[PowerPC] swdiv builtins for XL compatibility

This patch is in a series of patches to provide builtins for compatibility with
the XL compiler. This patch implements the software divide builtin as
wrappers for a floating point divide. XL provided these builtins because it
didn't produce software estimates by default at `-Ofast`. When compiled
with `-Ofast` these builtins will produce the software estimate for divide.

Reviewed By: #powerpc, nemanjai

Differential Revision: https://reviews.llvm.org/D106959

diff --git a/clang/include/clang/Basic/BuiltinsPPC.def b/clang/include/clang/Basic/BuiltinsPPC.def
index 6fee978..26286c2 100644 (file)
--- a/clang/include/clang/Basic/BuiltinsPPC.def
+++ b/clang/include/clang/Basic/BuiltinsPPC.def
@@ -101,6 +101,8 @@ BUILTIN(__builtin_ppc_compare_exp_lt, "idd", "")
 BUILTIN(__builtin_ppc_compare_exp_gt, "idd", "")
 BUILTIN(__builtin_ppc_compare_exp_eq, "idd", "")
 BUILTIN(__builtin_ppc_test_data_class, "idIi", "t")
+BUILTIN(__builtin_ppc_swdiv, "ddd", "")
+BUILTIN(__builtin_ppc_swdivs, "fff", "")
 // Compare
 BUILTIN(__builtin_ppc_cmpeqb, "LLiLLiLLi", "")
 BUILTIN(__builtin_ppc_cmprb, "iCIiii", "")

diff --git a/clang/lib/Basic/Targets/PPC.cpp b/clang/lib/Basic/Targets/PPC.cpp
index 4835f1d..21376b3 100644 (file)
--- a/clang/lib/Basic/Targets/PPC.cpp
+++ b/clang/lib/Basic/Targets/PPC.cpp
@@ -243,6 +243,8 @@ static void defineXLCompatMacros(MacroBuilder &Builder) {
   Builder.defineMacro("__compare_exp_gt", "__builtin_ppc_compare_exp_gt");
   Builder.defineMacro("__compare_exp_eq", "__builtin_ppc_compare_exp_eq");
   Builder.defineMacro("__test_data_class", "__builtin_ppc_test_data_class");
+  Builder.defineMacro("__swdiv", "__builtin_ppc_swdiv");
+  Builder.defineMacro("__swdivs", "__builtin_ppc_swdivs");
 }
 
 /// PPCTargetInfo::getTargetDefines - Return a set of the PowerPC-specific

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index fe532a7..c7dcde1 100644 (file)
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -16077,7 +16077,7 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
                            *this, E, Intrinsic::sqrt,
                            Intrinsic::experimental_constrained_sqrt))
         .getScalarVal();
-  case PPC::BI__builtin_ppc_test_data_class:
+  case PPC::BI__builtin_ppc_test_data_class: {
     llvm::Type *ArgType = EmitScalarExpr(E->getArg(0))->getType();
     unsigned IntrinsicID;
     if (ArgType->isDoubleTy())
@@ -16089,6 +16089,10 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
     return Builder.CreateCall(CGM.getIntrinsic(IntrinsicID), Ops,
                               "test_data_class");
   }
+  case PPC::BI__builtin_ppc_swdiv:
+  case PPC::BI__builtin_ppc_swdivs:
+    return Builder.CreateFDiv(Ops[0], Ops[1], "swdiv");
+  }
 }
 
 namespace {

diff --git a/clang/test/CodeGen/builtins-ppc-xlcompat-swdiv.c b/clang/test/CodeGen/builtins-ppc-xlcompat-swdiv.c
new file mode 100644 (file)
index 0000000..33b3f14
--- /dev/null
+++ b/clang/test/CodeGen/builtins-ppc-xlcompat-swdiv.c
@@ -0,0 +1,80 @@
+// REQUIRES: powerpc-registered-target
+// RUN: %clang_cc1 -triple powerpc64-unknown-linux-gnu \
+// RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s
+// RUN: %clang_cc1 -triple powerpc64le-unknown-linux-gnu \
+// RUN:   -emit-llvm %s -o - -target-cpu pwr8 | FileCheck %s
+// RUN: %clang_cc1 -triple powerpc64-unknown-aix \
+// RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s
+// RUN: %clang_cc1 -triple powerpc-unknown-aix \
+// RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s
+// RUN: %clang_cc1 -triple powerpc64-unknown-linux-gnu -ffast-math -ffp-contract=fast \
+// RUN:   -emit-llvm %s -o - -target-cpu pwr7 | FileCheck %s --check-prefix CHECK-OFAST
+
+extern double a;
+extern double b;
+extern float c;
+extern float d;
+
+// CHECK-LABEL:   @test_swdiv(
+// CHECK:         [[TMP0:%.*]] = load double, double* @a
+// CHECK-NEXT:    [[TMP1:%.*]] = load double, double* @b
+// CHECK-NEXT:    [[SWDIV:%.*]] = fdiv double [[TMP0]], [[TMP1]]
+// CHECK-NEXT:    ret double [[SWDIV]]
+//
+// CHECK-OFAST-LABEL:   @test_swdiv(
+// CHECK-OFAST:         [[TMP0:%.*]] = load double, double* @a
+// CHECK-OFAST-NEXT:    [[TMP1:%.*]] = load double, double* @b
+// CHECK-OFAST-NEXT:    [[SWDIV:%.*]] = fdiv fast double [[TMP0]], [[TMP1]]
+// CHECK-OFAST-NEXT:    ret double [[SWDIV]]
+//
+double test_swdiv() {
+  return __swdiv(a, b);
+}
+
+// CHECK-LABEL:   @test_swdivs(
+// CHECK:         [[TMP0:%.*]] = load float, float* @c
+// CHECK-NEXT:    [[TMP1:%.*]] = load float, float* @d
+// CHECK-NEXT:    [[SWDIVS:%.*]] = fdiv float [[TMP0]], [[TMP1]]
+// CHECK-NEXT:    ret float [[SWDIVS]]
+//
+// CHECK-OFAST-LABEL:   @test_swdivs(
+// CHECK-OFAST:         [[TMP0:%.*]] = load float, float* @c
+// CHECK-OFAST-NEXT:    [[TMP1:%.*]] = load float, float* @d
+// CHECK-OFAST-NEXT:    [[SWDIVS:%.*]] = fdiv fast float [[TMP0]], [[TMP1]]
+// CHECK-OFAST-NEXT:    ret float [[SWDIVS]]
+//
+float test_swdivs() {
+  return __swdivs(c, d);
+}
+
+// CHECK-LABEL:   @test_builtin_ppc_swdiv(
+// CHECK:         [[TMP0:%.*]] = load double, double* @a
+// CHECK-NEXT:    [[TMP1:%.*]] = load double, double* @b
+// CHECK-NEXT:    [[SWDIV:%.*]] = fdiv double [[TMP0]], [[TMP1]]
+// CHECK-NEXT:    ret double [[SWDIV]]
+//
+// CHECK-OFAST-LABEL:   @test_builtin_ppc_swdiv(
+// CHECK-OFAST:         [[TMP0:%.*]] = load double, double* @a
+// CHECK-OFAST-NEXT:    [[TMP1:%.*]] = load double, double* @b
+// CHECK-OFAST-NEXT:    [[SWDIV:%.*]] = fdiv fast double [[TMP0]], [[TMP1]]
+// CHECK-OFAST-NEXT:    ret double [[SWDIV]]
+//
+double test_builtin_ppc_swdiv() {
+  return __builtin_ppc_swdiv(a, b);
+}
+
+// CHECK-LABEL:   @test_builtin_ppc_swdivs(
+// CHECK:         [[TMP0:%.*]] = load float, float* @c
+// CHECK-NEXT:    [[TMP1:%.*]] = load float, float* @d
+// CHECK-NEXT:    [[SWDIVS:%.*]] = fdiv float [[TMP0]], [[TMP1]]
+// CHECK-NEXT:    ret float [[SWDIVS]]
+//
+// CHECK-OFAST-LABEL:   @test_builtin_ppc_swdivs(
+// CHECK-OFAST:         [[TMP0:%.*]] = load float, float* @c
+// CHECK-OFAST-NEXT:    [[TMP1:%.*]] = load float, float* @d
+// CHECK-OFAST-NEXT:    [[SWDIVS:%.*]] = fdiv fast float [[TMP0]], [[TMP1]]
+// CHECK-OFAST-NEXT:    ret float [[SWDIVS]]
+//
+float test_builtin_ppc_swdivs() {
+  return __builtin_ppc_swdivs(c, d);
+}

diff --git a/llvm/test/CodeGen/PowerPC/fdiv.ll b/llvm/test/CodeGen/PowerPC/fdiv.ll
index f55d7a7..3ea28ec 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/fdiv.ll
+++ b/llvm/test/CodeGen/PowerPC/fdiv.ll
@@ -23,3 +23,16 @@ define dso_local float @foo(float %0, float %1) local_unnamed_addr {
   %3 = fdiv contract reassoc arcp nsz ninf float %0, %1
   ret float %3
 }
+
+define dso_local float @fdiv_fast(float %0, float %1) local_unnamed_addr {
+; CHECK-LABEL: fdiv_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xsresp 3, 2
+; CHECK-NEXT:    xsmulsp 0, 1, 3
+; CHECK-NEXT:    xsnmsubasp 1, 2, 0
+; CHECK-NEXT:    xsmaddasp 0, 3, 1
+; CHECK-NEXT:    fmr 1, 0
+; CHECK-NEXT:    blr
+  %3 = fdiv fast float %0, %1
+  ret float %3
+}