OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nir: Move compute system value lowering to a separate pass

Browse Source 
The actual variable -> intrinsic lowering stays where it is, but
ops which convert one intrinsic to be implemented in terms of
another have moved.

Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5891>
This commit is contained in:
Jesse Natalie
2020-08-21 10:18:14 -07:00
committed by Marge Bot
parent 58074143f5
commit 2e1df6a17f
13 changed files with 171 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/amd/vulkan/radv_shader.c
View File

@@ -540,6 +540,8 @@ radv_shader_compile_to_nir(struct radv_device *device,
NIR_PASS_V(nir, nir_propagate_invariant);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
NIR_PASS_V(nir, nir_lower_clip_cull_distance_arrays);
if (device->instance->debug_flags & RADV_DEBUG_DISCARD_TO_DEMOTE)

1
src/broadcom/compiler/vir.c
View File

@@ -586,6 +586,7 @@ v3d_lower_nir(struct v3d_compile *c)
NIR_PASS_V(c->s, nir_lower_tex, &tex_options);
NIR_PASS_V(c->s, nir_lower_system_values);
NIR_PASS_V(c->s, nir_lower_compute_system_values);
NIR_PASS_V(c->s, nir_lower_vars_to_scratch,
nir_var_function_temp,

2
src/compiler/nir/nir.h
View File

@@ -4276,6 +4276,8 @@ bool nir_lower_subgroups(nir_shader *shader,
bool nir_lower_system_values(nir_shader *shader);
bool nir_lower_compute_system_values(nir_shader *shader);
enum PACKED nir_lower_tex_packing {
nir_lower_tex_packing_none = 0,
/* The sampler returns up to 2 32-bit words of half floats or 16-bit signed

261
src/compiler/nir/nir_lower_system_values.c
View File

@@ -92,6 +92,150 @@ lower_system_value_instr(nir_builder *b, nir_instr *instr, void *_state)
return NULL;
}
case nir_intrinsic_load_helper_invocation:
if (b->shader->options->lower_helper_invocation) {
nir_ssa_def *tmp;
tmp = nir_ishl(b, nir_imm_int(b, 1),
nir_load_sample_id_no_per_sample(b));
tmp = nir_iand(b, nir_load_sample_mask_in(b), tmp);
return nir_inot(b, nir_i2b(b, tmp));
} else {
return NULL;
}
case nir_intrinsic_load_local_invocation_id:
case nir_intrinsic_load_local_invocation_index:
case nir_intrinsic_load_local_group_size:
return sanitize_32bit_sysval(b, intrin);
case nir_intrinsic_load_deref: {
nir_deref_instr *deref = nir_src_as_deref(intrin->src[0]);
if (deref->mode != nir_var_system_value)
return NULL;
if (deref->deref_type != nir_deref_type_var) {
/* The only one system value that is an array and that is
* gl_SampleMask which is always an array of one element.
*/
assert(deref->deref_type == nir_deref_type_array);
deref = nir_deref_instr_parent(deref);
assert(deref->deref_type == nir_deref_type_var);
assert(deref->var->data.location == SYSTEM_VALUE_SAMPLE_MASK_IN);
}
nir_variable *var = deref->var;
switch (var->data.location) {
case SYSTEM_VALUE_INSTANCE_INDEX:
return nir_iadd(b, nir_load_instance_id(b),
nir_load_base_instance(b));
case SYSTEM_VALUE_SUBGROUP_EQ_MASK:
case SYSTEM_VALUE_SUBGROUP_GE_MASK:
case SYSTEM_VALUE_SUBGROUP_GT_MASK:
case SYSTEM_VALUE_SUBGROUP_LE_MASK:
case SYSTEM_VALUE_SUBGROUP_LT_MASK: {
nir_intrinsic_op op =
nir_intrinsic_from_system_value(var->data.location);
nir_intrinsic_instr *load = nir_intrinsic_instr_create(b->shader, op);
nir_ssa_dest_init_for_type(&load->instr, &load->dest,
var->type, NULL);
load->num_components = load->dest.ssa.num_components;
nir_builder_instr_insert(b, &load->instr);
return &load->dest.ssa;
}
case SYSTEM_VALUE_DEVICE_INDEX:
if (b->shader->options->lower_device_index_to_zero)
return nir_imm_int(b, 0);
break;
case SYSTEM_VALUE_GLOBAL_GROUP_SIZE:
return build_global_group_size(b, bit_size);
case SYSTEM_VALUE_BARYCENTRIC_LINEAR_PIXEL:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_pixel,
INTERP_MODE_NOPERSPECTIVE);
case SYSTEM_VALUE_BARYCENTRIC_LINEAR_CENTROID:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_centroid,
INTERP_MODE_NOPERSPECTIVE);
case SYSTEM_VALUE_BARYCENTRIC_LINEAR_SAMPLE:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_sample,
INTERP_MODE_NOPERSPECTIVE);
case SYSTEM_VALUE_BARYCENTRIC_PERSP_PIXEL:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_pixel,
INTERP_MODE_SMOOTH);
case SYSTEM_VALUE_BARYCENTRIC_PERSP_CENTROID:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_centroid,
INTERP_MODE_SMOOTH);
case SYSTEM_VALUE_BARYCENTRIC_PERSP_SAMPLE:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_sample,
INTERP_MODE_SMOOTH);
case SYSTEM_VALUE_BARYCENTRIC_PULL_MODEL:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_model,
INTERP_MODE_NONE);
default:
break;
}
nir_intrinsic_op sysval_op =
nir_intrinsic_from_system_value(var->data.location);
return nir_load_system_value(b, sysval_op, 0,
intrin->dest.ssa.num_components,
intrin->dest.ssa.bit_size);
}
default:
return NULL;
}
}
bool
nir_lower_system_values(nir_shader *shader)
{
bool progress = nir_shader_lower_instructions(shader,
lower_system_value_filter,
lower_system_value_instr,
NULL);
/* We're going to delete the variables so we need to clean up all those
* derefs we left lying around.
*/
if (progress)
nir_remove_dead_derefs(shader);
nir_foreach_variable_with_modes_safe(var, shader, nir_var_system_value)
exec_node_remove(&var->node);
return progress;
}
static bool
lower_compute_system_value_filter(const nir_instr *instr, const void *_options)
{
return instr->type == nir_instr_type_intrinsic;
}
static nir_ssa_def *
lower_compute_system_value_instr(nir_builder *b,
nir_instr *instr, void *_options)
{
nir_intrinsic_instr *intrin = nir_instr_as_intrinsic(instr);
/* All the intrinsics we care about are loads */
if (!nir_intrinsic_infos[intrin->intrinsic].has_dest)
return NULL;
assert(intrin->dest.is_ssa);
const unsigned bit_size = intrin->dest.ssa.bit_size;
switch (intrin->intrinsic) {
case nir_intrinsic_load_local_invocation_id:
/* If lower_cs_local_id_from_index is true, then we derive the local
* index from the local id.
@@ -215,121 +359,20 @@ lower_system_value_instr(nir_builder *b, nir_instr *instr, void *_state)
return index;
}
case nir_intrinsic_load_helper_invocation:
if (b->shader->options->lower_helper_invocation) {
nir_ssa_def *tmp;
tmp = nir_ishl(b, nir_imm_int(b, 1),
nir_load_sample_id_no_per_sample(b));
tmp = nir_iand(b, nir_load_sample_mask_in(b), tmp);
return nir_inot(b, nir_i2b(b, tmp));
} else {
return NULL;
}
case nir_intrinsic_load_deref: {
nir_deref_instr *deref = nir_src_as_deref(intrin->src[0]);
if (deref->mode != nir_var_system_value)
return NULL;
if (deref->deref_type != nir_deref_type_var) {
/* The only one system value that is an array and that is
* gl_SampleMask which is always an array of one element.
*/
assert(deref->deref_type == nir_deref_type_array);
deref = nir_deref_instr_parent(deref);
assert(deref->deref_type == nir_deref_type_var);
assert(deref->var->data.location == SYSTEM_VALUE_SAMPLE_MASK_IN);
}
nir_variable *var = deref->var;
switch (var->data.location) {
case SYSTEM_VALUE_INSTANCE_INDEX:
return nir_iadd(b, nir_load_instance_id(b),
nir_load_base_instance(b));
case SYSTEM_VALUE_SUBGROUP_EQ_MASK:
case SYSTEM_VALUE_SUBGROUP_GE_MASK:
case SYSTEM_VALUE_SUBGROUP_GT_MASK:
case SYSTEM_VALUE_SUBGROUP_LE_MASK:
case SYSTEM_VALUE_SUBGROUP_LT_MASK: {
nir_intrinsic_op op =
nir_intrinsic_from_system_value(var->data.location);
nir_intrinsic_instr *load = nir_intrinsic_instr_create(b->shader, op);
nir_ssa_dest_init_for_type(&load->instr, &load->dest,
var->type, NULL);
load->num_components = load->dest.ssa.num_components;
nir_builder_instr_insert(b, &load->instr);
return &load->dest.ssa;
}
case SYSTEM_VALUE_DEVICE_INDEX:
if (b->shader->options->lower_device_index_to_zero)
return nir_imm_int(b, 0);
break;
case SYSTEM_VALUE_GLOBAL_GROUP_SIZE:
return build_global_group_size(b, bit_size);
case SYSTEM_VALUE_BARYCENTRIC_LINEAR_PIXEL:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_pixel,
INTERP_MODE_NOPERSPECTIVE);
case SYSTEM_VALUE_BARYCENTRIC_LINEAR_CENTROID:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_centroid,
INTERP_MODE_NOPERSPECTIVE);
case SYSTEM_VALUE_BARYCENTRIC_LINEAR_SAMPLE:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_sample,
INTERP_MODE_NOPERSPECTIVE);
case SYSTEM_VALUE_BARYCENTRIC_PERSP_PIXEL:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_pixel,
INTERP_MODE_SMOOTH);
case SYSTEM_VALUE_BARYCENTRIC_PERSP_CENTROID:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_centroid,
INTERP_MODE_SMOOTH);
case SYSTEM_VALUE_BARYCENTRIC_PERSP_SAMPLE:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_sample,
INTERP_MODE_SMOOTH);
case SYSTEM_VALUE_BARYCENTRIC_PULL_MODEL:
return nir_load_barycentric(b, nir_intrinsic_load_barycentric_model,
INTERP_MODE_NONE);
default:
break;
}
nir_intrinsic_op sysval_op =
nir_intrinsic_from_system_value(var->data.location);
return nir_load_system_value(b, sysval_op, 0,
intrin->dest.ssa.num_components,
intrin->dest.ssa.bit_size);
}
default:
return NULL;
}
}
bool
nir_lower_system_values(nir_shader *shader)
nir_lower_compute_system_values(nir_shader *shader)
{
bool progress = nir_shader_lower_instructions(shader,
lower_system_value_filter,
lower_system_value_instr,
NULL);
if (shader->info.stage != MESA_SHADER_COMPUTE &&
shader->info.stage != MESA_SHADER_KERNEL)
return false;
/* We're going to delete the variables so we need to clean up all those
* derefs we left lying around.
*/
if (progress)
nir_remove_dead_derefs(shader);
nir_foreach_variable_with_modes_safe(var, shader, nir_var_system_value)
exec_node_remove(&var->node);
return progress;
return nir_shader_lower_instructions(shader,
lower_compute_system_value_filter,
lower_compute_system_value_instr,
NULL);
}

2
src/freedreno/vulkan/tu_shader.c
View File

@@ -765,6 +765,8 @@ tu_shader_create(struct tu_device *dev,
nir_assign_io_var_locations(nir, nir_var_shader_out, &nir->num_outputs, stage);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
NIR_PASS_V(nir, nir_lower_frexp);
if (stage == MESA_SHADER_FRAGMENT) {

1
src/gallium/auxiliary/nir/tgsi_to_nir.c
View File

@@ -2559,6 +2559,7 @@ ttn_finalize_nir(struct ttn_compile *c, struct pipe_screen *screen)
NIR_PASS_V(nir, nir_split_var_copies);
NIR_PASS_V(nir, nir_lower_var_copies);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
if (c->cap_packed_uniforms)
NIR_PASS_V(nir, nir_lower_uniforms_to_ubo, 16);

3
src/gallium/drivers/freedreno/ir3/ir3_cmdline.c
View File

@@ -185,6 +185,8 @@ load_glsl(unsigned num_files, char* const* files, gl_shader_stage stage)
ir3_glsl_type_size);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
NIR_PASS_V(nir, nir_lower_frexp);
NIR_PASS_V(nir, nir_lower_io,
nir_var_shader_in | nir_var_shader_out | nir_var_uniform,
@@ -401,6 +403,7 @@ main(int argc, char **argv)
/* TODO do this somewhere else */
nir_lower_int64(nir);
nir_lower_system_values(nir);
nir_lower_compute_system_values(nir);
} else if (num_files > 0) {
nir = load_glsl(num_files, filenames, stage);
} else {

2
src/gallium/frontends/clover/nir/invocation.cpp
View File

@@ -169,6 +169,8 @@ module clover::nir::spirv_to_nir(const module &mod, const device &dev,
spirv_options.global_addr_format);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
if (compiler_options->lower_int64_options)
NIR_PASS_V(nir, nir_lower_int64);

1
src/gallium/frontends/vallium/val_pipeline.c
View File

@@ -562,6 +562,7 @@ val_shader_compile_to_ir(struct val_pipeline *pipeline,
if (stage == MESA_SHADER_FRAGMENT)
val_lower_input_attachments(nir, false);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
NIR_PASS_V(nir, nir_lower_clip_cull_distance_arrays);
nir_remove_dead_variables(nir, nir_var_uniform, NULL);

1
src/intel/compiler/brw_nir.c
View File

@@ -709,6 +709,7 @@ brw_preprocess_nir(const struct brw_compiler *compiler, nir_shader *nir,
}
OPT(nir_lower_system_values);
OPT(nir_lower_compute_system_values);
const nir_lower_subgroups_options subgroups_options = {
.ballot_bit_size = 32,

2
src/mesa/state_tracker/st_glsl_to_nir.cpp
View File

@@ -771,6 +771,8 @@ st_link_nir(struct gl_context *ctx,
st->pipe->screen);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
NIR_PASS_V(nir, nir_lower_clip_cull_distance_arrays);
st_shader_gather_info(nir, shader->Program);

1
src/mesa/state_tracker/st_nir_builtins.c
View File

@@ -43,6 +43,7 @@ st_nir_finish_builtin_shader(struct st_context *st,
NIR_PASS_V(nir, nir_split_var_copies);
NIR_PASS_V(nir, nir_lower_var_copies);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
if (nir->options->lower_to_scalar) {
nir_variable_mode mask =

1
src/mesa/state_tracker/st_program.c
View File

@@ -388,6 +388,7 @@ st_translate_prog_to_nir(struct st_context *st, struct gl_program *prog,
NIR_PASS_V(nir, st_nir_lower_wpos_ytransform, prog, screen);
NIR_PASS_V(nir, nir_lower_system_values);
NIR_PASS_V(nir, nir_lower_compute_system_values);
/* Optimise NIR */
NIR_PASS_V(nir, nir_opt_constant_folding);