From: Francisco Casas fcasas@codeweavers.com
--- libs/vkd3d-shader/hlsl.c | 78 +++++++++++++++++++++++--------- libs/vkd3d-shader/hlsl.h | 32 +++++++++---- libs/vkd3d-shader/hlsl_codegen.c | 64 ++++++++++++++------------ libs/vkd3d-shader/hlsl_sm1.c | 2 +- libs/vkd3d-shader/hlsl_sm4.c | 4 +- 5 files changed, 117 insertions(+), 63 deletions(-)
diff --git a/libs/vkd3d-shader/hlsl.c b/libs/vkd3d-shader/hlsl.c index 13aac3d4..97d4f09f 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; }
+enum hlsl_regset hlsl_type_get_regset(struct hlsl_ctx *ctx, const struct hlsl_type *type) +{ + unsigned int k; + + if (type->type == HLSL_CLASS_OBJECT) + { + for (k = 0; k <= HLSL_REGSET_LAST_OBJECT; ++k) + { + if (type->reg_size[k] > 0) + return k; + } + vkd3d_unreachable(); + } + return HLSL_REGSET_NUM; +} + unsigned int hlsl_type_get_sm4_offset(const struct hlsl_type *type, unsigned int offset) { /* Align to the next vec4 boundary if: @@ -171,7 +187,7 @@ 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_NUM] > 4) return align(offset, 4); return offset; } @@ -179,31 +195,40 @@ 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_NUM] = 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_NUM] = 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_NUM] = 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_NUM) + 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 +237,17 @@ 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_NUM) + 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 +255,24 @@ static void hlsl_type_calculate_reg_size(struct hlsl_ctx *ctx, struct hlsl_type }
case HLSL_CLASS_OBJECT: - type->reg_size = 0; + if (type->base_type == HLSL_TYPE_SAMPLER) + type->reg_size[HLSL_REGSET_S] = 1; + if (type->base_type == HLSL_TYPE_TEXTURE) + type->reg_size[HLSL_REGSET_T] = 1; + if (type->base_type == HLSL_TYPE_UAV) + type->reg_size[HLSL_REGSET_U] = 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 rset) { - return align(type->reg_size, 4); + if (rset == HLSL_REGSET_NUM) + return align(type->reg_size[rset], 4); + return type->reg_size[rset]; }
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 059abe18..83f0076d 100644 --- a/libs/vkd3d-shader/hlsl.h +++ b/libs/vkd3d-shader/hlsl.h @@ -114,6 +114,15 @@ enum hlsl_matrix_majority HLSL_ROW_MAJOR };
+enum hlsl_regset { + HLSL_REGSET_S, + HLSL_REGSET_T, + HLSL_REGSET_U, + HLSL_REGSET_LAST_OBJECT = HLSL_REGSET_U, + HLSL_REGSET_NUM, + HLSL_REGSET_LAST = HLSL_REGSET_NUM, +}; + /* An HLSL source-level data type, including anonymous structs and typedefs. */ struct hlsl_type { @@ -175,12 +184,12 @@ 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_NUM, 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; }; @@ -205,8 +214,8 @@ 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; @@ -536,10 +545,12 @@ 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 @@ -1055,13 +1066,14 @@ 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 rset); 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); +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 9b644d1b..489f791d 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 rset, 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, rset);
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[rset], 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); @@ -134,6 +135,8 @@ 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);
+ deref->offset_regset = hlsl_type_get_regset(ctx, hlsl_deref_get_type(ctx, deref)); + if (!(offset = new_offset_instr_from_deref(ctx, &block, deref, &instr->loc))) return; list_move_before(&instr->entry, &block.instrs); @@ -1982,32 +1985,33 @@ 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_NUM];
- 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_NUM]; + 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); } @@ -2021,12 +2025,12 @@ 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_NUM]; + + 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); } @@ -2084,7 +2088,7 @@ 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_NUM];
if (reg_size > 4) constant->reg = allocate_range(ctx, liveness, 1, UINT_MAX, reg_size); @@ -2183,15 +2187,15 @@ 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_NUM] == 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_NUM] > 4) + var->reg = allocate_range(ctx, &liveness, 1, UINT_MAX, var->data_type->reg_size[HLSL_REGSET_NUM]); 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_NUM]) - 1; } TRACE("Allocated %s to %s.\n", var->name, debug_register('c', var->reg, var->data_type)); } @@ -2308,7 +2312,7 @@ 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_NUM]; if (var->last_read) buffer->used_size = buffer->size; } @@ -2563,6 +2567,7 @@ 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) { @@ -2579,10 +2584,11 @@ 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; }
@@ -2608,6 +2614,8 @@ 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_NUM); + 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 ba22925e..6d45208f 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_NUM] / 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 9232ea78..c394ba55 100644 --- a/libs/vkd3d-shader/hlsl_sm4.c +++ b/libs/vkd3d-shader/hlsl_sm4.c @@ -383,7 +383,7 @@ 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_NUM]); } }
@@ -699,7 +699,7 @@ 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_NUM] * sizeof(float)); put_u32(&buffer, flags); put_u32(&buffer, 0); /* type */ put_u32(&buffer, 0); /* FIXME: default value */