[llvm] r371518 - [InstCombine] Use SimplifyFMulInst to simplify multiply in fma.

[Florian Hahn via llvm-commits]

Author: fhahn
Date: Tue Sep 10 06:10:28 2019
New Revision: 371518

URL: http://llvm.org/viewvc/llvm-project?rev=371518&view=rev
Log:
[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

Modified:
    llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
    llvm/trunk/test/Transforms/InstCombine/fma.ll

Modified: llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp?rev=371518&r1=371517&r2=371518&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp (original)
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineCalls.cpp Tue Sep 10 06:10:28 2019
@@ -2258,9 +2258,11 @@ Instruction *InstCombiner::visitCallInst
       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;
     }

Modified: llvm/trunk/test/Transforms/InstCombine/fma.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/fma.ll?rev=371518&r1=371517&r2=371518&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/fma.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/fma.ll Tue Sep 10 06:10:28 2019
@@ -372,8 +372,7 @@ define float @fmuladd_x_1_z_fast(float %
 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
 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: