softfloat: Move sf_canonicalize to softfloat-parts.c.inc

At the same time, convert to pointers, rename to parts$N_canonicalize
and define a macro for parts_canonicalize using QEMU_GENERIC.

Rearrange the cases to recognize float_class_normal as
early as possible.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

2 files changed, 112 insertions, 38 deletions

diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc
index a78d61e..25bf99b 100644
--- a/fpu/softfloat-parts.c.inc
+++ b/fpu/softfloat-parts.c.inc
@@ -100,3 +100,36 @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b,
     }
     return a;
 }
+
+/*
+ * Canonicalize the FloatParts structure.  Determine the class,
+ * unbias the exponent, and normalize the fraction.
+ */
+static void partsN(canonicalize)(FloatPartsN *p, float_status *status,
+                                 const FloatFmt *fmt)
+{
+    if (unlikely(p->exp == 0)) {
+        if (likely(frac_eqz(p))) {
+            p->cls = float_class_zero;
+        } else if (status->flush_inputs_to_zero) {
+            float_raise(float_flag_input_denormal, status);
+            p->cls = float_class_zero;
+            frac_clear(p);
+        } else {
+            int shift = frac_normalize(p);
+            p->cls = float_class_normal;
+            p->exp = fmt->frac_shift - fmt->exp_bias - shift + 1;
+        }
+    } else if (likely(p->exp < fmt->exp_max) || fmt->arm_althp) {
+        p->cls = float_class_normal;
+        p->exp -= fmt->exp_bias;
+        frac_shl(p, fmt->frac_shift);
+        p->frac_hi |= DECOMPOSED_IMPLICIT_BIT;
+    } else if (likely(frac_eqz(p))) {
+        p->cls = float_class_inf;
+    } else {
+        frac_shl(p, fmt->frac_shift);
+        p->cls = (parts_is_snan_frac(p->frac_hi, status)
+                  ? float_class_snan : float_class_qnan);
+    }
+}
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index df004db..535261d 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -733,6 +733,14 @@ static FloatParts128 *parts128_pick_nan_muladd(FloatParts128 *a,
 #define parts_pick_nan_muladd(A, B, C, S, ABM, ABCM) \
     PARTS_GENERIC_64_128(pick_nan_muladd, A)(A, B, C, S, ABM, ABCM)
 
+static void parts64_canonicalize(FloatParts64 *p, float_status *status,
+                                 const FloatFmt *fmt);
+static void parts128_canonicalize(FloatParts128 *p, float_status *status,
+                                  const FloatFmt *fmt);
+
+#define parts_canonicalize(A, S, F) \
+    PARTS_GENERIC_64_128(canonicalize, A)(A, S, F)
+
 /*
  * Helper functions for softfloat-parts.c.inc, per-size operations.
  */
@@ -759,53 +767,86 @@ static int frac128_cmp(FloatParts128 *a, FloatParts128 *b)
 
 #define frac_cmp(A, B)  FRAC_GENERIC_64_128(cmp, A)(A, B)
 
-static void frac128_shl(FloatParts128 *a, int c)
+static void frac64_clear(FloatParts64 *a)
 {
-    shift128Left(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+    a->frac = 0;
+}
+
+static void frac128_clear(FloatParts128 *a)
+{
+    a->frac_hi = a->frac_lo = 0;
 }
 
-#define frac_shl(A, C)             frac128_shl(A, C)
+#define frac_clear(A)  FRAC_GENERIC_64_128(clear, A)(A)
 
-static void frac128_shr(FloatParts128 *a, int c)
+static bool frac64_eqz(FloatParts64 *a)
 {
-    shift128Right(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+    return a->frac == 0;
+}
+
+static bool frac128_eqz(FloatParts128 *a)
+{
+    return (a->frac_hi | a->frac_lo) == 0;
 }
 
-#define frac_shr(A, C)             frac128_shr(A, C)
+#define frac_eqz(A)  FRAC_GENERIC_64_128(eqz, A)(A)
 
-/* Canonicalize EXP and FRAC, setting CLS.  */
-static FloatParts64 sf_canonicalize(FloatParts64 part, const FloatFmt *parm,
-                                  float_status *status)
+static int frac64_normalize(FloatParts64 *a)
 {
-    if (part.exp == parm->exp_max && !parm->arm_althp) {
-        if (part.frac == 0) {
-            part.cls = float_class_inf;
-        } else {
-            part.frac <<= parm->frac_shift;
-            part.cls = (parts_is_snan_frac(part.frac, status)
-                        ? float_class_snan : float_class_qnan);
-        }
-    } else if (part.exp == 0) {
-        if (likely(part.frac == 0)) {
-            part.cls = float_class_zero;
-        } else if (status->flush_inputs_to_zero) {
-            float_raise(float_flag_input_denormal, status);
-            part.cls = float_class_zero;
-            part.frac = 0;
-        } else {
-            int shift = clz64(part.frac);
-            part.cls = float_class_normal;
-            part.exp = parm->frac_shift - parm->exp_bias - shift + 1;
-            part.frac <<= shift;
+    if (a->frac) {
+        int shift = clz64(a->frac);
+        a->frac <<= shift;
+        return shift;
+    }
+    return 64;
+}
+
+static int frac128_normalize(FloatParts128 *a)
+{
+    if (a->frac_hi) {
+        int shl = clz64(a->frac_hi);
+        if (shl) {
+            int shr = 64 - shl;
+            a->frac_hi = (a->frac_hi << shl) | (a->frac_lo >> shr);
+            a->frac_lo = (a->frac_lo << shl);
         }
-    } else {
-        part.cls = float_class_normal;
-        part.exp -= parm->exp_bias;
-        part.frac = DECOMPOSED_IMPLICIT_BIT + (part.frac << parm->frac_shift);
+        return shl;
+    } else if (a->frac_lo) {
+        int shl = clz64(a->frac_lo);
+        a->frac_hi = (a->frac_lo << shl);
+        a->frac_lo = 0;
+        return shl + 64;
     }
-    return part;
+    return 128;
 }
 
+#define frac_normalize(A)  FRAC_GENERIC_64_128(normalize, A)(A)
+
+static void frac64_shl(FloatParts64 *a, int c)
+{
+    a->frac <<= c;
+}
+
+static void frac128_shl(FloatParts128 *a, int c)
+{
+    shift128Left(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+}
+
+#define frac_shl(A, C)  FRAC_GENERIC_64_128(shl, A)(A, C)
+
+static void frac64_shr(FloatParts64 *a, int c)
+{
+    a->frac >>= c;
+}
+
+static void frac128_shr(FloatParts128 *a, int c)
+{
+    shift128Right(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+}
+
+#define frac_shr(A, C)  FRAC_GENERIC_64_128(shr, A)(A, C)
+
+
 /* Round and uncanonicalize a floating-point number by parts. There
  * are FRAC_SHIFT bits that may require rounding at the bottom of the
  * fraction; these bits will be removed. The exponent will be biased
@@ -984,7 +1025,7 @@ static void float16a_unpack_canonical(FloatParts64 *p, float16 f,
                                       float_status *s, const FloatFmt *params)
 {
     float16_unpack_raw(p, f);
-    *p = sf_canonicalize(*p, params, s);
+    parts_canonicalize(p, s, params);
 }
 
 static void float16_unpack_canonical(FloatParts64 *p, float16 f,
@@ -997,7 +1038,7 @@ static void bfloat16_unpack_canonical(FloatParts64 *p, bfloat16 f,
                                       float_status *s)
 {
     bfloat16_unpack_raw(p, f);
-    *p = sf_canonicalize(*p, &bfloat16_params, s);
+    parts_canonicalize(p, s, &bfloat16_params);
 }
 
 static float16 float16a_round_pack_canonical(FloatParts64 *p,
@@ -1025,7 +1066,7 @@ static void float32_unpack_canonical(FloatParts64 *p, float32 f,
                                      float_status *s)
 {
     float32_unpack_raw(p, f);
-    *p = sf_canonicalize(*p, &float32_params, s);
+    parts_canonicalize(p, s, &float32_params);
 }
 
 static float32 float32_round_pack_canonical(FloatParts64 *p,
@@ -1039,7 +1080,7 @@ static void float64_unpack_canonical(FloatParts64 *p, float64 f,
                                      float_status *s)
 {
     float64_unpack_raw(p, f);
-    *p = sf_canonicalize(*p, &float64_params, s);
+    parts_canonicalize(p, s, &float64_params);
 }
 
 static float64 float64_round_pack_canonical(FloatParts64 *p,