[AArch64] Fix incorrect LD1 of 16-bit FP vectors in big endian

Summary:
Loading a vector of 4 half-precision FP sometimes results in an LD1
of 2 single-precision FP + a reversal. This results in an incorrect
byte swap due to the conversion from little endian to big endian.

In order to generate the correct byte swap, it is easier to
generate the correct LD1 of 4 half-precision FP, thus avoiding the
subsequent reversal.

Reviewers: craig.topper, jmolloy, olista01

Reviewed By: olista01

Subscribers: efriedma, samparker, SjoerdMeijer, rogfer01, aemerson, rengolin, javed.absar, kristof.beyls, llvm-commits

Differential Revision: https://reviews.llvm.org/D41863

llvm-svn: 322663

1 files changed, 8 insertions, 18 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index c750e87a4dc..c0975795604 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -5807,7 +5807,7 @@ def : Pat<(v2i32 (bitconvert (f64   FPR64:$src))),
 def : Pat<(v2i32 (bitconvert (v1f64 FPR64:$src))),
                              (v2i32 (REV64v2i32 FPR64:$src))>;
 def : Pat<(v2i32 (bitconvert (v4f16 FPR64:$src))),
-                             (v2i32 (REV64v4i16 FPR64:$src))>;
+                             (v2i32 (REV32v4i16 FPR64:$src))>;
 }
 def : Pat<(v2i32 (bitconvert (v2f32 FPR64:$src))), (v2i32 FPR64:$src)>;
 
@@ -5816,7 +5816,6 @@ def : Pat<(v4i16 (bitconvert (v1i64 FPR64:$src))), (v4i16 FPR64:$src)>;
 def : Pat<(v4i16 (bitconvert (v2i32 FPR64:$src))), (v4i16 FPR64:$src)>;
 def : Pat<(v4i16 (bitconvert (v8i8  FPR64:$src))), (v4i16 FPR64:$src)>;
 def : Pat<(v4i16 (bitconvert (f64   FPR64:$src))), (v4i16 FPR64:$src)>;
-def : Pat<(v4i16 (bitconvert (v4f16 FPR64:$src))), (v4i16 FPR64:$src)>;
 def : Pat<(v4i16 (bitconvert (v2f32 FPR64:$src))), (v4i16 FPR64:$src)>;
 def : Pat<(v4i16 (bitconvert (v1f64 FPR64:$src))), (v4i16 FPR64:$src)>;
 }
@@ -5829,18 +5828,16 @@ def : Pat<(v4i16 (bitconvert (v8i8  FPR64:$src))),
                              (v4i16 (REV16v8i8 FPR64:$src))>;
 def : Pat<(v4i16 (bitconvert (f64   FPR64:$src))),
                              (v4i16 (REV64v4i16 FPR64:$src))>;
-def : Pat<(v4i16 (bitconvert (v4f16 FPR64:$src))),
-                             (v4i16 (REV32v4i16 FPR64:$src))>;
 def : Pat<(v4i16 (bitconvert (v2f32 FPR64:$src))),
                              (v4i16 (REV32v4i16 FPR64:$src))>;
 def : Pat<(v4i16 (bitconvert (v1f64 FPR64:$src))),
                              (v4i16 (REV64v4i16 FPR64:$src))>;
 }
+def : Pat<(v4i16 (bitconvert (v4f16 FPR64:$src))), (v4i16 FPR64:$src)>;
 
 let Predicates = [IsLE] in {
 def : Pat<(v4f16 (bitconvert (v1i64 FPR64:$src))), (v4f16 FPR64:$src)>;
 def : Pat<(v4f16 (bitconvert (v2i32 FPR64:$src))), (v4f16 FPR64:$src)>;
-def : Pat<(v4f16 (bitconvert (v4i16 FPR64:$src))), (v4f16 FPR64:$src)>;
 def : Pat<(v4f16 (bitconvert (v8i8  FPR64:$src))), (v4f16 FPR64:$src)>;
 def : Pat<(v4f16 (bitconvert (f64   FPR64:$src))), (v4f16 FPR64:$src)>;
 def : Pat<(v4f16 (bitconvert (v2f32 FPR64:$src))), (v4f16 FPR64:$src)>;
@@ -5850,20 +5847,17 @@ let Predicates = [IsBE] in {
 def : Pat<(v4f16 (bitconvert (v1i64 FPR64:$src))),
                              (v4f16 (REV64v4i16 FPR64:$src))>;
 def : Pat<(v4f16 (bitconvert (v2i32 FPR64:$src))),
-                             (v4f16 (REV64v4i16 FPR64:$src))>;
-def : Pat<(v4f16 (bitconvert (v4i16 FPR64:$src))),
-                             (v4f16 (REV64v4i16 FPR64:$src))>;
+                             (v4f16 (REV32v4i16 FPR64:$src))>;
 def : Pat<(v4f16 (bitconvert (v8i8  FPR64:$src))),
                              (v4f16 (REV16v8i8 FPR64:$src))>;
 def : Pat<(v4f16 (bitconvert (f64   FPR64:$src))),
                              (v4f16 (REV64v4i16 FPR64:$src))>;
 def : Pat<(v4f16 (bitconvert (v2f32 FPR64:$src))),
-                             (v4f16 (REV64v4i16 FPR64:$src))>;
+                             (v4f16 (REV32v4i16 FPR64:$src))>;
 def : Pat<(v4f16 (bitconvert (v1f64 FPR64:$src))),
                              (v4f16 (REV64v4i16 FPR64:$src))>;
 }
-
-
+def : Pat<(v4f16 (bitconvert (v4i16 FPR64:$src))), (v4f16 FPR64:$src)>;
 
 let Predicates = [IsLE] in {
 def : Pat<(v8i8  (bitconvert (v1i64 FPR64:$src))), (v8i8  FPR64:$src)>;
@@ -5955,7 +5949,7 @@ def : Pat<(v2f32 (bitconvert (v1f64 FPR64:$src))),
 def : Pat<(v2f32 (bitconvert (f64   FPR64:$src))),
                              (v2f32 (REV64v2i32 FPR64:$src))>;
 def : Pat<(v2f32 (bitconvert (v4f16 FPR64:$src))),
-                             (v2f32 (REV64v4i16 FPR64:$src))>;
+                             (v2f32 (REV32v4i16 FPR64:$src))>;
 }
 def : Pat<(v2f32 (bitconvert (v2i32 FPR64:$src))), (v2f32 FPR64:$src)>;
 
@@ -6098,7 +6092,6 @@ def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))), (v8i16 FPR128:$src)>;
 def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))), (v8i16 FPR128:$src)>;
 def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))), (v8i16 FPR128:$src)>;
 def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))), (v8i16 FPR128:$src)>;
-def : Pat<(v8i16 (bitconvert (v8f16 FPR128:$src))), (v8i16 FPR128:$src)>;
 }
 let Predicates = [IsBE] in {
 def : Pat<(v8i16 (bitconvert (f128  FPR128:$src))),
@@ -6115,15 +6108,13 @@ def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))),
                              (v8i16 (REV64v8i16 FPR128:$src))>;
 def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))),
                              (v8i16 (REV32v8i16 FPR128:$src))>;
-def : Pat<(v8i16 (bitconvert (v8f16 FPR128:$src))),
-                             (v8i16 (REV32v8i16 FPR128:$src))>;
 }
+def : Pat<(v8i16 (bitconvert (v8f16 FPR128:$src))), (v8i16 FPR128:$src)>;
 
 let Predicates = [IsLE] in {
 def : Pat<(v8f16 (bitconvert (f128  FPR128:$src))), (v8f16 FPR128:$src)>;
 def : Pat<(v8f16 (bitconvert (v2i64 FPR128:$src))), (v8f16 FPR128:$src)>;
 def : Pat<(v8f16 (bitconvert (v4i32 FPR128:$src))), (v8f16 FPR128:$src)>;
-def : Pat<(v8f16 (bitconvert (v8i16 FPR128:$src))), (v8f16 FPR128:$src)>;
 def : Pat<(v8f16 (bitconvert (v16i8 FPR128:$src))), (v8f16 FPR128:$src)>;
 def : Pat<(v8f16 (bitconvert (v2f64 FPR128:$src))), (v8f16 FPR128:$src)>;
 def : Pat<(v8f16 (bitconvert (v4f32 FPR128:$src))), (v8f16 FPR128:$src)>;
@@ -6137,8 +6128,6 @@ def : Pat<(v8f16 (bitconvert (v2i64 FPR128:$src))),
                              (v8f16 (REV64v8i16 FPR128:$src))>;
 def : Pat<(v8f16 (bitconvert (v4i32 FPR128:$src))),
                              (v8f16 (REV32v8i16 FPR128:$src))>;
-def : Pat<(v8f16 (bitconvert (v8i16 FPR128:$src))),
-                             (v8f16 (REV64v8i16 FPR128:$src))>;
 def : Pat<(v8f16 (bitconvert (v16i8 FPR128:$src))),
                              (v8f16 (REV16v16i8 FPR128:$src))>;
 def : Pat<(v8f16 (bitconvert (v2f64 FPR128:$src))),
@@ -6146,6 +6135,7 @@ def : Pat<(v8f16 (bitconvert (v2f64 FPR128:$src))),
 def : Pat<(v8f16 (bitconvert (v4f32 FPR128:$src))),
                              (v8f16 (REV32v8i16 FPR128:$src))>;
 }
+def : Pat<(v8f16 (bitconvert (v8i16 FPR128:$src))), (v8f16 FPR128:$src)>;
 
 let Predicates = [IsLE] in {
 def : Pat<(v16i8 (bitconvert (f128  FPR128:$src))), (v16i8 FPR128:$src)>;