[PULL 55/72] softfloat: Add float{16,32,64}_muladd_scalbn

[Richard Henderson]

We currently have a flag, float_muladd_halve_result, to scale
the result by 2**-1.  Extend this to handle arbitrary scaling.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/fpu/softfloat.h   |  6 ++++
 fpu/softfloat.c           | 58 ++++++++++++++++++++++-----------------
 fpu/softfloat-parts.c.inc |  7 +++--
 3 files changed, 44 insertions(+), 27 deletions(-)

diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index eb64075b9c..c34ce0477d 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -238,6 +238,8 @@ float16 float16_add(float16, float16, float_status *status);
 float16 float16_sub(float16, float16, float_status *status);
 float16 float16_mul(float16, float16, float_status *status);
 float16 float16_muladd(float16, float16, float16, int, float_status *status);
+float16 float16_muladd_scalbn(float16, float16, float16,
+                              int, int, float_status *status);
 float16 float16_div(float16, float16, float_status *status);
 float16 float16_scalbn(float16, int, float_status *status);
 float16 float16_min(float16, float16, float_status *status);
@@ -597,6 +599,8 @@ float32 float32_mul(float32, float32, float_status *status);
 float32 float32_div(float32, float32, float_status *status);
 float32 float32_rem(float32, float32, float_status *status);
 float32 float32_muladd(float32, float32, float32, int, float_status *status);
+float32 float32_muladd_scalbn(float32, float32, float32,
+                              int, int, float_status *status);
 float32 float32_sqrt(float32, float_status *status);
 float32 float32_exp2(float32, float_status *status);
 float32 float32_log2(float32, float_status *status);
@@ -792,6 +796,8 @@ float64 float64_mul(float64, float64, float_status *status);
 float64 float64_div(float64, float64, float_status *status);
 float64 float64_rem(float64, float64, float_status *status);
 float64 float64_muladd(float64, float64, float64, int, float_status *status);
+float64 float64_muladd_scalbn(float64, float64, float64,
+                              int, int, float_status *status);
 float64 float64_sqrt(float64, float_status *status);
 float64 float64_log2(float64, float_status *status);
 FloatRelation float64_compare(float64, float64, float_status *status);
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 8de8d5f342..b5936cc0f8 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -789,15 +789,15 @@ static FloatParts128 *parts128_mul(FloatParts128 *a, 
FloatParts128 *b,
 #define parts_mul(A, B, S) \
     PARTS_GENERIC_64_128(mul, A)(A, B, S)
 
-static FloatParts64 *parts64_muladd(FloatParts64 *a, FloatParts64 *b,
-                                    FloatParts64 *c, int flags,
-                                    float_status *s);
-static FloatParts128 *parts128_muladd(FloatParts128 *a, FloatParts128 *b,
-                                      FloatParts128 *c, int flags,
-                                      float_status *s);
+static FloatParts64 *parts64_muladd_scalbn(FloatParts64 *a, FloatParts64 *b,
+                                           FloatParts64 *c, int scale,
+                                           int flags, float_status *s);
+static FloatParts128 *parts128_muladd_scalbn(FloatParts128 *a, FloatParts128 
*b,
+                                             FloatParts128 *c, int scale,
+                                             int flags, float_status *s);
 
-#define parts_muladd(A, B, C, Z, S) \
-    PARTS_GENERIC_64_128(muladd, A)(A, B, C, Z, S)
+#define parts_muladd_scalbn(A, B, C, Z, Y, S) \
+    PARTS_GENERIC_64_128(muladd_scalbn, A)(A, B, C, Z, Y, S)
 
 static FloatParts64 *parts64_div(FloatParts64 *a, FloatParts64 *b,
                                  float_status *s);
@@ -2212,43 +2212,50 @@ floatx80_mul(floatx80 a, floatx80 b, float_status 
*status)
  * Fused multiply-add
  */
 
-float16 QEMU_FLATTEN float16_muladd(float16 a, float16 b, float16 c,
-                                    int flags, float_status *status)
+float16 QEMU_FLATTEN
+float16_muladd_scalbn(float16 a, float16 b, float16 c,
+                      int scale, int flags, float_status *status)
 {
     FloatParts64 pa, pb, pc, *pr;
 
     float16_unpack_canonical(&pa, a, status);
     float16_unpack_canonical(&pb, b, status);
     float16_unpack_canonical(&pc, c, status);
-    pr = parts_muladd(&pa, &pb, &pc, flags, status);
+    pr = parts_muladd_scalbn(&pa, &pb, &pc, scale, flags, status);
 
     return float16_round_pack_canonical(pr, status);
 }
 
-static float32 QEMU_SOFTFLOAT_ATTR
-soft_f32_muladd(float32 a, float32 b, float32 c, int flags,
-                float_status *status)
+float16 float16_muladd(float16 a, float16 b, float16 c,
+                       int flags, float_status *status)
+{
+    return float16_muladd_scalbn(a, b, c, 0, flags, status);
+}
+
+float32 QEMU_SOFTFLOAT_ATTR
+float32_muladd_scalbn(float32 a, float32 b, float32 c,
+                      int scale, int flags, float_status *status)
 {
     FloatParts64 pa, pb, pc, *pr;
 
     float32_unpack_canonical(&pa, a, status);
     float32_unpack_canonical(&pb, b, status);
     float32_unpack_canonical(&pc, c, status);
-    pr = parts_muladd(&pa, &pb, &pc, flags, status);
+    pr = parts_muladd_scalbn(&pa, &pb, &pc, scale, flags, status);
 
     return float32_round_pack_canonical(pr, status);
 }
 
-static float64 QEMU_SOFTFLOAT_ATTR
-soft_f64_muladd(float64 a, float64 b, float64 c, int flags,
-                float_status *status)
+float64 QEMU_SOFTFLOAT_ATTR
+float64_muladd_scalbn(float64 a, float64 b, float64 c,
+                      int scale, int flags, float_status *status)
 {
     FloatParts64 pa, pb, pc, *pr;
 
     float64_unpack_canonical(&pa, a, status);
     float64_unpack_canonical(&pb, b, status);
     float64_unpack_canonical(&pc, c, status);
-    pr = parts_muladd(&pa, &pb, &pc, flags, status);
+    pr = parts_muladd_scalbn(&pa, &pb, &pc, scale, flags, status);
 
     return float64_round_pack_canonical(pr, status);
 }
@@ -2323,7 +2330,7 @@ float32_muladd(float32 xa, float32 xb, float32 xc, int 
flags, float_status *s)
     return ur.s;
 
  soft:
-    return soft_f32_muladd(ua.s, ub.s, uc.s, flags, s);
+    return float32_muladd_scalbn(ua.s, ub.s, uc.s, 0, flags, s);
 }
 
 float64 QEMU_FLATTEN
@@ -2394,7 +2401,7 @@ float64_muladd(float64 xa, float64 xb, float64 xc, int 
flags, float_status *s)
     return ur.s;
 
  soft:
-    return soft_f64_muladd(ua.s, ub.s, uc.s, flags, s);
+    return float64_muladd_scalbn(ua.s, ub.s, uc.s, 0, flags, s);
 }
 
 float64 float64r32_muladd(float64 a, float64 b, float64 c,
@@ -2405,7 +2412,7 @@ float64 float64r32_muladd(float64 a, float64 b, float64 c,
     float64_unpack_canonical(&pa, a, status);
     float64_unpack_canonical(&pb, b, status);
     float64_unpack_canonical(&pc, c, status);
-    pr = parts_muladd(&pa, &pb, &pc, flags, status);
+    pr = parts_muladd_scalbn(&pa, &pb, &pc, 0, flags, status);
 
     return float64r32_round_pack_canonical(pr, status);
 }
@@ -2418,7 +2425,7 @@ bfloat16 QEMU_FLATTEN bfloat16_muladd(bfloat16 a, 
bfloat16 b, bfloat16 c,
     bfloat16_unpack_canonical(&pa, a, status);
     bfloat16_unpack_canonical(&pb, b, status);
     bfloat16_unpack_canonical(&pc, c, status);
-    pr = parts_muladd(&pa, &pb, &pc, flags, status);
+    pr = parts_muladd_scalbn(&pa, &pb, &pc, 0, flags, status);
 
     return bfloat16_round_pack_canonical(pr, status);
 }
@@ -2431,7 +2438,7 @@ float128 QEMU_FLATTEN float128_muladd(float128 a, 
float128 b, float128 c,
     float128_unpack_canonical(&pa, a, status);
     float128_unpack_canonical(&pb, b, status);
     float128_unpack_canonical(&pc, c, status);
-    pr = parts_muladd(&pa, &pb, &pc, flags, status);
+    pr = parts_muladd_scalbn(&pa, &pb, &pc, 0, flags, status);
 
     return float128_round_pack_canonical(pr, status);
 }
@@ -5249,8 +5256,9 @@ float32 float32_exp2(float32 a, float_status *status)
 
     float64_unpack_canonical(&rp, float64_one, status);
     for (i = 0 ; i < 15 ; i++) {
+
         float64_unpack_canonical(&tp, float32_exp2_coefficients[i], status);
-        rp = *parts_muladd(&tp, &xnp, &rp, 0, status);
+        rp = *parts_muladd_scalbn(&tp, &xnp, &rp, 0, 0, status);
         xnp = *parts_mul(&xnp, &xp, status);
     }
 
diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc
index ba8de7be76..4a62d6ca24 100644
--- a/fpu/softfloat-parts.c.inc
+++ b/fpu/softfloat-parts.c.inc
@@ -562,8 +562,9 @@ static FloatPartsN *partsN(mul)(FloatPartsN *a, FloatPartsN 
*b,
  * Requires A and C extracted into a double-sized structure to provide the
  * extra space for the widening multiply.
  */
-static FloatPartsN *partsN(muladd)(FloatPartsN *a, FloatPartsN *b,
-                                   FloatPartsN *c, int flags, float_status *s)
+static FloatPartsN *partsN(muladd_scalbn)(FloatPartsN *a, FloatPartsN *b,
+                                          FloatPartsN *c, int scale,
+                                          int flags, float_status *s)
 {
     int ab_mask, abc_mask;
     FloatPartsW p_widen, c_widen;
@@ -652,9 +653,11 @@ static FloatPartsN *partsN(muladd)(FloatPartsN *a, 
FloatPartsN *b,
     a->exp = p_widen.exp;
 
  return_normal:
+    /* TODO: Replace all use of float_muladd_halve_result with scale. */
     if (flags & float_muladd_halve_result) {
         a->exp -= 1;
     }
+    a->exp += scale;
  finish_sign:
     if (flags & float_muladd_negate_result) {
         a->sign ^= 1;
-- 
2.43.0