lower_tess_ctrl_block assumes that the gl_TessLevel*
intrinsic_store_outputs have already been collapsed into a single
instruction before the tess lowering step:
store_output ... /* base=0 */ /* wrmask=xyzw */ /* component=0 */
store_output ... /* base=1 */ /* wrmask=xy */ /* component=0 */
While this is true in fd because of st_nir_vectorize_io, we don't do
the same lowering in turnip so each tess level component still has
its own store instruction:
store_output ... /* base=0 */ /* wrmask=x */ /* component=0 */
store_output ... /* base=0 */ /* wrmask=x */ /* component=1 */
store_output ... /* base=0 */ /* wrmask=x */ /* component=2 */
store_output ... /* base=0 */ /* wrmask=x */ /* component=3 */
store_output ... /* base=1 */ /* wrmask=x */ /* component=0 */
store_output ... /* base=1 */ /* wrmask=x */ /* component=1 */
This commit adds a component offset to the tess control lowering. An
alternative is to also perform nir_lower_io_to_vector in turnip, but
ir3 seems to generate the same assembly either way and it's nice to
not have a lowering prereq before tess lowering.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5059>
b->cursor = nir_before_instr(&intr->instr);
if (levels) {
- for (int i = 0; i < 4; i++)
- if (nir_intrinsic_write_mask(intr) & (1 << i))
- levels[i] = nir_channel(b, intr->src[0].ssa, i);
+ for (int i = 0; i < 4; i++) {
+ if (nir_intrinsic_write_mask(intr) & (1 << i)) {
+ uint32_t component = nir_intrinsic_component(intr);
+ levels[i + component] = nir_channel(b, intr->src[0].ssa, i);
+ }
+ }
nir_instr_remove(&intr->instr);
} else {
nir_ssa_def *address = nir_load_tess_param_base_ir3(b);