nir/algebraic: optimize a*#b & -4

fossil-db (Sienna Cichlid):
Totals from 611 (0.47% of 128647) affected shaders:
CodeSize: 3096680 -> 3090976 (-0.18%)
Instrs: 570494 -> 569249 (-0.22%)
Latency: 5765865 -> 5759619 (-0.11%)
InvThroughput: 969840 -> 967608 (-0.23%)
VClause: 9690 -> 9688 (-0.02%)
Copies: 42884 -> 42894 (+0.02%); split: -0.01%, +0.03%
PreVGPRs: 28290 -> 28288 (-0.01%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13752>

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 6e6c1ed..58d5ee2 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -408,6 +408,11 @@ for size, mask in ((8, 0xff), (16, 0xffff), (32, 0xffffffff), (64, 0xfffffffffff
        (('ushr', ('ishl', a_sz, '#b'), b), ('iand', a, ('ushr', mask, b))),
     ])
 
+optimizations.extend([
+    (('iand', ('ishl', 'a@32', '#b(is_first_5_bits_uge_2)'), -4), ('ishl', a, b)),
+    (('iand', ('imul', a, '#b(is_unsigned_multiple_of_4)'), -4), ('imul', a, b)),
+])
+
 for log2 in range(1, 7): # powers of two from 2 to 64
    v = 1 << log2
    mask = 0xffffffff & ~(v - 1)

diff --git a/src/compiler/nir/nir_search_helpers.h b/src/compiler/nir/nir_search_helpers.h
index 1188b50..6353129 100644 (file)
--- a/src/compiler/nir/nir_search_helpers.h
+++ b/src/compiler/nir/nir_search_helpers.h
@@ -226,6 +226,27 @@ is_ult_0xfffc07fc(UNUSED struct hash_table *ht, const nir_alu_instr *instr,
    return true;
 }
 
+/** Is the first 5 bits of value unsigned greater than or equal 2? */
+static inline bool
+is_first_5_bits_uge_2(UNUSED struct hash_table *ht, const nir_alu_instr *instr,
+                      unsigned src, unsigned num_components,
+                      const uint8_t *swizzle)
+{
+   /* only constant srcs: */
+   if (!nir_src_is_const(instr->src[src].src))
+      return false;
+
+   for (unsigned i = 0; i < num_components; i++) {
+      const unsigned val =
+         nir_src_comp_as_uint(instr->src[src].src, swizzle[i]);
+
+      if ((val & 0x1f) < 2)
+         return false;
+   }
+
+   return true;
+}
+
 static inline bool
 is_not_const(UNUSED struct hash_table *ht, const nir_alu_instr *instr,
              unsigned src, UNUSED unsigned num_components,