diff options
author | Iago Toral Quiroga <itoral@igalia.com> | 2018-04-18 11:02:51 +0200 |
---|---|---|
committer | Juan A. Suarez Romero <jasuarez@igalia.com> | 2019-03-25 16:08:25 +0100 |
commit | 3766334923e9180c5ed98a97808dda1a2665332d (patch) | |
tree | 661b7447ce6c61082d046d18c6aad9692d46502f /src | |
parent | ca31df6f1fbc2c502644dd7be7424000dc02541c (diff) |
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>
Diffstat (limited to 'src')
-rw-r--r-- | src/compiler/nir/nir.h | 1 | ||||
-rw-r--r-- | src/compiler/nir/nir_opt_algebraic.py | 1 | ||||
-rw-r--r-- | src/intel/compiler/brw_compiler.c | 1 |
3 files changed, 3 insertions, 0 deletions
diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h index ee766d5238a7..92b17275b456 100644 --- 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 ddd8d40676f2..78e273d0e647 100644 --- 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 b588d5be97b6..a3a0a393fad1 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, \ |