[Mesa-dev] [PATCH v4 11/40] compiler/nir: add lowering for 16-bit flrp

[Iago Toral Quiroga]

And enable it on Intel.

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

Reviewed-by: Jason Ekstrand <jason at jlekstrand.net>
---
 src/compiler/nir/nir.h                | 1 +
 src/compiler/nir/nir_opt_algebraic.py | 1 +
 src/intel/compiler/brw_compiler.c     | 1 +
 3 files changed, 3 insertions(+)

diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h
index 6547a468648..740c64d2a94 100644
--- a/src/compiler/nir/nir.h
+++ b/src/compiler/nir/nir.h
@@ -2113,6 +2113,7 @@ 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 cd969de1f88..40eb3de02c3 100644
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -124,6 +124,7 @@ optimizations = [
    (('~flrp', 0.0, a, b), ('fmul', a, b)),
    (('~flrp', a, b, ('b2f', 'c at 1')), ('bcsel', c, b, a), 'options->lower_flrp32'),
    (('~flrp', a, 0.0, c), ('fadd', ('fmul', ('fneg', a), c), a)),
+   (('flrp at 16', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp16'),
    (('flrp at 32', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp32'),
    (('flrp at 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 f885e79c3e6..04a1a7cac4e 100644
--- 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,                                                     \
-- 
2.17.1