From e19584db2b8085dd6cf2a2d977b783dcd0a05378 Mon Sep 17 00:00:00 2001
From: Rhys Perry <pendingchaos02@gmail.com>
Date: Wed, 2 Nov 2022 16:45:41 +0000
Subject: [PATCH] nir/algebraic: optimize open-coded uadd_sat/usub_sat

fossil-db (navi21):
Totals from 19 (0.01% of 135636) affected shaders:
Instrs: 40730 -> 40688 (-0.10%)
CodeSize: 217708 -> 217568 (-0.06%)
Latency: 261466 -> 261373 (-0.04%)
InvThroughput: 74944 -> 74896 (-0.06%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19473>
---
 src/compiler/nir/nir_opt_algebraic.py | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index f35232a66ca..421bb18b3f3 100644
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -2079,6 +2079,32 @@ optimizations.extend([
    (('imul24', a, 0), (0)),
 ])
 
+for bit_size in [8, 16, 32, 64]:
+   cond = '!options->lower_uadd_sat'
+   if bit_size == 64:
+      cond += ' && !(options->lower_int64_options & nir_lower_iadd64)'
+   add = 'iadd@' + str(bit_size)
+
+   optimizations += [
+      (('bcsel', ('ult', ('iadd', a, b), a), -1, (add, a, b)), ('uadd_sat', a, b), cond),
+      (('bcsel', ('uge', ('iadd', a, b), a), (add, a, b), -1), ('uadd_sat', a, b), cond),
+      (('bcsel', ('ieq', ('uadd_carry', a, b), 0), (add, a, b), -1), ('uadd_sat', a, b), cond),
+      (('bcsel', ('ine', ('uadd_carry', a, b), 0), -1, (add, a, b)), ('uadd_sat', a, b), cond),
+   ]
+
+for bit_size in [8, 16, 32, 64]:
+   cond = '!options->lower_usub_sat'
+   if bit_size == 64:
+      cond += ' && !(options->lower_int64_options & nir_lower_usub_sat64)'
+   add = 'iadd@' + str(bit_size)
+
+   optimizations += [
+      (('bcsel', ('ult', a, b), 0, (add, a, ('ineg', b))), ('usub_sat', a, b), cond),
+      (('bcsel', ('uge', a, b), (add, a, ('ineg', b)), 0), ('usub_sat', a, b), cond),
+      (('bcsel', ('ieq', ('usub_borrow', a, b), 0), (add, a, ('ineg', b)), 0), ('usub_sat', a, b), cond),
+      (('bcsel', ('ine', ('usub_borrow', a, b), 0), 0, (add, a, ('ineg', b))), ('usub_sat', a, b), cond),
+   ]
+
 # bit_size dependent lowerings
 for bit_size in [8, 16, 32, 64]:
    # convenience constants