[X86] Add ISel patterns to select 'f32_to_f16' and 'f16_to_f32' dag nodes.

This patch adds tablegen patterns to select F16C float-to-half-float
conversion instructions from 'f32_to_f16' and 'f16_to_f32' dag nodes.

If the target doesn't have F16C, then 'f32_to_f16' and 'f16_to_f32'
are expanded into library calls.

llvm-svn: 212293

2 files changed, 23 insertions, 0 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 09052eddc93..67fa64b29fd 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -515,6 +515,14 @@ void X86TargetLowering::resetOperationActions() {
     }
   }
 
+  // Special handling for half-precision floating point conversions.
+  // If we don't have F16C support, then lower half float conversions
+  // into library calls.
+  if (TM.Options.UseSoftFloat || !Subtarget->hasF16C()) {
+    setOperationAction(ISD::FP16_TO_FP32, MVT::f32, Expand);
+    setOperationAction(ISD::FP32_TO_FP16, MVT::i16, Expand);
+  }
+
   if (Subtarget->hasPOPCNT()) {
     setOperationAction(ISD::CTPOP          , MVT::i8   , Promote);
   } else {
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index e6ca519b7d5..f9a5ae1a3d5 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -8538,6 +8538,21 @@ let Predicates = [HasF16C] in {
             (VCVTPH2PSrm addr:$src)>;
 }
 
+// Patterns for  matching conversions from float to half-float and vice versa.
+let Predicates = [HasF16C] in {
+  def : Pat<(f32_to_f16 FR32:$src),
+            (i16 (EXTRACT_SUBREG (VMOVPDI2DIrr (VCVTPS2PHrr
+              (COPY_TO_REGCLASS FR32:$src, VR128), 0)), sub_16bit))>;
+
+  def : Pat<(f16_to_f32 GR16:$src),
+            (f32 (COPY_TO_REGCLASS (VCVTPH2PSrr
+              (COPY_TO_REGCLASS (MOVSX32rr16 GR16:$src), VR128)), FR32)) >;
+
+  def : Pat<(f16_to_f32 (i16 (f32_to_f16 FR32:$src))),
+            (f32 (COPY_TO_REGCLASS (VCVTPH2PSrr
+              (VCVTPS2PHrr (COPY_TO_REGCLASS FR32:$src, VR128), 0)), FR32)) >;
+}
+
 //===----------------------------------------------------------------------===//
 // AVX2 Instructions
 //===----------------------------------------------------------------------===//