Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-fp-20210516' into staging

Reorg FloatParts to use QEMU_GENERIC.
Begin replacing the Berkeley float128 routines with FloatParts128.
  - includes a new implementation of float128_muladd
  - includes the snan silencing that was missing from
    float{32,64}_to_float128 and float128_to_float{32,64}.
  - does not include float128_min/max* (written but not yet reviewed).

# gpg: Signature made Sun 16 May 2021 13:27:10 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-fp-20210516: (46 commits)
  softfloat: Move round_to_int_and_pack to softfloat-parts.c.inc
  softfloat: Move round_to_int to softfloat-parts.c.inc
  softfloat: Convert float-to-float conversions with float128
  softfloat: Split float_to_float
  softfloat: Move div_floats to softfloat-parts.c.inc
  softfloat: Introduce sh[lr]_double primitives
  softfloat: Tidy mul128By64To192
  softfloat: Use add192 in mul128To256
  softfloat: Use mulu64 for mul64To128
  softfloat: Move muladd_floats to softfloat-parts.c.inc
  softfloat: Move mul_floats to softfloat-parts.c.inc
  softfloat: Implement float128_add/sub via parts
  softfloat: Move addsub_floats to softfloat-parts.c.inc
  softfloat: Use uadd64_carry, usub64_borrow in softfloat-macros.h
  softfloat: Move round_canonical to softfloat-parts.c.inc
  softfloat: Move sf_canonicalize to softfloat-parts.c.inc
  softfloat: Move pick_nan_muladd to softfloat-parts.c.inc
  softfloat: Move pick_nan to softfloat-parts.c.inc
  softfloat: Move return_nan to softfloat-parts.c.inc
  softfloat: Convert float128_default_nan to parts
  ...

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

1 files changed, 83 insertions, 132 deletions

diff --git a/include/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h
index a35ec2893a..ec4e27a595 100644
--- a/include/fpu/softfloat-macros.h
+++ b/include/fpu/softfloat-macros.h
@@ -83,6 +83,43 @@ this code that are retained.
 #define FPU_SOFTFLOAT_MACROS_H
 
 #include "fpu/softfloat-types.h"
+#include "qemu/host-utils.h"
+
+/**
+ * shl_double: double-word merging left shift
+ * @l: left or most-significant word
+ * @r: right or least-significant word
+ * @c: shift count
+ *
+ * Shift @l left by @c bits, shifting in bits from @r.
+ */
+static inline uint64_t shl_double(uint64_t l, uint64_t r, int c)
+{
+#if defined(__x86_64__)
+    asm("shld %b2, %1, %0" : "+r"(l) : "r"(r), "ci"(c));
+    return l;
+#else
+    return c ? (l << c) | (r >> (64 - c)) : l;
+#endif
+}
+
+/**
+ * shr_double: double-word merging right shift
+ * @l: left or most-significant word
+ * @r: right or least-significant word
+ * @c: shift count
+ *
+ * Shift @r right by @c bits, shifting in bits from @l.
+ */
+static inline uint64_t shr_double(uint64_t l, uint64_t r, int c)
+{
+#if defined(__x86_64__)
+    asm("shrd %b2, %1, %0" : "+r"(r) : "r"(l), "ci"(c));
+    return r;
+#else
+    return c ? (r >> c) | (l << (64 - c)) : r;
+#endif
+}
 
 /*----------------------------------------------------------------------------
 | Shifts `a' right by the number of bits given in `count'.  If any nonzero
@@ -403,16 +440,12 @@ static inline void
 | are stored at the locations pointed to by `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- add128(
-     uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void add128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
-    uint64_t z1;
-
-    z1 = a1 + b1;
-    *z1Ptr = z1;
-    *z0Ptr = a0 + b0 + ( z1 < a1 );
-
+    bool c = 0;
+    *z1Ptr = uadd64_carry(a1, b1, &c);
+    *z0Ptr = uadd64_carry(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -423,34 +456,14 @@ static inline void
 | `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- add192(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t a2,
-     uint64_t b0,
-     uint64_t b1,
-     uint64_t b2,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr
- )
+static inline void add192(uint64_t a0, uint64_t a1, uint64_t a2,
+                          uint64_t b0, uint64_t b1, uint64_t b2,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr)
 {
-    uint64_t z0, z1, z2;
-    int8_t carry0, carry1;
-
-    z2 = a2 + b2;
-    carry1 = ( z2 < a2 );
-    z1 = a1 + b1;
-    carry0 = ( z1 < a1 );
-    z0 = a0 + b0;
-    z1 += carry1;
-    z0 += ( z1 < carry1 );
-    z0 += carry0;
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
-
+    bool c = 0;
+    *z2Ptr = uadd64_carry(a2, b2, &c);
+    *z1Ptr = uadd64_carry(a1, b1, &c);
+    *z0Ptr = uadd64_carry(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -461,14 +474,12 @@ static inline void
 | `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- sub128(
-     uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void sub128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
-
-    *z1Ptr = a1 - b1;
-    *z0Ptr = a0 - b0 - ( a1 < b1 );
-
+    bool c = 0;
+    *z1Ptr = usub64_borrow(a1, b1, &c);
+    *z0Ptr = usub64_borrow(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -479,34 +490,14 @@ static inline void
 | pointed to by `z0Ptr', `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- sub192(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t a2,
-     uint64_t b0,
-     uint64_t b1,
-     uint64_t b2,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr
- )
+static inline void sub192(uint64_t a0, uint64_t a1, uint64_t a2,
+                          uint64_t b0, uint64_t b1, uint64_t b2,
+                          uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr)
 {
-    uint64_t z0, z1, z2;
-    int8_t borrow0, borrow1;
-
-    z2 = a2 - b2;
-    borrow1 = ( a2 < b2 );
-    z1 = a1 - b1;
-    borrow0 = ( a1 < b1 );
-    z0 = a0 - b0;
-    z0 -= ( z1 < borrow1 );
-    z1 -= borrow1;
-    z0 -= borrow0;
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
-
+    bool c = 0;
+    *z2Ptr = usub64_borrow(a2, b2, &c);
+    *z1Ptr = usub64_borrow(a1, b1, &c);
+    *z0Ptr = usub64_borrow(a0, b0, &c);
 }
 
 /*----------------------------------------------------------------------------
@@ -515,27 +506,10 @@ static inline void
 | `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void
+mul64To128(uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
-    uint32_t aHigh, aLow, bHigh, bLow;
-    uint64_t z0, zMiddleA, zMiddleB, z1;
-
-    aLow = a;
-    aHigh = a>>32;
-    bLow = b;
-    bHigh = b>>32;
-    z1 = ( (uint64_t) aLow ) * bLow;
-    zMiddleA = ( (uint64_t) aLow ) * bHigh;
-    zMiddleB = ( (uint64_t) aHigh ) * bLow;
-    z0 = ( (uint64_t) aHigh ) * bHigh;
-    zMiddleA += zMiddleB;
-    z0 += ( ( (uint64_t) ( zMiddleA < zMiddleB ) )<<32 ) + ( zMiddleA>>32 );
-    zMiddleA <<= 32;
-    z1 += zMiddleA;
-    z0 += ( z1 < zMiddleA );
-    *z1Ptr = z1;
-    *z0Ptr = z0;
-
+    mulu64(z1Ptr, z0Ptr, a, b);
 }
 
 /*----------------------------------------------------------------------------
@@ -546,24 +520,14 @@ static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t
 *----------------------------------------------------------------------------*/
 
 static inline void
- mul128By64To192(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t b,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr
- )
+mul128By64To192(uint64_t a0, uint64_t a1, uint64_t b,
+                uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr)
 {
-    uint64_t z0, z1, z2, more1;
-
-    mul64To128( a1, b, &z1, &z2 );
-    mul64To128( a0, b, &z0, &more1 );
-    add128( z0, more1, 0, z1, &z0, &z1 );
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
+    uint64_t z0, z1, m1;
 
+    mul64To128(a1, b, &m1, z2Ptr);
+    mul64To128(a0, b, &z0, &z1);
+    add128(z0, z1, 0, m1, z0Ptr, z1Ptr);
 }
 
 /*----------------------------------------------------------------------------
@@ -573,34 +537,21 @@ static inline void
 | the locations pointed to by `z0Ptr', `z1Ptr', `z2Ptr', and `z3Ptr'.
 *----------------------------------------------------------------------------*/
 
-static inline void
- mul128To256(
-     uint64_t a0,
-     uint64_t a1,
-     uint64_t b0,
-     uint64_t b1,
-     uint64_t *z0Ptr,
-     uint64_t *z1Ptr,
-     uint64_t *z2Ptr,
-     uint64_t *z3Ptr
- )
+static inline void mul128To256(uint64_t a0, uint64_t a1,
+                               uint64_t b0, uint64_t b1,
+                               uint64_t *z0Ptr, uint64_t *z1Ptr,
+                               uint64_t *z2Ptr, uint64_t *z3Ptr)
 {
-    uint64_t z0, z1, z2, z3;
-    uint64_t more1, more2;
-
-    mul64To128( a1, b1, &z2, &z3 );
-    mul64To128( a1, b0, &z1, &more2 );
-    add128( z1, more2, 0, z2, &z1, &z2 );
-    mul64To128( a0, b0, &z0, &more1 );
-    add128( z0, more1, 0, z1, &z0, &z1 );
-    mul64To128( a0, b1, &more1, &more2 );
-    add128( more1, more2, 0, z2, &more1, &z2 );
-    add128( z0, z1, 0, more1, &z0, &z1 );
-    *z3Ptr = z3;
-    *z2Ptr = z2;
-    *z1Ptr = z1;
-    *z0Ptr = z0;
+    uint64_t z0, z1, z2;
+    uint64_t m0, m1, m2, n1, n2;
+
+    mul64To128(a1, b0, &m1, &m2);
+    mul64To128(a0, b1, &n1, &n2);
+    mul64To128(a1, b1, &z2, z3Ptr);
+    mul64To128(a0, b0, &z0, &z1);
 
+    add192( 0, m1, m2,  0, n1, n2, &m0, &m1, &m2);
+    add192(m0, m1, m2, z0, z1, z2, z0Ptr, z1Ptr, z2Ptr);
 }
 
 /*----------------------------------------------------------------------------