BBVectorize: Enable vectorization of the fmuladd intrinsic

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171075 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/BBVectorize.cpp b/lib/Transforms/Vectorize/BBVectorize.cpp
index ee3202a3624f49ed66eabf8053c0c0d0a498a3f7..4a2c8781957c6db84f5457791c9d52c6df93e463 100644 (file)
--- a/lib/Transforms/Vectorize/BBVectorize.cpp
+++ b/lib/Transforms/Vectorize/BBVectorize.cpp
@@ -660,6 +660,7 @@ namespace {
       case Intrinsic::pow:
         return Config.VectorizeMath;
       case Intrinsic::fma:
+      case Intrinsic::fmuladd:
         return Config.VectorizeFMA;
       }
     }

diff --git a/test/Transforms/BBVectorize/simple-int.ll b/test/Transforms/BBVectorize/simple-int.ll
index ae1d63bfd852b337ed563785cc1fea3f2245c7c3..179a1fdf95aa87cf477a038cb4884e86f59ba62a 100644 (file)
--- a/test/Transforms/BBVectorize/simple-int.ll
+++ b/test/Transforms/BBVectorize/simple-int.ll
@@ -2,6 +2,7 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
 ; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s
 
 declare double @llvm.fma.f64(double, double, double)
+declare double @llvm.fmuladd.f64(double, double, double)
 declare double @llvm.cos.f64(double)
 declare double @llvm.powi.f64(double, i32)
 
@@ -31,6 +32,32 @@ define double @test1(double %A1, double %A2, double %B1, double %B2, double %C1,
 ; CHECK: ret double %R
 }
 
+; Basic depth-3 chain with fmuladd
+define double @test1a(double %A1, double %A2, double %B1, double %B2, double %C1, double %C2) {
+       %X1 = fsub double %A1, %B1
+       %X2 = fsub double %A2, %B2
+       %Y1 = call double @llvm.fmuladd.f64(double %X1, double %A1, double %C1)
+       %Y2 = call double @llvm.fmuladd.f64(double %X2, double %A2, double %C2)
+       %Z1 = fadd double %Y1, %B1
+       %Z2 = fadd double %Y2, %B2
+       %R  = fmul double %Z1, %Z2
+       ret double %R
+; CHECK: @test1a
+; CHECK: %X1.v.i1.1 = insertelement <2 x double> undef, double %B1, i32 0
+; CHECK: %X1.v.i1.2 = insertelement <2 x double> %X1.v.i1.1, double %B2, i32 1
+; CHECK: %X1.v.i0.1 = insertelement <2 x double> undef, double %A1, i32 0
+; CHECK: %X1.v.i0.2 = insertelement <2 x double> %X1.v.i0.1, double %A2, i32 1
+; CHECK: %X1 = fsub <2 x double> %X1.v.i0.2, %X1.v.i1.2
+; CHECK: %Y1.v.i2.1 = insertelement <2 x double> undef, double %C1, i32 0
+; CHECK: %Y1.v.i2.2 = insertelement <2 x double> %Y1.v.i2.1, double %C2, i32 1
+; CHECK: %Y1 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> %X1, <2 x double> %X1.v.i0.2, <2 x double> %Y1.v.i2.2)
+; CHECK: %Z1 = fadd <2 x double> %Y1, %X1.v.i1.2
+; CHECK: %Z1.v.r1 = extractelement <2 x double> %Z1, i32 0
+; CHECK: %Z1.v.r2 = extractelement <2 x double> %Z1, i32 1
+; CHECK: %R = fmul double %Z1.v.r1, %Z1.v.r2
+; CHECK: ret double %R
+}
+
 ; Basic depth-3 chain with cos
 define double @test2(double %A1, double %A2, double %B1, double %B2) {
        %X1 = fsub double %A1, %B1
@@ -98,6 +125,7 @@ define double @test4(double %A1, double %A2, double %B1, double %B2, i32 %P) {
 }
 
 ; CHECK: declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
+; CHECK: declare <2 x double> @llvm.fmuladd.v2f64(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
 ; CHECK: declare <2 x double> @llvm.cos.v2f64(<2 x double>) nounwind readonly
 ; CHECK: declare <2 x double> @llvm.powi.v2f64(<2 x double>, i32) nounwind readonly