[llvm] r305824 - [GISel]: Add G_FMA opcode for fused multiply adds

[Aditya Nandakumar via llvm-commits]

Author: aditya_nandakumar
Date: Tue Jun 20 14:25:23 2017
New Revision: 305824

URL: http://llvm.org/viewvc/llvm-project?rev=305824&view=rev
Log:
[GISel]: Add G_FMA opcode for fused multiply adds

https://reviews.llvm.org/D34372

Reviewed by dsanders

Modified:
    llvm/trunk/include/llvm/Target/GenericOpcodes.td
    llvm/trunk/include/llvm/Target/TargetOpcodes.def
    llvm/trunk/lib/CodeGen/GlobalISel/IRTranslator.cpp
    llvm/trunk/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll

Modified: llvm/trunk/include/llvm/Target/GenericOpcodes.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/GenericOpcodes.td?rev=305824&r1=305823&r2=305824&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Target/GenericOpcodes.td (original)
+++ llvm/trunk/include/llvm/Target/GenericOpcodes.td Tue Jun 20 14:25:23 2017
@@ -386,6 +386,14 @@ def G_FMUL : Instruction {
   let isCommutable = 1;
 }
 
+// Generic fused multiply-add instruction.
+def G_FMA : Instruction {
+  let OutOperandList = (outs type0:$dst);
+  let InOperandList = (ins type0:$src1, type0:$src2, type0:$src3);
+  let hasSideEffects = 0;
+  let isCommutable = 0;
+}
+
 // Generic FP division.
 def G_FDIV : Instruction {
   let OutOperandList = (outs type0:$dst);

Modified: llvm/trunk/include/llvm/Target/TargetOpcodes.def
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetOpcodes.def?rev=305824&r1=305823&r2=305824&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Target/TargetOpcodes.def (original)
+++ llvm/trunk/include/llvm/Target/TargetOpcodes.def Tue Jun 20 14:25:23 2017
@@ -359,6 +359,9 @@ HANDLE_TARGET_OPCODE(G_FSUB)
 /// Generic FP multiplication.
 HANDLE_TARGET_OPCODE(G_FMUL)
 
+/// Generic FMA multiplication. Behaves like llvm fma intrinsic
+HANDLE_TARGET_OPCODE(G_FMA)
+
 /// Generic FP division.
 HANDLE_TARGET_OPCODE(G_FDIV)
 

Modified: llvm/trunk/lib/CodeGen/GlobalISel/IRTranslator.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/GlobalISel/IRTranslator.cpp?rev=305824&r1=305823&r2=305824&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/GlobalISel/IRTranslator.cpp (original)
+++ llvm/trunk/lib/CodeGen/GlobalISel/IRTranslator.cpp Tue Jun 20 14:25:23 2017
@@ -686,6 +686,13 @@ bool IRTranslator::translateKnownIntrins
         .addUse(getOrCreateVReg(*CI.getArgOperand(0)))
         .addUse(getOrCreateVReg(*CI.getArgOperand(1)));
     return true;
+  case Intrinsic::fma:
+    MIRBuilder.buildInstr(TargetOpcode::G_FMA)
+        .addDef(getOrCreateVReg(CI))
+        .addUse(getOrCreateVReg(*CI.getArgOperand(0)))
+        .addUse(getOrCreateVReg(*CI.getArgOperand(1)))
+        .addUse(getOrCreateVReg(*CI.getArgOperand(2)));
+    return true;
   case Intrinsic::memcpy:
   case Intrinsic::memmove:
   case Intrinsic::memset:

Modified: llvm/trunk/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll?rev=305824&r1=305823&r2=305824&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll (original)
+++ llvm/trunk/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll Tue Jun 20 14:25:23 2017
@@ -1247,6 +1247,18 @@ define float @test_pow_intrin(float %l,
   ret float %res
 }
 
+declare float @llvm.fma.f32(float, float, float)
+define float @test_fma_intrin(float %a, float %b, float %c) {
+; CHECK-LABEL: name: test_fma_intrin
+; CHECK: [[A:%[0-9]+]](s32) = COPY %s0
+; CHECK: [[B:%[0-9]+]](s32) = COPY %s1
+; CHECK: [[C:%[0-9]+]](s32) = COPY %s2
+; CHECK: [[RES:%[0-9]+]](s32) = G_FMA [[A]], [[B]], [[C]]
+; CHECK: %s0 = COPY [[RES]]
+  %res = call float @llvm.fma.f32(float %a, float %b, float %c)
+  ret float %res
+}
+
 declare void @llvm.lifetime.start.p0i8(i64, i8*)
 declare void @llvm.lifetime.end.p0i8(i64, i8*)
 define void @test_lifetime_intrin() {