[PATCH] x86: Add a new option -mdaz-ftz to enable FTZ and DAZ flags in MXCSR.

[liuhongt <hongtao.liu@intel.com>]

> The quoted patch shows -shared in context and  you didn't post a
> backport version
> to look at.  But yes, we shouldn't change -shared behavior on a
> branch, even less so make it
> inconsistent between targets.
Here's the patch.

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for GCC 11/12 backport?

    if (mdaz-ftz)
      link crtfastmath.o
    else if ((Ofast || ffast-math || funsafe-math-optimizations)
             && !mno-daz-ftz)
      link crtfastmath.o
    else
      Don't link crtfastmath.o

gcc/ChangeLog:

	* config/i386/cygwin.h (ENDFILE_SPEC): Link crtfastmath.o
	whenever -mdaz-ftz is specified. Don't link crtfastmath.o
	when -mno-daz-ftz is specified.
	* config/i386/darwin.h (ENDFILE_SPEC): Ditto.
	* config/i386/gnu-user-common.h
	(GNU_USER_TARGET_MATHFILE_SPEC): Ditto.
	* config/i386/mingw32.h (ENDFILE_SPEC): Ditto.
	* config/i386/i386.opt (mdaz-ftz): New option.
	* doc/invoke.texi (x86 options): Document mftz-daz.
---
 gcc/config/i386/cygwin.h          |  2 +-
 gcc/config/i386/darwin.h          |  4 ++--
 gcc/config/i386/gnu-user-common.h |  2 +-
 gcc/config/i386/i386.opt          |  4 ++++
 gcc/config/i386/mingw32.h         |  2 +-
 gcc/doc/invoke.texi               | 11 ++++++++++-
 6 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/gcc/config/i386/cygwin.h b/gcc/config/i386/cygwin.h
index d06eda369cf..5412c5d4479 100644
--- a/gcc/config/i386/cygwin.h
+++ b/gcc/config/i386/cygwin.h
@@ -57,7 +57,7 @@ along with GCC; see the file COPYING3.  If not see
 
 #undef ENDFILE_SPEC
 #define ENDFILE_SPEC \
-  "%{Ofast|ffast-math|funsafe-math-optimizations:crtfastmath.o%s}\
+  "%{mdaz-ftz:crtfastmath.o%s;Ofast|ffast-math|funsafe-math-optimizations:%{!mno-daz-ftz:crtfastmath.o%s}} \
    %{!shared:%:if-exists(default-manifest.o%s)}\
    %{fvtable-verify=none:%s; \
     fvtable-verify=preinit:vtv_end.o%s; \
diff --git a/gcc/config/i386/darwin.h b/gcc/config/i386/darwin.h
index a55f6b2b874..2f773924d6e 100644
--- a/gcc/config/i386/darwin.h
+++ b/gcc/config/i386/darwin.h
@@ -109,8 +109,8 @@ along with GCC; see the file COPYING3.  If not see
 "%{!force_cpusubtype_ALL:-force_cpusubtype_ALL} "
 
 #undef ENDFILE_SPEC
-#define ENDFILE_SPEC \
-  "%{Ofast|ffast-math|funsafe-math-optimizations:crtfastmath.o%s} \
+#define ENDFILE_SPEC
+\  "%{mdaz-ftz:crtfastmath.o%s;Ofast|ffast-math|funsafe-math-optimizations:%{!mno-daz-ftz:crtfastmath.o%s}} \
    %{mpc32:crtprec32.o%s} \
    %{mpc64:crtprec64.o%s} \
    %{mpc80:crtprec80.o%s}" TM_DESTRUCTOR
diff --git a/gcc/config/i386/gnu-user-common.h b/gcc/config/i386/gnu-user-common.h
index 23b54c5be52..3d2a33f1714 100644
--- a/gcc/config/i386/gnu-user-common.h
+++ b/gcc/config/i386/gnu-user-common.h
@@ -47,7 +47,7 @@ along with GCC; see the file COPYING3.  If not see
 
 /* Similar to standard GNU userspace, but adding -ffast-math support.  */
 #define GNU_USER_TARGET_MATHFILE_SPEC \
-  "%{Ofast|ffast-math|funsafe-math-optimizations:crtfastmath.o%s} \
+  "%{mdaz-ftz:crtfastmath.o%s;Ofast|ffast-math|funsafe-math-optimizations:%{!mno-daz-ftz:crtfastmath.o%s}} \
    %{mpc32:crtprec32.o%s} \
    %{mpc64:crtprec64.o%s} \
    %{mpc80:crtprec80.o%s}"
diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index a3675e515bc..5cfb7cdcbc2 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -420,6 +420,10 @@ mpc80
 Target RejectNegative
 Set 80387 floating-point precision to 80-bit.
 
+mdaz-ftz
+Target
+Set the FTZ and DAZ Flags.
+
 mpreferred-stack-boundary=
 Target RejectNegative Joined UInteger Var(ix86_preferred_stack_boundary_arg)
 Attempt to keep stack aligned to this power of 2.
diff --git a/gcc/config/i386/mingw32.h b/gcc/config/i386/mingw32.h
index d3ca0cd0279..ddbe6a4054b 100644
--- a/gcc/config/i386/mingw32.h
+++ b/gcc/config/i386/mingw32.h
@@ -197,7 +197,7 @@ along with GCC; see the file COPYING3.  If not see
 
 #undef ENDFILE_SPEC
 #define ENDFILE_SPEC \
-  "%{Ofast|ffast-math|funsafe-math-optimizations:crtfastmath.o%s} \
+  "%{mdaz-ftz:crtfastmath.o%s;Ofast|ffast-math|funsafe-math-optimizations:%{!mno-daz-ftz:crtfastmath.o%s}} \
    %{!shared:%:if-exists(default-manifest.o%s)}\
    %{fvtable-verify=none:%s; \
     fvtable-verify=preinit:vtv_end.o%s; \
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index cb83dd8a1cc..87eedfffa6c 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1434,7 +1434,7 @@ See RS/6000 and PowerPC Options.
 -m96bit-long-double  -mlong-double-64  -mlong-double-80  -mlong-double-128 @gol
 -mregparm=@var{num}  -msseregparm @gol
 -mveclibabi=@var{type}  -mvect8-ret-in-mem @gol
--mpc32  -mpc64  -mpc80  -mstackrealign @gol
+-mpc32  -mpc64  -mpc80 -mdaz-ftz -mstackrealign @gol
 -momit-leaf-frame-pointer  -mno-red-zone  -mno-tls-direct-seg-refs @gol
 -mcmodel=@var{code-model}  -mabi=@var{name}  -maddress-mode=@var{mode} @gol
 -m32  -m64  -mx32  -m16  -miamcu  -mlarge-data-threshold=@var{num} @gol
@@ -32078,6 +32078,15 @@ are enabled by default; routines in such libraries could suffer significant
 loss of accuracy, typically through so-called ``catastrophic cancellation'',
 when this option is used to set the precision to less than extended precision.
 
+@item -mdaz-ftz
+@opindex mdaz-ftz
+
+The flush-to-zero (FTZ) and denormals-are-zero (DAZ) flags in the MXCSR register
+are used to control floating-point calculations.SSE and AVX instructions
+including scalar and vector instructions could benefit from enabling the FTZ
+and DAZ flags when @option{-mdaz-ftz} is specified. Don't set FTZ/DAZ flags
+when @option{-mno-daz-ftz} is specified.
+
 @item -mstackrealign
 @opindex mstackrealign
 Realign the stack at entry.  On the x86, the @option{-mstackrealign}
-- 
2.39.1.388.g2fc9e9ca3c