aco: disallow SMEM offsets that are not multiples of 4

These can't be encoded on GFX6/7, and combining these additions causes
CTS failures on GFX10.3.

I think the low 2 MSBs are ignored before the addition, not after, so
load(a + 3, 0) becomes load(a, 3), which is the same as load(a, 0).

No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13755>

diff --git a/src/amd/compiler/aco_optimizer.cpp b/src/amd/compiler/aco_optimizer.cpp
index 9b1ac02..8ea5dac 100644 (file)
--- a/src/amd/compiler/aco_optimizer.cpp
+++ b/src/amd/compiler/aco_optimizer.cpp
@@ -1189,7 +1189,8 @@ label_instruction(opt_ctx& ctx, aco_ptr<Instruction>& instr)
             continue;
          } else if (i == 1 &&
                     parse_base_offset(ctx, instr.get(), i, &base, &offset, prevent_overflow) &&
-                    base.regClass() == s1 && offset <= 0xFFFFF && ctx.program->chip_class >= GFX9) {
+                    base.regClass() == s1 && offset <= 0xFFFFF && ctx.program->chip_class >= GFX9 &&
+                    offset % 4u == 0) {
             bool soe = smem.operands.size() >= (!smem.definitions.empty() ? 3 : 4);
             if (soe && (!ctx.info[smem.operands.back().tempId()].is_constant_or_literal(32) ||
                         ctx.info[smem.operands.back().tempId()].val != 0)) {