aco: add missing usable_read2 check

A Hitman 2 shader does: read64(local_invocation_index() * 4 - 4). This was
likely emitting a ds_read2_b32 on GFX6. For local_invocation_index()=0,
because the first dword was out-of-bounds, the second was likely also
considered out-of-bounds (even though it's not, at offset 0).

Likely fixes https://gitlab.freedesktop.org/mesa/mesa/-/issues/3882

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: 57e6886f981 ("aco: refactor load_lds to use new helpers")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9332>

diff --git a/src/amd/compiler/aco_instruction_selection.cpp b/src/amd/compiler/aco_instruction_selection.cpp
index 3e49c88..0446870 100644 (file)
--- a/src/amd/compiler/aco_instruction_selection.cpp
+++ b/src/amd/compiler/aco_instruction_selection.cpp
@@ -3483,7 +3483,7 @@ Temp lds_load_callback(Builder& bld, const LoadEmitInfo &info,
    } else if (bytes_needed >= 8 && align % 8 == 0) {
       size = 8;
       op = aco_opcode::ds_read_b64;
-   } else if (bytes_needed >= 8 && align % 4 == 0 && const_offset % 4 == 0) {
+   } else if (bytes_needed >= 8 && align % 4 == 0 && const_offset % 4 == 0 && usable_read2) {
       size = 8;
       read2 = true;
       op = aco_opcode::ds_read2_b32;