diff --git a/src/compiler/nir/nir_opt_load_store_vectorize.c b/src/compiler/nir/nir_opt_load_store_vectorize.c
index 928ba233f09..4b476f97ca1 100644
--- a/src/compiler/nir/nir_opt_load_store_vectorize.c
+++ b/src/compiler/nir/nir_opt_load_store_vectorize.c
@@ -1326,13 +1326,14 @@ vectorize_sorted_entries(struct vectorize_ctx *ctx, nir_function_impl *impl,
          struct entry *second = low->index < high->index ? high : low;
 
          uint64_t diff = high->offset_signed - low->offset_signed;
-         /* Allow overfetching by 4 bytes, which can be rejected
-          * by the callback if needed.
+         /* Allow overfetching by 28 bytes, which can be rejected by the
+          * callback if needed.  Driver callbacks will likely want to
+          * restrict this to a smaller value, say 4 bytes (or none).
           */
          unsigned max_hole =
             first->is_store ||
             (ctx->options->has_shared2_amd &&
-             get_variable_mode(first) == nir_var_mem_shared) ? 0 : 4;
+             get_variable_mode(first) == nir_var_mem_shared) ? 0 : 28;
          unsigned low_size = get_bit_size(low) / 8u * low->num_components;
          bool separate = diff > max_hole + low_size;
 
diff --git a/src/compiler/nir/tests/load_store_vectorizer_tests.cpp b/src/compiler/nir/tests/load_store_vectorizer_tests.cpp
index feae1c51259..66bc813623f 100644
--- a/src/compiler/nir/tests/load_store_vectorizer_tests.cpp
+++ b/src/compiler/nir/tests/load_store_vectorizer_tests.cpp
@@ -346,8 +346,6 @@ bool nir_load_store_vectorize_test::mem_vectorize_callback(
 {
    nir_load_store_vectorize_test *test = (nir_load_store_vectorize_test *)data;
 
-   assert(hole_size <= 4);
-
    if (hole_size > test->max_hole_size ||
        (!test->overfetch && !nir_num_components_valid(num_components)))
       return false;