Teach the AArch64 backend to handle f16

This allows the AArch64 backend to handle fadd, fsub, fmul and fdiv
operations on f16 (half-precision) types by promoting to f32.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215891 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index 232cbd81f76826c6adba7ff37a715a0ef532c41a..ea88264d95f9e0323761c1d1b938c484c9be8345 100644 (file)
--- a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -4264,6 +4264,9 @@ void SelectionDAGLegalize::PromoteNode(SDNode *Node) {
                                   Tmp1, Tmp2, Node->getOperand(2)));
     break;
   }
+  case ISD::FADD:
+  case ISD::FSUB:
+  case ISD::FMUL:
   case ISD::FDIV:
   case ISD::FREM:
   case ISD::FPOW: {

diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index e277a5e0780a27463b67733eeee8c06c565a7e03..49e0ed2e2ab17daffa71607556529047d98fff2d 100644 (file)
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -278,6 +278,15 @@ AArch64TargetLowering::AArch64TargetLowering(TargetMachine &TM)
   setOperationAction(ISD::FCOPYSIGN, MVT::f64, Custom);
   setOperationAction(ISD::FCOPYSIGN, MVT::f32, Custom);
 
+  // f16 is storage-only, so we promote operations to f32 if we know this is
+  // valid, and ignore them otherwise. The operations not mentioned here will
+  // fail to select, but this is not a major problem as no source language
+  // should be emitting native f16 operations yet.
+  setOperationAction(ISD::FADD, MVT::f16, Promote);
+  setOperationAction(ISD::FDIV, MVT::f16, Promote);
+  setOperationAction(ISD::FMUL, MVT::f16, Promote);
+  setOperationAction(ISD::FSUB, MVT::f16, Promote);
+
   // AArch64 has implementations of a lot of rounding-like FP operations.
   static MVT RoundingTypes[] = { MVT::f32, MVT::f64};
   for (unsigned I = 0; I < array_lengthof(RoundingTypes); ++I) {

diff --git a/test/CodeGen/AArch64/fp16-instructions.ll b/test/CodeGen/AArch64/fp16-instructions.ll
new file mode 100644 (file)
index 0000000..ab5cf6c
--- /dev/null
+++ b/test/CodeGen/AArch64/fp16-instructions.ll
@@ -0,0 +1,109 @@
+; RUN: llc < %s -mtriple=aarch64-none-eabi | FileCheck %s
+
+define half @add_h(half %a, half %b) {
+entry:
+; CHECK-LABEL: add_h:
+; CHECK: fcvt
+; CHECK: fcvt
+; CHECK: fadd
+; CHECK: fcvt
+  %0 = fadd half %a, %b
+  ret half %0
+}
+
+
+define half @sub_h(half %a, half %b) {
+entry:
+; CHECK-LABEL: sub_h:
+; CHECK: fcvt
+; CHECK: fcvt
+; CHECK: fsub
+; CHECK: fcvt
+  %0 = fsub half %a, %b
+  ret half %0
+}
+
+
+define half @mul_h(half %a, half %b) {
+entry:
+; CHECK-LABEL: mul_h:
+; CHECK: fcvt
+; CHECK: fcvt
+; CHECK: fmul
+; CHECK: fcvt
+  %0 = fmul half %a, %b
+  ret half %0
+}
+
+
+define half @div_h(half %a, half %b) {
+entry:
+; CHECK-LABEL: div_h:
+; CHECK: fcvt
+; CHECK: fcvt
+; CHECK: fdiv
+; CHECK: fcvt
+  %0 = fdiv half %a, %b
+  ret half %0
+}
+
+
+define half @load_h(half* %a) {
+entry:
+; CHECK-LABEL: load_h:
+; CHECK: ldr h
+  %0 = load half* %a, align 4
+  ret half %0
+}
+
+
+define void @store_h(half* %a, half %b) {
+entry:
+; CHECK-LABEL: store_h:
+; CHECK: str h
+  store half %b, half* %a, align 4
+  ret void
+}
+
+define half @s_to_h(float %a) {
+; CHECK-LABEL: s_to_h:
+; CHECK: fcvt
+  %1 = fptrunc float %a to half
+  ret half %1
+}
+
+define half @d_to_h(double %a) {
+; CHECK-LABEL: d_to_h:
+; CHECK: fcvt
+  %1 = fptrunc double %a to half
+  ret half %1
+}
+
+define float @h_to_s(half %a) {
+; CHECK-LABEL: h_to_s:
+; CHECK: fcvt
+  %1 = fpext half %a to float
+  ret float %1
+}
+
+define double @h_to_d(half %a) {
+; CHECK-LABEL: h_to_d:
+; CHECK: fcvt
+  %1 = fpext half %a to double
+  ret double %1
+}
+
+define half @bitcast_i_to_h(i16 %a) {
+; CHECK-LABEL: bitcast_i_to_h:
+; CHECK: fmov
+  %1 = bitcast i16 %a to half
+  ret half %1
+}
+
+
+define i16 @bitcast_h_to_i(half %a) {
+; CHECK-LABEL: bitcast_h_to_i:
+; CHECK: fmov
+  %1 = bitcast half %a to i16
+  ret i16 %1
+}