[arm+x86] Make GNU variants behave like GNU w.r.t combining sin+cos into sincos.

Summary:
canCombineSinCosLibcall() would previously combine sin+cos into sincos for
GNUX32/GNUEABI/GNUEABIHF regardless of whether UnsafeFPMath were set or not.
However, GNU would only combine them for UnsafeFPMath because sincos does not
set errno like sin and cos do. It seems likely that this is an oversight.

Reviewers: t.p.northover

Subscribers: t.p.northover, aemerson, llvm-commits, rengolin

Differential Revision: http://reviews.llvm.org/D21431

llvm-svn: 273259
This commit is contained in:
Daniel Sanders 2016-06-21 12:29:03 +00:00
parent a266cf0518
commit bf2c03ee69
5 changed files with 56 additions and 3 deletions

View File

@ -470,6 +470,12 @@ public:
return getOS() == Triple::ELFIAMCU;
}
bool isGNUEnvironment() const {
EnvironmentType Env = getEnvironment();
return Env == Triple::GNU || Env == Triple::GNUEABI ||
Env == Triple::GNUEABIHF || Env == Triple::GNUX32;
}
/// Checks if the environment could be MSVC.
bool isWindowsMSVCEnvironment() const {
return getOS() == Triple::Win32 &&

View File

@ -2176,8 +2176,7 @@ static bool canCombineSinCosLibcall(SDNode *Node, const TargetLowering &TLI,
return false;
// GNU sin/cos functions set errno while sincos does not. Therefore
// combining sin and cos is only safe if unsafe-fpmath is enabled.
bool isGNU = Triple(TM.getTargetTriple()).getEnvironment() == Triple::GNU;
if (isGNU && !TM.Options.UnsafeFPMath)
if (TM.getTargetTriple().isGNUEnvironment() && !TM.Options.UnsafeFPMath)
return false;
return true;
}

View File

@ -473,7 +473,7 @@ static void InitLibcallNames(const char **Names, const Triple &TT) {
Names[RTLIB::ATOMIC_FETCH_NAND_8] = "__atomic_fetch_nand_8";
Names[RTLIB::ATOMIC_FETCH_NAND_16] = "__atomic_fetch_nand_16";
if (TT.getEnvironment() == Triple::GNU) {
if (TT.isGNUEnvironment()) {
Names[RTLIB::SINCOS_F32] = "sincosf";
Names[RTLIB::SINCOS_F64] = "sincos";
Names[RTLIB::SINCOS_F80] = "sincosl";

View File

@ -1,5 +1,8 @@
; RUN: llc < %s -mtriple=armv7-apple-ios6 -mcpu=cortex-a8 | FileCheck %s --check-prefix=NOOPT
; RUN: llc < %s -mtriple=armv7-apple-ios7 -mcpu=cortex-a8 | FileCheck %s --check-prefix=SINCOS
; RUN: llc < %s -mtriple=armv7-linux-gnu -mcpu=cortex-a8 | FileCheck %s --check-prefix=NOOPT-GNU
; RUN: llc < %s -mtriple=armv7-linux-gnueabi -mcpu=cortex-a8 \
; RUN: --enable-unsafe-fp-math | FileCheck %s --check-prefix=SINCOS-GNU
; Combine sin / cos into a single call.
; rdar://12856873
@ -9,9 +12,17 @@ entry:
; SINCOS-LABEL: test1:
; SINCOS: bl ___sincosf_stret
; SINCOS-GNU-LABEL: test1:
; SINCOS-GNU: bl sincosf
; NOOPT-LABEL: test1:
; NOOPT: bl _sinf
; NOOPT: bl _cosf
; NOOPT-GNU-LABEL: test1:
; NOOPT-GNU: bl sinf
; NOOPT-GNU: bl cosf
%call = tail call float @sinf(float %x) nounwind readnone
%call1 = tail call float @cosf(float %x) nounwind readnone
%add = fadd float %call, %call1
@ -23,9 +34,16 @@ entry:
; SINCOS-LABEL: test2:
; SINCOS: bl ___sincos_stret
; SINCOS-GNU-LABEL: test2:
; SINCOS-GNU: bl sincos
; NOOPT-LABEL: test2:
; NOOPT: bl _sin
; NOOPT: bl _cos
; NOOPT-GNU-LABEL: test2:
; NOOPT-GNU: bl sin
; NOOPT-GNU: bl cos
%call = tail call double @sin(double %x) nounwind readnone
%call1 = tail call double @cos(double %x) nounwind readnone
%add = fadd double %call, %call1

View File

@ -1,6 +1,8 @@
; RUN: llc < %s -mtriple=x86_64-apple-macosx10.9.0 -mcpu=core2 | FileCheck %s --check-prefix=OSX_SINCOS
; RUN: llc < %s -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core2 | FileCheck %s --check-prefix=OSX_NOOPT
; RUN: llc < %s -mtriple=x86_64-pc-linux-gnu -mcpu=core2 | FileCheck %s --check-prefix=GNU_NOOPT
; RUN: llc < %s -mtriple=x86_64-pc-linux-gnu -mcpu=core2 -enable-unsafe-fp-math | FileCheck %s --check-prefix=GNU_SINCOS
; RUN: llc < %s -mtriple=x86_64-pc-linux-gnux32 -mcpu=core2 -enable-unsafe-fp-math | FileCheck %s --check-prefix=GNUX32_SINCOS
; Combine sin / cos into a single call.
; rdar://13087969
@ -13,6 +15,15 @@ entry:
; GNU_SINCOS: movss 4(%rsp), %xmm0
; GNU_SINCOS: addss (%rsp), %xmm0
; GNUX32_SINCOS-LABEL: test1:
; GNUX32_SINCOS: callq sincosf
; GNUX32_SINCOS: movss 4(%esp), %xmm0
; GNUX32_SINCOS: addss (%esp), %xmm0
; GNU_NOOPT: test1
; GNU_NOOPT: callq sinf
; GNU_NOOPT: callq cosf
; OSX_SINCOS-LABEL: test1:
; OSX_SINCOS: callq ___sincosf_stret
; OSX_SINCOS: movshdup {{.*}} xmm1 = xmm0[1,1,3,3]
@ -34,6 +45,15 @@ entry:
; GNU_SINCOS: movsd 16(%rsp), %xmm0
; GNU_SINCOS: addsd 8(%rsp), %xmm0
; GNUX32_SINCOS-LABEL: test2:
; GNUX32_SINCOS: callq sincos
; GNUX32_SINCOS: movsd 16(%esp), %xmm0
; GNUX32_SINCOS: addsd 8(%esp), %xmm0
; GNU_NOOPT: test2:
; GNU_NOOPT: callq sin
; GNU_NOOPT: callq cos
; OSX_SINCOS-LABEL: test2:
; OSX_SINCOS: callq ___sincos_stret
; OSX_SINCOS: addsd %xmm1, %xmm0
@ -53,6 +73,16 @@ entry:
; GNU_SINCOS: callq sinl
; GNU_SINCOS: callq cosl
; GNU_SINCOS: ret
; GNUX32_SINCOS-LABEL: test3:
; GNUX32_SINCOS: callq sinl
; GNUX32_SINCOS: callq cosl
; GNUX32_SINCOS: ret
; GNU_NOOPT: test3:
; GNU_NOOPT: callq sinl
; GNU_NOOPT: callq cosl
%call = tail call x86_fp80 @sinl(x86_fp80 %x) nounwind
%call1 = tail call x86_fp80 @cosl(x86_fp80 %x) nounwind
%add = fadd x86_fp80 %call, %call1