ac/llvm: fix the local invocation index for wave32

Fixes dEQP-VK.compute.builtin_var.local_invocation_index with
RADV_PERFTEST=cswave32.

My initial fix was to lower it but Rhys suggested the shift-right
and it's much better like this.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>

src/amd/llvm/ac_nir_to_llvm.c

@@ -2905,6 +2905,10 @@ visit_load_local_invocation_index(struct ac_nir_context *ctx)
 	result = LLVMBuildAnd(ctx->ac.builder, ctx->abi->tg_size,
 			      LLVMConstInt(ctx->ac.i32, 0xfc0, false), "");
 
+	if (ctx->ac.wave_size == 32)
+		result = LLVMBuildLShr(ctx->ac.builder, result,
+				       LLVMConstInt(ctx->ac.i32, 1, false), "");
+
 	return LLVMBuildAdd(ctx->ac.builder, result, thread_id, "");
 }