From 99eb4685efada56574fc4a954038624be96457b8 Mon Sep 17 00:00:00 2001
From: Jingyue Wu <jingyue@google.com>
Date: Tue, 11 Aug 2015 19:21:46 +0000
Subject: [PATCH] SelectionDAG: Prefer to combine multiplication with less uses
 for fma

Summary:
For example:

  s6 = s0*s5;
  s2 = s6*s6 + s6;
  ...
  s4 = s6*s3;

We notice that it is possible for s2 is folded to fma (s0, s5, fmul (s6 s6)).
This only happens when Aggressive is true, otherwise hasOneUse() check
already prevents from folding the multiplication with more uses.

Test Plan: test/CodeGen/NVPTX/fma-assoc.ll

Patch by Xuetian Weng

Reviewers: hfinkel, apazos, jingyue, ohsallen, arsenm

Subscribers: arsenm, jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D11855

llvm-svn: 244649
---
 llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp |  8 ++++++++
 llvm/test/CodeGen/NVPTX/fma-assoc.ll          | 13 +++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 2c87d120cb7a..c4cbeb007665 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -7426,6 +7426,14 @@ SDValue DAGCombiner::visitFADDForFMACombine(SDNode *N) {
   bool Aggressive = TLI.enableAggressiveFMAFusion(VT);
   bool LookThroughFPExt = TLI.isFPExtFree(VT);
 
+  // If we have two choices trying to fold (fadd (fmul u, v), (fmul x, y)),
+  // prefer to fold the multiply with fewer uses.
+  if (Aggressive && N0.getOpcode() == ISD::FMUL &&
+      N1.getOpcode() == ISD::FMUL) {
+    if (N0.getNode()->use_size() > N1.getNode()->use_size())
+      std::swap(N0, N1);
+  }
+
   // fold (fadd (fmul x, y), z) -> (fma x, y, z)
   if (N0.getOpcode() == ISD::FMUL &&
       (Aggressive || N0->hasOneUse())) {
diff --git a/llvm/test/CodeGen/NVPTX/fma-assoc.ll b/llvm/test/CodeGen/NVPTX/fma-assoc.ll
index fc04c61dd691..80a08a86316c 100644
--- a/llvm/test/CodeGen/NVPTX/fma-assoc.ll
+++ b/llvm/test/CodeGen/NVPTX/fma-assoc.ll
@@ -23,3 +23,16 @@ define ptx_device double @t1_f64(double %x, double %y, double %z,
   %d = fadd double %c, %z
   ret double %d
 }
+
+define double @two_choices(double %val1, double %val2) {
+; CHECK-LABEL: two_choices(
+; CHECK: mul.f64
+; CHECK-NOT: mul.f64
+; CHECK: fma.rn.f64
+  %1 = fmul double %val1, %val2
+  %2 = fmul double %1, %1
+  %3 = fadd double %1, %2
+
+  ret double %3
+}
+