compiler/nir: add lowering option for 16-bit fmod

And enable it on Intel.

v2:
 - Squash the change to enable this lowering on Intel (Jason)

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

diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h
index b6a2ba7ec8c31e53180f22f15a0e6af64ad9e2a3..ee766d5238a76d9fe9de1167763c67eb2a462e56 100644 (file)
--- a/src/compiler/nir/nir.h
+++ b/src/compiler/nir/nir.h
@@ -2169,6 +2169,7 @@ typedef struct nir_shader_compiler_options {
    bool lower_fpow;
    bool lower_fsat;
    bool lower_fsqrt;
+   bool lower_fmod16;
    bool lower_fmod32;
    bool lower_fmod64;
    /** Lowers ibitfield_extract/ubitfield_extract to ibfe/ubfe. */

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 3326bbef684088e61511d56a42b71b0d719ee71d..ddd8d40676f2a7e9ff7db4c34973db7435ed7971 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -674,6 +674,7 @@ optimizations = [
    (('bcsel', ('ine', a, -1), ('ifind_msb', a), -1), ('ifind_msb', a)),
 
    # Misc. lowering
+   (('fmod@16', a, b), ('fsub', a, ('fmul', b, ('ffloor', ('fdiv', a, b)))), 'options->lower_fmod16'),
    (('fmod@32', a, b), ('fsub', a, ('fmul', b, ('ffloor', ('fdiv', a, b)))), 'options->lower_fmod32'),
    (('fmod@64', a, b), ('fsub', a, ('fmul', b, ('ffloor', ('fdiv', a, b)))), 'options->lower_fmod64'),
    (('frem', a, b), ('fsub', a, ('fmul', b, ('ftrunc', ('fdiv', a, b)))), 'options->lower_fmod32'),

diff --git a/src/intel/compiler/brw_compiler.c b/src/intel/compiler/brw_compiler.c
index 4fa02ca4d100ad6fca6cb87b8ce6df9864e13bb1..b588d5be97b695d9b6e66fb112ed617152f07f57 100644 (file)
--- a/src/intel/compiler/brw_compiler.c
+++ b/src/intel/compiler/brw_compiler.c
@@ -33,6 +33,7 @@
    .lower_sub = true,                                                         \
    .lower_fdiv = true,                                                        \
    .lower_scmp = true,                                                        \
+   .lower_fmod16 = true,                                                      \
    .lower_fmod32 = true,                                                      \
    .lower_fmod64 = false,                                                     \
    .lower_bitfield_extract = true,                                            \