aco: use s_delay_alu skip field

fossil-db (gfx1100):
Totals from 130066 (96.65% of 134574) affected shaders:
Instrs: 80208817 -> 71420648 (-10.96%)
CodeSize: 403523036 -> 368370360 (-8.71%)
Latency: 658064779 -> 657935384 (-0.02%); split: -0.02%, +0.00%
InvThroughput: 87698268 -> 87693326 (-0.01%); split: -0.01%, +0.00%

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/20512>

1 files changed, 27 insertions, 0 deletions

diff --git a/src/amd/compiler/aco_insert_waitcnt.cpp b/src/amd/compiler/aco_insert_waitcnt.cpp
index fdaea72e5a1..7ac2c822ff0 100644
--- a/src/amd/compiler/aco_insert_waitcnt.cpp
+++ b/src/amd/compiler/aco_insert_waitcnt.cpp
@@ -1097,6 +1097,33 @@ insert_wait_states(Program* program)
 
       out_ctx[current.index] = std::move(ctx);
    }
+
+   /* Combine s_delay_alu using the skip field. */
+   if (program->gfx_level >= GFX11) {
+      for (Block& block : program->blocks) {
+         int i = 0;
+         int prev_delay_alu = -1;
+         for (aco_ptr<Instruction>& instr : block.instructions) {
+            if (instr->opcode != aco_opcode::s_delay_alu) {
+               block.instructions[i++] = std::move(instr);
+               continue;
+            }
+
+            uint16_t imm = instr->sopp().imm;
+            int skip = i - prev_delay_alu - 1;
+            if (imm >> 7 || prev_delay_alu < 0 || skip >= 6) {
+               if (imm >> 7 == 0)
+                  prev_delay_alu = i;
+               block.instructions[i++] = std::move(instr);
+               continue;
+            }
+
+            block.instructions[prev_delay_alu]->sopp().imm |= (skip << 4) | (imm << 7);
+            prev_delay_alu = -1;
+         }
+         block.instructions.resize(i);
+      }
+   }
 }
 
 } // namespace aco