nir: support lowering clipdist to arrays
This allows us to make sure clipdist is emitted as a scalar array rather than two vec4s. This matches SPIR-V semantics, and will be useful for Zink. Reviewed-by: Marek Olšák <marek.olsak@amd.com>
This commit is contained in:
@@ -825,7 +825,7 @@ v3d_nir_lower_vs_late(struct v3d_compile *c)
|
||||
|
||||
if (c->key->ucp_enables) {
|
||||
NIR_PASS_V(c->s, nir_lower_clip_vs, c->key->ucp_enables,
|
||||
false);
|
||||
false, false);
|
||||
NIR_PASS_V(c->s, nir_lower_io_to_scalar,
|
||||
nir_var_shader_out);
|
||||
}
|
||||
@@ -850,7 +850,8 @@ v3d_nir_lower_fs_late(struct v3d_compile *c)
|
||||
}
|
||||
|
||||
if (c->key->ucp_enables)
|
||||
NIR_PASS_V(c->s, nir_lower_clip_fs, c->key->ucp_enables);
|
||||
NIR_PASS_V(c->s, nir_lower_clip_fs, c->key->ucp_enables,
|
||||
false);
|
||||
|
||||
/* Note: FS input scalarizing must happen after
|
||||
* nir_lower_two_sided_color, which only handles a vec4 at a time.
|
||||
|
@@ -3906,9 +3906,13 @@ bool nir_lower_idiv(nir_shader *shader);
|
||||
|
||||
bool nir_lower_input_attachments(nir_shader *shader, bool use_fragcoord_sysval);
|
||||
|
||||
bool nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables, bool use_vars);
|
||||
bool nir_lower_clip_gs(nir_shader *shader, unsigned ucp_enables);
|
||||
bool nir_lower_clip_fs(nir_shader *shader, unsigned ucp_enables);
|
||||
bool nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables,
|
||||
bool use_vars,
|
||||
bool use_clipdist_array);
|
||||
bool nir_lower_clip_gs(nir_shader *shader, unsigned ucp_enables,
|
||||
bool use_clipdist_array);
|
||||
bool nir_lower_clip_fs(nir_shader *shader, unsigned ucp_enables,
|
||||
bool use_clipdist_array);
|
||||
bool nir_lower_clip_cull_distance_arrays(nir_shader *nir);
|
||||
|
||||
void nir_lower_point_size_mov(nir_shader *shader,
|
||||
|
@@ -42,17 +42,23 @@
|
||||
|
||||
static nir_variable *
|
||||
create_clipdist_var(nir_shader *shader, unsigned drvloc,
|
||||
bool output, gl_varying_slot slot)
|
||||
bool output, gl_varying_slot slot, unsigned array_size)
|
||||
{
|
||||
nir_variable *var = rzalloc(shader, nir_variable);
|
||||
|
||||
var->data.driver_location = drvloc;
|
||||
var->type = glsl_vec4_type();
|
||||
var->data.mode = output ? nir_var_shader_out : nir_var_shader_in;
|
||||
var->name = ralloc_asprintf(var, "clipdist_%d", drvloc);
|
||||
var->data.index = 0;
|
||||
var->data.location = slot;
|
||||
|
||||
if (array_size > 0) {
|
||||
var->type = glsl_array_type(glsl_float_type(), array_size,
|
||||
sizeof(float));
|
||||
var->data.compact = 1;
|
||||
} else
|
||||
var->type = glsl_vec4_type();
|
||||
|
||||
if (output) {
|
||||
exec_list_push_tail(&shader->outputs, &var->node);
|
||||
shader->num_outputs++; /* TODO use type_size() */
|
||||
@@ -66,16 +72,24 @@ create_clipdist_var(nir_shader *shader, unsigned drvloc,
|
||||
|
||||
static void
|
||||
create_clipdist_vars(nir_shader *shader, nir_variable **io_vars,
|
||||
unsigned ucp_enables, int *drvloc, bool output)
|
||||
unsigned ucp_enables, int *drvloc, bool output,
|
||||
bool use_clipdist_array)
|
||||
{
|
||||
if (use_clipdist_array) {
|
||||
io_vars[0] =
|
||||
create_clipdist_var(shader, ++(*drvloc), true,
|
||||
VARYING_SLOT_CLIP_DIST0,
|
||||
util_last_bit(ucp_enables));
|
||||
} else {
|
||||
if (ucp_enables & 0x0f)
|
||||
io_vars[0] =
|
||||
create_clipdist_var(shader, ++(*drvloc), output,
|
||||
VARYING_SLOT_CLIP_DIST0);
|
||||
VARYING_SLOT_CLIP_DIST0, 0);
|
||||
if (ucp_enables & 0xf0)
|
||||
io_vars[1] =
|
||||
create_clipdist_var(shader, ++(*drvloc), output,
|
||||
VARYING_SLOT_CLIP_DIST1);
|
||||
VARYING_SLOT_CLIP_DIST1, 0);
|
||||
}
|
||||
}
|
||||
|
||||
static void
|
||||
@@ -192,7 +206,8 @@ find_clipvertex_and_position_outputs(nir_shader *shader,
|
||||
static void
|
||||
lower_clip_outputs(nir_builder *b, nir_variable *position,
|
||||
nir_variable *clipvertex, nir_variable **out,
|
||||
unsigned ucp_enables, bool use_vars)
|
||||
unsigned ucp_enables, bool use_vars,
|
||||
bool use_clipdist_array)
|
||||
{
|
||||
nir_ssa_def *clipdist[MAX_CLIP_PLANES];
|
||||
nir_ssa_def *cv;
|
||||
@@ -224,8 +239,17 @@ lower_clip_outputs(nir_builder *b, nir_variable *position,
|
||||
/* 0.0 == don't-clip == disabled: */
|
||||
clipdist[plane] = nir_imm_float(b, 0.0);
|
||||
}
|
||||
if (use_clipdist_array && plane < util_last_bit(ucp_enables)) {
|
||||
assert(use_vars);
|
||||
nir_deref_instr *deref;
|
||||
deref = nir_build_deref_array_imm(b,
|
||||
nir_build_deref_var(b, out[0]),
|
||||
plane);
|
||||
nir_store_deref(b, deref, clipdist[plane], 1);
|
||||
}
|
||||
}
|
||||
|
||||
if (!use_clipdist_array) {
|
||||
if (use_vars) {
|
||||
if (ucp_enables & 0x0f)
|
||||
nir_store_var(b, out[0], nir_vec(b, clipdist, 4), 0xf);
|
||||
@@ -238,6 +262,7 @@ lower_clip_outputs(nir_builder *b, nir_variable *position,
|
||||
store_clipdist_output(b, out[1], &clipdist[4]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* VS lowering
|
||||
@@ -248,9 +273,13 @@ lower_clip_outputs(nir_builder *b, nir_variable *position,
|
||||
*
|
||||
* If use_vars is true, the pass will use variable loads and stores instead
|
||||
* of working with store_output intrinsics.
|
||||
*
|
||||
* If use_clipdist_array is true, the pass will use compact arrays for the
|
||||
* clipdist output instead of two vec4s.
|
||||
*/
|
||||
bool
|
||||
nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables, bool use_vars)
|
||||
nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables, bool use_vars,
|
||||
bool use_clipdist_array)
|
||||
{
|
||||
nir_function_impl *impl = nir_shader_get_entrypoint(shader);
|
||||
nir_builder b;
|
||||
@@ -281,9 +310,11 @@ nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables, bool use_vars)
|
||||
return false;
|
||||
|
||||
/* insert CLIPDIST outputs */
|
||||
create_clipdist_vars(shader, out, ucp_enables, &maxloc, true);
|
||||
create_clipdist_vars(shader, out, ucp_enables, &maxloc, true,
|
||||
use_clipdist_array);
|
||||
|
||||
lower_clip_outputs(&b, position, clipvertex, out, ucp_enables, use_vars);
|
||||
lower_clip_outputs(&b, position, clipvertex, out, ucp_enables, use_vars,
|
||||
use_clipdist_array);
|
||||
|
||||
nir_metadata_preserve(impl, nir_metadata_dominance);
|
||||
|
||||
@@ -293,7 +324,7 @@ nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables, bool use_vars)
|
||||
static void
|
||||
lower_clip_in_gs_block(nir_builder *b, nir_block *block, nir_variable *position,
|
||||
nir_variable *clipvertex, nir_variable **out,
|
||||
unsigned ucp_enables)
|
||||
unsigned ucp_enables, bool use_clipdist_array)
|
||||
{
|
||||
nir_foreach_instr_safe(instr, block) {
|
||||
if (instr->type != nir_instr_type_intrinsic)
|
||||
@@ -304,7 +335,8 @@ lower_clip_in_gs_block(nir_builder *b, nir_block *block, nir_variable *position,
|
||||
case nir_intrinsic_emit_vertex_with_counter:
|
||||
case nir_intrinsic_emit_vertex:
|
||||
b->cursor = nir_before_instr(instr);
|
||||
lower_clip_outputs(b, position, clipvertex, out, ucp_enables, true);
|
||||
lower_clip_outputs(b, position, clipvertex, out, ucp_enables, true,
|
||||
use_clipdist_array);
|
||||
break;
|
||||
default:
|
||||
/* not interesting; skip this */
|
||||
@@ -318,7 +350,8 @@ lower_clip_in_gs_block(nir_builder *b, nir_block *block, nir_variable *position,
|
||||
*/
|
||||
|
||||
bool
|
||||
nir_lower_clip_gs(nir_shader *shader, unsigned ucp_enables)
|
||||
nir_lower_clip_gs(nir_shader *shader, unsigned ucp_enables,
|
||||
bool use_clipdist_array)
|
||||
{
|
||||
nir_function_impl *impl = nir_shader_get_entrypoint(shader);
|
||||
nir_builder b;
|
||||
@@ -335,12 +368,14 @@ nir_lower_clip_gs(nir_shader *shader, unsigned ucp_enables)
|
||||
return false;
|
||||
|
||||
/* insert CLIPDIST outputs */
|
||||
create_clipdist_vars(shader, out, ucp_enables, &maxloc, true);
|
||||
create_clipdist_vars(shader, out, ucp_enables, &maxloc, true,
|
||||
use_clipdist_array);
|
||||
|
||||
nir_builder_init(&b, impl);
|
||||
|
||||
nir_foreach_block(block, impl)
|
||||
lower_clip_in_gs_block(&b, block, position, clipvertex, out, ucp_enables);
|
||||
lower_clip_in_gs_block(&b, block, position, clipvertex, out,
|
||||
ucp_enables, use_clipdist_array);
|
||||
|
||||
nir_metadata_preserve(impl, nir_metadata_dominance);
|
||||
|
||||
@@ -388,7 +423,8 @@ lower_clip_fs(nir_function_impl *impl, unsigned ucp_enables,
|
||||
/* insert conditional kill based on interpolated CLIPDIST
|
||||
*/
|
||||
bool
|
||||
nir_lower_clip_fs(nir_shader *shader, unsigned ucp_enables)
|
||||
nir_lower_clip_fs(nir_shader *shader, unsigned ucp_enables,
|
||||
bool use_clipdist_array)
|
||||
{
|
||||
nir_variable *in[2];
|
||||
int maxloc = -1;
|
||||
@@ -410,7 +446,8 @@ nir_lower_clip_fs(nir_shader *shader, unsigned ucp_enables)
|
||||
* must add our own:
|
||||
*/
|
||||
/* insert CLIPDIST inputs */
|
||||
create_clipdist_vars(shader, in, ucp_enables, &maxloc, false);
|
||||
create_clipdist_vars(shader, in, ucp_enables, &maxloc, false,
|
||||
use_clipdist_array);
|
||||
|
||||
nir_foreach_function(function, shader) {
|
||||
if (!strcmp(function->name, "main"))
|
||||
|
@@ -223,11 +223,11 @@ ir3_optimize_nir(struct ir3_shader *shader, nir_shader *s,
|
||||
|
||||
if (key) {
|
||||
if (s->info.stage == MESA_SHADER_VERTEX) {
|
||||
OPT_V(s, nir_lower_clip_vs, key->ucp_enables, false);
|
||||
OPT_V(s, nir_lower_clip_vs, key->ucp_enables, false, false);
|
||||
if (key->vclamp_color)
|
||||
OPT_V(s, nir_lower_clamp_color_outputs);
|
||||
} else if (s->info.stage == MESA_SHADER_FRAGMENT) {
|
||||
OPT_V(s, nir_lower_clip_fs, key->ucp_enables);
|
||||
OPT_V(s, nir_lower_clip_fs, key->ucp_enables, false);
|
||||
if (key->fclamp_color)
|
||||
OPT_V(s, nir_lower_clamp_color_outputs);
|
||||
}
|
||||
|
@@ -938,7 +938,8 @@ iris_compile_vs(struct iris_context *ice,
|
||||
|
||||
if (key->nr_userclip_plane_consts) {
|
||||
nir_function_impl *impl = nir_shader_get_entrypoint(nir);
|
||||
nir_lower_clip_vs(nir, (1 << key->nr_userclip_plane_consts) - 1, true);
|
||||
nir_lower_clip_vs(nir, (1 << key->nr_userclip_plane_consts) - 1, true,
|
||||
false);
|
||||
nir_lower_io_to_temporaries(nir, impl, true, false);
|
||||
nir_lower_global_vars_to_local(nir);
|
||||
nir_lower_vars_to_ssa(nir);
|
||||
@@ -1281,7 +1282,8 @@ iris_compile_tes(struct iris_context *ice,
|
||||
|
||||
if (key->nr_userclip_plane_consts) {
|
||||
nir_function_impl *impl = nir_shader_get_entrypoint(nir);
|
||||
nir_lower_clip_vs(nir, (1 << key->nr_userclip_plane_consts) - 1, true);
|
||||
nir_lower_clip_vs(nir, (1 << key->nr_userclip_plane_consts) - 1, true,
|
||||
false);
|
||||
nir_lower_io_to_temporaries(nir, impl, true, false);
|
||||
nir_lower_global_vars_to_local(nir);
|
||||
nir_lower_vars_to_ssa(nir);
|
||||
@@ -1401,7 +1403,7 @@ iris_compile_gs(struct iris_context *ice,
|
||||
|
||||
if (key->nr_userclip_plane_consts) {
|
||||
nir_function_impl *impl = nir_shader_get_entrypoint(nir);
|
||||
nir_lower_clip_gs(nir, (1 << key->nr_userclip_plane_consts) - 1);
|
||||
nir_lower_clip_gs(nir, (1 << key->nr_userclip_plane_consts) - 1, false);
|
||||
nir_lower_io_to_temporaries(nir, impl, true, false);
|
||||
nir_lower_global_vars_to_local(nir);
|
||||
nir_lower_vars_to_ssa(nir);
|
||||
|
@@ -2313,10 +2313,11 @@ vc4_shader_ntq(struct vc4_context *vc4, enum qstage stage,
|
||||
|
||||
if (c->key->ucp_enables) {
|
||||
if (stage == QSTAGE_FRAG) {
|
||||
NIR_PASS_V(c->s, nir_lower_clip_fs, c->key->ucp_enables);
|
||||
NIR_PASS_V(c->s, nir_lower_clip_fs,
|
||||
c->key->ucp_enables, false);
|
||||
} else {
|
||||
NIR_PASS_V(c->s, nir_lower_clip_vs,
|
||||
c->key->ucp_enables, false);
|
||||
c->key->ucp_enables, false, false);
|
||||
NIR_PASS_V(c->s, nir_lower_io_to_scalar,
|
||||
nir_var_shader_out);
|
||||
}
|
||||
|
@@ -407,7 +407,7 @@ brw_nir_lower_legacy_clipping(nir_shader *nir, int nr_userclip_plane_consts,
|
||||
|
||||
nir_function_impl *impl = nir_shader_get_entrypoint(nir);
|
||||
|
||||
nir_lower_clip_vs(nir, (1 << nr_userclip_plane_consts) - 1, true);
|
||||
nir_lower_clip_vs(nir, (1 << nr_userclip_plane_consts) - 1, true, false);
|
||||
nir_lower_io_to_temporaries(nir, impl, true, false);
|
||||
nir_lower_global_vars_to_local(nir);
|
||||
nir_lower_vars_to_ssa(nir);
|
||||
|
Reference in New Issue
Block a user