Softloat updates, mostly in preparation for s390x usage

-----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCgAdFiEEZoWumedRZ7yvyN81+9DbCVqeKkQFAlx1SJ4ACgkQ+9DbCVqe
 KkRLvgf/RyooKgC4+Gien26iuaEEaNJXcPmwPfzC18BiuxIV6GuWAIX3A5X8LRvJ
 HlRj32ervZUMPLk2Amttur9ijh8MCifTt7KyRIFWW1e97WCHX0BuD+DZgD8xT5yX
 zEL8z1MVdyh9ZeBQm930LbcwLeEwtV1jZHCNdlYNhFI4ZlZ8F4SmRdv8rfbAwz0d
 1aC6rDSQhRaY6j5EurTZvDo4s1PA0fYa6LOkWSX/6rCWg1Z2Dtmb16ZTYscBFZ2P
 RhDILojQ6DSPvglcgCYzd/kCQD+OzE3TRSQc40MCS6gX8C4rfAkiuYpDFKNvzdnE
 aAkzemgiBBnslJ0m2VEmfGuJmvXbVg==
 =ApKt
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/stsquad/tags/pull-fpu-next-260219-1' into staging

Softloat updates, mostly in preparation for s390x usage

# gpg: Signature made Tue 26 Feb 2019 14:09:34 GMT
# gpg:                using RSA key 6685AE99E75167BCAFC8DF35FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>" [full]
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-fpu-next-260219-1:
  tests/Makefile.include: test all rounding modes of softfloat
  softfloat: Support float_round_to_odd more places
  tests/fp: enable f128_to_ui[32/64] tests in float-to-uint
  tests/fp: add wrapping for f128_to_ui32
  softfloat: Implement float128_to_uint32
  softfloat: add float128_is_{normal,denormal}
  tests: Ignore fp test outputs

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

fpu/softfloat.c

@@ -696,6 +696,7 @@ static FloatParts sf_canonicalize(FloatParts part, const FloatFmt *parm,
 static FloatParts round_canonical(FloatParts p, float_status *s,
                                   const FloatFmt *parm)
 {
+    const uint64_t frac_lsb = parm->frac_lsb;
     const uint64_t frac_lsbm1 = parm->frac_lsbm1;
     const uint64_t round_mask = parm->round_mask;
     const uint64_t roundeven_mask = parm->roundeven_mask;
@@ -731,6 +732,10 @@ static FloatParts round_canonical(FloatParts p, float_status *s,
             inc = p.sign ? round_mask : 0;
             overflow_norm = !p.sign;
             break;
+        case float_round_to_odd:
+            overflow_norm = true;
+            inc = frac & frac_lsb ? 0 : round_mask;
+            break;
         default:
             g_assert_not_reached();
         }
@@ -778,9 +783,14 @@ static FloatParts round_canonical(FloatParts p, float_status *s,
             shift64RightJamming(frac, 1 - exp, &frac);
             if (frac & round_mask) {
                 /* Need to recompute round-to-even.  */
-                if (s->float_rounding_mode == float_round_nearest_even) {
+                switch (s->float_rounding_mode) {
+                case float_round_nearest_even:
                     inc = ((frac & roundeven_mask) != frac_lsbm1
                            ? frac_lsbm1 : 0);
+                    break;
+                case float_round_to_odd:
+                    inc = frac & frac_lsb ? 0 : round_mask;
+                    break;
                 }
                 flags |= float_flag_inexact;
                 frac += inc;
@@ -1988,6 +1998,9 @@ static FloatParts round_to_int(FloatParts a, int rmode,
             case float_round_down:
                 one = a.sign;
                 break;
+            case float_round_to_odd:
+                one = true;
+                break;
             default:
                 g_assert_not_reached();
             }
@@ -2021,6 +2034,9 @@ static FloatParts round_to_int(FloatParts a, int rmode,
             case float_round_down:
                 inc = a.sign ? rnd_mask : 0;
                 break;
+            case float_round_to_odd:
+                inc = a.frac & frac_lsb ? 0 : rnd_mask;
+                break;
             default:
                 g_assert_not_reached();
             }
@@ -3314,6 +3330,9 @@ static int32_t roundAndPackInt32(flag zSign, uint64_t absZ, float_status *status
     case float_round_down:
         roundIncrement = zSign ? 0x7f : 0;
         break;
+    case float_round_to_odd:
+        roundIncrement = absZ & 0x80 ? 0 : 0x7f;
+        break;
     default:
         abort();
     }
@@ -3368,6 +3387,9 @@ static int64_t roundAndPackInt64(flag zSign, uint64_t absZ0, uint64_t absZ1,
     case float_round_down:
         increment = zSign && absZ1;
         break;
+    case float_round_to_odd:
+        increment = !(absZ0 & 1) && absZ1;
+        break;
     default:
         abort();
     }
@@ -3424,6 +3446,9 @@ static int64_t roundAndPackUint64(flag zSign, uint64_t absZ0,
     case float_round_down:
         increment = zSign && absZ1;
         break;
+    case float_round_to_odd:
+        increment = !(absZ0 & 1) && absZ1;
+        break;
     default:
         abort();
     }
@@ -3526,6 +3551,9 @@ static float32 roundAndPackFloat32(flag zSign, int zExp, uint32_t zSig,
     case float_round_down:
         roundIncrement = zSign ? 0x7f : 0;
         break;
+    case float_round_to_odd:
+        roundIncrement = zSig & 0x80 ? 0 : 0x7f;
+        break;
     default:
         abort();
         break;
@@ -3536,8 +3564,10 @@ static float32 roundAndPackFloat32(flag zSign, int zExp, uint32_t zSig,
              || (    ( zExp == 0xFD )
                   && ( (int32_t) ( zSig + roundIncrement ) < 0 ) )
            ) {
+            bool overflow_to_inf = roundingMode != float_round_to_odd &&
+                                   roundIncrement != 0;
             float_raise(float_flag_overflow | float_flag_inexact, status);
-            return packFloat32( zSign, 0xFF, - ( roundIncrement == 0 ));
+            return packFloat32(zSign, 0xFF, -!overflow_to_inf);
         }
         if ( zExp < 0 ) {
             if (status->flush_to_zero) {
@@ -3555,6 +3585,13 @@ static float32 roundAndPackFloat32(flag zSign, int zExp, uint32_t zSig,
             if (isTiny && roundBits) {
                 float_raise(float_flag_underflow, status);
             }
+            if (roundingMode == float_round_to_odd) {
+                /*
+                 * For round-to-odd case, the roundIncrement depends on
+                 * zSig which just changed.
+                 */
+                roundIncrement = zSig & 0x80 ? 0 : 0x7f;
+            }
         }
     }
     if (roundBits) {
@@ -6792,6 +6829,35 @@ uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *status)
     return res;
 }
 
+/*----------------------------------------------------------------------------
+| Returns the result of converting the quadruple-precision floating-point value
+| `a' to the 32-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic---which means in particular that the conversion is rounded
+| according to the current rounding mode.  If `a' is a NaN, the largest
+| positive integer is returned.  If the conversion overflows, the
+| largest unsigned integer is returned.  If 'a' is negative, the value is
+| rounded and zero is returned; negative values that do not round to zero
+| will raise the inexact exception.
+*----------------------------------------------------------------------------*/
+
+uint32_t float128_to_uint32(float128 a, float_status *status)
+{
+    uint64_t v;
+    uint32_t res;
+    int old_exc_flags = get_float_exception_flags(status);
+
+    v = float128_to_uint64(a, status);
+    if (v > 0xffffffff) {
+        res = 0xffffffff;
+    } else {
+        return v;
+    }
+    set_float_exception_flags(old_exc_flags, status);
+    float_raise(float_flag_invalid, status);
+    return res;
+}
+
 /*----------------------------------------------------------------------------
 | Returns the result of converting the quadruple-precision floating-point
 | value `a' to the single-precision floating-point format.  The conversion
@@ -6958,6 +7024,15 @@ float128 float128_round_to_int(float128 a, float_status *status)
                 add128(z.high, z.low, 0, roundBitsMask, &z.high, &z.low);
             }
             break;
+        case float_round_to_odd:
+            /*
+             * Note that if lastBitMask == 0, the last bit is the lsb
+             * of high, and roundBitsMask == -1.
+             */
+            if ((lastBitMask ? z.low & lastBitMask : z.high & 1) == 0) {
+                add128(z.high, z.low, 0, roundBitsMask, &z.high, &z.low);
+            }
+            break;
         default:
             abort();
         }
@@ -6990,6 +7065,9 @@ float128 float128_round_to_int(float128 a, float_status *status)
                 return
                       aSign ? packFloat128( 1, 0, 0, 0 )
                     : packFloat128( 0, 0x3FFF, 0, 0 );
+
+            case float_round_to_odd:
+                return packFloat128(aSign, 0x3FFF, 0, 0);
             }
             return packFloat128( aSign, 0, 0, 0 );
         }
@@ -7022,6 +7100,12 @@ float128 float128_round_to_int(float128 a, float_status *status)
                 z.high += roundBitsMask;
             }
             break;
+        case float_round_to_odd:
+            if ((z.high & lastBitMask) == 0) {
+                z.high |= (a.low != 0);
+                z.high += roundBitsMask;
+            }
+            break;
         default:
             abort();
         }

include/fpu/softfloat.h

@@ -466,7 +466,7 @@ static inline int float32_is_zero_or_denormal(float32 a)
 
 static inline bool float32_is_normal(float32 a)
 {
-    return ((float32_val(a) + 0x00800000) & 0x7fffffff) >= 0x01000000;
+    return (((float32_val(a) >> 23) + 1) & 0xff) >= 2;
 }
 
 static inline bool float32_is_denormal(float32 a)
@@ -622,7 +622,7 @@ static inline int float64_is_zero_or_denormal(float64 a)
 
 static inline bool float64_is_normal(float64 a)
 {
-    return ((float64_val(a) + (1ULL << 52)) & -1ULL >> 1) >= 1ULL << 53;
+    return (((float64_val(a) >> 52) + 1) & 0x7ff) >= 2;
 }
 
 static inline bool float64_is_denormal(float64 a)
@@ -878,6 +878,7 @@ int64_t float128_to_int64(float128, float_status *status);
 int64_t float128_to_int64_round_to_zero(float128, float_status *status);
 uint64_t float128_to_uint64(float128, float_status *status);
 uint64_t float128_to_uint64_round_to_zero(float128, float_status *status);
+uint32_t float128_to_uint32(float128, float_status *status);
 uint32_t float128_to_uint32_round_to_zero(float128, float_status *status);
 float32 float128_to_float32(float128, float_status *status);
 float64 float128_to_float64(float128, float_status *status);
@@ -940,6 +941,16 @@ static inline int float128_is_zero_or_denormal(float128 a)
     return (a.high & 0x7fff000000000000LL) == 0;
 }
 
+static inline bool float128_is_normal(float128 a)
+{
+    return (((a.high >> 48) + 1) & 0x7fff) >= 2;
+}
+
+static inline bool float128_is_denormal(float128 a)
+{
+    return float128_is_zero_or_denormal(a) && !float128_is_zero(a);
+}
+
 static inline int float128_is_any_nan(float128 a)
 {
     return ((a.high >> 48) & 0x7fff) == 0x7fff &&

tests/.gitignore

@@ -5,6 +5,7 @@ benchmark-crypto-hmac
 check-*
 !check-*.c
 !check-*.sh
+fp/*.out
 qht-bench
 rcutorture
 test-*

tests/Makefile.include

@@ -916,19 +916,18 @@ $(FP_TEST_BIN):
 # The full test suite can take a bit of time, default to a quick run
 # "-l 2 -r all" can take more than a day for some operations and is best
 # run manually
-FP_TL=-l 1
+FP_TL=-l 1 -r all
 
-# $1 = tests, $2 = description
+# $1 = tests, $2 = description, $3 = test flags
 test-softfloat = $(call quiet-command, \
 			cd $(BUILD_DIR)/tests/fp && \
-			./fp-test -s $(FP_TL) $1 > $2.out 2>&1 || \
+			./fp-test -s $(if $3,$3,$(FP_TL)) $1 > $2.out 2>&1 || \
 			(cat $2.out && exit 1;), \
 			"FLOAT TEST", $2)
 
 # Conversion Routines:
 # FIXME: i32_to_extF80 (broken), i64_to_extF80 (broken)
-#        ui32_to_f128 (not implemented), f128_to_ui32 (not implemented)
+#        ui32_to_f128 (not implemented), extF80_roundToInt (broken)
-#        extF80_roundToInt (broken)
 #
 check-softfloat-conv: $(FP_TEST_BIN)
 	$(call test-softfloat, \
@@ -957,9 +956,11 @@ check-softfloat-conv: $(FP_TEST_BIN)
 		f16_to_ui32 f16_to_ui32_r_minMag \
 		f32_to_ui32 f32_to_ui32_r_minMag \
 		f64_to_ui32 f64_to_ui32_r_minMag \
+		f128_to_ui32 f128_to_ui32_r_minMag \
 		f16_to_ui64 f16_to_ui64_r_minMag \
 		f32_to_ui64 f32_to_ui64_r_minMag \
-		f64_to_ui64 f64_to_ui64_r_minMag, \
+		f64_to_ui64 f64_to_ui64_r_minMag \
+		f128_to_ui64 f128_to_ui64_r_minMag, \
 		float-to-uint)
 	$(call test-softfloat, \
 		f16_roundToInt f32_roundToInt \
@@ -1001,7 +1002,7 @@ check-softfloat-compare: $(SF_COMPARE_RULES)
 check-softfloat-mulAdd: $(FP_TEST_BIN)
 	$(call test-softfloat, \
 		f16_mulAdd f32_mulAdd f64_mulAdd f128_mulAdd, \
-		mulAdd)
+		mulAdd,-l 1)
 
 # FIXME: extF80_rem (broken)
 check-softfloat-rem: $(FP_TEST_BIN)

tests/fp/fp-test.c

@@ -125,17 +125,42 @@ static void not_implemented(void)
 
 static bool blacklisted(unsigned op, int rmode)
 {
-    /* odd has only been implemented for a few 128-bit ops */
+    /* odd has not been implemented for any 80-bit ops */
     if (rmode == softfloat_round_odd) {
         switch (op) {
-        case F128_ADD:
+        case EXTF80_TO_UI32:
-        case F128_SUB:
+        case EXTF80_TO_UI64:
-        case F128_MUL:
+        case EXTF80_TO_I32:
-        case F128_DIV:
+        case EXTF80_TO_I64:
-        case F128_TO_F64:
+        case EXTF80_TO_UI32_R_MINMAG:
-        case F128_SQRT:
+        case EXTF80_TO_UI64_R_MINMAG:
-            return false;
+        case EXTF80_TO_I32_R_MINMAG:
-        default:
+        case EXTF80_TO_I64_R_MINMAG:
+        case EXTF80_TO_F16:
+        case EXTF80_TO_F32:
+        case EXTF80_TO_F64:
+        case EXTF80_TO_F128:
+        case EXTF80_ROUNDTOINT:
+        case EXTF80_ADD:
+        case EXTF80_SUB:
+        case EXTF80_MUL:
+        case EXTF80_DIV:
+        case EXTF80_REM:
+        case EXTF80_SQRT:
+        case EXTF80_EQ:
+        case EXTF80_LE:
+        case EXTF80_LT:
+        case EXTF80_EQ_SIGNALING:
+        case EXTF80_LE_QUIET:
+        case EXTF80_LT_QUIET:
+        case UI32_TO_EXTF80:
+        case UI64_TO_EXTF80:
+        case I32_TO_EXTF80:
+        case I64_TO_EXTF80:
+        case F16_TO_EXTF80:
+        case F32_TO_EXTF80:
+        case F64_TO_EXTF80:
+        case F128_TO_EXTF80:
             return true;
         }
     }
@@ -622,7 +647,8 @@ static void do_testfloat(int op, int rmode, bool exact)
         test_ab_extF80_z_bool(true_ab_extF80M_z_bool, subj_ab_extF80M_z_bool);
         break;
     case F128_TO_UI32:
-        not_implemented();
+        test_a_f128_z_ui32_rx(slow_f128M_to_ui32, qemu_f128M_to_ui32, rmode,
+                              exact);
         break;
     case F128_TO_UI64:
         test_a_f128_z_ui64_rx(slow_f128M_to_ui64, qemu_f128M_to_ui64, rmode,

tests/fp/wrap.inc.c

@@ -367,6 +367,7 @@ WRAP_80_TO_INT_MINMAG(qemu_extF80M_to_i64_r_minMag,
 WRAP_128_TO_INT(qemu_f128M_to_i32, float128_to_int32, int_fast32_t)
 WRAP_128_TO_INT(qemu_f128M_to_i64, float128_to_int64, int_fast64_t)
 
+WRAP_128_TO_INT(qemu_f128M_to_ui32, float128_to_uint32, uint_fast32_t)
 WRAP_128_TO_INT(qemu_f128M_to_ui64, float128_to_uint64, uint_fast64_t)
 #undef WRAP_128_TO_INT