[PowerPC 2/4] Little-endian adjustments for VSX insert/extract operations

For little endian, we need to make some straightforward adjustments in
the code expansions for scalar_to_vector and vector_extract of v2f64.
First, scalar_to_vector must place the scalar into vector element
zero.  However, our implementation of SUBREG_TO_REG will place it into
big-element vector element zero (high-order bits), and for little
endian we need it in the low-order bits.  The LE implementation splats
the high-order doubleword into the low-order doubleword.

Second, the meaning of (vector_extract x, 0) and (vector_extract x, 1)
must be reversed for similar reasons.

A new test is added that tests code generation for insertelement and
extractelement for both element 0 and element 1.  It is disabled in
this patch but enabled in patch 4/4, for reasons stated in the test.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223788 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/PPCInstrVSX.td b/lib/Target/PowerPC/PPCInstrVSX.td
index d8003c9d8c89145c881a3ce853599d5e98449833..b21b251443eb70c7681167db356e8e87c8497a26 100644 (file)
--- a/lib/Target/PowerPC/PPCInstrVSX.td
+++ b/lib/Target/PowerPC/PPCInstrVSX.td
@@ -793,6 +793,8 @@ def : InstAlias<"xxswapd $XT, $XB",
                 (XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 2)>;
 
 let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
+
+let Predicates = [IsBigEndian] in {
 def : Pat<(v2f64 (scalar_to_vector f64:$A)),
           (v2f64 (SUBREG_TO_REG (i64 1), $A, sub_64))>;
 
@@ -800,6 +802,18 @@ def : Pat<(f64 (vector_extract v2f64:$S, 0)),
           (f64 (EXTRACT_SUBREG $S, sub_64))>;
 def : Pat<(f64 (vector_extract v2f64:$S, 1)),
           (f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
+}
+
+let Predicates = [IsLittleEndian] in {
+def : Pat<(v2f64 (scalar_to_vector f64:$A)),
+          (v2f64 (XXPERMDI (SUBREG_TO_REG (i64 1), $A, sub_64),
+                           (SUBREG_TO_REG (i64 1), $A, sub_64), 0))>;
+
+def : Pat<(f64 (vector_extract v2f64:$S, 0)),
+          (f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
+def : Pat<(f64 (vector_extract v2f64:$S, 1)),
+          (f64 (EXTRACT_SUBREG $S, sub_64))>;
+}
 
 // Additional fnmsub patterns: -a*c + b == -(a*c - b)
 def : Pat<(fma (fneg f64:$A), f64:$C, f64:$B),