[PowerPC] Complete the custom legalization of vector int to fp conversion

A recent patch has added custom legalization of vector conversions of
v2i16 -> v2f64. This just rounds it out for other types where the input vector
has an illegal (narrower) type than the result vector. Specifically, this will
handle the following conversions:

v2i8 -> v2f64
v4i8 -> v4f32
v4i16 -> v4f32

Differential revision: https://reviews.llvm.org/D54663

llvm-svn: 350155

1 files changed, 55 insertions, 24 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCInstrVSX.td b/llvm/lib/Target/PowerPC/PPCInstrVSX.td
index 8321d7f2ecf..0f073388dc7 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrVSX.td
+++ b/llvm/lib/Target/PowerPC/PPCInstrVSX.td
@@ -1217,6 +1217,27 @@ def ScalarLoads {
   dag Li32 = (i32 (load xoaddr:$src));
 }
 
+def DWToSPExtractConv {
+  dag El0US1 = (f32 (PPCfcfidus
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 0))))));
+  dag El1US1 = (f32 (PPCfcfidus
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 1))))));
+  dag El0US2 = (f32 (PPCfcfidus
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 0))))));
+  dag El1US2 = (f32 (PPCfcfidus
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 1))))));
+  dag El0SS1 = (f32 (PPCfcfids
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 0))))));
+  dag El1SS1 = (f32 (PPCfcfids
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S1, 1))))));
+  dag El0SS2 = (f32 (PPCfcfids
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 0))))));
+  dag El1SS2 = (f32 (PPCfcfids
+                    (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S2, 1))))));
+  dag BVU = (v4f32 (build_vector El0US1, El1US1, El0US2, El1US2));
+  dag BVS = (v4f32 (build_vector El0SS1, El1SS1, El0SS2, El1SS2));
+}
+
 // The following VSX instructions were introduced in Power ISA 2.07
 /* FIXME: if the operands are v2i64, these patterns will not match.
    we should define new patterns or otherwise match the same patterns
@@ -1452,35 +1473,27 @@ let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
   } // UseVSXReg = 1
 
   let Predicates = [IsLittleEndian] in {
-  def : Pat<(f32 (PPCfcfids
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 0)))))),
-            (f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
-  def : Pat<(f32 (PPCfcfids
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 1)))))),
+  def : Pat<DWToSPExtractConv.El0SS1,
+            (f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El1SS1,
             (f32 (XSCVSXDSP (COPY_TO_REGCLASS
-                              (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
-  def : Pat<(f32 (PPCfcfidus
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 0)))))),
-            (f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
-  def : Pat<(f32 (PPCfcfidus
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 1)))))),
+                              (f64 (COPY_TO_REGCLASS $S1, VSRC)), VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El0US1,
+            (f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El1US1,
             (f32 (XSCVUXDSP (COPY_TO_REGCLASS
-                              (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
+                              (f64 (COPY_TO_REGCLASS $S1, VSRC)), VSFRC)))>;
   }
 
   let Predicates = [IsBigEndian] in {
-  def : Pat<(f32 (PPCfcfids
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 0)))))),
-            (f32 (XSCVSXDSP (COPY_TO_REGCLASS $S, VSFRC)))>;
-  def : Pat<(f32 (PPCfcfids
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 1)))))),
-            (f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
-  def : Pat<(f32 (PPCfcfidus
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 0)))))),
-            (f32 (XSCVUXDSP (COPY_TO_REGCLASS $S, VSFRC)))>;
-  def : Pat<(f32 (PPCfcfidus
-                   (f64 (PPCmtvsra (i64 (vector_extract v2i64:$S, 1)))))),
-            (f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El0SS1,
+            (f32 (XSCVSXDSP (COPY_TO_REGCLASS $S1, VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El1SS1,
+            (f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El0US1,
+            (f32 (XSCVUXDSP (COPY_TO_REGCLASS $S1, VSFRC)))>;
+  def : Pat<DWToSPExtractConv.El1US1,
+            (f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S1, $S1, 2), VSFRC)))>;
   }
 
   // Instructions for converting float to i64 feeding a store.
@@ -3814,6 +3827,15 @@ let AddedComplexity = 400 in {
                                               (XFLOADf32 xoaddr:$A), VSFRC)), 0))>;
   }
 
+  let Predicates = [IsBigEndian, HasP8Vector] in {
+    def : Pat<DWToSPExtractConv.BVU,
+              (v4f32 (VPKUDUM (XXSLDWI (XVCVUXDSP $S1), (XVCVUXDSP $S1), 3),
+                              (XXSLDWI (XVCVUXDSP $S2), (XVCVUXDSP $S2), 3)))>;
+    def : Pat<DWToSPExtractConv.BVS,
+              (v4f32 (VPKUDUM (XXSLDWI (XVCVSXDSP $S1), (XVCVSXDSP $S1), 3),
+                              (XXSLDWI (XVCVSXDSP $S2), (XVCVSXDSP $S2), 3)))>;
+  }
+
   // Big endian, available on all targets with VSX
   let Predicates = [IsBigEndian, HasVSX] in {
     def : Pat<(v2f64 (build_vector f64:$A, f64:$B)),
@@ -3842,6 +3864,15 @@ let AddedComplexity = 400 in {
               (v4i32 (VMRGEW MrgWords.CVA0B0U, MrgWords.CVA1B1U))>;
   }
 
+  let Predicates = [IsLittleEndian, HasP8Vector] in {
+    def : Pat<DWToSPExtractConv.BVU,
+              (v4f32 (VPKUDUM (XXSLDWI (XVCVUXDSP $S2), (XVCVUXDSP $S2), 3),
+                              (XXSLDWI (XVCVUXDSP $S1), (XVCVUXDSP $S1), 3)))>;
+    def : Pat<DWToSPExtractConv.BVS,
+              (v4f32 (VPKUDUM (XXSLDWI (XVCVSXDSP $S2), (XVCVSXDSP $S2), 3),
+                              (XXSLDWI (XVCVSXDSP $S1), (XVCVSXDSP $S1), 3)))>;
+  }
+
   let Predicates = [IsLittleEndian, HasVSX] in {
   // Little endian, available on all targets with VSX
     def : Pat<(v2f64 (build_vector f64:$A, f64:$B)),