[glibc/ibm/2.30/master] [powerpc] libc_feupdateenv_test: optimize FPSCR access

[glibc/ibm/2.30/master] [powerpc] libc_feupdateenv_test: optimize FPSCR access

[Paul Clarke]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=11c0fd3ab34a06dd0faf401daecd07911414eb24

commit 11c0fd3ab34a06dd0faf401daecd07911414eb24
Author: Paul A. Clarke <pc@us.ibm.com>
Date:   Thu Sep 19 11:18:33 2019 -0500

    [powerpc] libc_feupdateenv_test: optimize FPSCR access
    
    ROUND_TO_ODD and a couple of other places use libc_feupdateenv_test to
    restore the rounding mode and exception enables, preserve exception flags,
    and test whether given exception(s) were generated.
    
    If the exception flags haven't changed, then it is sufficient and a bit
    more efficient to just restore the rounding mode and enables, rather than
    writing the full Floating-Point Status and Control Register (FPSCR).
    
    Reviewed-by: Paul E. Murphy <murphyp@linux.ibm.com>

Diff:
---
 ChangeLog                          |  6 ++++++
 sysdeps/powerpc/fpu/fenv_libc.h    |  4 ++++
 sysdeps/powerpc/fpu/fenv_private.h | 16 ++++++++++++++--
 3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 7a633d7..5fde58a 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,11 @@
 2019-09-27  Paul A. Clarke  <pc@us.ibm.com>
 
+	* sysdeps/powerpc/fpu/fenv_libc.h (FPSCR_EXCEPTIONS_MASK):  New.
+	* sysdeps/powerpc/fpu/fenv_private.h (__libc_femergeenv_ppc):  Optimize
+	to write FPSCR control only, if exceptions have not changed.
+
+2019-09-27  Paul A. Clarke  <pc@us.ibm.com>
+
 	* sysdeps/powerpc/fpu/fenv_libc.h:
 	(__TEST_AND_ENTER_NON_STOP): New.
 	(__TEST_AND_EXIT_NON_STOP): New.
diff --git a/sysdeps/powerpc/fpu/fenv_libc.h b/sysdeps/powerpc/fpu/fenv_libc.h
index 9163fb6..38ab6cd 100644
--- a/sysdeps/powerpc/fpu/fenv_libc.h
+++ b/sysdeps/powerpc/fpu/fenv_libc.h
@@ -256,6 +256,10 @@ enum {
   (FPSCR_VE_MASK|FPSCR_OE_MASK|FPSCR_UE_MASK|FPSCR_ZE_MASK|FPSCR_XE_MASK)
 #define FPSCR_BASIC_EXCEPTIONS_MASK \
   (FPSCR_VX_MASK|FPSCR_OX_MASK|FPSCR_UX_MASK|FPSCR_ZX_MASK|FPSCR_XX_MASK)
+#define FPSCR_EXCEPTIONS_MASK (FPSCR_BASIC_EXCEPTIONS_MASK| \
+  FPSCR_VXSNAN_MASK|FPSCR_VXISI_MASK|FPSCR_VXIDI_MASK|FPSCR_VXZDZ_MASK| \
+  FPSCR_VXIMZ_MASK|FPSCR_VXVC_MASK|FPSCR_VXSOFT_MASK|FPSCR_VXSQRT_MASK| \
+  FPSCR_VXCVI_MASK)
 #define FPSCR_FPRF_MASK \
   (FPSCR_FPRF_C_MASK|FPSCR_FPRF_FL_MASK|FPSCR_FPRF_FG_MASK| \
    FPSCR_FPRF_FE_MASK|FPSCR_FPRF_FU_MASK)
diff --git a/sysdeps/powerpc/fpu/fenv_private.h b/sysdeps/powerpc/fpu/fenv_private.h
index 0036cca..d080553 100644
--- a/sysdeps/powerpc/fpu/fenv_private.h
+++ b/sysdeps/powerpc/fpu/fenv_private.h
@@ -52,8 +52,20 @@ __libc_femergeenv_ppc (const fenv_t *envp, unsigned long long old_mask,
   __TEST_AND_EXIT_NON_STOP (old.l, new.l);
   __TEST_AND_ENTER_NON_STOP (old.l, new.l);
 
-  /* Atomically enable and raise (if appropriate) exceptions set in `new'.  */
-  fesetenv_register (new.fenv);
+  /* If requesting to keep status, replace control, and merge exceptions,
+     and exceptions haven't changed, we can just set new control instead
+     of the whole FPSCR.  */
+  if ((old_mask & (FPSCR_CONTROL_MASK|FPSCR_STATUS_MASK|FPSCR_EXCEPTIONS_MASK))
+      == (FPSCR_STATUS_MASK|FPSCR_EXCEPTIONS_MASK) &&
+      (new_mask & (FPSCR_CONTROL_MASK|FPSCR_STATUS_MASK|FPSCR_EXCEPTIONS_MASK))
+      == (FPSCR_CONTROL_MASK|FPSCR_EXCEPTIONS_MASK) &&
+      (old.l & FPSCR_EXCEPTIONS_MASK) == (new.l & FPSCR_EXCEPTIONS_MASK))
+  {
+    fesetenv_mode (new.fenv);
+  }
+  else
+    /* Atomically enable and raise (if appropriate) exceptions set in `new'.  */
+    fesetenv_register (new.fenv);
 
   return old.l;
 }