[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE

This patch corresponds to review:
https://reviews.llvm.org/D26861

It also fixes PR30730.

Committing on behalf of Lei Huang.

llvm-svn: 287679

1 files changed, 26 insertions, 20 deletions

diff --git a/llvm/test/CodeGen/PowerPC/swaps-le-1.ll b/llvm/test/CodeGen/PowerPC/swaps-le-1.ll
index cb83bf262b4..29c94f89543 100644
--- a/llvm/test/CodeGen/PowerPC/swaps-le-1.ll
+++ b/llvm/test/CodeGen/PowerPC/swaps-le-1.ll
@@ -13,6 +13,12 @@
 ; RUN:  -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu < %s \
 ; RUN:  | FileCheck -check-prefix=NOOPTSWAP %s
 
+; LH: 2016-11-17
+;   Updated align attritue from 16 to 8 to keep swap instructions tests.
+;   Changes have been made on little-endian to use lvx and stvx
+;   instructions instead of lxvd2x/xxswapd and xxswapd/stxvd2x for
+;   aligned vectors with elements up to 4 bytes
+
 ; This test was generated from the following source:
 ;
 ; #define N 4096
@@ -29,10 +35,10 @@
 ;   }
 ; }
 
-@cb = common global [4096 x i32] zeroinitializer, align 16
-@cc = common global [4096 x i32] zeroinitializer, align 16
-@cd = common global [4096 x i32] zeroinitializer, align 16
-@ca = common global [4096 x i32] zeroinitializer, align 16
+@cb = common global [4096 x i32] zeroinitializer, align 8
+@cc = common global [4096 x i32] zeroinitializer, align 8
+@cd = common global [4096 x i32] zeroinitializer, align 8
+@ca = common global [4096 x i32] zeroinitializer, align 8
 
 define void @foo() {
 entry:
@@ -42,63 +48,63 @@ vector.body:
   %index = phi i64 [ 0, %entry ], [ %index.next.3, %vector.body ]
   %0 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index
   %1 = bitcast i32* %0 to <4 x i32>*
-  %wide.load = load <4 x i32>, <4 x i32>* %1, align 16
+  %wide.load = load <4 x i32>, <4 x i32>* %1, align 8
   %2 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index
   %3 = bitcast i32* %2 to <4 x i32>*
-  %wide.load13 = load <4 x i32>, <4 x i32>* %3, align 16
+  %wide.load13 = load <4 x i32>, <4 x i32>* %3, align 8
   %4 = add nsw <4 x i32> %wide.load13, %wide.load
   %5 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index
   %6 = bitcast i32* %5 to <4 x i32>*
-  %wide.load14 = load <4 x i32>, <4 x i32>* %6, align 16
+  %wide.load14 = load <4 x i32>, <4 x i32>* %6, align 8
   %7 = mul nsw <4 x i32> %4, %wide.load14
   %8 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index
   %9 = bitcast i32* %8 to <4 x i32>*
-  store <4 x i32> %7, <4 x i32>* %9, align 16
+  store <4 x i32> %7, <4 x i32>* %9, align 8
   %index.next = add nuw nsw i64 %index, 4
   %10 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index.next
   %11 = bitcast i32* %10 to <4 x i32>*
-  %wide.load.1 = load <4 x i32>, <4 x i32>* %11, align 16
+  %wide.load.1 = load <4 x i32>, <4 x i32>* %11, align 8
   %12 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index.next
   %13 = bitcast i32* %12 to <4 x i32>*
-  %wide.load13.1 = load <4 x i32>, <4 x i32>* %13, align 16
+  %wide.load13.1 = load <4 x i32>, <4 x i32>* %13, align 8
   %14 = add nsw <4 x i32> %wide.load13.1, %wide.load.1
   %15 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index.next
   %16 = bitcast i32* %15 to <4 x i32>*
-  %wide.load14.1 = load <4 x i32>, <4 x i32>* %16, align 16
+  %wide.load14.1 = load <4 x i32>, <4 x i32>* %16, align 8
   %17 = mul nsw <4 x i32> %14, %wide.load14.1
   %18 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index.next
   %19 = bitcast i32* %18 to <4 x i32>*
-  store <4 x i32> %17, <4 x i32>* %19, align 16
+  store <4 x i32> %17, <4 x i32>* %19, align 8
   %index.next.1 = add nuw nsw i64 %index.next, 4
   %20 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index.next.1
   %21 = bitcast i32* %20 to <4 x i32>*
-  %wide.load.2 = load <4 x i32>, <4 x i32>* %21, align 16
+  %wide.load.2 = load <4 x i32>, <4 x i32>* %21, align 8
   %22 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index.next.1
   %23 = bitcast i32* %22 to <4 x i32>*
-  %wide.load13.2 = load <4 x i32>, <4 x i32>* %23, align 16
+  %wide.load13.2 = load <4 x i32>, <4 x i32>* %23, align 8
   %24 = add nsw <4 x i32> %wide.load13.2, %wide.load.2
   %25 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index.next.1
   %26 = bitcast i32* %25 to <4 x i32>*
-  %wide.load14.2 = load <4 x i32>, <4 x i32>* %26, align 16
+  %wide.load14.2 = load <4 x i32>, <4 x i32>* %26, align 8
   %27 = mul nsw <4 x i32> %24, %wide.load14.2
   %28 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index.next.1
   %29 = bitcast i32* %28 to <4 x i32>*
-  store <4 x i32> %27, <4 x i32>* %29, align 16
+  store <4 x i32> %27, <4 x i32>* %29, align 8
   %index.next.2 = add nuw nsw i64 %index.next.1, 4
   %30 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cb, i64 0, i64 %index.next.2
   %31 = bitcast i32* %30 to <4 x i32>*
-  %wide.load.3 = load <4 x i32>, <4 x i32>* %31, align 16
+  %wide.load.3 = load <4 x i32>, <4 x i32>* %31, align 8
   %32 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cc, i64 0, i64 %index.next.2
   %33 = bitcast i32* %32 to <4 x i32>*
-  %wide.load13.3 = load <4 x i32>, <4 x i32>* %33, align 16
+  %wide.load13.3 = load <4 x i32>, <4 x i32>* %33, align 8
   %34 = add nsw <4 x i32> %wide.load13.3, %wide.load.3
   %35 = getelementptr inbounds [4096 x i32], [4096 x i32]* @cd, i64 0, i64 %index.next.2
   %36 = bitcast i32* %35 to <4 x i32>*
-  %wide.load14.3 = load <4 x i32>, <4 x i32>* %36, align 16
+  %wide.load14.3 = load <4 x i32>, <4 x i32>* %36, align 8
   %37 = mul nsw <4 x i32> %34, %wide.load14.3
   %38 = getelementptr inbounds [4096 x i32], [4096 x i32]* @ca, i64 0, i64 %index.next.2
   %39 = bitcast i32* %38 to <4 x i32>*
-  store <4 x i32> %37, <4 x i32>* %39, align 16
+  store <4 x i32> %37, <4 x i32>* %39, align 8
   %index.next.3 = add nuw nsw i64 %index.next.2, 4
   %40 = icmp eq i64 %index.next.3, 4096
   br i1 %40, label %for.end, label %vector.body