compiler/nir: add lowering for 16-bit flrp

And enable it on Intel.

v2:
 - Squash the change to enable it 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 ee766d5238a76d9fe9de1167763c67eb2a462e56..92b17275b456b121f0303bb1d3f56cbabecabf20 100644 (file)
--- a/src/compiler/nir/nir.h
+++ b/src/compiler/nir/nir.h
@@ -2163,6 +2163,7 @@ typedef struct nir_shader_compiler_options {
    bool lower_fdiv;
    bool lower_ffma;
    bool fuse_ffma;
+   bool lower_flrp16;
    bool lower_flrp32;
    /** Lowers flrp when it does not support doubles */
    bool lower_flrp64;

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index ddd8d40676f2a7e9ff7db4c34973db7435ed7971..78e273d0e6471a7f15f24cef2008dc27ac85a90f 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -128,6 +128,7 @@ optimizations = [
    (('~flrp', 0.0, a, b), ('fmul', a, b)),
    (('~flrp', a, b, ('b2f', 'c@1')), ('bcsel', c, b, a), 'options->lower_flrp32'),
    (('~flrp', a, 0.0, c), ('fadd', ('fmul', ('fneg', a), c), a)),
+   (('flrp@16', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp16'),
    (('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'),
    (('ffloor', a), ('fsub', a, ('ffract', a)), 'options->lower_ffloor'),

diff --git a/src/intel/compiler/brw_compiler.c b/src/intel/compiler/brw_compiler.c
index b588d5be97b695d9b6e66fb112ed617152f07f57..a3a0a393fad1cd703e16e640fa2bec4e3283eefe 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_flrp16 = true,                                                      \
    .lower_fmod16 = true,                                                      \
    .lower_fmod32 = true,                                                      \
    .lower_fmod64 = false,                                                     \