soft-fp64/fadd: Rename aFrac and bFrac variables

[mesa.git] / src / compiler / glsl / float64.glsl

diff --git a/src/compiler/glsl/float64.glsl b/src/compiler/glsl/float64.glsl
index 3cc8aa7fa4b4e6adde8696efb3acc278312e1be1..cdecfdb8dbbdacfb595a66b5b676db1832d8b2ff 100644 (file)
--- a/src/compiler/glsl/float64.glsl
+++ b/src/compiler/glsl/float64.glsl
@@ -661,6 +661,17 @@ __propagateFloat64NaN(uint64_t __a, uint64_t __b)
 #endif
 }
 
+/* If a shader is in the soft-fp64 path, it almost certainly has register
+ * pressure problems.  Choose a method to exchange two values that does not
+ * require a temporary.
+ */
+#define EXCHANGE(a, b) \
+   do {                \
+       a ^= b;         \
+       b ^= a;         \
+       a ^= b;         \
+   } while (false)
+
 /* Returns the result of adding the double-precision floating-point values
  * `a' and `b'.  The operation is performed according to the IEEE Standard for
  * Floating-Point Arithmetic.
@@ -676,15 +687,14 @@ __fadd64(uint64_t a, uint64_t b)
    uint bFracHi = __extractFloat64FracHi(b);
    int aExp = __extractFloat64Exp(a);
    int bExp = __extractFloat64Exp(b);
-   uint zFrac0 = 0u;
-   uint zFrac1 = 0u;
    int expDiff = aExp - bExp;
    if (aSign == bSign) {
-      uint zFrac2 = 0u;
+      uint zFrac0;
+      uint zFrac1;
+      uint zFrac2;
       int zExp;
-      bool orig_exp_diff_is_zero = (expDiff == 0);
 
-      if (orig_exp_diff_is_zero) {
+      if (expDiff == 0) {
          if (aExp == 0x7FF) {
             bool propagate = ((aFracHi | bFracHi) | (aFracLo| bFracLo)) != 0u;
             return mix(a, __propagateFloat64NaN(a, b), propagate);
@@ -697,29 +707,34 @@ __fadd64(uint64_t a, uint64_t b)
          zExp = aExp;
          __shift64ExtraRightJamming(
             zFrac0, zFrac1, zFrac2, 1, zFrac0, zFrac1, zFrac2);
-      } else if (0 < expDiff) {
-         if (aExp == 0x7FF) {
-            bool propagate = (aFracHi | aFracLo) != 0u;
-            return mix(a, __propagateFloat64NaN(a, b), propagate);
-         }
+      } else {
+         if (0 < expDiff) {
+            if (aExp == 0x7FF) {
+               bool propagate = (aFracHi | aFracLo) != 0u;
+               return mix(a, __propagateFloat64NaN(a, b), propagate);
+            }
 
-         expDiff = mix(expDiff, expDiff - 1, bExp == 0);
-         bFracHi = mix(bFracHi | 0x00100000u, bFracHi, bExp == 0);
-         __shift64ExtraRightJamming(
-            bFracHi, bFracLo, 0u, expDiff, bFracHi, bFracLo, zFrac2);
-         zExp = aExp;
-      } else if (expDiff < 0) {
-         if (bExp == 0x7FF) {
-            bool propagate = (bFracHi | bFracLo) != 0u;
-            return mix(__packFloat64(aSign, 0x7ff, 0u, 0u), __propagateFloat64NaN(a, b), propagate);
+            expDiff = mix(expDiff, expDiff - 1, bExp == 0);
+            bFracHi = mix(bFracHi | 0x00100000u, bFracHi, bExp == 0);
+            __shift64ExtraRightJamming(
+               bFracHi, bFracLo, 0u, expDiff, bFracHi, bFracLo, zFrac2);
+            zExp = aExp;
+         } else {
+            EXCHANGE(aFracHi, bFracHi);
+            EXCHANGE(aFracLo, bFracLo);
+            EXCHANGE(aExp, bExp);
+
+            if (aExp == 0x7FF) {
+               bool propagate = (aFracHi | aFracLo) != 0u;
+               return mix(__packFloat64(aSign, 0x7ff, 0u, 0u), __propagateFloat64NaN(a, b), propagate);
+            }
+            expDiff = mix(expDiff, expDiff + 1, bExp == 0);
+            bFracHi = mix(bFracHi | 0x00100000u, bFracHi, bExp == 0);
+            __shift64ExtraRightJamming(
+               bFracHi, bFracLo, 0u, - expDiff, bFracHi, bFracLo, zFrac2);
+            zExp = aExp;
          }
-         expDiff = mix(expDiff, expDiff + 1, aExp == 0);
-         aFracHi = mix(aFracHi | 0x00100000u, aFracHi, aExp == 0);
-         __shift64ExtraRightJamming(
-            aFracHi, aFracLo, 0u, - expDiff, aFracHi, aFracLo, zFrac2);
-         zExp = bExp;
-      }
-      if (!orig_exp_diff_is_zero) {
+
          aFracHi |= 0x00100000u;
          __add64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1);
          --zExp;
@@ -736,6 +751,9 @@ __fadd64(uint64_t a, uint64_t b)
       __shortShift64Left(aFracHi, aFracLo, 10, aFracHi, aFracLo);
       __shortShift64Left(bFracHi, bFracLo, 10, bFracHi, bFracLo);
       if (0 < expDiff) {
+         uint zFrac0;
+         uint zFrac1;
+
          if (aExp == 0x7FF) {
             bool propagate = (aFracHi | aFracLo) != 0u;
             return mix(a, __propagateFloat64NaN(a, b), propagate);
@@ -750,6 +768,9 @@ __fadd64(uint64_t a, uint64_t b)
          return __normalizeRoundAndPackFloat64(aSign, zExp - 10, zFrac0, zFrac1);
       }
       if (expDiff < 0) {
+         uint zFrac0;
+         uint zFrac1;
+
          if (bExp == 0x7FF) {
             bool propagate = (bFracHi | bFracLo) != 0u;
             return mix(__packFloat64(aSign ^ 0x80000000u, 0x7ff, 0u, 0u), __propagateFloat64NaN(a, b), propagate);
@@ -770,31 +791,30 @@ __fadd64(uint64_t a, uint64_t b)
       }
       bExp = mix(bExp, 1, aExp == 0);
       aExp = mix(aExp, 1, aExp == 0);
-      bool zexp_normal = false;
-      bool blta = true;
+
+      uint zFrac0;
+      uint zFrac1;
+      uint sign_of_difference = 0;
       if (bFracHi < aFracHi) {
          __sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1);
-         zexp_normal = true;
       }
       else if (aFracHi < bFracHi) {
          __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
-         blta = false;
-         zexp_normal = true;
+         sign_of_difference = 0x80000000;
       }
-      else if (bFracLo < aFracLo) {
+      else if (bFracLo <= aFracLo) {
+         /* It is possible that zFrac0 and zFrac1 may be zero after this. */
          __sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1);
-         zexp_normal = true;
       }
-      else if (aFracLo < bFracLo) {
+      else {
          __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
-          blta = false;
-          zexp_normal = true;
+         sign_of_difference = 0x80000000;
       }
-      zExp = mix(bExp, aExp, blta);
-      aSign = mix(aSign ^ 0x80000000u, aSign, blta);
+      zExp = mix(bExp, aExp, sign_of_difference == 0u);
+      aSign ^= sign_of_difference;
       uint64_t retval_0 = __packFloat64(uint(FLOAT_ROUNDING_MODE == FLOAT_ROUND_DOWN) << 31, 0, 0u, 0u);
       uint64_t retval_1 = __normalizeRoundAndPackFloat64(aSign, zExp - 11, zFrac0, zFrac1);
-      return mix(retval_0, retval_1, zexp_normal);
+      return mix(retval_0, retval_1, zFrac0 != 0u || zFrac1 != 0u);
    }
 }