[Mesa-dev] [PATCH] nir/search: Use the correct bit size for integer comparisons

[Jason Ekstrand]

The previous code always compared integers as 64-bit.  Due to variations
in sign-extension in the code generated by nir_opt_algebraic.py, this
meant that nir_search doesn't always do what you want.  Instead, 32-bit
values should be matched as 32-bit and 64-bit values should be matched
as 64-bit.  While we're here we unify the unsigned and signed paths.
Now that we're using the right bit size, they should be the same since
the only difference we had before was sign extension.

This gets the UE4 bitfield_extract optimization working again.  It had
stopped working due to the constant 0xff00ff00 getting sign-extended
when it shouldn't have.

Cc: "17.0 13.0" <mesa-stable at lists.freedesktop.org>
Cc: Eric Anholt <eric at anholt.net>
---
 src/compiler/nir/nir_search.c | 48 +++++++++++++++----------------------------
 1 file changed, 16 insertions(+), 32 deletions(-)

diff --git a/src/compiler/nir/nir_search.c b/src/compiler/nir/nir_search.c
index 68275e4..dec56fe 100644
--- a/src/compiler/nir/nir_search.c
+++ b/src/compiler/nir/nir_search.c
@@ -210,43 +210,27 @@ match_value(const nir_search_value *value, nir_alu_instr *instr, unsigned src,
          return true;
 
       case nir_type_int:
-         for (unsigned i = 0; i < num_components; ++i) {
-            int64_t val;
-            switch (load->def.bit_size) {
-            case 32:
-               val = load->value.i32[new_swizzle[i]];
-               break;
-            case 64:
-               val = load->value.i64[new_swizzle[i]];
-               break;
-            default:
-               unreachable("unknown bit size");
-            }
-
-            if (val != const_val->data.i)
-               return false;
-         }
-         return true;
-
       case nir_type_uint:
       case nir_type_bool32:
-         for (unsigned i = 0; i < num_components; ++i) {
-            uint64_t val;
-            switch (load->def.bit_size) {
-            case 32:
-               val = load->value.u32[new_swizzle[i]];
-               break;
-            case 64:
-               val = load->value.u64[new_swizzle[i]];
-               break;
-            default:
-               unreachable("unknown bit size");
+         switch (load->def.bit_size) {
+         case 32:
+            for (unsigned i = 0; i < num_components; ++i) {
+               if (load->value.u32[new_swizzle[i]] !=
+                   (uint32_t)const_val->data.u)
+                  return false;
             }
+            return true;
 
-            if (val != const_val->data.u)
-               return false;
+         case 64:
+            for (unsigned i = 0; i < num_components; ++i) {
+               if (load->value.u64[new_swizzle[i]] != const_val->data.u)
+                  return false;
+            }
+            return true;
+
+         default:
+            unreachable("unknown bit size");
          }
-         return true;
 
       default:
          unreachable("Invalid alu source type");
-- 
2.5.0.400.gff86faf