From c0c08d02c82275353f5c556f935a1a01714d9d7f Mon Sep 17 00:00:00 2001 From: Wilco Date: Thu, 15 May 2014 15:21:55 +0100 Subject: ARM: Improve fenv implementation --- ChangeLog | 18 ++++++++++++++++++ sysdeps/arm/fclrexcpt.c | 10 +++++----- sysdeps/arm/fedisblxcpt.c | 4 +++- sysdeps/arm/feenablxcpt.c | 10 +++++----- sysdeps/arm/fegetround.c | 14 ++------------ sysdeps/arm/feholdexcpt.c | 16 ++-------------- sysdeps/arm/fesetenv.c | 42 +++++++++++++++++++++--------------------- sysdeps/arm/fesetround.c | 10 ++-------- sysdeps/arm/feupdateenv.c | 24 ++++++++++++++++-------- sysdeps/arm/fgetexcptflg.c | 9 ++------- sysdeps/arm/fsetexcptflg.c | 13 ++++++++----- sysdeps/arm/ftestexcept.c | 11 +++-------- sysdeps/arm/setfpucw.c | 11 ++++++----- 13 files changed, 93 insertions(+), 99 deletions(-) diff --git a/ChangeLog b/ChangeLog index 83719ed450..29ffc2d621 100644 --- a/ChangeLog +++ b/ChangeLog @@ -895,6 +895,24 @@ * nptl/sysdeps/unix/sysv/linux/s390/bits/pthreadtypes.h (pthread_mutex_t): Add lock elision support for s390. +2014-05-14 Wilco + + * sysdeps/arm/fclrexcpt.c: Optimize to avoid unnecessary FPSCR writes. + * sysdeps/arm/fedisblxcpt.c: Likewise. + * sysdeps/arm/feenablxcpt.c: Likewise. + * sysdeps/arm/fegetround.c: Call (get_rounding_mode). + * sysdeps/arm/feholdexcpt.c: Call optimized (libc_feholdexcept_vfp). + * sysdeps/arm/fesetenv.c: Special case FE_DFL_ENV and FE_NOMASK_ENV. + Call optimized (libc_fesetenv_vfp). + * sysdeps/arm/fesetround.c: Call optimized (libc_fesetround_vfp). + * sysdeps/arm/feupdateenv.c: Special case FE_DFL_ENV and FE_NOMASK_ENV. + Call optimized (libc_feupdateenv_vfp). + * sysdeps/arm/fgetexcptflg.c: Call optimized (libc_fetestexcept_vfp). + * sysdeps/arm/fsetexcptflg.c: Optimize to avoid unnecessary FPSCR + writes. + * sysdeps/arm/ftestexcept.c: Call optimized (libc_fetestexcept_vfp). + * sysdeps/arm/setfpucw.c: Optimize to avoid unnecessary FPSCR writes. + 2014-05-14 Wilco * sysdeps/arm/fclrexcpt.c: Cleanup. diff --git a/sysdeps/arm/fclrexcpt.c b/sysdeps/arm/fclrexcpt.c index cbf61a6f4a..31420ed3c7 100644 --- a/sysdeps/arm/fclrexcpt.c +++ b/sysdeps/arm/fclrexcpt.c @@ -24,7 +24,7 @@ int feclearexcept (int excepts) { - fpu_control_t fpscr; + fpu_control_t fpscr, new_fpscr; /* Fail if a VFP unit isn't present unless nothing needs to be done. */ if (!ARM_HAVE_VFP) @@ -32,11 +32,11 @@ feclearexcept (int excepts) _FPU_GETCW (fpscr); excepts &= FE_ALL_EXCEPT; + new_fpscr = fpscr & ~excepts; - /* Clear the relevant bits. */ - fpscr = (fpscr & ~FE_ALL_EXCEPT) | (fpscr & FE_ALL_EXCEPT & ~excepts); - - _FPU_SETCW (fpscr); + /* Write new exception flags if changed. */ + if (new_fpscr != fpscr) + _FPU_SETCW (new_fpscr); return 0; } diff --git a/sysdeps/arm/fedisblxcpt.c b/sysdeps/arm/fedisblxcpt.c index f2956cd32a..d5e0f0031a 100644 --- a/sysdeps/arm/fedisblxcpt.c +++ b/sysdeps/arm/fedisblxcpt.c @@ -35,7 +35,9 @@ fedisableexcept (int excepts) excepts &= FE_ALL_EXCEPT; new_fpscr = fpscr & ~(excepts << FE_EXCEPT_SHIFT); - _FPU_SETCW (new_fpscr); + /* Write new exceptions if changed. */ + if (new_fpscr != fpscr) + _FPU_SETCW (new_fpscr); return (fpscr >> FE_EXCEPT_SHIFT) & FE_ALL_EXCEPT; } diff --git a/sysdeps/arm/feenablxcpt.c b/sysdeps/arm/feenablxcpt.c index afd8943638..e649b2f1e1 100644 --- a/sysdeps/arm/feenablxcpt.c +++ b/sysdeps/arm/feenablxcpt.c @@ -35,15 +35,15 @@ feenableexcept (int excepts) excepts &= FE_ALL_EXCEPT; new_fpscr = fpscr | (excepts << FE_EXCEPT_SHIFT); - _FPU_SETCW (new_fpscr); - - if (excepts != 0) + if (new_fpscr != fpscr) { + _FPU_SETCW (new_fpscr); + /* Not all VFP architectures support trapping exceptions, so test whether the relevant bits were set and fail if not. */ _FPU_GETCW (new_fpscr); - if ((new_fpscr & (excepts << FE_EXCEPT_SHIFT)) - != (excepts << FE_EXCEPT_SHIFT)) + + if (((new_fpscr >> FE_EXCEPT_SHIFT) & excepts) != excepts) return -1; } diff --git a/sysdeps/arm/fegetround.c b/sysdeps/arm/fegetround.c index 1c9c151a16..fbad0b3078 100644 --- a/sysdeps/arm/fegetround.c +++ b/sysdeps/arm/fegetround.c @@ -16,22 +16,12 @@ License along with the GNU C Library. If not, see . */ -#include -#include -#include +#include int fegetround (void) { - fpu_control_t fpscr; - - /* FE_TONEAREST is the only supported rounding mode - if a VFP unit isn't present. */ - if (!ARM_HAVE_VFP) - return FE_TONEAREST; - - _FPU_GETCW (fpscr); - return fpscr & FE_TOWARDZERO; + return get_rounding_mode (); } libm_hidden_def (fegetround) diff --git a/sysdeps/arm/feholdexcpt.c b/sysdeps/arm/feholdexcpt.c index 258ba6637f..2d79e0c46d 100644 --- a/sysdeps/arm/feholdexcpt.c +++ b/sysdeps/arm/feholdexcpt.c @@ -16,30 +16,18 @@ License along with the GNU C Library. If not, see . */ -#include -#include +#include #include int feholdexcept (fenv_t *envp) { - fpu_control_t fpscr; - /* Fail if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return 1; - _FPU_GETCW (fpscr); - envp->__cw = fpscr; - - /* Now set all exceptions to non-stop. */ - fpscr &= ~(FE_ALL_EXCEPT << FE_EXCEPT_SHIFT); - - /* And clear all exception flags. */ - fpscr &= ~FE_ALL_EXCEPT; - - _FPU_SETCW (fpscr); + libc_feholdexcept_vfp (envp); return 0; } diff --git a/sysdeps/arm/fesetenv.c b/sysdeps/arm/fesetenv.c index 62031d596d..9e2aa81f9b 100644 --- a/sysdeps/arm/fesetenv.c +++ b/sysdeps/arm/fesetenv.c @@ -16,43 +16,43 @@ License along with the GNU C Library. If not, see . */ -#include -#include +#include #include int fesetenv (const fenv_t *envp) { - fpu_control_t fpscr; - /* Fail if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return 1; - _FPU_GETCW (fpscr); + if ((envp == FE_DFL_ENV) || (envp == FE_NOMASK_ENV)) + { + fpu_control_t fpscr, new_fpscr; + + _FPU_GETCW (fpscr); - /* Preserve the reserved FPSCR flags. */ - fpscr &= _FPU_RESERVED; + /* Preserve the reserved FPSCR flags. */ + new_fpscr = fpscr & _FPU_RESERVED; - if (envp == FE_DFL_ENV) - fpscr |= _FPU_DEFAULT; - else if (envp == FE_NOMASK_ENV) - fpscr |= _FPU_IEEE; - else - fpscr |= envp->__cw & ~_FPU_RESERVED; + if (envp == FE_DFL_ENV) + _FPU_SETCW (new_fpscr | _FPU_DEFAULT); + else + { + _FPU_SETCW (new_fpscr | _FPU_IEEE); + /* Not all VFP architectures support trapping exceptions, so + test whether the relevant bits were set and fail if not. */ + _FPU_GETCW (fpscr); - _FPU_SETCW (fpscr); + if ((fpscr & _FPU_IEEE) != _FPU_IEEE) + return 1; + } - if (envp == FE_NOMASK_ENV) - { - /* Not all VFP architectures support trapping exceptions, so - test whether the relevant bits were set and fail if not. */ - _FPU_GETCW (fpscr); - if ((fpscr & _FPU_IEEE) != _FPU_IEEE) - return 1; + return 0; } + libc_fesetenv_vfp (envp); return 0; } diff --git a/sysdeps/arm/fesetround.c b/sysdeps/arm/fesetround.c index d1b92dc255..f52c50aec4 100644 --- a/sysdeps/arm/fesetround.c +++ b/sysdeps/arm/fesetround.c @@ -16,28 +16,22 @@ License along with the GNU C Library. If not, see . */ -#include -#include +#include #include int fesetround (int round) { - fpu_control_t fpscr; - /* FE_TONEAREST is the only supported rounding mode if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return (round == FE_TONEAREST) ? 0 : 1; - /* Fail if the rounding mode is not valid. */ if (round & ~FE_TOWARDZERO) return 1; - _FPU_GETCW (fpscr); - fpscr = (fpscr & ~FE_TOWARDZERO) | round; - _FPU_SETCW (fpscr); + libc_fesetround_vfp (round); return 0; } diff --git a/sysdeps/arm/feupdateenv.c b/sysdeps/arm/feupdateenv.c index 55a15025c6..2a7b3ec894 100644 --- a/sysdeps/arm/feupdateenv.c +++ b/sysdeps/arm/feupdateenv.c @@ -17,27 +17,35 @@ License along with the GNU C Library. If not, see . */ -#include -#include +#include #include int feupdateenv (const fenv_t *envp) { - fpu_control_t fpscr; + fenv_t fenv; /* Fail if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return 1; - _FPU_GETCW (fpscr); + if ((envp == FE_DFL_ENV) || (envp == FE_NOMASK_ENV)) + { + fpu_control_t fpscr; - /* Install new environment. */ - fesetenv (envp); + _FPU_GETCW (fpscr); - /* Raise the saved exceptions. */ - feraiseexcept (fpscr & FE_ALL_EXCEPT); + /* Preserve the reserved FPSCR flags. */ + fpscr &= _FPU_RESERVED; + fpscr |= (envp == FE_DFL_ENV) ? _FPU_DEFAULT : _FPU_IEEE; + + /* Create a valid fenv to pass to libc_feupdateenv_vfp. */ + fenv.__cw = fpscr; + envp = &fenv; + } + + libc_feupdateenv_vfp (envp); return 0; } libm_hidden_def (feupdateenv) diff --git a/sysdeps/arm/fgetexcptflg.c b/sysdeps/arm/fgetexcptflg.c index 63fdfbf747..994555ca19 100644 --- a/sysdeps/arm/fgetexcptflg.c +++ b/sysdeps/arm/fgetexcptflg.c @@ -17,22 +17,17 @@ License along with the GNU C Library. If not, see . */ -#include -#include +#include #include int fegetexceptflag (fexcept_t *flagp, int excepts) { - fpu_control_t fpscr; - /* Fail if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return 1; - _FPU_GETCW (fpscr); - - *flagp = fpscr & excepts & FE_ALL_EXCEPT; + *flagp = libc_fetestexcept_vfp (excepts); return 0; } diff --git a/sysdeps/arm/fsetexcptflg.c b/sysdeps/arm/fsetexcptflg.c index 1a610ff912..28810d3ec8 100644 --- a/sysdeps/arm/fsetexcptflg.c +++ b/sysdeps/arm/fsetexcptflg.c @@ -25,19 +25,22 @@ int fesetexceptflag (const fexcept_t *flagp, int excepts) { - fpu_control_t fpscr; + fpu_control_t fpscr, new_fpscr; /* Fail if a VFP unit isn't present unless nothing needs to be done. */ if (!ARM_HAVE_VFP) return (excepts != 0); _FPU_GETCW (fpscr); + excepts &= FE_ALL_EXCEPT; /* Set the desired exception mask. */ - fpscr &= ~(excepts & FE_ALL_EXCEPT); - fpscr |= (*flagp & excepts & FE_ALL_EXCEPT); + new_fpscr = fpscr & ~excepts; + new_fpscr |= *flagp & excepts; + + /* Write new exception flags if changed. */ + if (new_fpscr != fpscr) + _FPU_SETCW (new_fpscr); - /* Save state back to the FPU. */ - _FPU_SETCW (fpscr); return 0; } diff --git a/sysdeps/arm/ftestexcept.c b/sysdeps/arm/ftestexcept.c index de082b281a..6c5d3a8288 100644 --- a/sysdeps/arm/ftestexcept.c +++ b/sysdeps/arm/ftestexcept.c @@ -16,23 +16,18 @@ License along with the GNU C Library. If not, see . */ -#include -#include +#include #include int fetestexcept (int excepts) { - fpu_control_t fpscr; - /* Return no exception flags if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return 0; - /* Get current exceptions. */ - _FPU_GETCW (fpscr); - - return fpscr & excepts & FE_ALL_EXCEPT; + return libc_fetestexcept_vfp (excepts); } + libm_hidden_def (fetestexcept) diff --git a/sysdeps/arm/setfpucw.c b/sysdeps/arm/setfpucw.c index 7416377f9e..259b020f81 100644 --- a/sysdeps/arm/setfpucw.c +++ b/sysdeps/arm/setfpucw.c @@ -24,19 +24,20 @@ void __setfpucw (fpu_control_t set) { - fpu_control_t fpscr; + fpu_control_t fpscr, new_fpscr; /* Do nothing if a VFP unit isn't present. */ if (!ARM_HAVE_VFP) return; - /* Fetch the current control word. */ _FPU_GETCW (fpscr); /* Preserve the reserved bits, and set the rest as the user specified (or the default, if the user gave zero). */ - fpscr &= _FPU_RESERVED; - fpscr |= set & ~_FPU_RESERVED; + new_fpscr = fpscr & _FPU_RESERVED; + new_fpscr |= set & ~_FPU_RESERVED; - _FPU_SETCW (fpscr); + /* Write FPSCR if changed. */ + if (new_fpscr != fpscr) + _FPU_SETCW (fpscr); } -- cgit 1.4.1