diff mbox series

[PULL,35/46] softfloat: Implement float128_add/sub via parts

Message ID 20210516123431.718318-36-richard.henderson@linaro.org
State Accepted
Commit 3ff49e56a7294e1b0d29ee62250a877838f4a1eb
Headers show
Series softfloat: Convert float128 to FloatParts (part 1) | expand

Commit Message

Richard Henderson May 16, 2021, 12:34 p.m. UTC
Replace the existing Berkeley implementation with the
FloatParts implementation.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 fpu/softfloat.c | 257 +++++++-----------------------------------------
 1 file changed, 36 insertions(+), 221 deletions(-)

-- 
2.25.1
diff mbox series

Patch

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index afeef00097..8f734f6020 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -1046,6 +1046,20 @@  static float64 float64_round_pack_canonical(FloatParts64 *p,
     return float64_pack_raw(p);
 }
 
+static void float128_unpack_canonical(FloatParts128 *p, float128 f,
+                                      float_status *s)
+{
+    float128_unpack_raw(p, f);
+    parts_canonicalize(p, s, &float128_params);
+}
+
+static float128 float128_round_pack_canonical(FloatParts128 *p,
+                                              float_status *s)
+{
+    parts_uncanon(p, s, &float128_params);
+    return float128_pack_raw(p);
+}
+
 /*
  * Addition and subtraction
  */
@@ -1213,6 +1227,28 @@  bfloat16 bfloat16_sub(bfloat16 a, bfloat16 b, float_status *status)
     return bfloat16_addsub(a, b, status, true);
 }
 
+static float128 QEMU_FLATTEN
+float128_addsub(float128 a, float128 b, float_status *status, bool subtract)
+{
+    FloatParts128 pa, pb, *pr;
+
+    float128_unpack_canonical(&pa, a, status);
+    float128_unpack_canonical(&pb, b, status);
+    pr = parts_addsub(&pa, &pb, status, subtract);
+
+    return float128_round_pack_canonical(pr, status);
+}
+
+float128 float128_add(float128 a, float128 b, float_status *status)
+{
+    return float128_addsub(a, b, status, false);
+}
+
+float128 float128_sub(float128 a, float128 b, float_status *status)
+{
+    return float128_addsub(a, b, status, true);
+}
+
 /*
  * Returns the result of multiplying the floating-point values `a' and
  * `b'. The operation is performed according to the IEC/IEEE Standard
@@ -7032,227 +7068,6 @@  float128 float128_round_to_int(float128 a, float_status *status)
 
 }
 
-/*----------------------------------------------------------------------------
-| Returns the result of adding the absolute values of the quadruple-precision
-| floating-point values `a' and `b'.  If `zSign' is 1, the sum is negated
-| before being returned.  `zSign' is ignored if the result is a NaN.
-| The addition is performed according to the IEC/IEEE Standard for Binary
-| Floating-Point Arithmetic.
-*----------------------------------------------------------------------------*/
-
-static float128 addFloat128Sigs(float128 a, float128 b, bool zSign,
-                                float_status *status)
-{
-    int32_t aExp, bExp, zExp;
-    uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2;
-    int32_t expDiff;
-
-    aSig1 = extractFloat128Frac1( a );
-    aSig0 = extractFloat128Frac0( a );
-    aExp = extractFloat128Exp( a );
-    bSig1 = extractFloat128Frac1( b );
-    bSig0 = extractFloat128Frac0( b );
-    bExp = extractFloat128Exp( b );
-    expDiff = aExp - bExp;
-    if ( 0 < expDiff ) {
-        if ( aExp == 0x7FFF ) {
-            if (aSig0 | aSig1) {
-                return propagateFloat128NaN(a, b, status);
-            }
-            return a;
-        }
-        if ( bExp == 0 ) {
-            --expDiff;
-        }
-        else {
-            bSig0 |= UINT64_C(0x0001000000000000);
-        }
-        shift128ExtraRightJamming(
-            bSig0, bSig1, 0, expDiff, &bSig0, &bSig1, &zSig2 );
-        zExp = aExp;
-    }
-    else if ( expDiff < 0 ) {
-        if ( bExp == 0x7FFF ) {
-            if (bSig0 | bSig1) {
-                return propagateFloat128NaN(a, b, status);
-            }
-            return packFloat128( zSign, 0x7FFF, 0, 0 );
-        }
-        if ( aExp == 0 ) {
-            ++expDiff;
-        }
-        else {
-            aSig0 |= UINT64_C(0x0001000000000000);
-        }
-        shift128ExtraRightJamming(
-            aSig0, aSig1, 0, - expDiff, &aSig0, &aSig1, &zSig2 );
-        zExp = bExp;
-    }
-    else {
-        if ( aExp == 0x7FFF ) {
-            if ( aSig0 | aSig1 | bSig0 | bSig1 ) {
-                return propagateFloat128NaN(a, b, status);
-            }
-            return a;
-        }
-        add128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 );
-        if ( aExp == 0 ) {
-            if (status->flush_to_zero) {
-                if (zSig0 | zSig1) {
-                    float_raise(float_flag_output_denormal, status);
-                }
-                return packFloat128(zSign, 0, 0, 0);
-            }
-            return packFloat128( zSign, 0, zSig0, zSig1 );
-        }
-        zSig2 = 0;
-        zSig0 |= UINT64_C(0x0002000000000000);
-        zExp = aExp;
-        goto shiftRight1;
-    }
-    aSig0 |= UINT64_C(0x0001000000000000);
-    add128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 );
-    --zExp;
-    if ( zSig0 < UINT64_C(0x0002000000000000) ) goto roundAndPack;
-    ++zExp;
- shiftRight1:
-    shift128ExtraRightJamming(
-        zSig0, zSig1, zSig2, 1, &zSig0, &zSig1, &zSig2 );
- roundAndPack:
-    return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status);
-
-}
-
-/*----------------------------------------------------------------------------
-| Returns the result of subtracting the absolute values of the quadruple-
-| precision floating-point values `a' and `b'.  If `zSign' is 1, the
-| difference is negated before being returned.  `zSign' is ignored if the
-| result is a NaN.  The subtraction is performed according to the IEC/IEEE
-| Standard for Binary Floating-Point Arithmetic.
-*----------------------------------------------------------------------------*/
-
-static float128 subFloat128Sigs(float128 a, float128 b, bool zSign,
-                                float_status *status)
-{
-    int32_t aExp, bExp, zExp;
-    uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1;
-    int32_t expDiff;
-
-    aSig1 = extractFloat128Frac1( a );
-    aSig0 = extractFloat128Frac0( a );
-    aExp = extractFloat128Exp( a );
-    bSig1 = extractFloat128Frac1( b );
-    bSig0 = extractFloat128Frac0( b );
-    bExp = extractFloat128Exp( b );
-    expDiff = aExp - bExp;
-    shortShift128Left( aSig0, aSig1, 14, &aSig0, &aSig1 );
-    shortShift128Left( bSig0, bSig1, 14, &bSig0, &bSig1 );
-    if ( 0 < expDiff ) goto aExpBigger;
-    if ( expDiff < 0 ) goto bExpBigger;
-    if ( aExp == 0x7FFF ) {
-        if ( aSig0 | aSig1 | bSig0 | bSig1 ) {
-            return propagateFloat128NaN(a, b, status);
-        }
-        float_raise(float_flag_invalid, status);
-        return float128_default_nan(status);
-    }
-    if ( aExp == 0 ) {
-        aExp = 1;
-        bExp = 1;
-    }
-    if ( bSig0 < aSig0 ) goto aBigger;
-    if ( aSig0 < bSig0 ) goto bBigger;
-    if ( bSig1 < aSig1 ) goto aBigger;
-    if ( aSig1 < bSig1 ) goto bBigger;
-    return packFloat128(status->float_rounding_mode == float_round_down,
-                        0, 0, 0);
- bExpBigger:
-    if ( bExp == 0x7FFF ) {
-        if (bSig0 | bSig1) {
-            return propagateFloat128NaN(a, b, status);
-        }
-        return packFloat128( zSign ^ 1, 0x7FFF, 0, 0 );
-    }
-    if ( aExp == 0 ) {
-        ++expDiff;
-    }
-    else {
-        aSig0 |= UINT64_C(0x4000000000000000);
-    }
-    shift128RightJamming( aSig0, aSig1, - expDiff, &aSig0, &aSig1 );
-    bSig0 |= UINT64_C(0x4000000000000000);
- bBigger:
-    sub128( bSig0, bSig1, aSig0, aSig1, &zSig0, &zSig1 );
-    zExp = bExp;
-    zSign ^= 1;
-    goto normalizeRoundAndPack;
- aExpBigger:
-    if ( aExp == 0x7FFF ) {
-        if (aSig0 | aSig1) {
-            return propagateFloat128NaN(a, b, status);
-        }
-        return a;
-    }
-    if ( bExp == 0 ) {
-        --expDiff;
-    }
-    else {
-        bSig0 |= UINT64_C(0x4000000000000000);
-    }
-    shift128RightJamming( bSig0, bSig1, expDiff, &bSig0, &bSig1 );
-    aSig0 |= UINT64_C(0x4000000000000000);
- aBigger:
-    sub128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 );
-    zExp = aExp;
- normalizeRoundAndPack:
-    --zExp;
-    return normalizeRoundAndPackFloat128(zSign, zExp - 14, zSig0, zSig1,
-                                         status);
-
-}
-
-/*----------------------------------------------------------------------------
-| Returns the result of adding the quadruple-precision floating-point values
-| `a' and `b'.  The operation is performed according to the IEC/IEEE Standard
-| for Binary Floating-Point Arithmetic.
-*----------------------------------------------------------------------------*/
-
-float128 float128_add(float128 a, float128 b, float_status *status)
-{
-    bool aSign, bSign;
-
-    aSign = extractFloat128Sign( a );
-    bSign = extractFloat128Sign( b );
-    if ( aSign == bSign ) {
-        return addFloat128Sigs(a, b, aSign, status);
-    }
-    else {
-        return subFloat128Sigs(a, b, aSign, status);
-    }
-
-}
-
-/*----------------------------------------------------------------------------
-| Returns the result of subtracting the quadruple-precision floating-point
-| values `a' and `b'.  The operation is performed according to the IEC/IEEE
-| Standard for Binary Floating-Point Arithmetic.
-*----------------------------------------------------------------------------*/
-
-float128 float128_sub(float128 a, float128 b, float_status *status)
-{
-    bool aSign, bSign;
-
-    aSign = extractFloat128Sign( a );
-    bSign = extractFloat128Sign( b );
-    if ( aSign == bSign ) {
-        return subFloat128Sigs(a, b, aSign, status);
-    }
-    else {
-        return addFloat128Sigs(a, b, aSign, status);
-    }
-
-}
-
 /*----------------------------------------------------------------------------
 | Returns the result of multiplying the quadruple-precision floating-point
 | values `a' and `b'.  The operation is performed according to the IEC/IEEE