Add remaining 256-bit vector bitcasts. This also fixes PR10451

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@136003 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index 82e0d2a2ff64985940bf964e5fd785c6820f5670..d574a7b8db319b0e8d62f095534fe9ee3ec6627b 100644 (file)
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -3639,9 +3639,8 @@ let Predicates = [HasSSE2] in
  def : Pat<(fextend (loadf32 addr:$src)),
            (CVTSS2SDrm addr:$src)>;
 
-
-
-// bit_convert
+// Bitcasts between 128-bit vector types. Return the original type since
+// no instruction is needed for the conversion
 let Predicates = [HasXMMInt] in {
   def : Pat<(v2i64 (bitconvert (v4i32 VR128:$src))), (v2i64 VR128:$src)>;
   def : Pat<(v2i64 (bitconvert (v8i16 VR128:$src))), (v2i64 VR128:$src)>;
@@ -3675,24 +3674,39 @@ let Predicates = [HasXMMInt] in {
   def : Pat<(v2f64 (bitconvert (v4f32 VR128:$src))), (v2f64 VR128:$src)>;
 }
 
+// Bitcasts between 256-bit vector types. Return the original type since
+// no instruction is needed for the conversion
 let Predicates = [HasAVX] in {
   def : Pat<(v4f64  (bitconvert (v8f32 VR256:$src))),  (v4f64 VR256:$src)>;
+  def : Pat<(v4f64  (bitconvert (v8i32 VR256:$src))),  (v4f64 VR256:$src)>;
   def : Pat<(v4f64  (bitconvert (v4i64 VR256:$src))),  (v4f64 VR256:$src)>;
+  def : Pat<(v4f64  (bitconvert (v16i16 VR256:$src))), (v4f64 VR256:$src)>;
   def : Pat<(v4f64  (bitconvert (v32i8 VR256:$src))),  (v4f64 VR256:$src)>;
+  def : Pat<(v8f32  (bitconvert (v8i32 VR256:$src))),  (v8f32 VR256:$src)>;
   def : Pat<(v8f32  (bitconvert (v4i64 VR256:$src))),  (v8f32 VR256:$src)>;
   def : Pat<(v8f32  (bitconvert (v4f64 VR256:$src))),  (v8f32 VR256:$src)>;
   def : Pat<(v8f32  (bitconvert (v32i8 VR256:$src))),  (v8f32 VR256:$src)>;
   def : Pat<(v8f32  (bitconvert (v16i16 VR256:$src))), (v8f32 VR256:$src)>;
-  def : Pat<(v8i32  (bitconvert (v8f32 VR256:$src))),  (v8i32 VR256:$src)>;
   def : Pat<(v4i64  (bitconvert (v8f32 VR256:$src))),  (v4i64 VR256:$src)>;
+  def : Pat<(v4i64  (bitconvert (v8i32 VR256:$src))),  (v4i64 VR256:$src)>;
   def : Pat<(v4i64  (bitconvert (v4f64 VR256:$src))),  (v4i64 VR256:$src)>;
   def : Pat<(v4i64  (bitconvert (v32i8 VR256:$src))),  (v4i64 VR256:$src)>;
+  def : Pat<(v4i64  (bitconvert (v16i16 VR256:$src))), (v4i64 VR256:$src)>;
   def : Pat<(v32i8  (bitconvert (v4f64 VR256:$src))),  (v32i8 VR256:$src)>;
   def : Pat<(v32i8  (bitconvert (v4i64 VR256:$src))),  (v32i8 VR256:$src)>;
   def : Pat<(v32i8  (bitconvert (v8f32 VR256:$src))),  (v32i8 VR256:$src)>;
   def : Pat<(v32i8  (bitconvert (v8i32 VR256:$src))),  (v32i8 VR256:$src)>;
+  def : Pat<(v32i8  (bitconvert (v16i16 VR256:$src))), (v32i8 VR256:$src)>;
   def : Pat<(v8i32  (bitconvert (v32i8 VR256:$src))),  (v8i32 VR256:$src)>;
+  def : Pat<(v8i32  (bitconvert (v16i16 VR256:$src))), (v8i32 VR256:$src)>;
+  def : Pat<(v8i32  (bitconvert (v8f32 VR256:$src))),  (v8i32 VR256:$src)>;
+  def : Pat<(v8i32  (bitconvert (v4i64 VR256:$src))),  (v8i32 VR256:$src)>;
+  def : Pat<(v8i32  (bitconvert (v4f64 VR256:$src))),  (v8i32 VR256:$src)>;
   def : Pat<(v16i16 (bitconvert (v8f32 VR256:$src))),  (v16i16 VR256:$src)>;
+  def : Pat<(v16i16 (bitconvert (v8i32 VR256:$src))),  (v16i16 VR256:$src)>;
+  def : Pat<(v16i16 (bitconvert (v4i64 VR256:$src))),  (v16i16 VR256:$src)>;
+  def : Pat<(v16i16 (bitconvert (v4f64 VR256:$src))),  (v16i16 VR256:$src)>;
+  def : Pat<(v16i16 (bitconvert (v32i8 VR256:$src))),  (v16i16 VR256:$src)>;
 }
 
 // Move scalar to XMM zero-extended