From 18a1f0818b659cee13865b4fad2648d85984a4ed Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo@fhahn.com>
Date: Tue, 10 Sep 2019 13:10:28 +0000
Subject: [PATCH] [InstCombine] Use SimplifyFMulInst to simplify multiply in
 fma.

This allows us to fold fma's that multiply with 0.0. Also, the
multiply by 1.0 case is handled there as well. The fneg/fabs cases
are not handled by SimplifyFMulInst, so we need to keep them.

Reviewers: spatel, anemet, lebedev.ri

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D67351

llvm-svn: 371518
---
 llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp |  8 +++++---
 llvm/test/Transforms/InstCombine/fma.ll              | 15 +++++----------
 2 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index d304f98..3863e5f 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -2258,9 +2258,11 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
       return II;
     }
 
-    // fma x, 1, z -> fadd x, z
-    if (match(Src1, m_FPOne())) {
-      auto *FAdd = BinaryOperator::CreateFAdd(Src0, II->getArgOperand(2));
+    // Try to simplify the underlying FMul.
+    if (Value *V = SimplifyFMulInst(II->getArgOperand(0), II->getArgOperand(1),
+                                    II->getFastMathFlags(),
+                                    SQ.getWithInstruction(II))) {
+      auto *FAdd = BinaryOperator::CreateFAdd(V, II->getArgOperand(2));
       FAdd->copyFastMathFlags(II);
       return FAdd;
     }
diff --git a/llvm/test/Transforms/InstCombine/fma.ll b/llvm/test/Transforms/InstCombine/fma.ll
index 89fdc6b..42ed587 100644
--- a/llvm/test/Transforms/InstCombine/fma.ll
+++ b/llvm/test/Transforms/InstCombine/fma.ll
@@ -372,8 +372,7 @@ define float @fmuladd_x_1_z_fast(float %x, float %z) {
 define <2 x double> @fmuladd_a_0_b(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: @fmuladd_a_0_b(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[RES:%.*]] = call nnan nsz <2 x double> @llvm.fmuladd.v2f64(<2 x double> [[A:%.*]], <2 x double> zeroinitializer, <2 x double> [[B:%.*]])
-; CHECK-NEXT:    ret <2 x double> [[RES]]
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
 ;
 entry:
   %res = call nnan nsz <2 x double> @llvm.fmuladd.v2f64(<2 x double> %a, <2 x double> zeroinitializer, <2 x double> %b)
@@ -383,8 +382,7 @@ entry:
 define <2 x double> @fmuladd_0_a_b(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: @fmuladd_0_a_b(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[RES:%.*]] = call nnan nsz <2 x double> @llvm.fmuladd.v2f64(<2 x double> [[A:%.*]], <2 x double> zeroinitializer, <2 x double> [[B:%.*]])
-; CHECK-NEXT:    ret <2 x double> [[RES]]
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
 ;
 entry:
   %res = call nnan nsz <2 x double> @llvm.fmuladd.v2f64(<2 x double> zeroinitializer, <2 x double> %a, <2 x double> %b)
@@ -407,8 +405,7 @@ declare <2 x double> @llvm.fmuladd.v2f64(<2 x double>, <2 x double>, <2 x double
 define <2 x double> @fma_a_0_b(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: @fma_a_0_b(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[RES:%.*]] = call nnan nsz <2 x double> @llvm.fma.v2f64(<2 x double> [[A:%.*]], <2 x double> zeroinitializer, <2 x double> [[B:%.*]])
-; CHECK-NEXT:    ret <2 x double> [[RES]]
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
 ;
 entry:
   %res = call nnan nsz <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> zeroinitializer, <2 x double> %b)
@@ -418,8 +415,7 @@ entry:
 define <2 x double> @fma_0_a_b(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: @fma_0_a_b(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[RES:%.*]] = call nnan nsz <2 x double> @llvm.fma.v2f64(<2 x double> [[A:%.*]], <2 x double> zeroinitializer, <2 x double> [[B:%.*]])
-; CHECK-NEXT:    ret <2 x double> [[RES]]
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
 ;
 entry:
   %res = call nnan nsz <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> %a, <2 x double> %b)
@@ -440,8 +436,7 @@ entry:
 define <2 x double> @fma_sqrt(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: @fma_sqrt(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SQRT:%.*]] = call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> [[A:%.*]])
-; CHECK-NEXT:    [[RES:%.*]] = call fast <2 x double> @llvm.fma.v2f64(<2 x double> [[SQRT]], <2 x double> [[SQRT]], <2 x double> [[B:%.*]])
+; CHECK-NEXT:    [[RES:%.*]] = fadd fast <2 x double> [[A:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    ret <2 x double> [[RES]]
 ;
 entry:
-- 
2.7.4