDAGISel::SelectAddrMode6(SDNode *Parent, SDValue N, SDValue &Addr,
     // The maximum alignment is equal to the memory size being referenced.
     unsigned LSNAlign = LSN->getAlignment();
     unsigned MemSize = LSN->getMemoryVT().getSizeInBits() / 8;
-    if (LSNAlign > MemSize && MemSize > 1)
+    if (LSNAlign >= MemSize && MemSize > 1)
       Alignment = MemSize;
   } else {
     // All other uses of addrmode6 are for intrinsics.  For now just record

diff --git a/test/CodeGen/ARM/vlddup.ll b/test/CodeGen/ARM/vlddup.ll
index d0e9ac3ad3c4e4cfdbdf10c898e6cbeab92ae0d9..61d73c15f31fe6a1df60753197a0915334a02048 100644 (file)
--- a/test/CodeGen/ARM/vlddup.ll
+++ b/test/CodeGen/ARM/vlddup.ll
@@ -32,7 +32,7 @@ define <2 x i32> @vld1dupi32(i32* %A) nounwind {
 
 define <2 x float> @vld1dupf(float* %A) nounwind {
 ;CHECK: vld1dupf:
-;CHECK: vld1.32 {d16[]}, [r0]
+;CHECK: vld1.32 {d16[]}, [r0, :32]
        %tmp0 = load float* %A
         %tmp1 = insertelement <2 x float> undef, float %tmp0, i32 0
         %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
@@ -51,7 +51,7 @@ define <16 x i8> @vld1dupQi8(i8* %A) nounwind {
 
 define <4 x float> @vld1dupQf(float* %A) nounwind {
 ;CHECK: vld1dupQf:
-;CHECK: vld1.32 {d16[], d17[]}, [r0]
+;CHECK: vld1.32 {d16[], d17[]}, [r0, :32]
         %tmp0 = load float* %A
         %tmp1 = insertelement <4 x float> undef, float %tmp0, i32 0
         %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer

diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll
index 0d7d4ec2949f823cc61b0a081b1033723a85f599..7bd0cbda02b1dc8728c33df0f6a864496a1919b0 100644 (file)
--- a/test/CodeGen/ARM/vldlane.ll
+++ b/test/CodeGen/ARM/vldlane.ll
@@ -31,9 +31,19 @@ define <2 x i32> @vld1lanei32(i32* %A, <2 x i32>* %B) nounwind {
         ret <2 x i32> %tmp3
 }
 
+define <2 x i32> @vld1lanei32a32(i32* %A, <2 x i32>* %B) nounwind {
+;CHECK: vld1lanei32a32:
+;Check the alignment value.  Legal values are none or :32.
+;CHECK: vld1.32 {d16[1]}, [r0, :32]
+       %tmp1 = load <2 x i32>* %B
+       %tmp2 = load i32* %A, align 4
+       %tmp3 = insertelement <2 x i32> %tmp1, i32 %tmp2, i32 1
+        ret <2 x i32> %tmp3
+}
+
 define <2 x float> @vld1lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vld1lanef:
-;CHECK: vld1.32 {d16[1]}, [r0]
+;CHECK: vld1.32 {d16[1]}, [r0, :32]
        %tmp1 = load <2 x float>* %B
        %tmp2 = load float* %A, align 4
        %tmp3 = insertelement <2 x float> %tmp1, float %tmp2, i32 1
@@ -69,7 +79,7 @@ define <4 x i32> @vld1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 
 define <4 x float> @vld1laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vld1laneQf:
-;CHECK: vld1.32 {d16[0]}, [r0]
+;CHECK: vld1.32 {d16[0]}, [r0, :32]
        %tmp1 = load <4 x float>* %B
        %tmp2 = load float* %A
        %tmp3 = insertelement <4 x float> %tmp1, float %tmp2, i32 0

diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll
index f3239da6c88180e7edb3cb2b1da95f16c70793c6..758b355736d06d1d61aefd57ad8c75b983a3827e 100644 (file)
--- a/test/CodeGen/ARM/vstlane.ll
+++ b/test/CodeGen/ARM/vstlane.ll
@@ -45,7 +45,7 @@ define void @vst1lanei32(i32* %A, <2 x i32>* %B) nounwind {
 
 define void @vst1lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst1lanef:
-;CHECK: vst1.32 {d16[1]}, [r0]
+;CHECK: vst1.32 {d16[1]}, [r0, :32]
        %tmp1 = load <2 x float>* %B
         %tmp2 = extractelement <2 x float> %tmp1, i32 1
         store float %tmp2, float* %A