diff --git a/src/compiler/nir/nir_opt_offsets.c b/src/compiler/nir/nir_opt_offsets.c
index e2ec1daeded..471fab1747d 100644
--- a/src/compiler/nir/nir_opt_offsets.c
+++ b/src/compiler/nir/nir_opt_offsets.c
@@ -128,9 +128,16 @@ process_instr(nir_builder *b, nir_instr *instr, void *s)
    nir_intrinsic_instr *intrin = nir_instr_as_intrinsic(instr);
 
    switch (intrin->intrinsic) {
+      /* Note that while it's tempting to include nir_intrinsic_load_uniform
+       * here, freedreno doesn't want that because it can have to move the base
+       * back to a register plus a small constant offset, and it's not clever
+       * enough to minimize the code that that emits.
+       */
    case nir_intrinsic_load_shared:
+   case nir_intrinsic_load_shared_ir3:
       return try_fold_load_store(b, intrin, state, 0);
    case nir_intrinsic_store_shared:
+   case nir_intrinsic_store_shared_ir3:
       return try_fold_load_store(b, intrin, state, 1);
    case nir_intrinsic_load_buffer_amd:
       return try_fold_load_store(b, intrin, state, 1);
diff --git a/src/freedreno/ir3/ir3_nir.c b/src/freedreno/ir3/ir3_nir.c
index 9db9b367f84..ccf3bdab63d 100644
--- a/src/freedreno/ir3/ir3_nir.c
+++ b/src/freedreno/ir3/ir3_nir.c
@@ -117,6 +117,7 @@ ir3_optimize_loop(struct ir3_compiler *compiler, nir_shader *s)
       progress |= OPT(s, nir_lower_alu);
       progress |= OPT(s, nir_lower_pack);
       progress |= OPT(s, nir_opt_constant_folding);
+      progress |= OPT(s, nir_opt_offsets);
 
       nir_load_store_vectorize_options vectorize_opts = {
          .modes = nir_var_mem_ubo,