nir: Add lowering for bitfieldInsert without using bfi.

If you don't have HW to do bfi, then lowering bitfieldInsert to bfi makes
things harder than keeping the "bits" argument around.

This still uses bfm, but I've added the obvious lowering of bfm if you
need it.

Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>

diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h
index 5a1f79515ad63af8fc6154804ed02bfe8fac2a53..6c0276fcc7f2c431d8a0335d7a47b4166f7ab732 100644 (file)
--- a/src/compiler/nir/nir.h
+++ b/src/compiler/nir/nir.h
@@ -1904,7 +1904,12 @@ typedef struct nir_shader_compiler_options {
    bool lower_fmod32;
    bool lower_fmod64;
    bool lower_bitfield_extract;
+   /** Lowers bitfield_insert to bfi/bfm */
    bool lower_bitfield_insert;
+   /** Lowers bitfield_insert to bfm, compares, and shifts. */
+   bool lower_bitfield_insert_to_shifts;
+   /** Lowers bfm to shifts and subtracts. */
+   bool lower_bfm;
    bool lower_uadd_carry;
    bool lower_usub_borrow;
    /** lowers fneg and ineg to fsub and isub. */

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index fdfb0250b0b2573054d186df5f328025b6172832..878d13ded5eb58c8e08d5bba6d96c88d47a02cb2 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -515,6 +515,20 @@ optimizations = [
               ('bfi', ('bfm', 'bits', 'offset'), 'insert', 'base')),
     'options->lower_bitfield_insert'),
 
+   # Alternative lowering that doesn't rely on bfi.
+   (('bitfield_insert', 'base', 'insert', 'offset', 'bits'),
+    ('bcsel', ('ilt', 31, 'bits'),
+     'insert',
+     ('ior',
+      ('iand', 'base', ('inot', ('bfm', 'bits', 'offset'))),
+      ('iand', ('ishl', 'insert', 'offset'), ('bfm', 'bits', 'offset')))),
+    'options->lower_bitfield_insert_to_shifts'),
+
+   # bfm lowering -- note that the NIR opcode is undefined if either arg is 32.
+   (('bfm', 'bits', 'offset'),
+    ('ishl', ('isub', ('ishl', 1, 'bits'), 1), 'offset'),
+    'options->lower_bfm'),
+
    (('ibitfield_extract', 'value', 'offset', 'bits'),
     ('bcsel', ('ilt', 31, 'bits'), 'value',
               ('ibfe', 'value', 'offset', 'bits')),