ac: split 16-bit ssbo loads that may not be dword aligned

Fixes: 7e7ee82698 ('ac: add support for 16bit buffer loads')
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108114
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>

src/amd/common/ac_nir_to_llvm.c

@@ -1640,6 +1640,8 @@ static LLVMValueRef visit_load_buffer(struct ac_nir_context *ctx,
 	LLVMValueRef results[4];
 	for (int i = 0; i < num_components;) {
 		int num_elems = num_components - i;
+		if (elem_size_bytes < 4 && nir_intrinsic_align(instr) % 4 != 0)
+			num_elems = 1;
 		if (num_elems * elem_size_bytes > 16)
 			num_elems = 16 / elem_size_bytes;
 		int load_bytes = num_elems * elem_size_bytes;