[PATCH 3/3] alpha: determine tininess after rounding in the FP emulation

IEEE 754 lets an architecture determine tininess of a floating-point
result either before or after rounding, but requires the same choice for
every operation.  Alpha determines it after rounding, and stdlib's
tst-tininess confirms the hardware does so for the results it produces
itself.

The soft-fp emulation has no notion of the distinction and always
determines tininess before rounding, so a result that the hardware would
not consider tiny is reported as underflowing whenever the instruction
happens to trap for software completion.  The two paths then disagree on
the same machine.  A multiply of the largest subnormal double by
1 + 2^-52 rounds up to the smallest normal and raises no underflow when
the operands are normal, but raises it when an operand is subnormal and
the instruction traps:

  glibc math testsuite, test-float32x-float64-mul:
    Failure: mul_double (0x3.ffffffffffffcp-1024, 0x1.0000000000001p+0):
    Exception "Underflow" set

Add _FP_TININESS_AFTER_ROUNDING, as glibc's copy of soft-fp has, and set
it for alpha.  It determines tininess by rounding a copy of the result as
if the exponent range were unbounded, which is what the definition asks
for; a plain check of whether the rounded result came out normal is not
equivalent and would be wrong for values that stay tiny under an
unbounded exponent range but round up to the smallest normal in the
subnormal grid.  The macro defaults to zero, so powerpc, sh and sparc
keep determining tininess before rounding as they do now.

Cc: [email protected] # 5.15+
Signed-off-by: Matt Turner <[email protected]>
---
 arch/alpha/include/asm/sfp-machine.h |  4 ++++
 include/math-emu/op-common.h         | 23 +++++++++++++++++++++--
 include/math-emu/soft-fp.h           |  8 ++++++++
 3 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/arch/alpha/include/asm/sfp-machine.h b/arch/alpha/include/asm/sfp-machine.h
index 5fe63afbd474..bff1ad963c68 100644
--- a/arch/alpha/include/asm/sfp-machine.h
+++ b/arch/alpha/include/asm/sfp-machine.h
@@ -59,6 +59,10 @@
     R##_c = FP_CLS_NAN;						\
   } while (0)
 
+/* Alpha determines tininess after rounding, so the emulation must do the
+   same as the hardware does for the results it produces itself.  */
+#define _FP_TININESS_AFTER_ROUNDING	1
+
 /* Obtain the current rounding mode. */
 #define FP_ROUNDMODE	mode
 #define FP_RND_NEAREST	(FPCR_DYN_NORMAL >> FPCR_DYN_SHIFT)
diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h
index 8ce066c035cf..1d1ce5c08efc 100644
--- a/include/math-emu/op-common.h
+++ b/include/math-emu/op-common.h
@@ -135,6 +135,24 @@ do {								\
     else							\
       {								\
 	/* we've got a denormalized number */			\
+	int _FP_PACK_CANONICAL_is_tiny = 1;			\
+	if (_FP_TININESS_AFTER_ROUNDING && X##_e == 0)		\
+	  {							\
+	    /* Architectures that detect tininess after rounding	\
+	       only signal underflow if the result is still		\
+	       subnormal once rounded as if the exponent range	\
+	       were unbounded.  Round a copy to find out.  */	\
+	    FP_DECL_##fs(_FP_PACK_CANONICAL_T);			\
+	    /* The class field is not used by the rounding below,	\
+	       and is unused entirely where this block is dead.  */	\
+	    (void)_FP_PACK_CANONICAL_T##_c;			\
+	    _FP_FRAC_COPY_##wc(_FP_PACK_CANONICAL_T, X);	\
+	    _FP_PACK_CANONICAL_T##_s = X##_s;			\
+	    _FP_PACK_CANONICAL_T##_e = X##_e;			\
+	    _FP_ROUND(wc, _FP_PACK_CANONICAL_T);		\
+	    if (_FP_FRAC_OVERP_##wc(fs, _FP_PACK_CANONICAL_T))	\
+	      _FP_PACK_CANONICAL_is_tiny = 0;			\
+	  }							\
 	X##_e = -X##_e + 1;					\
 	if (X##_e <= _FP_WFRACBITS_##fs)			\
 	  {							\
@@ -161,8 +179,9 @@ do {								\
 		    _FP_FRAC_SRL_##wc(X, _FP_WORKBITS);		\
 		  }						\
 	      }							\
-	    if ((FP_CUR_EXCEPTIONS & FP_EX_INEXACT) ||		\
-		(FP_TRAPPING_EXCEPTIONS & FP_EX_UNDERFLOW))	\
+	    if (_FP_PACK_CANONICAL_is_tiny			\
+		&& ((FP_CUR_EXCEPTIONS & FP_EX_INEXACT) ||	\
+		    (FP_TRAPPING_EXCEPTIONS & FP_EX_UNDERFLOW)))	\
 		FP_SET_EXCEPTION(FP_EX_UNDERFLOW);		\
 	  }							\
 	else							\
diff --git a/include/math-emu/soft-fp.h b/include/math-emu/soft-fp.h
index 5650c1628383..02ada0a9fca1 100644
--- a/include/math-emu/soft-fp.h
+++ b/include/math-emu/soft-fp.h
@@ -31,6 +31,14 @@
 #include <endian.h>
 #endif
 
+/* Whether the architecture determines tininess of a floating-point
+   result after rounding rather than before it.  IEEE 754 permits either
+   but requires the same choice for every operation, so this has to agree
+   with what the hardware does for the results it produces itself.  */
+#ifndef _FP_TININESS_AFTER_ROUNDING
+#define _FP_TININESS_AFTER_ROUNDING	0
+#endif
+
 #define _FP_WORKBITS		3
 #define _FP_WORK_LSB		((_FP_W_TYPE)1 << 3)
 #define _FP_WORK_ROUND		((_FP_W_TYPE)1 << 2)

-- 
2.54.0