[ARM] Select VFMA

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@368264 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/ARMInstrMVE.td b/lib/Target/ARM/ARMInstrMVE.td
index 48067e36f2e9945d5e08126dcc74191918e5bd20..373b92afbd15f8c42c1e6e3d29f04a55b8afa7d1 100644 (file)
--- a/lib/Target/ARM/ARMInstrMVE.td
+++ b/lib/Target/ARM/ARMInstrMVE.td
@@ -2646,6 +2646,13 @@ let Predicates = [HasMVEFloat, UseFusedMAC] in {
             (v4f32 (MVE_VFMSf32 $src1, $src2, $src3))>;
 }
 
+let Predicates = [HasMVEFloat] in {
+  def : Pat<(v8f16 (fma (v8f16 MQPR:$src1), (v8f16 MQPR:$src2), (v8f16 MQPR:$src3))),
+            (v8f16 (MVE_VFMAf16 $src3, $src1, $src2))>;
+  def : Pat<(v4f32 (fma (v4f32 MQPR:$src1), (v4f32 MQPR:$src2), (v4f32 MQPR:$src3))),
+            (v4f32 (MVE_VFMAf32 $src3, $src1, $src2))>;
+}
+
 
 def MVE_VADDf32 : MVE_VADDSUBFMA_fp<"vadd", "f32", 0b0, 0b0, 0b1, 0b0>;
 def MVE_VADDf16 : MVE_VADDSUBFMA_fp<"vadd", "f16", 0b1, 0b0, 0b1, 0b0>;

diff --git a/test/CodeGen/Thumb2/mve-vfma.ll b/test/CodeGen/Thumb2/mve-vfma.ll
new file mode 100644 (file)
index 0000000..7b38876
--- /dev/null
+++ b/test/CodeGen/Thumb2/mve-vfma.ll
@@ -0,0 +1,24 @@
+; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s
+
+define arm_aapcs_vfpcc <4 x float> @fma_v4f32(<4 x float> %dst, <4 x float> %s1, <4 x float> %s2) {
+; CHECK-LABEL: fma_v4f32:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vfma.f32 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call fast <4 x float> @llvm.fma.v4f32(<4 x float> %s1, <4 x float> %s2, <4 x float> %dst)
+  ret <4 x float> %0
+}
+
+define arm_aapcs_vfpcc <8 x half> @fma_v8f16(<8 x half> %dst, <8 x half> %s1, <8 x half> %s2) {
+; CHECK-LABEL: fma_v8f16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    vfma.f16 q0, q1, q2
+; CHECK-NEXT:    bx lr
+entry:
+  %0 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %s1, <8 x half> %s2, <8 x half> %dst)
+  ret <8 x half> %0
+}
+
+declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)
+declare <8 x half> @llvm.fma.v8f16(<8 x half>, <8 x half>, <8 x half>)