sbaranga created this revision.
sbaranga added a reviewer: t.p.northover.
sbaranga added a subscriber: cfe-commits.
Herald added subscribers: rengolin, aemerson.
According to the ACLE spec, "__ARM_FEATURE_FMA is defined to 1 if
the hardware floating-point architecture supports fused floating-point
multiply-accumulate".
This changes clang's behaviour from emitting this macro for v7-A and v7-R
cores to only emitting it when the target has VFPv4 (and therefore support
for the floating point multiply-accumulate instruction).
Fixes PR27216
http://reviews.llvm.org/D18963
Files:
lib/Basic/Targets.cpp
test/CodeGen/arm-neon-fma.c
test/Preprocessor/arm-acle-6.5.c
test/Sema/arm_vfma.c
Index: lib/Basic/Targets.cpp
===================================================================
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -4927,7 +4927,8 @@
Builder.defineMacro("__ARM_FP16_ARGS", "1");
// ACLE 6.5.3 Fused multiply-accumulate (FMA)
- if (ArchVersion >= 7 && (CPUProfile != "M" || CPUAttr == "7EM"))
+ if (ArchVersion >= 7 && (CPUProfile != "M" || CPUAttr == "7EM") &&
+ (FPU & VFP4FPU))
Builder.defineMacro("__ARM_FEATURE_FMA", "1");
// Subtarget options.
Index: test/CodeGen/arm-neon-fma.c
===================================================================
--- test/CodeGen/arm-neon-fma.c
+++ test/CodeGen/arm-neon-fma.c
@@ -3,6 +3,7 @@
// RUN: -target-cpu cortex-a8 \
// RUN: -mfloat-abi hard \
// RUN: -ffreestanding \
+// RUN: -target-feature +vfp4 \
// RUN: -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
#include <arm_neon.h>
Index: test/Preprocessor/arm-acle-6.5.c
===================================================================
--- test/Preprocessor/arm-acle-6.5.c
+++ test/Preprocessor/arm-acle-6.5.c
@@ -49,10 +49,13 @@
// CHECK-NO-FMA-NOT: __ARM_FEATURE_FMA
-// RUN: %clang -target armv7a-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-FMA
-// RUN: %clang -target armv7r-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-FMA
+// RUN: %clang -target armv7a-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-NO-FMA
+// RUN: %clang -target armv7a-eabi -mfpu=neon-vfpv4 -x c -E -dM %s -o - |
FileCheck %s -check-prefix CHECK-FMA
+// RUN: %clang -target armv7r-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-NO-FMA
+// RUN: %clang -target armv7r-eabi -mfpu=neon-vfpv4 -x c -E -dM %s -o - |
FileCheck %s -check-prefix CHECK-FMA
// RUN: %clang -target armv7em-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-FMA
-// RUN: %clang -target armv8-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-FMA
+// RUN: %clang -target armv8-eabi -x c -E -dM %s -o - | FileCheck %s
-check-prefix CHECK-NO-FMA
+// RUN: %clang -target armv8-eabi -mfpu=neon-vfpv4 -x c -E -dM %s -o - |
FileCheck %s -check-prefix CHECK-FMA
// CHECK-FMA: __ARM_FEATURE_FMA 1
Index: test/Sema/arm_vfma.c
===================================================================
--- test/Sema/arm_vfma.c
+++ test/Sema/arm_vfma.c
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -triple thumbv7s-apple-ios7.0 -target-feature +neon
-fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple thumbv7s-apple-ios7.0 -target-feature +neon
-target-feature +vfp4 -fsyntax-only -verify %s
#include <arm_neon.h>
// expected-no-diagnostics
Index: lib/Basic/Targets.cpp
===================================================================
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -4927,7 +4927,8 @@
Builder.defineMacro("__ARM_FP16_ARGS", "1");
// ACLE 6.5.3 Fused multiply-accumulate (FMA)
- if (ArchVersion >= 7 && (CPUProfile != "M" || CPUAttr == "7EM"))
+ if (ArchVersion >= 7 && (CPUProfile != "M" || CPUAttr == "7EM") &&
+ (FPU & VFP4FPU))
Builder.defineMacro("__ARM_FEATURE_FMA", "1");
// Subtarget options.
Index: test/CodeGen/arm-neon-fma.c
===================================================================
--- test/CodeGen/arm-neon-fma.c
+++ test/CodeGen/arm-neon-fma.c
@@ -3,6 +3,7 @@
// RUN: -target-cpu cortex-a8 \
// RUN: -mfloat-abi hard \
// RUN: -ffreestanding \
+// RUN: -target-feature +vfp4 \
// RUN: -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
#include <arm_neon.h>
Index: test/Preprocessor/arm-acle-6.5.c
===================================================================
--- test/Preprocessor/arm-acle-6.5.c
+++ test/Preprocessor/arm-acle-6.5.c
@@ -49,10 +49,13 @@
// CHECK-NO-FMA-NOT: __ARM_FEATURE_FMA
-// RUN: %clang -target armv7a-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
-// RUN: %clang -target armv7r-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
+// RUN: %clang -target armv7a-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-NO-FMA
+// RUN: %clang -target armv7a-eabi -mfpu=neon-vfpv4 -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
+// RUN: %clang -target armv7r-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-NO-FMA
+// RUN: %clang -target armv7r-eabi -mfpu=neon-vfpv4 -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
// RUN: %clang -target armv7em-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
-// RUN: %clang -target armv8-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
+// RUN: %clang -target armv8-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-NO-FMA
+// RUN: %clang -target armv8-eabi -mfpu=neon-vfpv4 -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-FMA
// CHECK-FMA: __ARM_FEATURE_FMA 1
Index: test/Sema/arm_vfma.c
===================================================================
--- test/Sema/arm_vfma.c
+++ test/Sema/arm_vfma.c
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -triple thumbv7s-apple-ios7.0 -target-feature +neon -fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple thumbv7s-apple-ios7.0 -target-feature +neon -target-feature +vfp4 -fsyntax-only -verify %s
#include <arm_neon.h>
// expected-no-diagnostics
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
