diff options
| author | Eric Anholt <eric@anholt.net> | 2015-01-30 13:49:48 -0800 |
|---|---|---|
| committer | Eric Anholt <eric@anholt.net> | 2015-02-18 14:47:51 -0800 |
| commit | e5ecf8e4272522e1950d1d4318df19377bf49ae1 (patch) | |
| tree | 9dd7c90b2549a3c9870c7b4809329d5579b1e845 | |
| parent | 42a8ace66e539957b31ea96fe9a2aaacdb90f30e (diff) | |
| download | external_mesa3d-e5ecf8e4272522e1950d1d4318df19377bf49ae1.zip external_mesa3d-e5ecf8e4272522e1950d1d4318df19377bf49ae1.tar.gz external_mesa3d-e5ecf8e4272522e1950d1d4318df19377bf49ae1.tar.bz2 | |
nir: Add a flag for lowering ffma.
vc4 cse/algebraic-disabled stats:
total uniforms in shared programs: 13966 -> 13791 (-1.25%)
uniforms in affected programs: 435 -> 260 (-40.23%)
total instructions in shared programs: 44732 -> 44356 (-0.84%)
instructions in affected programs: 9599 -> 9223 (-3.92%)
v2: Rebase to master (no TGSI->NIR present)
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org> (v1)
| -rw-r--r-- | src/glsl/nir/nir.h | 1 | ||||
| -rw-r--r-- | src/glsl/nir/nir_opt_algebraic.py | 3 |
2 files changed, 3 insertions, 1 deletions
diff --git a/src/glsl/nir/nir.h b/src/glsl/nir/nir.h index 6448d4a..7be1abb 100644 --- a/src/glsl/nir/nir.h +++ b/src/glsl/nir/nir.h @@ -1327,6 +1327,7 @@ typedef struct nir_function { exec_list_get_head(&(func)->overload_list), node) typedef struct nir_shader_compiler_options { + bool lower_ffma; bool lower_fpow; bool lower_fsqrt; /** lowers fneg and ineg to fsub and isub. */ diff --git a/src/glsl/nir/nir_opt_algebraic.py b/src/glsl/nir/nir_opt_algebraic.py index 8d5c03b..83a02b6 100644 --- a/src/glsl/nir/nir_opt_algebraic.py +++ b/src/glsl/nir/nir_opt_algebraic.py @@ -71,7 +71,8 @@ optimizations = [ (('flrp', a, b, 1.0), b), (('flrp', a, a, b), a), (('flrp', 0.0, a, b), ('fmul', a, b)), - (('fadd', ('fmul', a, b), c), ('ffma', a, b, c)), + (('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'), + (('fadd', ('fmul', a, b), c), ('ffma', a, b, c), '!options->lower_ffma'), # Comparison simplifications (('inot', ('flt', a, b)), ('fge', a, b)), (('inot', ('fge', a, b)), ('flt', a, b)), |