From f7d4ef04b81b374e0d7a91afd9d8ddf13bf85e20 Mon Sep 17 00:00:00 2001
From: Stephen Canon <scanon@apple.com>
Date: Mon, 16 Nov 2015 23:09:11 +0000
Subject: [PATCH] Make FP_CONTRACT ON the default.

Differential Revision: D14200


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@253269 91177308-0d34-0410-b5e6-96231b3b80d8
---
 include/clang/Basic/LangOptions.def |   2 +-
 lib/Frontend/CompilerInvocation.cpp |   1 -
 test/CodeGen/aarch64-neon-fma.c     |  23 ++--
 test/CodeGen/aarch64-scalar-fma.c   | 177 ++++++++++++++++++++++++++++
 test/CodeGen/fp-contract-pragma.cpp |   2 +
 test/Driver/clang_f_opts.c          |   2 +
 6 files changed, 192 insertions(+), 15 deletions(-)
 create mode 100644 test/CodeGen/aarch64-scalar-fma.c

diff --git a/include/clang/Basic/LangOptions.def b/include/clang/Basic/LangOptions.def
index fdf7e49499..8911d80523 100644
--- a/include/clang/Basic/LangOptions.def
+++ b/include/clang/Basic/LangOptions.def
@@ -187,7 +187,7 @@ BENIGN_LANGOPT(DebuggerObjCLiteral , 1, 0, "debugger Objective-C literals and su
 BENIGN_LANGOPT(SpellChecking , 1, 1, "spell-checking")
 LANGOPT(SinglePrecisionConstants , 1, 0, "treating double-precision floating point constants as single precision constants")
 LANGOPT(FastRelaxedMath , 1, 0, "OpenCL fast relaxed math")
-LANGOPT(DefaultFPContract , 1, 0, "FP_CONTRACT")
+LANGOPT(DefaultFPContract , 1, 1, "FP_CONTRACT")
 LANGOPT(NoBitFieldTypeAlign , 1, 0, "bit-field type alignment")
 LANGOPT(HexagonQdsp6Compat , 1, 0, "hexagon-qdsp6 backward compatibility")
 LANGOPT(ObjCAutoRefCount , 1, 0, "Objective-C automated reference counting")
diff --git a/lib/Frontend/CompilerInvocation.cpp b/lib/Frontend/CompilerInvocation.cpp
index 91917cf510..68f27ee4a3 100644
--- a/lib/Frontend/CompilerInvocation.cpp
+++ b/lib/Frontend/CompilerInvocation.cpp
@@ -1336,7 +1336,6 @@ void CompilerInvocation::setLangDefaults(LangOptions &Opts, InputKind IK,
     Opts.ZVector = 0;
     Opts.CXXOperatorNames = 1;
     Opts.LaxVectorConversions = 0;
-    Opts.DefaultFPContract = 1;
     Opts.NativeHalfType = 1;
   }
 
diff --git a/test/CodeGen/aarch64-neon-fma.c b/test/CodeGen/aarch64-neon-fma.c
index ac80833336..8126fb21da 100644
--- a/test/CodeGen/aarch64-neon-fma.c
+++ b/test/CodeGen/aarch64-neon-fma.c
@@ -1,5 +1,8 @@
 // REQUIRES: aarch64-registered-target
-// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -S -O3 -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -S -O3 \
+// RUN:   -ffp-contract=off -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -S -O3 \
+// RUN:   -o - %s | FileCheck -check-prefix=CHECK-FMA %s
 
 // Test new aarch64 intrinsics and types
 
@@ -10,8 +13,7 @@ float32x2_t test_vmla_n_f32(float32x2_t a, float32x2_t b, float32_t c) {
   return vmla_n_f32(a, b, c);
   // CHECK: fmul {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0]
   // CHECK: fadd {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
-  // CHECK-FMA: dup {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0]
-  // CHECK-FMA: fmla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
+  // CHECK-FMA: fmla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0]
 }
 
 float32x4_t test_vmlaq_n_f32(float32x4_t a, float32x4_t b, float32_t c) {
@@ -19,8 +21,7 @@ float32x4_t test_vmlaq_n_f32(float32x4_t a, float32x4_t b, float32_t c) {
   return vmlaq_n_f32(a, b, c);
   // CHECK: fmul {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0]
   // CHECK: fadd {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s
-  // CHECK-FMA: dup {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0]
-  // CHECK-FMA: fmla {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s
+  // CHECK-FMA: fmla {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0]
 }
 
 float64x2_t test_vmlaq_n_f64(float64x2_t a, float64x2_t b, float64_t c) {
@@ -28,8 +29,7 @@ float64x2_t test_vmlaq_n_f64(float64x2_t a, float64x2_t b, float64_t c) {
   return vmlaq_n_f64(a, b, c);
   // CHECK: fmul {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0]
   // CHECK: fadd {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
-  // CHECK-FMA: dup {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0]
-  // CHECK-FMA: fmla {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
+  // CHECK-FMA: fmla {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0]
 }
 
 float32x4_t test_vmlsq_n_f32(float32x4_t a, float32x4_t b, float32_t c) {
@@ -37,8 +37,7 @@ float32x4_t test_vmlsq_n_f32(float32x4_t a, float32x4_t b, float32_t c) {
   return vmlsq_n_f32(a, b, c);
   // CHECK: fmul {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0]
   // CHECK: fsub {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s
-  // CHECK-FMA: dup {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0]
-  // CHECK-FMA: fmls {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s
+  // CHECK-FMA: fmls {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0]
 }
 
 float32x2_t test_vmls_n_f32(float32x2_t a, float32x2_t b, float32_t c) {
@@ -46,8 +45,7 @@ float32x2_t test_vmls_n_f32(float32x2_t a, float32x2_t b, float32_t c) {
   return vmls_n_f32(a, b, c);
   // CHECK: fmul {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0]
   // CHECK: fsub {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
-  // CHECK-FMA: dup {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0]
-  // CHECK-FMA: fmls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
+  // CHECK-FMA: fmls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0]
 }
 
 float64x2_t test_vmlsq_n_f64(float64x2_t a, float64x2_t b, float64_t c) {
@@ -55,8 +53,7 @@ float64x2_t test_vmlsq_n_f64(float64x2_t a, float64x2_t b, float64_t c) {
   return vmlsq_n_f64(a, b, c);
   // CHECK: fmul {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0]
   // CHECK: fsub {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
-  // CHECK-FMA: dup {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0]
-  // CHECK-FMA: fmls {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d
+  // CHECK-FMA: fmls {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0]
 }
 
 float32x2_t test_vmla_lane_f32_0(float32x2_t a, float32x2_t b, float32x2_t v) {
diff --git a/test/CodeGen/aarch64-scalar-fma.c b/test/CodeGen/aarch64-scalar-fma.c
new file mode 100644
index 0000000000..ee4bd5065f
--- /dev/null
+++ b/test/CodeGen/aarch64-scalar-fma.c
@@ -0,0 +1,177 @@
+// RUN: %clang_cc1 -triple=aarch64-unknown -Os -ffp-contract=fast -S -o - %s | FileCheck -check-prefix=CHECK-FAST -check-prefix=CHECK-ALL %s
+// RUN: %clang_cc1 -triple=aarch64-unknown -Os -ffp-contract=on -S -o - %s | FileCheck -check-prefix=CHECK-ON -check-prefix=CHECK-ALL %s
+// RUN: %clang_cc1 -triple=aarch64-unknown -Os -ffp-contract=off -S -o - %s | FileCheck -check-prefix=CHECK-OFF -check-prefix=CHECK-ALL %s
+// RUN: %clang_cc1 -triple=aarch64-unknown -Os -S -o - %s | FileCheck -check-prefix=CHECK-ON -check-prefix=CHECK-ALL %s
+// REQUIRES: aarch64-registered-target
+
+float test1(float x, float y, float z) {
+  return x*y + z;
+  // CHECK-ALL-LABEL: test1:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test2(double x, double y, double z) {
+  z -= x*y;
+  return z;
+  // CHECK-ALL-LABEL: test2:
+  // CHECK-FAST: fmsub
+  // CHECK-ON: fmsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+float test3(float x, float y, float z) {
+  float tmp = x*y;
+  return tmp + z;
+  // CHECK-ALL-LABEL: test3:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test4(double x, double y, double z) {
+  double tmp = x*y;
+  return tmp - z;
+  // CHECK-ALL-LABEL: test4:
+  // CHECK-FAST: fnmsub
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+#pragma STDC FP_CONTRACT ON
+
+float test5(float x, float y, float z) {
+  return x*y + z;
+  // CHECK-ALL-LABEL: test5:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test6(double x, double y, double z) {
+  z -= x*y;
+  return z;
+  // CHECK-ALL-LABEL: test6:
+  // CHECK-FAST: fmsub
+  // CHECK-ON: fmsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+float test7(float x, float y, float z) {
+  float tmp = x*y;
+  return tmp + z;
+  // CHECK-ALL-LABEL: test7:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test8(double x, double y, double z) {
+  double tmp = x*y;
+  return tmp - z;
+  // CHECK-ALL-LABEL: test8:
+  // CHECK-FAST: fnmsub
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+#pragma STDC FP_CONTRACT OFF
+
+float test9(float x, float y, float z) {
+  return x*y + z;
+  // CHECK-ALL-LABEL: test9:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test10(double x, double y, double z) {
+  z -= x*y;
+  return z;
+  // CHECK-ALL-LABEL: test10:
+  // CHECK-FAST: fmsub
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+float test11(float x, float y, float z) {
+  float tmp = x*y;
+  return tmp + z;
+  // CHECK-ALL-LABEL: test11:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test12(double x, double y, double z) {
+  double tmp = x*y;
+  return tmp - z;
+  // CHECK-ALL-LABEL: test12:
+  // CHECK-FAST: fnmsub
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+#pragma STDC FP_CONTRACT DEFAULT
+
+float test17(float x, float y, float z) {
+  return x*y + z;
+  // CHECK-ALL-LABEL: test17:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test18(double x, double y, double z) {
+  z -= x*y;
+  return z;
+  // CHECK-ALL-LABEL: test18:
+  // CHECK-FAST: fmsub
+  // CHECK-ON: fmsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
+
+float test19(float x, float y, float z) {
+  float tmp = x*y;
+  return tmp + z;
+  // CHECK-ALL-LABEL: test19:
+  // CHECK-FAST: fmadd
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fadd
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fadd
+}
+
+double test20(double x, double y, double z) {
+  double tmp = x*y;
+  return tmp - z;
+  // CHECK-ALL-LABEL: test20:
+  // CHECK-FAST: fnmsub
+  // CHECK-ON: fmul
+  // CHECK-ON-NEXT: fsub
+  // CHECK-OFF: fmul
+  // CHECK-OFF-NEXT: fsub
+}
diff --git a/test/CodeGen/fp-contract-pragma.cpp b/test/CodeGen/fp-contract-pragma.cpp
index b4e24b9e68..b47bce0886 100644
--- a/test/CodeGen/fp-contract-pragma.cpp
+++ b/test/CodeGen/fp-contract-pragma.cpp
@@ -1,5 +1,7 @@
 // RUN: %clang_cc1 -O3 -triple %itanium_abi_triple -emit-llvm -o - %s | FileCheck %s
 
+#pragma STDC FP_CONTRACT OFF
+
 // Is FP_CONTRACT is honored in a simple case?
 float fp_contract_1(float a, float b, float c) {
 // CHECK: _Z13fp_contract_1fff
diff --git a/test/Driver/clang_f_opts.c b/test/Driver/clang_f_opts.c
index 25a1930bdd..48e7e0cafe 100644
--- a/test/Driver/clang_f_opts.c
+++ b/test/Driver/clang_f_opts.c
@@ -36,8 +36,10 @@
 // RUN: %clang -### -S -ffp-contract=fast %s 2>&1 | FileCheck -check-prefix=FP-CONTRACT-FAST-CHECK %s
 // RUN: %clang -### -S -ffast-math %s 2>&1 | FileCheck -check-prefix=FP-CONTRACT-FAST-CHECK %s
 // RUN: %clang -### -S -ffp-contract=off %s 2>&1 | FileCheck -check-prefix=FP-CONTRACT-OFF-CHECK %s
+// RUN: %clang -### -S -ffp-contract=on %s 2>&1 | FileCheck -check-prefix=FP-CONTRACT-ON-CHECK %s
 // FP-CONTRACT-FAST-CHECK: -ffp-contract=fast
 // FP-CONTRACT-OFF-CHECK: -ffp-contract=off
+// FP-CONTRACT-ON-CHECK: -ffp-contract=on
 
 // RUN: %clang -### -S -funroll-loops %s 2>&1 | FileCheck -check-prefix=CHECK-UNROLL-LOOPS %s
 // RUN: %clang -### -S -fno-unroll-loops %s 2>&1 | FileCheck -check-prefix=CHECK-NO-UNROLL-LOOPS %s
-- 
2.40.0