First part of v2 of !27, which aims to:
* Allow allocation of variables of complex types that contain both numerics and objects across multiple register sets (regsets). * Support the tex2D and tex3D intrinsics, inferring generic samplers dimension from usage, writing sampler declarations, and writing sample instructions. * Support for arrays of resources for both SM1 and SM4 (not to be confused with the resource-arrays of SM 5.1, which can have non-constant indexes). * Support for resources declared within structs. * Support for synthetic combined samplers for SM1 and synthetic separated samplers for SM4, considering that they can be arrays or members of structs. * Imitate the way the native compiler assigns the register indexes of the resources on allocation, which proved to be the most difficult thing. * Support for object components within complex input parameters. * Small fixes to corner cases.
This part consists on parsing the `tex2D()` and `tex3D()` intrinsics and beginning to support the allocation of variables across multiple regsets.
The whole series, is on my [master6](https://gitlab.winehq.org/fcasas/vkd3d/-/commits/master6) branch.
-- v7: vkd3d-shader/hlsl: Allocate register reservations in a separate pass. vkd3d-shader/hlsl: Respect object reservations even if the object is unused. vkd3d-shader/hlsl: Allocate objects according to register set. vkd3d-shader/hlsl: Keep an hlsl_reg for each register set in hlsl_ir_var. vkd3d-shader/hlsl: Store the type's register size for each register set.
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl_sm4.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/libs/vkd3d-shader/hlsl_sm4.c b/libs/vkd3d-shader/hlsl_sm4.c index fb14889d..107339cb 100644 --- a/libs/vkd3d-shader/hlsl_sm4.c +++ b/libs/vkd3d-shader/hlsl_sm4.c @@ -2243,7 +2243,10 @@ static void write_sm4_resource_load(struct hlsl_ctx *ctx,
case HLSL_RESOURCE_SAMPLE: if (!load->sampler.var) + { hlsl_fixme(ctx, &load->node.loc, "SM4 combined sample expression."); + return; + } write_sm4_sample(ctx, buffer, resource_type, &load->node, &load->resource, &load->sampler, coords, texel_offset); break;
From: Zebediah Figura zfigura@codeweavers.com
--- Modifications: * Using new hlsl_resource_load_params struct. * Removed `HLSL_OP2_SAMPLE` from enum hlsl_ir_expr_op, since it is not used. --- libs/vkd3d-shader/hlsl.y | 61 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+)
diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y index a4de0edd..d2a7c418 100644 --- a/libs/vkd3d-shader/hlsl.y +++ b/libs/vkd3d-shader/hlsl.y @@ -2888,6 +2888,66 @@ static bool intrinsic_step(struct hlsl_ctx *ctx, return !!add_implicit_conversion(ctx, params->instrs, ge, type, loc); }
+static bool intrinsic_tex(struct hlsl_ctx *ctx, const struct parse_initializer *params, + const struct vkd3d_shader_location *loc, const char *name, enum hlsl_sampler_dim dim) +{ + struct hlsl_resource_load_params load_params = {.type = HLSL_RESOURCE_SAMPLE}; + const struct hlsl_type *sampler_type; + struct hlsl_ir_resource_load *load; + struct hlsl_ir_load *sampler_load; + struct hlsl_ir_node *coords; + + if (params->args_count != 2 && params->args_count != 4) + { + hlsl_error(ctx, loc, VKD3D_SHADER_ERROR_HLSL_WRONG_PARAMETER_COUNT, + "Wrong number of arguments to function '%s': expected 2 or 4, but got %u.", name, params->args_count); + return false; + } + + if (params->args_count == 4) + { + hlsl_fixme(ctx, loc, "Samples with gradients are not implemented.\n"); + } + + sampler_type = params->args[0]->data_type; + if (sampler_type->type != HLSL_CLASS_OBJECT || sampler_type->base_type != HLSL_TYPE_SAMPLER + || (sampler_type->sampler_dim != dim && sampler_type->sampler_dim != HLSL_SAMPLER_DIM_GENERIC)) + { + struct vkd3d_string_buffer *string; + + if ((string = hlsl_type_to_string(ctx, sampler_type))) + hlsl_error(ctx, loc, VKD3D_SHADER_ERROR_HLSL_INVALID_TYPE, + "Wrong type for argument 1 of '%s': expected 'sampler' or '%s', but got '%s'.", + name, ctx->builtin_types.sampler[dim]->name, string->buffer); + hlsl_release_string_buffer(ctx, string); + } + else + { + /* Only HLSL_IR_LOAD can return an object. */ + sampler_load = hlsl_ir_load(params->args[0]); + + load_params.resource = sampler_load->src; + } + + if (!(coords = add_implicit_conversion(ctx, params->instrs, params->args[1], + hlsl_get_vector_type(ctx, HLSL_TYPE_FLOAT, hlsl_sampler_dim_count(dim)), loc))) + coords = params->args[1]; + + load_params.coords = coords; + load_params.format = hlsl_get_vector_type(ctx, HLSL_TYPE_FLOAT, 4); + + if (!(load = hlsl_new_resource_load(ctx, &load_params, loc))) + return false; + list_add_tail(params->instrs, &load->node.entry); + return true; +} + +static bool intrinsic_tex2D(struct hlsl_ctx *ctx, + const struct parse_initializer *params, const struct vkd3d_shader_location *loc) +{ + return intrinsic_tex(ctx, params, loc, "tex2D", HLSL_SAMPLER_DIM_2D); +} + static bool intrinsic_transpose(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { @@ -2981,6 +3041,7 @@ intrinsic_functions[] = {"smoothstep", 3, true, intrinsic_smoothstep}, {"sqrt", 1, true, intrinsic_sqrt}, {"step", 2, true, intrinsic_step}, + {"tex2D", -1, false, intrinsic_tex2D}, {"transpose", 1, true, intrinsic_transpose}, };
From: Zebediah Figura zfigura@codeweavers.com
--- libs/vkd3d-shader/hlsl.y | 7 +++++++ 1 file changed, 7 insertions(+)
diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y index d2a7c418..1ce399a6 100644 --- a/libs/vkd3d-shader/hlsl.y +++ b/libs/vkd3d-shader/hlsl.y @@ -2948,6 +2948,12 @@ static bool intrinsic_tex2D(struct hlsl_ctx *ctx, return intrinsic_tex(ctx, params, loc, "tex2D", HLSL_SAMPLER_DIM_2D); }
+static bool intrinsic_tex3D(struct hlsl_ctx *ctx, + const struct parse_initializer *params, const struct vkd3d_shader_location *loc) +{ + return intrinsic_tex(ctx, params, loc, "tex3D", HLSL_SAMPLER_DIM_3D); +} + static bool intrinsic_transpose(struct hlsl_ctx *ctx, const struct parse_initializer *params, const struct vkd3d_shader_location *loc) { @@ -3042,6 +3048,7 @@ intrinsic_functions[] = {"sqrt", 1, true, intrinsic_sqrt}, {"step", 2, true, intrinsic_step}, {"tex2D", -1, false, intrinsic_tex2D}, + {"tex3D", -1, false, intrinsic_tex3D}, {"transpose", 1, true, intrinsic_transpose}, };
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl.c | 106 ++++++++++++++++++++++++------- libs/vkd3d-shader/hlsl.h | 34 +++++++--- libs/vkd3d-shader/hlsl_codegen.c | 72 +++++++++++++-------- libs/vkd3d-shader/hlsl_sm1.c | 2 +- libs/vkd3d-shader/hlsl_sm4.c | 4 +- 5 files changed, 155 insertions(+), 63 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.c b/libs/vkd3d-shader/hlsl.c index 6b8e1b10..f6506ea5 100644 --- a/libs/vkd3d-shader/hlsl.c +++ b/libs/vkd3d-shader/hlsl.c @@ -164,6 +164,49 @@ static unsigned int get_array_size(const struct hlsl_type *type) return 1; }
+bool hlsl_type_is_resource(const struct hlsl_type *type) +{ + if (type->type == HLSL_CLASS_OBJECT) + { + switch (type->base_type) + { + case HLSL_TYPE_TEXTURE: + case HLSL_TYPE_SAMPLER: + case HLSL_TYPE_UAV: + return true; + default: + return false; + } + } + return false; +} + +enum hlsl_regset hlsl_type_get_regset(struct hlsl_ctx *ctx, const struct hlsl_type *type) +{ + if (type->type <= HLSL_CLASS_LAST_NUMERIC) + return HLSL_REGSET_NUMERIC; + + if (type->type == HLSL_CLASS_OBJECT) + { + switch (type->base_type) + { + case HLSL_TYPE_TEXTURE: + return HLSL_REGSET_TEXTURES; + + case HLSL_TYPE_SAMPLER: + return HLSL_REGSET_SAMPLERS; + + case HLSL_TYPE_UAV: + return HLSL_REGSET_UAVS; + + default: + vkd3d_unreachable(); + } + } + + vkd3d_unreachable(); +} + unsigned int hlsl_type_get_sm4_offset(const struct hlsl_type *type, unsigned int offset) { /* Align to the next vec4 boundary if: @@ -171,7 +214,7 @@ unsigned int hlsl_type_get_sm4_offset(const struct hlsl_type *type, unsigned int * (b) the type would cross a vec4 boundary; i.e. a vec3 and a * vec1 can be packed together, but not a vec3 and a vec2. */ - if (type->type > HLSL_CLASS_LAST_NUMERIC || (offset & 3) + type->reg_size > 4) + if (type->type > HLSL_CLASS_LAST_NUMERIC || (offset & 3) + type->reg_size[HLSL_REGSET_NUMERIC] > 4) return align(offset, 4); return offset; } @@ -179,31 +222,40 @@ unsigned int hlsl_type_get_sm4_offset(const struct hlsl_type *type, unsigned int static void hlsl_type_calculate_reg_size(struct hlsl_ctx *ctx, struct hlsl_type *type) { bool is_sm4 = (ctx->profile->major_version >= 4); + unsigned int k; + + for (k = 0; k <= HLSL_REGSET_LAST; ++k) + type->reg_size[k] = 0;
switch (type->type) { case HLSL_CLASS_SCALAR: case HLSL_CLASS_VECTOR: - type->reg_size = is_sm4 ? type->dimx : 4; + type->reg_size[HLSL_REGSET_NUMERIC] = is_sm4 ? type->dimx : 4; break;
case HLSL_CLASS_MATRIX: if (hlsl_type_is_row_major(type)) - type->reg_size = is_sm4 ? (4 * (type->dimy - 1) + type->dimx) : (4 * type->dimy); + type->reg_size[HLSL_REGSET_NUMERIC] = is_sm4 ? (4 * (type->dimy - 1) + type->dimx) : (4 * type->dimy); else - type->reg_size = is_sm4 ? (4 * (type->dimx - 1) + type->dimy) : (4 * type->dimx); + type->reg_size[HLSL_REGSET_NUMERIC] = is_sm4 ? (4 * (type->dimx - 1) + type->dimy) : (4 * type->dimx); break;
case HLSL_CLASS_ARRAY: { - unsigned int element_size = type->e.array.type->reg_size; - if (type->e.array.elements_count == HLSL_ARRAY_ELEMENTS_COUNT_IMPLICIT) - type->reg_size = 0; - else if (is_sm4) - type->reg_size = (type->e.array.elements_count - 1) * align(element_size, 4) + element_size; - else - type->reg_size = type->e.array.elements_count * element_size; + break; + + for (k = 0; k <= HLSL_REGSET_LAST; ++k) + { + unsigned int element_size = type->e.array.type->reg_size[k]; + + if (is_sm4 && k == HLSL_REGSET_NUMERIC) + type->reg_size[k] = (type->e.array.elements_count - 1) * align(element_size, 4) + element_size; + else + type->reg_size[k] = type->e.array.elements_count * element_size; + } + break; }
@@ -212,16 +264,17 @@ static void hlsl_type_calculate_reg_size(struct hlsl_ctx *ctx, struct hlsl_type unsigned int i;
type->dimx = 0; - type->reg_size = 0; - for (i = 0; i < type->e.record.field_count; ++i) { struct hlsl_struct_field *field = &type->e.record.fields[i]; - unsigned int field_size = field->type->reg_size;
- type->reg_size = hlsl_type_get_sm4_offset(field->type, type->reg_size); - field->reg_offset = type->reg_size; - type->reg_size += field_size; + for (k = 0; k <= HLSL_REGSET_LAST; ++k) + { + if (k == HLSL_REGSET_NUMERIC) + type->reg_size[k] = hlsl_type_get_sm4_offset(field->type, type->reg_size[k]); + field->reg_offset[k] = type->reg_size[k]; + type->reg_size[k] += field->type->reg_size[k]; + }
type->dimx += field->type->dimx * field->type->dimy * get_array_size(field->type); } @@ -229,16 +282,25 @@ static void hlsl_type_calculate_reg_size(struct hlsl_ctx *ctx, struct hlsl_type }
case HLSL_CLASS_OBJECT: - type->reg_size = 0; + { + if (hlsl_type_is_resource(type)) + { + enum hlsl_regset regset = hlsl_type_get_regset(ctx, type); + + type->reg_size[regset] = 1; + } break; + } } }
-/* Returns the size of a type, considered as part of an array of that type. - * As such it includes padding after the type. */ -unsigned int hlsl_type_get_array_element_reg_size(const struct hlsl_type *type) +/* Returns the size of a type, considered as part of an array of that type, within a specific + * register set. As such it includes padding after the type, when applicable. */ +unsigned int hlsl_type_get_array_element_reg_size(const struct hlsl_type *type, enum hlsl_regset regset) { - return align(type->reg_size, 4); + if (regset == HLSL_REGSET_NUMERIC) + return align(type->reg_size[regset], 4); + return type->reg_size[regset]; }
static struct hlsl_type *hlsl_new_type(struct hlsl_ctx *ctx, const char *name, enum hlsl_type_class type_class, diff --git a/libs/vkd3d-shader/hlsl.h b/libs/vkd3d-shader/hlsl.h index 2d0beb6c..61b22272 100644 --- a/libs/vkd3d-shader/hlsl.h +++ b/libs/vkd3d-shader/hlsl.h @@ -122,6 +122,16 @@ enum hlsl_matrix_majority HLSL_ROW_MAJOR };
+enum hlsl_regset +{ + HLSL_REGSET_SAMPLERS, + HLSL_REGSET_TEXTURES, + HLSL_REGSET_UAVS, + HLSL_REGSET_LAST_OBJECT = HLSL_REGSET_UAVS, + HLSL_REGSET_NUMERIC, + HLSL_REGSET_LAST = HLSL_REGSET_NUMERIC, +}; + /* An HLSL source-level data type, including anonymous structs and typedefs. */ struct hlsl_type { @@ -183,12 +193,12 @@ struct hlsl_type struct hlsl_type *resource_format; } e;
- /* Number of numeric register components used by one value of this type (4 components make 1 - * register). - * If type is HLSL_CLASS_STRUCT or HLSL_CLASS_ARRAY, this value includes the reg_size of - * their elements and padding (which varies according to the backend). - * This value is 0 for types without numeric components, like objects. */ - unsigned int reg_size; + /* Number of numeric register components used by one value of this type, for each regset. + * For HLSL_REGSET_NUMERIC, 4 components make 1 register, while for other regsets 1 component makes + * 1 register. + * If type is HLSL_CLASS_STRUCT or HLSL_CLASS_ARRAY, the reg_size of their elements and padding + * (which varies according to the backend) is also included. */ + unsigned int reg_size[HLSL_REGSET_LAST + 1]; /* Offset where the type's description starts in the output bytecode, in bytes. */ size_t bytecode_offset;
@@ -215,8 +225,8 @@ struct hlsl_struct_field * type->modifiers instead) and that also are specific to the field and not the whole variable. * In particular, interpolation modifiers. */ unsigned int storage_modifiers; - /* Offset of the field within the type it belongs to, in numeric register components. */ - unsigned int reg_offset; + /* Offset of the field within the type it belongs to, in register components, for each regset. */ + unsigned int reg_offset[HLSL_REGSET_LAST + 1];
/* Offset where the fields's name starts in the output bytecode, in bytes. */ size_t name_bytecode_offset; @@ -547,10 +557,12 @@ struct hlsl_deref struct hlsl_src *path;
/* Single instruction node of data type uint used to represent the register offset (in register - * components), from the start of the variable, of the part referenced. + * components, within the pertaining regset), from the start of the variable, of the part + * referenced. * The path is lowered to this single offset -- whose value may vary between SM1 and SM4 -- * before writing the bytecode. */ struct hlsl_src offset; + enum hlsl_regset offset_regset; };
struct hlsl_ir_load @@ -1066,13 +1078,15 @@ bool hlsl_scope_add_type(struct hlsl_scope *scope, struct hlsl_type *type); struct hlsl_type *hlsl_type_clone(struct hlsl_ctx *ctx, struct hlsl_type *old, unsigned int default_majority, unsigned int modifiers); unsigned int hlsl_type_component_count(const struct hlsl_type *type); -unsigned int hlsl_type_get_array_element_reg_size(const struct hlsl_type *type); +unsigned int hlsl_type_get_array_element_reg_size(const struct hlsl_type *type, enum hlsl_regset regset); struct hlsl_type *hlsl_type_get_component_type(struct hlsl_ctx *ctx, struct hlsl_type *type, unsigned int index); bool hlsl_type_is_row_major(const struct hlsl_type *type); unsigned int hlsl_type_minor_size(const struct hlsl_type *type); unsigned int hlsl_type_major_size(const struct hlsl_type *type); unsigned int hlsl_type_element_count(const struct hlsl_type *type); +bool hlsl_type_is_resource(const struct hlsl_type *type); +enum hlsl_regset hlsl_type_get_regset(struct hlsl_ctx *ctx, const struct hlsl_type *type); unsigned int hlsl_type_get_sm4_offset(const struct hlsl_type *type, unsigned int offset); bool hlsl_types_are_equal(const struct hlsl_type *t1, const struct hlsl_type *t2);
diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index aa950e35..a0373b58 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -24,7 +24,7 @@ /* TODO: remove when no longer needed, only used for new_offset_instr_from_deref() */ static struct hlsl_ir_node *new_offset_from_path_index(struct hlsl_ctx *ctx, struct hlsl_block *block, struct hlsl_type *type, struct hlsl_ir_node *offset, struct hlsl_ir_node *idx, - const struct vkd3d_shader_location *loc) + enum hlsl_regset regset, const struct vkd3d_shader_location *loc) { struct hlsl_ir_node *idx_offset = NULL; struct hlsl_ir_constant *c; @@ -52,7 +52,7 @@ static struct hlsl_ir_node *new_offset_from_path_index(struct hlsl_ctx *ctx, str
case HLSL_CLASS_ARRAY: { - unsigned int size = hlsl_type_get_array_element_reg_size(type->e.array.type); + unsigned int size = hlsl_type_get_array_element_reg_size(type->e.array.type, regset);
if (!(c = hlsl_new_uint_constant(ctx, size, loc))) return NULL; @@ -70,7 +70,7 @@ static struct hlsl_ir_node *new_offset_from_path_index(struct hlsl_ctx *ctx, str unsigned int field_idx = hlsl_ir_constant(idx)->value[0].u; struct hlsl_struct_field *field = &type->e.record.fields[field_idx];
- if (!(c = hlsl_new_uint_constant(ctx, field->reg_offset, loc))) + if (!(c = hlsl_new_uint_constant(ctx, field->reg_offset[regset], loc))) return NULL; list_add_tail(&block->instrs, &c->node.entry);
@@ -110,7 +110,8 @@ static struct hlsl_ir_node *new_offset_instr_from_deref(struct hlsl_ctx *ctx, st { struct hlsl_block idx_block;
- if (!(offset = new_offset_from_path_index(ctx, &idx_block, type, offset, deref->path[i].node, loc))) + if (!(offset = new_offset_from_path_index(ctx, &idx_block, type, offset, deref->path[i].node, + deref->offset_regset, loc))) return NULL;
list_move_tail(&block->instrs, &idx_block.instrs); @@ -125,6 +126,7 @@ static struct hlsl_ir_node *new_offset_instr_from_deref(struct hlsl_ctx *ctx, st static void replace_deref_path_with_offset(struct hlsl_ctx *ctx, struct hlsl_deref *deref, struct hlsl_ir_node *instr) { + const struct hlsl_type *type; struct hlsl_ir_node *offset; struct hlsl_block block;
@@ -134,6 +136,15 @@ static void replace_deref_path_with_offset(struct hlsl_ctx *ctx, struct hlsl_der /* register offsets shouldn't be used before this point is reached. */ assert(!deref->offset.node);
+ type = hlsl_deref_get_type(ctx, deref); + + /* Instruction that directly refer to structs and arrays (instead of single-register componets) + * are removed later by dce. So it is not a problem to consider them numerics for computing + * offsets. */ + deref->offset_regset = HLSL_REGSET_NUMERIC; + if (hlsl_type_is_resource(type)) + deref->offset_regset = hlsl_type_get_regset(ctx, type); + if (!(offset = new_offset_instr_from_deref(ctx, &block, deref, &instr->loc))) return; list_move_before(&instr->entry, &block.instrs); @@ -2228,32 +2239,33 @@ static struct hlsl_reg allocate_range(struct hlsl_ctx *ctx, struct liveness *liv static const char *debug_register(char class, struct hlsl_reg reg, const struct hlsl_type *type) { static const char writemask_offset[] = {'w','x','y','z'}; + unsigned int reg_size = type->reg_size[HLSL_REGSET_NUMERIC];
- if (type->reg_size > 4) + if (reg_size > 4) { - if (type->reg_size & 3) - return vkd3d_dbg_sprintf("%c%u-%c%u.%c", class, reg.id, class, - reg.id + (type->reg_size / 4), writemask_offset[type->reg_size & 3]); + if (reg_size & 3) + return vkd3d_dbg_sprintf("%c%u-%c%u.%c", class, reg.id, class, reg.id + (reg_size / 4), + writemask_offset[reg_size & 3]);
- return vkd3d_dbg_sprintf("%c%u-%c%u", class, reg.id, class, - reg.id + (type->reg_size / 4) - 1); + return vkd3d_dbg_sprintf("%c%u-%c%u", class, reg.id, class, reg.id + (reg_size / 4) - 1); } return vkd3d_dbg_sprintf("%c%u%s", class, reg.id, debug_hlsl_writemask(reg.writemask)); }
static void allocate_variable_temp_register(struct hlsl_ctx *ctx, struct hlsl_ir_var *var, struct liveness *liveness) { + unsigned int reg_size = var->data_type->reg_size[HLSL_REGSET_NUMERIC]; + if (var->is_input_semantic || var->is_output_semantic || var->is_uniform) return;
if (!var->reg.allocated && var->last_read) { - if (var->data_type->reg_size > 4) - var->reg = allocate_range(ctx, liveness, var->first_write, - var->last_read, var->data_type->reg_size); + if (reg_size > 4) + var->reg = allocate_range(ctx, liveness, var->first_write, var->last_read, reg_size); else - var->reg = allocate_register(ctx, liveness, var->first_write, - var->last_read, var->data_type->reg_size); + var->reg = allocate_register(ctx, liveness, var->first_write, var->last_read, reg_size); + TRACE("Allocated %s to %s (liveness %u-%u).\n", var->name, debug_register('r', var->reg, var->data_type), var->first_write, var->last_read); } @@ -2267,12 +2279,12 @@ static void allocate_temp_registers_recurse(struct hlsl_ctx *ctx, struct hlsl_bl { if (!instr->reg.allocated && instr->last_read) { - if (instr->data_type->reg_size > 4) - instr->reg = allocate_range(ctx, liveness, instr->index, - instr->last_read, instr->data_type->reg_size); + unsigned int reg_size = instr->data_type->reg_size[HLSL_REGSET_NUMERIC]; + + if (reg_size > 4) + instr->reg = allocate_range(ctx, liveness, instr->index, instr->last_read, reg_size); else - instr->reg = allocate_register(ctx, liveness, instr->index, - instr->last_read, instr->data_type->reg_size); + instr->reg = allocate_register(ctx, liveness, instr->index, instr->last_read, reg_size); TRACE("Allocated anonymous expression @%u to %s (liveness %u-%u).\n", instr->index, debug_register('r', instr->reg, instr->data_type), instr->index, instr->last_read); } @@ -2330,7 +2342,7 @@ static void allocate_const_registers_recurse(struct hlsl_ctx *ctx, struct hlsl_b struct hlsl_ir_constant *constant = hlsl_ir_constant(instr); const struct hlsl_type *type = instr->data_type; unsigned int x, y, i, writemask, end_reg; - unsigned int reg_size = type->reg_size; + unsigned int reg_size = type->reg_size[HLSL_REGSET_NUMERIC];
if (reg_size > 4) constant->reg = allocate_range(ctx, liveness, 1, UINT_MAX, reg_size); @@ -2429,15 +2441,15 @@ static void allocate_const_registers(struct hlsl_ctx *ctx, struct hlsl_ir_functi { if (var->is_uniform && var->last_read) { - if (var->data_type->reg_size == 0) + if (var->data_type->reg_size[HLSL_REGSET_NUMERIC] == 0) continue;
- if (var->data_type->reg_size > 4) - var->reg = allocate_range(ctx, &liveness, 1, UINT_MAX, var->data_type->reg_size); + if (var->data_type->reg_size[HLSL_REGSET_NUMERIC] > 4) + var->reg = allocate_range(ctx, &liveness, 1, UINT_MAX, var->data_type->reg_size[HLSL_REGSET_NUMERIC]); else { var->reg = allocate_register(ctx, &liveness, 1, UINT_MAX, 4); - var->reg.writemask = (1u << var->data_type->reg_size) - 1; + var->reg.writemask = (1u << var->data_type->reg_size[HLSL_REGSET_NUMERIC]) - 1; } TRACE("Allocated %s to %s.\n", var->name, debug_register('c', var->reg, var->data_type)); } @@ -2554,7 +2566,7 @@ static void calculate_buffer_offset(struct hlsl_ir_var *var)
var->buffer_offset = buffer->size; TRACE("Allocated buffer offset %u to %s.\n", var->buffer_offset, var->name); - buffer->size += var->data_type->reg_size; + buffer->size += var->data_type->reg_size[HLSL_REGSET_NUMERIC]; if (var->last_read) buffer->used_size = buffer->size; } @@ -2809,6 +2821,7 @@ bool hlsl_component_index_range_from_deref(struct hlsl_ctx *ctx, const struct hl bool hlsl_offset_from_deref(struct hlsl_ctx *ctx, const struct hlsl_deref *deref, unsigned int *offset) { struct hlsl_ir_node *offset_node = deref->offset.node; + unsigned int size;
if (!offset_node) { @@ -2825,10 +2838,11 @@ bool hlsl_offset_from_deref(struct hlsl_ctx *ctx, const struct hlsl_deref *deref
*offset = hlsl_ir_constant(offset_node)->value[0].u;
- if (*offset >= deref->var->data_type->reg_size) + size = deref->var->data_type->reg_size[deref->offset_regset]; + if (*offset >= size) { hlsl_error(ctx, &deref->offset.node->loc, VKD3D_SHADER_ERROR_HLSL_OFFSET_OUT_OF_BOUNDS, - "Dereference is out of bounds. %u/%u", *offset, deref->var->data_type->reg_size); + "Dereference is out of bounds. %u/%u", *offset, size); return false; }
@@ -2854,6 +2868,8 @@ struct hlsl_reg hlsl_reg_from_deref(struct hlsl_ctx *ctx, const struct hlsl_dere struct hlsl_reg ret = var->reg; unsigned int offset = hlsl_offset_from_deref_safe(ctx, deref);
+ assert(deref->offset_regset == HLSL_REGSET_NUMERIC); + ret.id += offset / 4;
ret.writemask = 0xf & (0xf << (offset % 4)); diff --git a/libs/vkd3d-shader/hlsl_sm1.c b/libs/vkd3d-shader/hlsl_sm1.c index a09d7566..22373d91 100644 --- a/libs/vkd3d-shader/hlsl_sm1.c +++ b/libs/vkd3d-shader/hlsl_sm1.c @@ -366,7 +366,7 @@ static void write_sm1_uniforms(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffe else { put_u32(buffer, vkd3d_make_u32(D3DXRS_FLOAT4, var->reg.id)); - put_u32(buffer, var->data_type->reg_size / 4); + put_u32(buffer, var->data_type->reg_size[HLSL_REGSET_NUMERIC] / 4); } put_u32(buffer, 0); /* type */ put_u32(buffer, 0); /* FIXME: default value */ diff --git a/libs/vkd3d-shader/hlsl_sm4.c b/libs/vkd3d-shader/hlsl_sm4.c index 107339cb..c61d5d78 100644 --- a/libs/vkd3d-shader/hlsl_sm4.c +++ b/libs/vkd3d-shader/hlsl_sm4.c @@ -395,7 +395,7 @@ static void write_sm4_type(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffer *b
put_u32(buffer, field->name_bytecode_offset); put_u32(buffer, field->type->bytecode_offset); - put_u32(buffer, field->reg_offset); + put_u32(buffer, field->reg_offset[HLSL_REGSET_NUMERIC]); } }
@@ -711,7 +711,7 @@ static void write_sm4_rdef(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc)
put_u32(&buffer, 0); /* name */ put_u32(&buffer, var->buffer_offset * sizeof(float)); - put_u32(&buffer, var->data_type->reg_size * sizeof(float)); + put_u32(&buffer, var->data_type->reg_size[HLSL_REGSET_NUMERIC] * sizeof(float)); put_u32(&buffer, flags); put_u32(&buffer, 0); /* type */ put_u32(&buffer, 0); /* FIXME: default value */
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl.h | 16 ++---- libs/vkd3d-shader/hlsl_codegen.c | 55 ++++++++++++-------- libs/vkd3d-shader/hlsl_sm1.c | 22 +++++--- libs/vkd3d-shader/hlsl_sm4.c | 86 +++++++++++++++++++++++--------- 4 files changed, 115 insertions(+), 64 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.h b/libs/vkd3d-shader/hlsl.h index 61b22272..3b8170f2 100644 --- a/libs/vkd3d-shader/hlsl.h +++ b/libs/vkd3d-shader/hlsl.h @@ -382,19 +382,13 @@ struct hlsl_ir_var /* Offset where the variable's value is stored within its buffer in numeric register components. * This in case the variable is uniform. */ unsigned int buffer_offset; - /* Register to which the variable is allocated during its lifetime. - * In case that the variable spans multiple registers, this is set to the start of the register - * range. - * The register type is inferred from the data type and the storage of the variable. + /* Register to which the variable is allocated during its lifetime, for each register set. + * In case that the variable spans multiple registers in one regset, this is set to the + * start of the register range. * Builtin semantics don't use the field. * In SM4, uniforms don't use the field because they are located using the buffer's hlsl_reg - * and the buffer_offset instead. - * If the variable is an input semantic copy, the register is 'v'. - * If the variable is an output semantic copy, the register is 'o'. - * Textures are stored on 's' registers in SM1, and 't' registers in SM4. - * Samplers are stored on 's' registers. - * UAVs are stored on 'u' registers. */ - struct hlsl_reg reg; + * and the buffer_offset instead. */ + struct hlsl_reg regs[HLSL_REGSET_LAST + 1];
uint32_t is_input_semantic : 1; uint32_t is_output_semantic : 1; diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index a0373b58..a3389ec7 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -2259,15 +2259,17 @@ static void allocate_variable_temp_register(struct hlsl_ctx *ctx, struct hlsl_ir if (var->is_input_semantic || var->is_output_semantic || var->is_uniform) return;
- if (!var->reg.allocated && var->last_read) + if (!var->regs[HLSL_REGSET_NUMERIC].allocated && var->last_read) { if (reg_size > 4) - var->reg = allocate_range(ctx, liveness, var->first_write, var->last_read, reg_size); + var->regs[HLSL_REGSET_NUMERIC] = allocate_range(ctx, liveness, var->first_write, + var->last_read, reg_size); else - var->reg = allocate_register(ctx, liveness, var->first_write, var->last_read, reg_size); + var->regs[HLSL_REGSET_NUMERIC] = allocate_register(ctx, liveness, var->first_write, + var->last_read, reg_size);
- TRACE("Allocated %s to %s (liveness %u-%u).\n", var->name, - debug_register('r', var->reg, var->data_type), var->first_write, var->last_read); + TRACE("Allocated %s to %s (liveness %u-%u).\n", var->name, debug_register('r', + var->regs[HLSL_REGSET_NUMERIC], var->data_type), var->first_write, var->last_read); } }
@@ -2441,17 +2443,21 @@ static void allocate_const_registers(struct hlsl_ctx *ctx, struct hlsl_ir_functi { if (var->is_uniform && var->last_read) { - if (var->data_type->reg_size[HLSL_REGSET_NUMERIC] == 0) + unsigned int reg_size = var->data_type->reg_size[HLSL_REGSET_NUMERIC]; + + if (reg_size == 0) continue;
- if (var->data_type->reg_size[HLSL_REGSET_NUMERIC] > 4) - var->reg = allocate_range(ctx, &liveness, 1, UINT_MAX, var->data_type->reg_size[HLSL_REGSET_NUMERIC]); + if (reg_size > 4) + { + var->regs[HLSL_REGSET_NUMERIC] = allocate_range(ctx, &liveness, 1, UINT_MAX, reg_size); + } else { - var->reg = allocate_register(ctx, &liveness, 1, UINT_MAX, 4); - var->reg.writemask = (1u << var->data_type->reg_size[HLSL_REGSET_NUMERIC]) - 1; + var->regs[HLSL_REGSET_NUMERIC] = allocate_register(ctx, &liveness, 1, UINT_MAX, 4); + var->regs[HLSL_REGSET_NUMERIC].writemask = (1u << reg_size) - 1; } - TRACE("Allocated %s to %s.\n", var->name, debug_register('c', var->reg, var->data_type)); + TRACE("Allocated %s to %s.\n", var->name, debug_register('c', var->regs[HLSL_REGSET_NUMERIC], var->data_type)); } } } @@ -2525,10 +2531,11 @@ static void allocate_semantic_register(struct hlsl_ctx *ctx, struct hlsl_ir_var } else { - var->reg.allocated = true; - var->reg.id = (*counter)++; - var->reg.writemask = (1 << var->data_type->dimx) - 1; - TRACE("Allocated %s to %s.\n", var->name, debug_register(output ? 'o' : 'v', var->reg, var->data_type)); + var->regs[HLSL_REGSET_NUMERIC].allocated = true; + var->regs[HLSL_REGSET_NUMERIC].id = (*counter)++; + var->regs[HLSL_REGSET_NUMERIC].writemask = (1 << var->data_type->dimx) - 1; + TRACE("Allocated %s to %s.\n", var->name, debug_register(output ? 'o' : 'v', + var->regs[HLSL_REGSET_NUMERIC], var->data_type)); } }
@@ -2691,10 +2698,14 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type)
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { + enum hlsl_regset regset; + if (!var->last_read || var->data_type->type != HLSL_CLASS_OBJECT || var->data_type->base_type != type) continue;
+ regset = hlsl_type_get_regset(ctx, var->data_type); + if (var->reg_reservation.type == type_info->reg_name) { const struct hlsl_ir_var *reserved_object = get_reserved_object(ctx, type_info->reg_name, @@ -2716,8 +2727,8 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type) type_info->reg_name, var->reg_reservation.index); }
- var->reg.id = var->reg_reservation.index; - var->reg.allocated = true; + var->regs[regset].id = var->reg_reservation.index; + var->regs[regset].allocated = true; TRACE("Allocated reserved %s to %c%u.\n", var->name, type_info->reg_name, var->reg_reservation.index); } else if (!var->reg_reservation.type) @@ -2725,8 +2736,8 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type) while (get_reserved_object(ctx, type_info->reg_name, index)) ++index;
- var->reg.id = index; - var->reg.allocated = true; + var->regs[regset].id = index; + var->regs[regset].allocated = true; TRACE("Allocated object to %c%u.\n", type_info->reg_name, index); ++index; } @@ -2865,7 +2876,7 @@ unsigned int hlsl_offset_from_deref_safe(struct hlsl_ctx *ctx, const struct hlsl struct hlsl_reg hlsl_reg_from_deref(struct hlsl_ctx *ctx, const struct hlsl_deref *deref) { const struct hlsl_ir_var *var = deref->var; - struct hlsl_reg ret = var->reg; + struct hlsl_reg ret = var->regs[HLSL_REGSET_NUMERIC]; unsigned int offset = hlsl_offset_from_deref_safe(ctx, deref);
assert(deref->offset_regset == HLSL_REGSET_NUMERIC); @@ -2873,8 +2884,8 @@ struct hlsl_reg hlsl_reg_from_deref(struct hlsl_ctx *ctx, const struct hlsl_dere ret.id += offset / 4;
ret.writemask = 0xf & (0xf << (offset % 4)); - if (var->reg.writemask) - ret.writemask = hlsl_combine_writemasks(var->reg.writemask, ret.writemask); + if (var->regs[HLSL_REGSET_NUMERIC].writemask) + ret.writemask = hlsl_combine_writemasks(var->regs[HLSL_REGSET_NUMERIC].writemask, ret.writemask);
return ret; } diff --git a/libs/vkd3d-shader/hlsl_sm1.c b/libs/vkd3d-shader/hlsl_sm1.c index 22373d91..7e8cd69c 100644 --- a/libs/vkd3d-shader/hlsl_sm1.c +++ b/libs/vkd3d-shader/hlsl_sm1.c @@ -315,7 +315,9 @@ static void write_sm1_uniforms(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffe
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - if (!var->semantic.name && var->reg.allocated) + enum hlsl_regset regset = hlsl_type_get_regset(ctx, var->data_type); + + if (!var->semantic.name && var->regs[regset].allocated) { ++uniform_count;
@@ -353,20 +355,24 @@ static void write_sm1_uniforms(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffe
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - if (!var->semantic.name && var->reg.allocated) + enum hlsl_regset regset = hlsl_type_get_regset(ctx, var->data_type); + + if (!var->semantic.name && var->regs[regset].allocated) { put_u32(buffer, 0); /* name */ if (var->data_type->type == HLSL_CLASS_OBJECT && (var->data_type->base_type == HLSL_TYPE_SAMPLER || var->data_type->base_type == HLSL_TYPE_TEXTURE)) { - put_u32(buffer, vkd3d_make_u32(D3DXRS_SAMPLER, var->reg.id)); + assert(regset == HLSL_REGSET_SAMPLERS); + put_u32(buffer, vkd3d_make_u32(D3DXRS_SAMPLER, var->regs[regset].id)); put_u32(buffer, 1); } else { - put_u32(buffer, vkd3d_make_u32(D3DXRS_FLOAT4, var->reg.id)); - put_u32(buffer, var->data_type->reg_size[HLSL_REGSET_NUMERIC] / 4); + assert(regset == HLSL_REGSET_NUMERIC); + put_u32(buffer, vkd3d_make_u32(D3DXRS_FLOAT4, var->regs[regset].id)); + put_u32(buffer, var->data_type->reg_size[regset] / 4); } put_u32(buffer, 0); /* type */ put_u32(buffer, 0); /* FIXME: default value */ @@ -377,7 +383,9 @@ static void write_sm1_uniforms(struct hlsl_ctx *ctx, struct vkd3d_bytecode_buffe
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - if (!var->semantic.name && var->reg.allocated) + enum hlsl_regset regset = hlsl_type_get_regset(ctx, var->data_type); + + if (!var->semantic.name && var->regs[regset].allocated) { size_t var_offset = vars_start + (uniform_count * 5 * sizeof(uint32_t)); size_t name_offset; @@ -574,7 +582,7 @@ static void write_sm1_semantic_dcl(struct hlsl_ctx *ctx, struct vkd3d_bytecode_b ret = hlsl_sm1_usage_from_semantic(&var->semantic, &usage, &usage_idx); assert(ret); reg.type = output ? D3DSPR_OUTPUT : D3DSPR_INPUT; - reg.reg = var->reg.id; + reg.reg = var->regs[HLSL_REGSET_NUMERIC].id; }
token = D3DSIO_DCL; diff --git a/libs/vkd3d-shader/hlsl_sm4.c b/libs/vkd3d-shader/hlsl_sm4.c index c61d5d78..3790e220 100644 --- a/libs/vkd3d-shader/hlsl_sm4.c +++ b/libs/vkd3d-shader/hlsl_sm4.c @@ -182,9 +182,9 @@ static void write_sm4_signature(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc, } else { - assert(var->reg.allocated); + assert(var->regs[HLSL_REGSET_NUMERIC].allocated); type = VKD3D_SM4_RT_INPUT; - reg_idx = var->reg.id; + reg_idx = var->regs[HLSL_REGSET_NUMERIC].id; }
use_mask = width; /* FIXME: accurately report use mask */ @@ -480,16 +480,34 @@ static D3D_SRV_DIMENSION sm4_rdef_resource_dimension(const struct hlsl_type *typ } }
-static int sm4_compare_externs(const struct hlsl_ir_var *a, const struct hlsl_ir_var *b) +static int sm4_compare_externs(struct hlsl_ctx *ctx, const struct hlsl_ir_var *a, const struct hlsl_ir_var *b) { - if (a->data_type->base_type != b->data_type->base_type) - return a->data_type->base_type - b->data_type->base_type; - if (a->reg.allocated && b->reg.allocated) - return a->reg.id - b->reg.id; + enum hlsl_regset a_regset, b_regset; + bool a_allocated, b_allocated; + unsigned int a_id, b_id; + + a_regset = HLSL_REGSET_NUMERIC; + if (hlsl_type_is_resource(a->data_type)) + a_regset = hlsl_type_get_regset(ctx, a->data_type); + + b_regset = HLSL_REGSET_NUMERIC; + if (hlsl_type_is_resource(b->data_type)) + b_regset = hlsl_type_get_regset(ctx, b->data_type); + + a_allocated = a->regs[a_regset].allocated; + a_id = a->regs[a_regset].id; + + b_allocated = b->regs[b_regset].allocated; + b_id = b->regs[b_regset].id; + + if (a_regset != b_regset) + return a_regset - b_regset; + if (a_allocated && b_allocated) + return a_id - b_id; return strcmp(a->name, b->name); }
-static void sm4_sort_extern(struct list *sorted, struct hlsl_ir_var *to_sort) +static void sm4_sort_extern(struct hlsl_ctx *ctx, struct list *sorted, struct hlsl_ir_var *to_sort) { struct hlsl_ir_var *var;
@@ -497,7 +515,7 @@ static void sm4_sort_extern(struct list *sorted, struct hlsl_ir_var *to_sort)
LIST_FOR_EACH_ENTRY(var, sorted, struct hlsl_ir_var, extern_entry) { - if (sm4_compare_externs(to_sort, var) < 0) + if (sm4_compare_externs(ctx, to_sort, var) < 0) { list_add_before(&var->extern_entry, &to_sort->extern_entry); return; @@ -515,7 +533,7 @@ static void sm4_sort_externs(struct hlsl_ctx *ctx) LIST_FOR_EACH_ENTRY_SAFE(var, next, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { if (var->data_type->type == HLSL_CLASS_OBJECT) - sm4_sort_extern(&sorted, var); + sm4_sort_extern(ctx, &sorted, var); } list_move_tail(&ctx->extern_vars, &sorted); } @@ -544,8 +562,14 @@ static void write_sm4_rdef(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc)
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - if (var->reg.allocated && var->data_type->type == HLSL_CLASS_OBJECT) - ++resource_count; + enum hlsl_regset regset; + + if (!hlsl_type_is_resource(var->data_type)) + continue; + regset = hlsl_type_get_regset(ctx, var->data_type); + if (!var->regs[regset].allocated) + continue; + ++resource_count; }
LIST_FOR_EACH_ENTRY(cbuffer, &ctx->buffers, struct hlsl_buffer, entry) @@ -585,9 +609,13 @@ static void write_sm4_rdef(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc)
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { + enum hlsl_regset regset; uint32_t flags = 0;
- if (!var->reg.allocated || var->data_type->type != HLSL_CLASS_OBJECT) + if (!hlsl_type_is_resource(var->data_type)) + continue; + regset = hlsl_type_get_regset(ctx, var->data_type); + if (!var->regs[regset].allocated) continue;
if (var->reg_reservation.type) @@ -595,7 +623,7 @@ static void write_sm4_rdef(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc)
put_u32(&buffer, 0); /* name */ put_u32(&buffer, sm4_resource_type(var->data_type)); - if (var->data_type->base_type == HLSL_TYPE_SAMPLER) + if (regset == HLSL_REGSET_SAMPLERS) { put_u32(&buffer, 0); put_u32(&buffer, 0); @@ -608,7 +636,7 @@ static void write_sm4_rdef(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc) put_u32(&buffer, ~0u); /* FIXME: multisample count */ flags |= (var->data_type->e.resource_format->dimx - 1) << VKD3D_SM4_SIF_TEXTURE_COMPONENTS_SHIFT; } - put_u32(&buffer, var->reg.id); + put_u32(&buffer, var->regs[regset].id); put_u32(&buffer, 1); /* bind count */ put_u32(&buffer, flags); } @@ -637,7 +665,12 @@ static void write_sm4_rdef(struct hlsl_ctx *ctx, struct dxbc_writer *dxbc)
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - if (!var->reg.allocated || var->data_type->type != HLSL_CLASS_OBJECT) + enum hlsl_regset regset; + + if (!hlsl_type_is_resource(var->data_type)) + continue; + regset = hlsl_type_get_regset(ctx, var->data_type); + if (!var->regs[regset].allocated) continue;
string_offset = put_string(&buffer, var->name); @@ -863,7 +896,7 @@ static void sm4_register_from_deref(struct hlsl_ctx *ctx, struct sm4_register *r reg->dim = VKD3D_SM4_DIMENSION_VEC4; if (swizzle_type) *swizzle_type = VKD3D_SM4_SWIZZLE_VEC4; - reg->idx[0] = var->reg.id; + reg->idx[0] = var->regs[HLSL_REGSET_TEXTURES].id; reg->idx_count = 1; *writemask = VKD3DSP_WRITEMASK_ALL; } @@ -873,7 +906,7 @@ static void sm4_register_from_deref(struct hlsl_ctx *ctx, struct sm4_register *r reg->dim = VKD3D_SM4_DIMENSION_VEC4; if (swizzle_type) *swizzle_type = VKD3D_SM4_SWIZZLE_VEC4; - reg->idx[0] = var->reg.id; + reg->idx[0] = var->regs[HLSL_REGSET_UAVS].id; reg->idx_count = 1; *writemask = VKD3DSP_WRITEMASK_ALL; } @@ -883,7 +916,7 @@ static void sm4_register_from_deref(struct hlsl_ctx *ctx, struct sm4_register *r reg->dim = VKD3D_SM4_DIMENSION_NONE; if (swizzle_type) *swizzle_type = VKD3D_SM4_SWIZZLE_NONE; - reg->idx[0] = var->reg.id; + reg->idx[0] = var->regs[HLSL_REGSET_SAMPLERS].id; reg->idx_count = 1; *writemask = VKD3DSP_WRITEMASK_ALL; } @@ -1153,7 +1186,7 @@ static void write_sm4_dcl_sampler(struct vkd3d_bytecode_buffer *buffer, const st .opcode = VKD3D_SM4_OP_DCL_SAMPLER,
.dsts[0].reg.type = VKD3D_SM4_RT_SAMPLER, - .dsts[0].reg.idx = {var->reg.id}, + .dsts[0].reg.idx = {var->regs[HLSL_REGSET_SAMPLERS].id}, .dsts[0].reg.idx_count = 1, .dst_count = 1, }; @@ -1169,7 +1202,7 @@ static void write_sm4_dcl_texture(struct vkd3d_bytecode_buffer *buffer, const st | (sm4_resource_dimension(var->data_type) << VKD3D_SM4_RESOURCE_TYPE_SHIFT),
.dsts[0].reg.type = uav ? VKD3D_SM5_RT_UAV : VKD3D_SM4_RT_RESOURCE, - .dsts[0].reg.idx = {var->reg.id}, + .dsts[0].reg.idx = {uav ? var->regs[HLSL_REGSET_UAVS].id : var->regs[HLSL_REGSET_TEXTURES].id}, .dsts[0].reg.idx_count = 1, .dst_count = 1,
@@ -1208,9 +1241,9 @@ static void write_sm4_dcl_semantic(struct hlsl_ctx *ctx, struct vkd3d_bytecode_b else { instr.dsts[0].reg.type = output ? VKD3D_SM4_RT_OUTPUT : VKD3D_SM4_RT_INPUT; - instr.dsts[0].reg.idx[0] = var->reg.id; + instr.dsts[0].reg.idx[0] = var->regs[HLSL_REGSET_NUMERIC].id; instr.dsts[0].reg.idx_count = 1; - instr.dsts[0].writemask = var->reg.writemask; + instr.dsts[0].writemask = var->regs[HLSL_REGSET_NUMERIC].writemask; }
if (instr.dsts[0].reg.type == VKD3D_SM4_RT_DEPTHOUT) @@ -2442,7 +2475,12 @@ static void write_sm4_shdr(struct hlsl_ctx *ctx,
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, const struct hlsl_ir_var, extern_entry) { - if (!var->reg.allocated || var->data_type->type != HLSL_CLASS_OBJECT) + enum hlsl_regset regset; + + if (!hlsl_type_is_resource(var->data_type)) + continue; + regset = hlsl_type_get_regset(ctx, var->data_type); + if (!var->regs[regset].allocated) continue;
if (var->data_type->base_type == HLSL_TYPE_SAMPLER)
From: Francisco Casas fcasas@codeweavers.com
Note that hlsl_regset_name() requires the ctx argument because, conceptually, regsets are not to be associated to a particular letter in the assembly. It could happen that the letter depends on the shader profile. --- libs/vkd3d-shader/hlsl.c | 16 ++++++++ libs/vkd3d-shader/hlsl.h | 2 + libs/vkd3d-shader/hlsl_codegen.c | 69 ++++++++++---------------------- 3 files changed, 39 insertions(+), 48 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.c b/libs/vkd3d-shader/hlsl.c index f6506ea5..ac2bfae0 100644 --- a/libs/vkd3d-shader/hlsl.c +++ b/libs/vkd3d-shader/hlsl.c @@ -164,6 +164,22 @@ static unsigned int get_array_size(const struct hlsl_type *type) return 1; }
+char hlsl_regset_name(const struct hlsl_ctx *ctx, enum hlsl_regset regset) +{ + switch (regset) + { + case HLSL_REGSET_SAMPLERS: + return 's'; + case HLSL_REGSET_TEXTURES: + return 't'; + case HLSL_REGSET_UAVS: + return 'u'; + case HLSL_REGSET_NUMERIC: + vkd3d_unreachable(); + } + vkd3d_unreachable(); +} + bool hlsl_type_is_resource(const struct hlsl_type *type) { if (type->type == HLSL_CLASS_OBJECT) diff --git a/libs/vkd3d-shader/hlsl.h b/libs/vkd3d-shader/hlsl.h index 3b8170f2..2e3eb9fe 100644 --- a/libs/vkd3d-shader/hlsl.h +++ b/libs/vkd3d-shader/hlsl.h @@ -1069,6 +1069,8 @@ void hlsl_pop_scope(struct hlsl_ctx *ctx);
bool hlsl_scope_add_type(struct hlsl_scope *scope, struct hlsl_type *type);
+char hlsl_regset_name(const struct hlsl_ctx *ctx, enum hlsl_regset regset); + struct hlsl_type *hlsl_type_clone(struct hlsl_ctx *ctx, struct hlsl_type *old, unsigned int default_majority, unsigned int modifiers); unsigned int hlsl_type_component_count(const struct hlsl_type *type); diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index a3389ec7..1c362b0e 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -2641,50 +2641,28 @@ static void allocate_buffers(struct hlsl_ctx *ctx) } }
-static const struct hlsl_ir_var *get_reserved_object(struct hlsl_ctx *ctx, char type, uint32_t index) +static const struct hlsl_ir_var *get_reserved_object(struct hlsl_ctx *ctx, enum hlsl_regset regset, + uint32_t index) { const struct hlsl_ir_var *var;
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, const struct hlsl_ir_var, extern_entry) { - if (var->last_read && var->reg_reservation.type == type && var->reg_reservation.index == index) + if (var->last_read && var->reg_reservation.type == hlsl_regset_name(ctx, regset) + && var->reg_reservation.index == index) return var; } return NULL; }
-static const struct object_type_info +static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_regset regset) { - enum hlsl_base_type type; - char reg_name; -} -object_types[] = -{ - { HLSL_TYPE_SAMPLER, 's' }, - { HLSL_TYPE_TEXTURE, 't' }, - { HLSL_TYPE_UAV, 'u' }, -}; - -static const struct object_type_info *get_object_type_info(enum hlsl_base_type type) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(object_types); ++i) - if (type == object_types[i].type) - return &object_types[i]; - - WARN("No type info for object type %u.\n", type); - return NULL; -} - -static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type) -{ - const struct object_type_info *type_info = get_object_type_info(type); + char regset_name = hlsl_regset_name(ctx, regset); struct hlsl_ir_var *var; uint32_t min_index = 0; uint32_t index;
- if (type == HLSL_TYPE_UAV) + if (regset == HLSL_REGSET_UAVS) { LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { @@ -2698,21 +2676,17 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type)
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - enum hlsl_regset regset; - - if (!var->last_read || var->data_type->type != HLSL_CLASS_OBJECT - || var->data_type->base_type != type) + if (!var->last_read || var->data_type->reg_size[regset] == 0) continue;
- regset = hlsl_type_get_regset(ctx, var->data_type); - - if (var->reg_reservation.type == type_info->reg_name) + if (var->reg_reservation.type == regset_name) { - const struct hlsl_ir_var *reserved_object = get_reserved_object(ctx, type_info->reg_name, + const struct hlsl_ir_var *reserved_object = get_reserved_object(ctx, regset, var->reg_reservation.index);
if (var->reg_reservation.index < min_index) { + assert(regset == HLSL_REGSET_UAVS); hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_OVERLAPPING_RESERVATIONS, "UAV index (%u) must be higher than the maximum render target index (%u).", var->reg_reservation.index, min_index - 1); @@ -2720,25 +2694,24 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type) else if (reserved_object && reserved_object != var) { hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_OVERLAPPING_RESERVATIONS, - "Multiple objects bound to %c%u.", type_info->reg_name, - var->reg_reservation.index); + "Multiple objects bound to %c%u.", regset_name, var->reg_reservation.index); hlsl_note(ctx, &reserved_object->loc, VKD3D_SHADER_LOG_ERROR, - "Object '%s' is already bound to %c%u.", reserved_object->name, - type_info->reg_name, var->reg_reservation.index); + "Object '%s' is already bound to %c%u.", reserved_object->name, regset_name, + var->reg_reservation.index); }
var->regs[regset].id = var->reg_reservation.index; var->regs[regset].allocated = true; - TRACE("Allocated reserved %s to %c%u.\n", var->name, type_info->reg_name, var->reg_reservation.index); + TRACE("Allocated reserved %s to %c%u.\n", var->name, regset_name, var->regs[regset].id); } else if (!var->reg_reservation.type) { - while (get_reserved_object(ctx, type_info->reg_name, index)) + while (get_reserved_object(ctx, regset, index)) ++index;
var->regs[regset].id = index; var->regs[regset].allocated = true; - TRACE("Allocated object to %c%u.\n", type_info->reg_name, index); + TRACE("Allocated object to %c%u.\n", regset_name, index); ++index; } else @@ -2748,7 +2721,7 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_base_type type) type_string = hlsl_type_to_string(ctx, var->data_type); hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_INVALID_RESERVATION, "Object of type '%s' must be bound to register type '%c'.", - type_string->buffer, type_info->reg_name); + type_string->buffer, regset_name); hlsl_release_string_buffer(ctx, type_string); } } @@ -3058,11 +3031,11 @@ int hlsl_emit_bytecode(struct hlsl_ctx *ctx, struct hlsl_ir_function_decl *entry else { allocate_buffers(ctx); - allocate_objects(ctx, HLSL_TYPE_TEXTURE); - allocate_objects(ctx, HLSL_TYPE_UAV); + allocate_objects(ctx, HLSL_REGSET_TEXTURES); + allocate_objects(ctx, HLSL_REGSET_UAVS); } allocate_semantic_registers(ctx); - allocate_objects(ctx, HLSL_TYPE_SAMPLER); + allocate_objects(ctx, HLSL_REGSET_SAMPLERS);
if (ctx->result) return ctx->result;
From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl_codegen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index 1c362b0e..057ea7bc 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -2648,7 +2648,7 @@ static const struct hlsl_ir_var *get_reserved_object(struct hlsl_ctx *ctx, enum
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, const struct hlsl_ir_var, extern_entry) { - if (var->last_read && var->reg_reservation.type == hlsl_regset_name(ctx, regset) + if (var->reg_reservation.type == hlsl_regset_name(ctx, regset) && var->reg_reservation.index == index) return var; }
From: Francisco Casas fcasas@codeweavers.com
This refactoring is required for improving the allocation strategy so it works with multiple-register variables. --- libs/vkd3d-shader/hlsl_codegen.c | 77 ++++++++++++++++++++++---------- 1 file changed, 53 insertions(+), 24 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl_codegen.c b/libs/vkd3d-shader/hlsl_codegen.c index 057ea7bc..0b9e7537 100644 --- a/libs/vkd3d-shader/hlsl_codegen.c +++ b/libs/vkd3d-shader/hlsl_codegen.c @@ -1988,6 +1988,40 @@ static void dump_function(struct rb_entry *entry, void *context) rb_for_each_entry(&func->overloads, dump_function_decl, ctx); }
+static void allocate_register_reservations(struct hlsl_ctx *ctx) +{ + struct hlsl_ir_var *var; + + LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) + { + enum hlsl_regset regset; + + if (!hlsl_type_is_resource(var->data_type)) + continue; + regset = hlsl_type_get_regset(ctx, var->data_type); + + if (var->reg_reservation.type) + { + if (var->reg_reservation.type != hlsl_regset_name(ctx, regset)) + { + struct vkd3d_string_buffer *type_string; + + type_string = hlsl_type_to_string(ctx, var->data_type); + hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_INVALID_RESERVATION, + "Object of type '%s' must be bound to register type '%c'.", + type_string->buffer, hlsl_regset_name(ctx, regset)); + hlsl_release_string_buffer(ctx, type_string); + } + else + { + var->regs[regset].allocated = true; + var->regs[regset].id = var->reg_reservation.index; + TRACE("Allocated reserved %s to %c%u.\n", var->name, var->reg_reservation.type, var->reg_reservation.index); + } + } + } +} + /* Compute the earliest and latest liveness for each variable. In the case that * a variable is accessed inside of a loop, we promote its liveness to extend * to at least the range of the entire loop. Note that we don't need to do this @@ -2641,15 +2675,17 @@ static void allocate_buffers(struct hlsl_ctx *ctx) } }
-static const struct hlsl_ir_var *get_reserved_object(struct hlsl_ctx *ctx, enum hlsl_regset regset, +static const struct hlsl_ir_var *get_allocated_object(struct hlsl_ctx *ctx, enum hlsl_regset regset, uint32_t index) { const struct hlsl_ir_var *var;
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, const struct hlsl_ir_var, extern_entry) { - if (var->reg_reservation.type == hlsl_regset_name(ctx, regset) - && var->reg_reservation.index == index) + if (!var->regs[regset].allocated) + continue; + + if (index == var->regs[regset].id) return var; } return NULL; @@ -2676,37 +2712,39 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_regset regset)
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, struct hlsl_ir_var, extern_entry) { - if (!var->last_read || var->data_type->reg_size[regset] == 0) + if (!var->last_read || !var->data_type->reg_size[regset]) continue;
- if (var->reg_reservation.type == regset_name) + if (var->regs[regset].allocated) { - const struct hlsl_ir_var *reserved_object = get_reserved_object(ctx, regset, - var->reg_reservation.index); + const struct hlsl_ir_var *reserved_object; + unsigned int index = var->regs[regset].id;
- if (var->reg_reservation.index < min_index) + reserved_object = get_allocated_object(ctx, regset, index); + + if (var->regs[regset].id < min_index) { assert(regset == HLSL_REGSET_UAVS); hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_OVERLAPPING_RESERVATIONS, "UAV index (%u) must be higher than the maximum render target index (%u).", - var->reg_reservation.index, min_index - 1); + var->regs[regset].id, min_index - 1); } else if (reserved_object && reserved_object != var) { hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_OVERLAPPING_RESERVATIONS, - "Multiple objects bound to %c%u.", regset_name, var->reg_reservation.index); + "Multiple objects bound to %c%u.", regset_name, index); hlsl_note(ctx, &reserved_object->loc, VKD3D_SHADER_LOG_ERROR, - "Object '%s' is already bound to %c%u.", reserved_object->name, regset_name, - var->reg_reservation.index); + "Object '%s' is already bound to %c%u.", reserved_object->name, + regset_name, index); }
var->regs[regset].id = var->reg_reservation.index; var->regs[regset].allocated = true; TRACE("Allocated reserved %s to %c%u.\n", var->name, regset_name, var->regs[regset].id); } - else if (!var->reg_reservation.type) + else { - while (get_reserved_object(ctx, regset, index)) + while (get_allocated_object(ctx, regset, index)) ++index;
var->regs[regset].id = index; @@ -2714,16 +2752,6 @@ static void allocate_objects(struct hlsl_ctx *ctx, enum hlsl_regset regset) TRACE("Allocated object to %c%u.\n", regset_name, index); ++index; } - else - { - struct vkd3d_string_buffer *type_string; - - type_string = hlsl_type_to_string(ctx, var->data_type); - hlsl_error(ctx, &var->loc, VKD3D_SHADER_ERROR_HLSL_INVALID_RESERVATION, - "Object of type '%s' must be bound to register type '%c'.", - type_string->buffer, regset_name); - hlsl_release_string_buffer(ctx, type_string); - } } }
@@ -3023,6 +3051,7 @@ int hlsl_emit_bytecode(struct hlsl_ctx *ctx, struct hlsl_ir_function_decl *entry if (TRACE_ON()) rb_for_each_entry(&ctx->functions, dump_function, ctx);
+ allocate_register_reservations(ctx); allocate_temp_registers(ctx, entry_func); if (profile->major_version < 4) {
:arrow_up: Renamed `HLSL_REGSET_S`, `HLSL_REGSET_T`, and `HLSL_REGSET_U`, to `HLSL_REGSET_SAMPLERS`, `HLSL_REGSET_TEXTURES`, and `HLSL_REGSET_UAVS`.
Zebediah Figura (@zfigura) commented about libs/vkd3d-shader/hlsl_codegen.c:
/* register offsets shouldn't be used before this point is reached. */ assert(!deref->offset.node);
- type = hlsl_deref_get_type(ctx, deref);
- /* Instruction that directly refer to structs and arrays (instead of single-register componets)
* are removed later by dce. So it is not a problem to consider them numerics for computing* offsets. */- deref->offset_regset = HLSL_REGSET_NUMERIC;
- if (hlsl_type_is_resource(type))
deref->offset_regset = hlsl_type_get_regset(ctx, type);
I'm not a fan of this for clarity. I'd rather guard out the offset_regset assignment by checking if the type is a struct (or array?) and then just leave it undefined otherwise. [I know this is kind of what you were trying to achieve with HLSL_REGSET_VOID, but I still am inclined to say that's not worth existing.]
I can live with it on the grounds that this function is eventually going to go away, but I do want to push for actually moving forward on that. I don't want to litter the code with half-finished refactors; it's not the worst thing for maintenance but it's not great either.
Zebediah Figura (@zfigura) commented about libs/vkd3d-shader/hlsl.c:
- if (type->type == HLSL_CLASS_OBJECT)
- {
switch (type->base_type){case HLSL_TYPE_TEXTURE:case HLSL_TYPE_SAMPLER:case HLSL_TYPE_UAV:return true;default:return false;}- }
- return false;
+}
+enum hlsl_regset hlsl_type_get_regset(struct hlsl_ctx *ctx, const struct hlsl_type *type)
This doesn't use its hlsl_ctx argument (anymore).
Zebediah Figura (@zfigura) commented about libs/vkd3d-shader/hlsl_sm4.c:
{
- if (a->data_type->base_type != b->data_type->base_type)
return a->data_type->base_type - b->data_type->base_type;- if (a->reg.allocated && b->reg.allocated)
return a->reg.id - b->reg.id;
- enum hlsl_regset a_regset, b_regset;
- bool a_allocated, b_allocated;
- unsigned int a_id, b_id;
- a_regset = HLSL_REGSET_NUMERIC;
- if (hlsl_type_is_resource(a->data_type))
a_regset = hlsl_type_get_regset(ctx, a->data_type);- b_regset = HLSL_REGSET_NUMERIC;
- if (hlsl_type_is_resource(b->data_type))
b_regset = hlsl_type_get_regset(ctx, b->data_type);
I don't know if this is right, but it looks like a hack. What are we supposed to do with structs?
Zebediah Figura (@zfigura) commented about libs/vkd3d-shader/hlsl.c:
return 1;}
+char hlsl_regset_name(const struct hlsl_ctx *ctx, enum hlsl_regset regset) Note that hlsl_regset_name() requires the ctx argument because, conceptually, regsets are not to be associated to a particular letter in the assembly. It could happen that the letter depends on the shader profile.
Honestly I think we'll (eventually?) want that just to be a char/string argument to allocate_objects() [whose callers are already conditional on profile].
Edit: never mind, I guess 8/8 makes that uglier...
Anyway I think this function belongs in hlsl_codegen.c.
Zebediah Figura (@zfigura) commented about libs/vkd3d-shader/hlsl_codegen.c:
LIST_FOR_EACH_ENTRY(var, &ctx->extern_vars, const struct hlsl_ir_var, extern_entry) {
if (var->last_read && var->reg_reservation.type == hlsl_regset_name(ctx, regset)
if (var->reg_reservation.type == hlsl_regset_name(ctx, regset)
Huh, interesting. I'd have thought I wrote that on purpose, but testing again now I can't seem to replicate a situation where unused objects are ignored. Or unused cbuffers for that matter.
Doesn't need to block this series, but tests for this would be good.
On Wed Feb 8 19:21:39 2023 +0000, Zebediah Figura wrote:
I don't know if this is right, but it looks like a hack. What are we supposed to do with structs?
`sm4_sort_externs()` only cares about sorting resources relative to other resoures; for writing the RDEF section.
Structs themselves don't appear in the RDEF section so any comparison function is okay for them as long as it is consistent.
Uniform structs containing objects are only allowed in profiles >= 5, and in those profiles these components have to be promoted to individual variables, so they are not to be shown either.
On Wed Feb 8 19:21:39 2023 +0000, Zebediah Figura wrote:
This doesn't use its hlsl_ctx argument (anymore).
You mentioned my commit message regarding why I put the `hlsl_ctx` argument in another thread, but I am not sure if I should remove it or not...
Anyways, I moved the function to `hlsl_codegen.c` as you suggested.
On Wed Feb 8 19:21:38 2023 +0000, Zebediah Figura wrote:
I'm not a fan of this for clarity. I'd rather guard out the offset_regset assignment by checking if the type is a struct (or array?) and then just leave it undefined otherwise. [I know this is kind of what you were trying to achieve with HLSL_REGSET_VOID, but I still am inclined to say that's not worth existing.] I can live with it on the grounds that this function is eventually going to go away, but I do want to push for actually moving forward on that. I don't want to litter the code with half-finished refactors; it's not the worst thing for maintenance but it's not great either.
Okay, I added the guard in a new patch before this one. I had already removed `HLSL_REGSET_VOID`.
On Thu Feb 9 23:34:53 2023 +0000, Zebediah Figura wrote:
Huh, interesting. I'd have thought I wrote that on purpose, but testing again now I can't seem to replicate a situation where unused objects are ignored. Or unused cbuffers for that matter. Doesn't need to block this series, but tests for this would be good.
I added a couple of tests.
-
Francisco Casas -
Francisco Casas (＠fcasas)
-
Zebediah Figura
-
Zebediah Figura (＠zfigura)