aco: try to always find a register with stride for even sizes

Totals from affected shaders:
SGPRS: 1162400 -> 1162400 (0.00 %)
VGPRS: 947364 -> 946960 (-0.04 %)
Code Size: 98399300 -> 98399004 (-0.00 %) bytes
Max Waves: 74665 -> 74682 (0.02 %)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4573>

diff --git a/src/amd/compiler/aco_register_allocation.cpp b/src/amd/compiler/aco_register_allocation.cpp
index 9a36019ff37916c496efba2687c2dee416fb8c24..eae3822e61c64209f0d346c8fc452e39f833912a 100644 (file)
--- a/src/amd/compiler/aco_register_allocation.cpp
+++ b/src/amd/compiler/aco_register_allocation.cpp
@@ -395,8 +395,10 @@ std::pair<PhysReg, bool> get_reg_simple(ra_ctx& ctx,
 
    if (stride == 1) {
 
-      if (rc.type() == RegType::vgpr && (size == 4 || size == 8)) {
-         info.stride = 4;
+      for (unsigned stride = 8; stride > 1; stride /= 2) {
+         if (size % stride)
+            continue;
+         info.stride = stride;
          std::pair<PhysReg, bool> res = get_reg_simple(ctx, reg_file, info);
          if (res.second)
             return res;