soft-fp64/fadd: Pick zero or non-zero result based on subtraction result

The main purpose of this commit is to prepare for "soft-fp64/fadd: Move
common code out of both branches of an if-statement".

Results on the 308 shaders extracted from the fp64 portion of the OpenGL
CTS:

Tiger Lake and Ice Lake had similar results. (Tiger Lake shown)
total instructions in shared programs: 817327 -> 815717 (-0.20%)
instructions in affected programs: 755504 -> 753894 (-0.21%)
helped: 73
HURT: 1
helped stats (abs) min: 1 max: 159 x̄: 22.12 x̃: 14
helped stats (rel) min: 0.05% max: 0.40% x̄: 0.22% x̃: 0.23%
HURT stats (abs)   min: 5 max: 5 x̄: 5.00 x̃: 5
HURT stats (rel)   min: 0.07% max: 0.07% x̄: 0.07% x̃: 0.07%
95% mean confidence interval for instructions value: -27.27 -16.24
95% mean confidence interval for instructions %-change: -0.24% -0.20%
Instructions are helped.

total cycles in shared programs: 6822826 -> 6820707 (-0.03%)
cycles in affected programs: 6390844 -> 6388725 (-0.03%)
helped: 71
HURT: 3
helped stats (abs) min: 2 max: 537 x̄: 30.72 x̃: 18
helped stats (rel) min: <.01% max: 0.08% x̄: 0.03% x̃: 0.03%
HURT stats (abs)   min: 10 max: 32 x̄: 20.67 x̃: 20
HURT stats (rel)   min: 0.01% max: 0.02% x̄: 0.02% x̃: 0.02%
95% mean confidence interval for cycles value: -43.41 -13.86
95% mean confidence interval for cycles %-change: -0.04% -0.03%
Cycles are helped.

Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4142>

diff --git a/src/compiler/glsl/float64.glsl b/src/compiler/glsl/float64.glsl
index 6208a37757e9d9d37ff6ba296fcc67dd7ee92712..f26d5e2926425b474e3db5e813383ed9d6aa5e0c 100644 (file)
--- a/src/compiler/glsl/float64.glsl
+++ b/src/compiler/glsl/float64.glsl
@@ -779,31 +779,26 @@ __fadd64(uint64_t a, uint64_t b)
 
       uint zFrac0 = 0;
       uint zFrac1 = 0;
 
       uint zFrac0 = 0;
       uint zFrac1 = 0;

-      bool zexp_normal = false;

       uint sign_of_difference = 0;
       if (bFracHi < aFracHi) {
          __sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, 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);
          sign_of_difference = 0x80000000;
       }
       else if (aFracHi < bFracHi) {
          __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
          sign_of_difference = 0x80000000;

-         zexp_normal = true;

       }
       else if (bFracLo < aFracLo) {
          __sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1);
       }
       else if (bFracLo < aFracLo) {
          __sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1);

-         zexp_normal = true;

       }
       else if (aFracLo < bFracLo) {
          __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
          sign_of_difference = 0x80000000;
       }
       else if (aFracLo < bFracLo) {
          __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
          sign_of_difference = 0x80000000;

-          zexp_normal = true;

       }
       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);
       }
       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);

    }
 }
 
    }
 }