nir: add imprecise flrp optimisation

On BDW:

total instructions in shared programs: 13061890 -> 13061877 (-0.00%)
instructions in affected programs: 2441 -> 2428 (-0.53%)
helped: 13
HURT: 0

total cycles in shared programs: 256612254 -> 256611784 (-0.00%)
cycles in affected programs: 16418 -> 15948 (-2.86%)
helped: 10
HURT: 2

V2: don't use ffma directly

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 85cdc7bdaf9072d0aa0b8c6c783840b81d31a490..57e386279cdf3b2061e96b2e64b62d93bae1463f 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -112,6 +112,7 @@ optimizations = [
    (('~flrp', a, a, b), a),
    (('~flrp', 0.0, a, b), ('fmul', a, b)),
    (('~flrp', a, b, ('b2f', c)), ('bcsel', c, b, a), 'options->lower_flrp32'),
+   (('~flrp', a, 0.0, c), ('fadd', ('fmul', ('fneg', a), c), a)),
    (('flrp@32', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp32'),
    (('flrp@64', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp64'),
    (('ffract', a), ('fsub', a, ('ffloor', a)), 'options->lower_ffract'),