glsl: Add implementation of inverse() for mat2/3/4.

This is taken from the ogl-math project, with Inverse renamed to adj
(since it's not actually the inverse), transposed, and our types
plugged in.  There are potential CSE opportunities in this code
(particularly for hardware with RCP but not DIV), but we should be
doing CSE anyway, so don't hand-optimize.

Fixes piglit inverse tests.

Acked-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/glsl/Makefile b/src/glsl/Makefile
index f6c722997e3295cbd28c7f4d922647e1e80c6dc3..7c80c95d804c3eca2357fbf589ae470de1cbbbeb 100644 (file)
--- a/src/glsl/Makefile
+++ b/src/glsl/Makefile
@@ -165,7 +165,7 @@ glcpp/glcpp-parse.c: glcpp/glcpp-parse.y
 builtin_compiler: $(GLSL2_OBJECTS) $(OBJECTS) builtin_stubs.o
        $(APP_CXX) $(INCLUDES) $(CXXFLAGS) $(LDFLAGS) $(OBJECTS) $(GLSL2_OBJECTS) builtin_stubs.o -o $@
 
-builtin_function.cpp: builtins/profiles/* builtins/ir/* builtins/tools/generate_builtins.py builtins/tools/texture_builtins.py builtin_compiler
+builtin_function.cpp: builtins/profiles/* builtins/ir/* builtins/glsl/* builtins/tools/generate_builtins.py builtins/tools/texture_builtins.py builtin_compiler
        @echo Regenerating builtin_function.cpp...
        $(PYTHON2) $(PYTHON_FLAGS) builtins/tools/generate_builtins.py ./builtin_compiler > builtin_function.cpp || rm -f builtin_function.cpp
 

diff --git a/src/glsl/builtins/glsl/inverse.glsl b/src/glsl/builtins/glsl/inverse.glsl
new file mode 100644 (file)
index 0000000..ffb84f9
--- /dev/null
+++ b/src/glsl/builtins/glsl/inverse.glsl
@@ -0,0 +1,106 @@
+/* Copyright (c) 2005 - 2012 G-Truc Creation (www.g-truc.net)
+ * Copyright © 2012 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#version 120
+mat2 inverse(mat2 m)
+{
+   mat2 adj;
+   adj[0][0] = m[1][1];
+   adj[0][1] = -m[0][1];
+   adj[1][0] = -m[1][0];
+   adj[1][1] = m[0][0];
+   float det = m[0][0] * m[1][1] - m[1][0] * m[0][1];
+   return adj / det;
+}
+
+mat3 inverse(mat3 m)
+{
+   mat3 adj;
+   adj[0][0] = + (m[1][1] * m[2][2] - m[2][1] * m[1][2]);
+   adj[1][0] = - (m[1][0] * m[2][2] - m[2][0] * m[1][2]);
+   adj[2][0] = + (m[1][0] * m[2][1] - m[2][0] * m[1][1]);
+   adj[0][1] = - (m[0][1] * m[2][2] - m[2][1] * m[0][2]);
+   adj[1][1] = + (m[0][0] * m[2][2] - m[2][0] * m[0][2]);
+   adj[2][1] = - (m[0][0] * m[2][1] - m[2][0] * m[0][1]);
+   adj[0][2] = + (m[0][1] * m[1][2] - m[1][1] * m[0][2]);
+   adj[1][2] = - (m[0][0] * m[1][2] - m[1][0] * m[0][2]);
+   adj[2][2] = + (m[0][0] * m[1][1] - m[1][0] * m[0][1]);
+
+   float det = (+ m[0][0] * (m[1][1] * m[2][2] - m[1][2] * m[2][1])
+               - m[0][1] * (m[1][0] * m[2][2] - m[1][2] * m[2][0])
+               + m[0][2] * (m[1][0] * m[2][1] - m[1][1] * m[2][0]));
+
+   return adj / det;
+}
+
+mat4 inverse(mat4 m)
+{
+   float SubFactor00 = m[2][2] * m[3][3] - m[3][2] * m[2][3];
+   float SubFactor01 = m[2][1] * m[3][3] - m[3][1] * m[2][3];
+   float SubFactor02 = m[2][1] * m[3][2] - m[3][1] * m[2][2];
+   float SubFactor03 = m[2][0] * m[3][3] - m[3][0] * m[2][3];
+   float SubFactor04 = m[2][0] * m[3][2] - m[3][0] * m[2][2];
+   float SubFactor05 = m[2][0] * m[3][1] - m[3][0] * m[2][1];
+   float SubFactor06 = m[1][2] * m[3][3] - m[3][2] * m[1][3];
+   float SubFactor07 = m[1][1] * m[3][3] - m[3][1] * m[1][3];
+   float SubFactor08 = m[1][1] * m[3][2] - m[3][1] * m[1][2];
+   float SubFactor09 = m[1][0] * m[3][3] - m[3][0] * m[1][3];
+   float SubFactor10 = m[1][0] * m[3][2] - m[3][0] * m[1][2];
+   float SubFactor11 = m[1][1] * m[3][3] - m[3][1] * m[1][3];
+   float SubFactor12 = m[1][0] * m[3][1] - m[3][0] * m[1][1];
+   float SubFactor13 = m[1][2] * m[2][3] - m[2][2] * m[1][3];
+   float SubFactor14 = m[1][1] * m[2][3] - m[2][1] * m[1][3];
+   float SubFactor15 = m[1][1] * m[2][2] - m[2][1] * m[1][2];
+   float SubFactor16 = m[1][0] * m[2][3] - m[2][0] * m[1][3];
+   float SubFactor17 = m[1][0] * m[2][2] - m[2][0] * m[1][2];
+   float SubFactor18 = m[1][0] * m[2][1] - m[2][0] * m[1][1];
+
+   mat4 adj;
+
+   adj[0][0] = + (m[1][1] * SubFactor00 - m[1][2] * SubFactor01 + m[1][3] * SubFactor02);
+   adj[1][0] = - (m[1][0] * SubFactor00 - m[1][2] * SubFactor03 + m[1][3] * SubFactor04);
+   adj[2][0] = + (m[1][0] * SubFactor01 - m[1][1] * SubFactor03 + m[1][3] * SubFactor05);
+   adj[3][0] = - (m[1][0] * SubFactor02 - m[1][1] * SubFactor04 + m[1][2] * SubFactor05);
+
+   adj[0][1] = - (m[0][1] * SubFactor00 - m[0][2] * SubFactor01 + m[0][3] * SubFactor02);
+   adj[1][1] = + (m[0][0] * SubFactor00 - m[0][2] * SubFactor03 + m[0][3] * SubFactor04);
+   adj[2][1] = - (m[0][0] * SubFactor01 - m[0][1] * SubFactor03 + m[0][3] * SubFactor05);
+   adj[3][1] = + (m[0][0] * SubFactor02 - m[0][1] * SubFactor04 + m[0][2] * SubFactor05);
+
+   adj[0][2] = + (m[0][1] * SubFactor06 - m[0][2] * SubFactor07 + m[0][3] * SubFactor08);
+   adj[1][2] = - (m[0][0] * SubFactor06 - m[0][2] * SubFactor09 + m[0][3] * SubFactor10);
+   adj[2][2] = + (m[0][0] * SubFactor11 - m[0][1] * SubFactor09 + m[0][3] * SubFactor12);
+   adj[3][2] = - (m[0][0] * SubFactor08 - m[0][1] * SubFactor10 + m[0][2] * SubFactor12);
+
+   adj[0][3] = - (m[0][1] * SubFactor13 - m[0][2] * SubFactor14 + m[0][3] * SubFactor15);
+   adj[1][3] = + (m[0][0] * SubFactor13 - m[0][2] * SubFactor16 + m[0][3] * SubFactor17);
+   adj[2][3] = - (m[0][0] * SubFactor14 - m[0][1] * SubFactor16 + m[0][3] * SubFactor18);
+   adj[3][3] = + (m[0][0] * SubFactor15 - m[0][1] * SubFactor17 + m[0][2] * SubFactor18);
+
+   float det = (+ m[0][0] * adj[0][0]
+               + m[0][1] * adj[1][0]
+               + m[0][2] * adj[2][0]
+               + m[0][3] * adj[3][0]);
+
+   return adj / det;
+}
+

diff --git a/src/glsl/builtins/profiles/140.glsl b/src/glsl/builtins/profiles/140.glsl
index 159e89def457decc42e813cd05efb0f7e78f488f..90e04816d4e127543136dcefefabcff0778efefb 100644 (file)
--- a/src/glsl/builtins/profiles/140.glsl
+++ b/src/glsl/builtins/profiles/140.glsl
@@ -383,6 +383,10 @@ mat4x2 transpose(mat2x4 m);
 mat3x4 transpose(mat4x3 m);
 mat4x3 transpose(mat3x4 m);
 
+mat2 inverse(mat2 m);
+mat3 inverse(mat3 m);
+mat4 inverse(mat4 m);
+
 /*
  * 8.6 - Vector Relational Functions
  */