[PATCH] D40299: [Complex] Don't use __div?c3 when building with fast-math.

[Paul Walker via Phabricator via cfe-commits]

paulwalker-arm created this revision.

Plant an inline version of "((ac+bd)/(cc+dd)) + i((bc-ad)/(cc+dd))" instead.


https://reviews.llvm.org/D40299

Files:
  lib/CodeGen/CGExprComplex.cpp
  test/CodeGen/complex-math.c


Index: test/CodeGen/complex-math.c
===================================================================
--- test/CodeGen/complex-math.c
+++ test/CodeGen/complex-math.c
@@ -5,6 +5,7 @@
 // RUN %clang_cc1 %s -O1 -emit-llvm -triple armv7-none-linux-gnueabi -o - | FileCheck %s --check-prefix=ARM
 // RUN: %clang_cc1 %s -O1 -emit-llvm -triple armv7-none-linux-gnueabihf -o - | FileCheck %s --check-prefix=ARMHF
 // RUN: %clang_cc1 %s -O1 -emit-llvm -triple thumbv7k-apple-watchos2.0 -o - -target-abi aapcs16 | FileCheck %s --check-prefix=ARM7K
+// RUN %clang_cc1 %s -O1 -ffast-math -emit-llvm -triple x86_64-unknown-unknown | FileCheck %s --check-prefix=FASTMATH
 
 float _Complex add_float_rr(float a, float b) {
   // X86-LABEL: @add_float_rr(
@@ -128,13 +129,25 @@
   // X86-NOT: fdiv
   // X86: call {{.*}} @__divsc3(
   // X86: ret
+  // FASTMATH-LABEL: @div_float_rc(
+  // FASTMATH-NOT: @__divsc3
+  // FASTMATH: fdiv
+  // FASTMATH: fdiv
+  // FASTMATH-NOT: fdiv
+  // FASTMATH: ret
   return a / b;
 }
 float _Complex div_float_cc(float _Complex a, float _Complex b) {
   // X86-LABEL: @div_float_cc(
   // X86-NOT: fdiv
   // X86: call {{.*}} @__divsc3(
   // X86: ret
+  // FASTMATH-LABEL: @div_float_cc(
+  // FASTMATH-NOT: @__divsc3
+  // FASTMATH: fdiv
+  // FASTMATH: fdiv
+  // FASTMATH-NOT: fdiv
+  // FASTMATH: ret
   return a / b;
 }
 
@@ -260,13 +273,25 @@
   // X86-NOT: fdiv
   // X86: call {{.*}} @__divdc3(
   // X86: ret
+  // FASTMATH-LABEL: @div_double_rc(
+  // FASTMATH-NOT: @__divdc3
+  // FASTMATH: fdiv
+  // FASTMATH: fdiv
+  // FASTMATH-NOT: fdiv
+  // FASTMATH: ret
   return a / b;
 }
 double _Complex div_double_cc(double _Complex a, double _Complex b) {
   // X86-LABEL: @div_double_cc(
   // X86-NOT: fdiv
   // X86: call {{.*}} @__divdc3(
   // X86: ret
+  // FASTMATH-LABEL: @div_double_cc(
+  // FASTMATH-NOT: @__divdc3
+  // FASTMATH: fdiv
+  // FASTMATH: fdiv
+  // FASTMATH-NOT: fdiv
+  // FASTMATH: ret
   return a / b;
 }
 
@@ -410,6 +435,12 @@
   // PPC-NOT: fdiv
   // PPC: call {{.*}} @__divtc3(
   // PPC: ret
+  // FASTMATH-LABEL: @div_long_double_rc(
+  // FASTMATH-NOT: @__divxc3
+  // FASTMATH: fdiv
+  // FASTMATH: fdiv
+  // FASTMATH-NOT: fdiv
+  // FASTMATH: ret
   return a / b;
 }
 long double _Complex div_long_double_cc(long double _Complex a, long double _Complex b) {
@@ -421,6 +452,12 @@
   // PPC-NOT: fdiv
   // PPC: call {{.*}} @__divtc3(
   // PPC: ret
+  // FASTMATH-LABEL: @div_double_cc(
+  // FASTMATH-NOT: @__divxc3
+  // FASTMATH: fdiv
+  // FASTMATH: fdiv
+  // FASTMATH-NOT: fdiv
+  // FASTMATH: ret
   return a / b;
 }
 
Index: lib/CodeGen/CGExprComplex.cpp
===================================================================
--- lib/CodeGen/CGExprComplex.cpp
+++ lib/CodeGen/CGExprComplex.cpp
@@ -761,15 +761,16 @@
   llvm::Value *LHSr = Op.LHS.first, *LHSi = Op.LHS.second;
   llvm::Value *RHSr = Op.RHS.first, *RHSi = Op.RHS.second;
 
-
   llvm::Value *DSTr, *DSTi;
   if (LHSr->getType()->isFloatingPointTy()) {
+    llvm::FastMathFlags FMF = Builder.getFastMathFlags();
+
     // If we have a complex operand on the RHS, we delegate to a libcall to
     // handle all of the complexities and minimize underflow/overflow cases.
     //
     // FIXME: We would be able to avoid the libcall in many places if we
     // supported imaginary types in addition to complex types.
-    if (RHSi) {
+    if (RHSi && !FMF.isFast()) {
       BinOpInfo LibCallOp = Op;
       // If LHS was a real, supply a null imaginary part.
       if (!LHSi)
@@ -791,11 +792,31 @@
       case llvm::Type::FP128TyID:
         return EmitComplexBinOpLibCall("__divtc3", LibCallOp);
       }
-    }
-    assert(LHSi && "Can have at most one non-complex operand!");
+    } else if (RHSi) {
+      if (!LHSi)
+        LHSi = llvm::Constant::getNullValue(RHSi->getType());
+
+      // (a+ib) / (c+id) = ((ac+bd)/(cc+dd)) + i((bc-ad)/(cc+dd))
+      llvm::Value *AC = Builder.CreateFMul(LHSr, RHSr); // a*c
+      llvm::Value *BD = Builder.CreateFMul(LHSi, RHSi); // b*d
+      llvm::Value *ACpBD = Builder.CreateFAdd(AC, BD); // ac+bd
 
-    DSTr = Builder.CreateFDiv(LHSr, RHSr);
-    DSTi = Builder.CreateFDiv(LHSi, RHSr);
+      llvm::Value *CC = Builder.CreateFMul(RHSr, RHSr); // c*c
+      llvm::Value *DD = Builder.CreateFMul(RHSi, RHSi); // d*d
+      llvm::Value *CCpDD = Builder.CreateFAdd(CC, DD); // cc+dd
+
+      llvm::Value *BC = Builder.CreateFMul(LHSi, RHSr); // b*c
+      llvm::Value *AD = Builder.CreateFMul(LHSr, RHSi); // a*d
+      llvm::Value *BCmAD = Builder.CreateFSub(BC, AD); // bc-ad
+
+      DSTr = Builder.CreateFDiv(ACpBD, CCpDD);
+      DSTi = Builder.CreateFDiv(BCmAD, CCpDD);
+    } else {
+      assert(LHSi && "Can have at most one non-complex operand!");
+
+      DSTr = Builder.CreateFDiv(LHSr, RHSr);
+      DSTi = Builder.CreateFDiv(LHSi, RHSr);
+    }
   } else {
     assert(Op.LHS.second && Op.RHS.second &&
            "Both operands of integer complex operators must be complex!");

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits