commit 3c1766ea10043f2e9625f3cba3bda37c84b32cf0
Author: Paul A. Clarke <pc@us.ibm.com>
Date: Thu Jul 18 19:37:13 2019 -0500
[powerpc] fe{en,dis}ableexcept, fesetmode: optimize FPSCR accesses
Since fe{en,dis}ableexcept() and fesetmode() read-modify-write just the
"mode" (exception enable and rounding mode) bits of the Floating Point Status
Control Register (FPSCR), the lighter weight 'mffsl' instruction can be used
to read the FPSCR (enables and rounding mode), and 'mtfsf 0b00000011' can be
used to write just those bits back to the FPSCR. The net is better performance.
In addition, fe{en,dis}ableexcept() read the FPSCR again after writing it, or
they determine that it doesn't need to be written because it is not changing.
In either case, the local variable holds the current values of the enable
bits in the FPSCR. This local variable can be used instead of again reading
the FPSCR.
Also, that value of the FPSCR which is read the second time is validated
against the requested enables. Since the write can't fail, this validation
step is unnecessary, and can be removed. Instead, the exceptions to be
enabled (or disabled) are transformed into available bits in the FPSCR,
then validated after being transformed back, to ensure that all requested
bits are actually being set. For example, FE_INVALID_SQRT can be
requested, but cannot actually be set. This bit is not mapped during the
transformations, so a test for that bit being set before and after
transformations will show the bit would not be set, and the function will
return -1 for failure.
Finally, convert the local macros in fesetmode.c to more generally useful
macros in fenv_libc.h.
diff --git a/sysdeps/powerpc/fpu/fedisblxcpt.c b/sysdeps/powerpc/fpu/fedisblxcpt.c
index 90bc3d12c6d8558c..2a776c72fb5a2b70 100644
--- a/sysdeps/powerpc/fpu/fedisblxcpt.c
+++ b/sysdeps/powerpc/fpu/fedisblxcpt.c
@@ -26,23 +26,25 @@ fedisableexcept (int excepts)
int result, new;
/* Get current exception mask to return. */
- fe.fenv = curr.fenv = fegetenv_register ();
+ fe.fenv = curr.fenv = fegetenv_status ();
result = fenv_reg_to_exceptions (fe.l);
if ((excepts & FE_ALL_INVALID) == FE_ALL_INVALID)
excepts = (excepts | FE_INVALID) & ~ FE_ALL_INVALID;
+ new = fenv_exceptions_to_reg (excepts);
+
+ if (fenv_reg_to_exceptions (new) != excepts)
+ return -1;
+
/* Sets the new exception mask. */
- fe.l &= ~ fenv_exceptions_to_reg (excepts);
+ fe.l &= ~new;
if (fe.l != curr.l)
- fesetenv_register (fe.fenv);
+ fesetenv_mode (fe.fenv);
- new = __fegetexcept ();
if (new == 0 && result != 0)
(void)__fe_mask_env ();
- if ((new & excepts) != 0)
- result = -1;
return result;
}
diff --git a/sysdeps/powerpc/fpu/feenablxcpt.c b/sysdeps/powerpc/fpu/feenablxcpt.c
index e029971b9a460c28..6f5a828e80965bfa 100644
--- a/sysdeps/powerpc/fpu/feenablxcpt.c
+++ b/sysdeps/powerpc/fpu/feenablxcpt.c
@@ -26,24 +26,25 @@ feenableexcept (int excepts)
int result, new;
/* Get current exception mask to return. */
- fe.fenv = curr.fenv = fegetenv_register ();
+ fe.fenv = curr.fenv = fegetenv_status ();
result = fenv_reg_to_exceptions (fe.l);
if ((excepts & FE_ALL_INVALID) == FE_ALL_INVALID)
excepts = (excepts | FE_INVALID) & ~ FE_ALL_INVALID;
+ new = fenv_exceptions_to_reg (excepts);
+
+ if (fenv_reg_to_exceptions (new) != excepts)
+ return -1;
+
/* Sets the new exception mask. */
- fe.l |= fenv_exceptions_to_reg (excepts);
+ fe.l |= new;
if (fe.l != curr.l)
- fesetenv_register (fe.fenv);
+ fesetenv_mode (fe.fenv);
- new = __fegetexcept ();
if (new != 0 && result == 0)
(void) __fe_nomask_env_priv ();
- if ((new & excepts) != excepts)
- result = -1;
-
return result;
}
diff --git a/sysdeps/powerpc/fpu/fenv_libc.h b/sysdeps/powerpc/fpu/fenv_libc.h
index f9634a64d186c076..b244770d115ea7bb 100644
--- a/sysdeps/powerpc/fpu/fenv_libc.h
+++ b/sysdeps/powerpc/fpu/fenv_libc.h
@@ -71,6 +71,11 @@ extern const fenv_t *__fe_mask_env (void) attribute_hidden;
asm volatile ("mtfsf 0xff,%0" : : "f" (d)); \
} while(0)
+/* Set the last 2 nibbles of the FPSCR, which contain the
+ exception enables and the rounding mode.
+ 'fegetenv_status' retrieves these bits by reading the FPSCR. */
+#define fesetenv_mode(env) __builtin_mtfsf (0b00000011, (env));
+
/* This very handy macro:
- Sets the rounding mode to 'round to nearest';
- Sets the processor into IEEE mode; and
@@ -209,8 +214,11 @@ 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_FPRF_MASK \
+ (FPSCR_FPRF_C_MASK|FPSCR_FPRF_FL_MASK|FPSCR_FPRF_FG_MASK| \
+ FPSCR_FPRF_FE_MASK|FPSCR_FPRF_FU_MASK)
#define FPSCR_CONTROL_MASK (FPSCR_ENABLES_MASK|FPSCR_NI_MASK|FPSCR_RN_MASK)
+#define FPSCR_STATUS_MASK (FPSCR_FR_MASK|FPSCR_FI_MASK|FPSCR_FPRF_MASK)
/* The bits in the FENV(1) ABI for exceptions correspond one-to-one with bits
in the FPSCR, albeit shifted to different but corresponding locations.
diff --git a/sysdeps/powerpc/fpu/fesetmode.c b/sysdeps/powerpc/fpu/fesetmode.c
index 32203a24ff434a32..29e088d5ab1c0d93 100644
--- a/sysdeps/powerpc/fpu/fesetmode.c
+++ b/sysdeps/powerpc/fpu/fesetmode.c
@@ -19,11 +19,6 @@
#include <fenv_libc.h>
#include <fpu_control.h>
-#define _FPU_MASK_ALL (_FPU_MASK_ZM | _FPU_MASK_OM | _FPU_MASK_UM \
- | _FPU_MASK_XM | _FPU_MASK_IM)
-
-#define FPU_STATUS 0xbffff700ULL
-
int
fesetmode (const femode_t *modep)
{
@@ -32,18 +27,18 @@ fesetmode (const femode_t *modep)
/* Logic regarding enabled exceptions as in fesetenv. */
new.fenv = *modep;
- old.fenv = fegetenv_register ();
- new.l = (new.l & ~FPU_STATUS) | (old.l & FPU_STATUS);
+ old.fenv = fegetenv_status ();
+ new.l = (new.l & ~FPSCR_STATUS_MASK) | (old.l & FPSCR_STATUS_MASK);
if (old.l == new.l)
return 0;
- if ((old.l & _FPU_MASK_ALL) == 0 && (new.l & _FPU_MASK_ALL) != 0)
+ if ((old.l & FPSCR_ENABLES_MASK) == 0 && (new.l & FPSCR_ENABLES_MASK) != 0)
(void) __fe_nomask_env_priv ();
- if ((old.l & _FPU_MASK_ALL) != 0 && (new.l & _FPU_MASK_ALL) == 0)
+ if ((old.l & FPSCR_ENABLES_MASK) != 0 && (new.l & FPSCR_ENABLES_MASK) == 0)
(void) __fe_mask_env ();
- fesetenv_register (new.fenv);
+ fesetenv_mode (new.fenv);
return 0;
}