3 files changed, 42 insertions, 0 deletions
diff --git a/src/glsl/nir/nir.h b/src/glsl/nir/nir.h
index 23aec69..11add65 100644
--- a/src/glsl/nir/nir.h
+++ b/src/glsl/nir/nir.h
@@ -1447,6 +1447,7 @@ typedef struct nir_shader_compiler_options {
    bool lower_fsat;
    bool lower_fsqrt;
    bool lower_fmod;
+   bool lower_bitfield_extract;
    bool lower_bitfield_insert;
    bool lower_uadd_carry;
    bool lower_usub_borrow;
diff --git a/src/glsl/nir/nir_opcodes.py b/src/glsl/nir/nir_opcodes.py
index 3e43438..e79810c 100644
--- a/src/glsl/nir/nir_opcodes.py
+++ b/src/glsl/nir/nir_opcodes.py
@@ -573,6 +573,37 @@ if (mask == 0) {
 }
 """)
 
+# SM5 ubfe/ibfe assembly
+opcode("ubfe", 0, tuint,
+       [0, 0, 0], [tuint, tint, tint], "", """
+unsigned base = src0;
+int offset = src1, bits = src2;
+if (bits == 0) {
+   dst = 0;
+} else if (bits < 0 || offset < 0) {
+   dst = 0; /* undefined */
+} else if (offset + bits < 32) {
+   dst = (base << (32 - bits - offset)) >> (32 - bits);
+} else {
+   dst = base >> offset;
+}
+""")
+opcode("ibfe", 0, tint,
+       [0, 0, 0], [tint, tint, tint], "", """
+int base = src0;
+int offset = src1, bits = src2;
+if (bits == 0) {
+   dst = 0;
+} else if (bits < 0 || offset < 0) {
+   dst = 0; /* undefined */
+} else if (offset + bits < 32) {
+   dst = (base << (32 - bits - offset)) >> (32 - bits);
+} else {
+   dst = base >> offset;
+}
+""")
+
+# GLSL bitfieldExtract()
 opcode("ubitfield_extract", 0, tuint,
        [0, 0, 0], [tuint, tint, tint], "", """
 unsigned base = src0;
diff --git a/src/glsl/nir/nir_opt_algebraic.py b/src/glsl/nir/nir_opt_algebraic.py
index 0d31e39..7745b76 100644
--- a/src/glsl/nir/nir_opt_algebraic.py
+++ b/src/glsl/nir/nir_opt_algebraic.py
@@ -232,6 +232,16 @@ optimizations = [
     ('bcsel', ('ilt', 31, 'bits'), 'insert',
               ('bfi', ('bfm', 'bits', 'offset'), 'insert', 'base')),
     'options->lower_bitfield_insert'),
+
+   (('ibitfield_extract', 'value', 'offset', 'bits'),
+    ('bcsel', ('ilt', 31, 'bits'), 'value',
+              ('ibfe', 'value', 'offset', 'bits')),
+    'options->lower_bitfield_extract'),
+
+   (('ubitfield_extract', 'value', 'offset', 'bits'),
+    ('bcsel', ('ult', 31, 'bits'), 'value',
+              ('ubfe', 'value', 'offset', 'bits')),
+    'options->lower_bitfield_extract'),
 ]
 
 # Add optimizations to handle the case where the result of a ternary is