Merge remote-tracking branch 'mesa-public/master' into vulkan

[mesa.git] / src / compiler / nir / nir_opt_algebraic.py

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 50d37ea37f10a16245e469215ca7fbcb74f55066..d4f4a3d903c23d91a648d632752cc4c1d6fee3c3 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -1,4 +1,5 @@
 #! /usr/bin/env python
+# -*- encoding: utf-8 -*-
 #
 # Copyright (C) 2014 Intel Corporation
 #
@@ -74,6 +75,7 @@ optimizations = [
    (('imul', a, 1), a),
    (('fmul', a, -1.0), ('fneg', a)),
    (('imul', a, -1), ('ineg', a)),
+   (('fdiv', a, b), ('fmul', a, ('frcp', b)), 'options->lower_fdiv'),
    (('ffma', 0.0, a, b), b),
    (('ffma', a, 0.0, b), b),
    (('ffma', a, b, 0.0), ('fmul', a, b)),
@@ -225,8 +227,11 @@ optimizations = [
 
    # Misc. lowering
    (('fmod', a, b), ('fsub', a, ('fmul', b, ('ffloor', ('fdiv', a, b)))), 'options->lower_fmod'),
+   (('frem', a, b), ('fsub', a, ('fmul', b, ('ftrunc', ('fdiv', a, b)))), 'options->lower_fmod'),
    (('uadd_carry', a, b), ('b2i', ('ult', ('iadd', a, b), a)), 'options->lower_uadd_carry'),
    (('usub_borrow', a, b), ('b2i', ('ult', a, b)), 'options->lower_usub_borrow'),
+   (('ldexp', 'x', 'exp'),
+    ('fmul', 'x', ('ishl', ('imin', ('imax', ('iadd', 'exp', 0x7f), 0), 0xff), 23))),
 
    (('bitfield_insert', 'base', 'insert', 'offset', 'bits'),
     ('bcsel', ('ilt', 31, 'bits'), 'insert',
@@ -258,6 +263,54 @@ optimizations = [
    (('extract_u16', a, b),
     ('iand', ('ushr', a, ('imul', b, 16)), 0xffff),
     'options->lower_extract_word'),
+
+    (('pack_unorm_2x16', 'v'),
+     ('pack_uvec2_to_uint',
+        ('f2u', ('fround_even', ('fmul', ('fsat', 'v'), 65535.0)))),
+     'options->lower_pack_unorm_2x16'),
+
+    (('pack_unorm_4x8', 'v'),
+     ('pack_uvec4_to_uint',
+        ('f2u', ('fround_even', ('fmul', ('fsat', 'v'), 255.0)))),
+     'options->lower_pack_unorm_4x8'),
+
+    (('pack_snorm_2x16', 'v'),
+     ('pack_uvec2_to_uint',
+        ('f2i', ('fround_even', ('fmul', ('fmin', 1.0, ('fmax', -1.0, 'v')), 32767.0)))),
+     'options->lower_pack_snorm_2x16'),
+
+    (('pack_snorm_4x8', 'v'),
+     ('pack_uvec4_to_uint',
+        ('f2i', ('fround_even', ('fmul', ('fmin', 1.0, ('fmax', -1.0, 'v')), 127.0)))),
+     'options->lower_pack_snorm_4x8'),
+
+    (('unpack_unorm_2x16', 'v'),
+     ('fdiv', ('u2f', ('vec2', ('extract_u16', 'v', 0),
+                               ('extract_u16', 'v', 1))),
+              65535.0),
+     'options->lower_unpack_unorm_2x16'),
+
+    (('unpack_unorm_4x8', 'v'),
+     ('fdiv', ('u2f', ('vec4', ('extract_u8', 'v', 0),
+                               ('extract_u8', 'v', 1),
+                               ('extract_u8', 'v', 2),
+                               ('extract_u8', 'v', 3))),
+              255.0),
+     'options->lower_unpack_unorm_4x8'),
+
+    (('unpack_snorm_2x16', 'v'),
+     ('fmin', 1.0, ('fmax', -1.0, ('fdiv', ('i2f', ('vec2', ('extract_i16', 'v', 0),
+                                                            ('extract_i16', 'v', 1))),
+                                           32767.0))),
+     'options->lower_unpack_snorm_2x16'),
+
+    (('unpack_snorm_4x8', 'v'),
+     ('fmin', 1.0, ('fmax', -1.0, ('fdiv', ('i2f', ('vec4', ('extract_i8', 'v', 0),
+                                                            ('extract_i8', 'v', 1),
+                                                            ('extract_i8', 'v', 2),
+                                                            ('extract_i8', 'v', 3))),
+                                           127.0))),
+     'options->lower_unpack_snorm_4x8'),
 ]
 
 # Add optimizations to handle the case where the result of a ternary is