ARM: add patterns for [su]xta[bh] from just a shift.

Although the final shifter operand is a rotate, this actually only matters for
the half-word extends when the amount == 24. Otherwise folding a shift in is
just as good.

llvm-svn: 213753

2 files changed, 38 insertions, 6 deletions

diff --git a/llvm/test/CodeGen/Thumb2/thumb2-sxt_rot.ll b/llvm/test/CodeGen/Thumb2/thumb2-sxt_rot.ll
index 5e0977efd20..03acee259d5 100644
--- a/llvm/test/CodeGen/Thumb2/thumb2-sxt_rot.ll
+++ b/llvm/test/CodeGen/Thumb2/thumb2-sxt_rot.ll
@@ -2,14 +2,14 @@
 ; RUN:  | FileCheck %s
 
 define i32 @test0(i8 %A) {
-; CHECK: test0
+; CHECK-LABEL: test0:
 ; CHECK: sxtb r0, r0
         %B = sext i8 %A to i32
 	ret i32 %B
 }
 
 define signext i8 @test1(i32 %A)  {
-; CHECK: test1
+; CHECK-LABEL: test1:
 ; CHECK: lsrs r0, r0, #8
 ; CHECK: sxtb r0, r0
 	%B = lshr i32 %A, 8
@@ -20,9 +20,8 @@ define signext i8 @test1(i32 %A)  {
 }
 
 define signext i32 @test2(i32 %A, i32 %X)  {
-; CHECK: test2
-; CHECK: lsrs r0, r0, #8
-; CHECK: sxtab  r0, r1, r0
+; CHECK-LABEL: test2:
+; CHECK: sxtab  r0, r1, r0, ror #8
 	%B = lshr i32 %A, 8
 	%C = shl i32 %A, 24
 	%D = or i32 %B, %C
@@ -31,3 +30,14 @@ define signext i32 @test2(i32 %A, i32 %X)  {
         %G = add i32 %F, %X
 	ret i32 %G
 }
+
+define i32 @test3(i32 %A, i32 %X) {
+; CHECK-LABEL: test3:
+; CHECK: sxtah r0, r0, r1, ror #8
+  %X.hi = lshr i32 %X, 8
+  %X.trunc = trunc i32 %X.hi to i16
+  %addend = sext i16 %X.trunc to i32
+
+  %sum = add i32 %A, %addend
+  ret i32 %sum
+}
diff --git a/llvm/test/CodeGen/Thumb2/thumb2-uxt_rot.ll b/llvm/test/CodeGen/Thumb2/thumb2-uxt_rot.ll
index 06e78d5b0b8..4afea894aeb 100644
--- a/llvm/test/CodeGen/Thumb2/thumb2-uxt_rot.ll
+++ b/llvm/test/CodeGen/Thumb2/thumb2-uxt_rot.ll
@@ -24,7 +24,7 @@ define zeroext i32 @test2(i32 %A.u, i32 %B.u)  {
 }
 
 define zeroext i32 @test3(i32 %A.u)  {
-; A8: test3
+; A8-LABEL: test3
 ; A8: ubfx  r0, r0, #8, #16
     %B.u = lshr i32 %A.u, 8
     %C.u = shl i32 %A.u, 24
@@ -33,3 +33,25 @@ define zeroext i32 @test3(i32 %A.u)  {
     %F.u = zext i16 %E.u to i32
     ret i32 %F.u
 }
+
+define i32 @test4(i32 %A, i32 %X) {
+; A8-LABEL: test4:
+; A8: uxtab r0, r0, r1, ror #16
+  %X.hi = lshr i32 %X, 16
+  %X.trunc = trunc i32 %X.hi to i8
+  %addend = zext i8 %X.trunc to i32
+
+  %sum = add i32 %A, %addend
+  ret i32 %sum
+}
+
+define i32 @test5(i32 %A, i32 %X) {
+; A8-LABEL: test5:
+; A8: uxtah r0, r0, r1, ror #8
+  %X.hi = lshr i32 %X, 8
+  %X.trunc = trunc i32 %X.hi to i16
+  %addend = zext i16 %X.trunc to i32
+
+  %sum = add i32 %A, %addend
+  ret i32 %sum
+}