aboutsummaryrefslogtreecommitdiff
path: root/soft-fp
diff options
context:
space:
mode:
authorJoseph Myers <joseph@codesourcery.com>2014-10-09 01:09:22 +0000
committerJoseph Myers <joseph@codesourcery.com>2014-10-09 01:09:22 +0000
commit454ac701e3639bfcb8919706319a685341536eda (patch)
tree43a1bf6afd55b21347b743266adeb6c3048f272f /soft-fp
parent0022e688d082761a1e15b19121303cafbdad33ec (diff)
downloadglibc-454ac701e3639bfcb8919706319a685341536eda.zip
glibc-454ac701e3639bfcb8919706319a685341536eda.tar.gz
glibc-454ac701e3639bfcb8919706319a685341536eda.tar.bz2
soft-fp: Add FP_DENORM_ZERO.
Continuing the addition of soft-fp features used in the Linux kernel, this patch adds soft-fp support for FP_DENORM_ZERO (flushing input subnormal operands to zero of the same sign). There are some differences from the kernel version. In the kernel, the "inexact" exception is set when flushing to zero. This does not appear to match the documented semantics for either of the architectures (alpha and sh) for which the kernel uses FP_DENORM_ZERO, so this patch does not set "inexact" in this case. More operations now use raw or semi-raw unpacking for optimization than did in the ten-year-old soft-fp version in the kernel, so checks of FP_DENORM_ZERO are inserted in those operations. They are also inserted for comparisons (which already used raw unpacking in the old version) as I believe that's the correct thing to do when input subnormals are flushed to zero. They are *not* inserted for _FP_NEG. (If any processors do flush input subnormals to zero for negation, or otherwise vary from the rules implemented when FP_DENORM_ZERO is set, further macros for sfp-machine.h to control this may need to be added.) Although the addition for comparisons will cause FP_EX_DENORM to be set in this case, it still won't be set for comparisons involving subnormals when not flushed to zero. It's quite possible that accurate emulation of processors that have such an exception for subnormal operands will require further changes relating to when FP_EX_DENORM is set (in general, the support for things defined by IEEE should be considered more reliable and mature than the support for things outside the scope of IEEE floating point). Although some processors also have a mode for abrupt underflow - producing zeroes instead of output subnormals - there is no such mode in the kernel's soft-fp, so no such mode is added to glibc's soft-fp (although it could be if someone wanted to emulate such processor support). Tested for powerpc-nofpu that the disassembly of installed shared libraries is unchanged by this patch. * soft-fp/soft-fp.h (FP_DENORM_ZERO): New macro. * soft-fp/op-common.h (_FP_UNPACK_CANONICAL): Check FP_DENORM_ZERO. (_FP_CHECK_FLUSH_ZERO): New macro. (_FP_ADD_INTERNAL): Call _FP_CHECK_FLUSH_ZERO. (_FP_CMP): Likewise. (_FP_CMP_EQ): Likewise. (_FP_TO_INT): Do not set inexact for subnormal arguments if FP_DENORM_ZERO. (FP_EXTEND): Call _FP_CHECK_FLUSH_ZERO. (FP_TRUNC): Likewise.
Diffstat (limited to 'soft-fp')
-rw-r--r--soft-fp/op-common.h34
-rw-r--r--soft-fp/soft-fp.h5
2 files changed, 38 insertions, 1 deletions
diff --git a/soft-fp/op-common.h b/soft-fp/op-common.h
index e0a108a..3da234b 100644
--- a/soft-fp/op-common.h
+++ b/soft-fp/op-common.h
@@ -63,6 +63,12 @@
case 0: \
if (_FP_FRAC_ZEROP_##wc (X)) \
X##_c = FP_CLS_ZERO; \
+ else if (FP_DENORM_ZERO) \
+ { \
+ X##_c = FP_CLS_ZERO; \
+ _FP_FRAC_SET_##wc (X, _FP_ZEROFRAC_##wc); \
+ FP_SET_EXCEPTION (FP_EX_DENORM); \
+ } \
else \
{ \
/* A denormalized number. */ \
@@ -99,6 +105,21 @@
other classification is not done. */
#define _FP_UNPACK_SEMIRAW(fs, wc, X) _FP_FRAC_SLL_##wc (X, _FP_WORKBITS)
+/* Check whether a raw or semi-raw input value should be flushed to
+ zero, and flush it to zero if so. */
+#define _FP_CHECK_FLUSH_ZERO(fs, wc, X) \
+ do \
+ { \
+ if (FP_DENORM_ZERO \
+ && X##_e == 0 \
+ && !_FP_FRAC_ZEROP_##wc (X)) \
+ { \
+ _FP_FRAC_SET_##wc (X, _FP_ZEROFRAC_##wc); \
+ FP_SET_EXCEPTION (FP_EX_DENORM); \
+ } \
+ } \
+ while (0)
+
/* A semi-raw value has overflowed to infinity. Adjust the mantissa
and exponent appropriately. */
#define _FP_OVERFLOW_SEMIRAW(fs, wc, X) \
@@ -387,6 +408,8 @@
#define _FP_ADD_INTERNAL(fs, wc, R, X, Y, OP) \
do \
{ \
+ _FP_CHECK_FLUSH_ZERO (fs, wc, X); \
+ _FP_CHECK_FLUSH_ZERO (fs, wc, Y); \
if (X##_s == Y##_s) \
{ \
/* Addition. */ \
@@ -1222,6 +1245,9 @@
int _FP_CMP_is_zero_x; \
int _FP_CMP_is_zero_y; \
\
+ _FP_CHECK_FLUSH_ZERO (fs, wc, X); \
+ _FP_CHECK_FLUSH_ZERO (fs, wc, Y); \
+ \
_FP_CMP_is_zero_x \
= (!X##_e && _FP_FRAC_ZEROP_##wc (X)) ? 1 : 0; \
_FP_CMP_is_zero_y \
@@ -1264,6 +1290,9 @@
} \
else \
{ \
+ _FP_CHECK_FLUSH_ZERO (fs, wc, X); \
+ _FP_CHECK_FLUSH_ZERO (fs, wc, Y); \
+ \
ret = !(X##_e == Y##_e \
&& _FP_FRAC_EQ_##wc (X, Y) \
&& (X##_s == Y##_s || (!X##_e && _FP_FRAC_ZEROP_##wc (X)))); \
@@ -1361,7 +1390,8 @@
{ \
if (!_FP_FRAC_ZEROP_##wc (X)) \
{ \
- FP_SET_EXCEPTION (FP_EX_INEXACT); \
+ if (!FP_DENORM_ZERO) \
+ FP_SET_EXCEPTION (FP_EX_INEXACT); \
FP_SET_EXCEPTION (FP_EX_DENORM); \
} \
} \
@@ -1540,6 +1570,7 @@
{ \
if (S##_e == 0) \
{ \
+ _FP_CHECK_FLUSH_ZERO (sfs, swc, S); \
if (_FP_FRAC_ZEROP_##swc (S)) \
D##_e = 0; \
else if (_FP_EXPBIAS_##dfs \
@@ -1625,6 +1656,7 @@
{ \
if (S##_e == 0) \
{ \
+ _FP_CHECK_FLUSH_ZERO (sfs, swc, S); \
D##_e = 0; \
if (_FP_FRAC_ZEROP_##swc (S)) \
_FP_FRAC_SET_##dwc (D, _FP_ZEROFRAC_##dwc); \
diff --git a/soft-fp/soft-fp.h b/soft-fp/soft-fp.h
index 4018b0e..3ac269e 100644
--- a/soft-fp/soft-fp.h
+++ b/soft-fp/soft-fp.h
@@ -123,6 +123,11 @@
# define FP_HANDLE_EXCEPTIONS do {} while (0)
#endif
+/* Whether to flush subnormal inputs to zero with the same sign. */
+#ifndef FP_DENORM_ZERO
+# define FP_DENORM_ZERO 0
+#endif
+
#ifndef FP_INHIBIT_RESULTS
/* By default we write the results always.
sfp-machine may override this and e.g.