diff --git a/src/amd/compiler/aco_instruction_selection.cpp b/src/amd/compiler/aco_instruction_selection.cpp
index 34cad69b868..06ca0910b99 100644
--- a/src/amd/compiler/aco_instruction_selection.cpp
+++ b/src/amd/compiler/aco_instruction_selection.cpp
@@ -11290,6 +11290,13 @@ void select_program(Program *program,
       bool check_merged_wave_info = ctx.tcs_in_out_eq ? i == 0 : (shader_count >= 2 && !empty_shader && !(ngg_gs && i == 1));
       bool endif_merged_wave_info = ctx.tcs_in_out_eq ? i == 1 : (check_merged_wave_info && !(ngg_gs && i == 1));
 
+      if (program->chip_class == GFX10 &&
+          program->stage.hw == HWStage::NGG &&
+          program->stage.num_sw_stages() == 1) {
+         /* Workaround for Navi 1x HW bug to ensure all NGG waves launch before s_sendmsg(GS_ALLOC_REQ). */
+         Builder(ctx.program, ctx.block).sopp(aco_opcode::s_barrier, -1u, 0u);
+      }
+
       if (check_merged_wave_info) {
          Temp cond = merged_wave_info_to_mask(&ctx, i);
          begin_divergent_if_then(&ctx, &ic_merged_wave_info, cond);