diff --git a/src/broadcom/ci/traces-broadcom.yml b/src/broadcom/ci/traces-broadcom.yml
index e522ab84fde..c1470ad2d7f 100644
--- a/src/broadcom/ci/traces-broadcom.yml
+++ b/src/broadcom/ci/traces-broadcom.yml
@@ -198,9 +198,9 @@ traces:
 
   neverball/neverball-v2.trace:
     broadcom-rpi4:
-      checksum: 4f4b4b6f37c124fdda6a9efcad577257
+      checksum: c8e8ee352bdb303e4ed144b69272575e
     broadcom-rpi5:
-      checksum: 174394638c6f774948e7aac91c12f84d
+      checksum: 56a0adb0efdf799f269da2d734a6817c
 
   nheko/nheko-colors.trace:
     broadcom-rpi4:
diff --git a/src/broadcom/compiler/vir.c b/src/broadcom/compiler/vir.c
index 0b526768d8b..fd0fae5a9c2 100644
--- a/src/broadcom/compiler/vir.c
+++ b/src/broadcom/compiler/vir.c
@@ -1051,6 +1051,14 @@ v3d_nir_lower_vs_early(struct v3d_compile *c)
         NIR_PASS(_, c->s, nir_lower_io, nir_var_shader_in | nir_var_shader_out,
                  type_size_vec4,
                  (nir_lower_io_options)0);
+
+        /* For geometry stages using the same segment for inputs and outputs
+         * we need to read all inputs before writing any output. If we switch
+         * to separate segments in the future this may not longer be strictly
+         * required.
+         */
+        NIR_PASS(_, c->s, nir_move_output_stores_to_end);
+
         /* clean up nir_lower_io's deref_var remains and do a constant folding pass
          * on the code it generated.
          */