Checkpoint: rework shader input/output register mapping.

This is a step toward removing TGSI_ATTRIB_ tokens.
Basically, when translating Mesa programs to TGSI programs, pass in input and
output register re-maps, plus interpolation info.
There's some known breakage (cubemap.c) so more to be done...
This commit is contained in:
Brian
2007-09-18 19:37:36 -06:00
parent 63be96bdc7
commit bb611c5f1f
12 changed files with 256 additions and 102 deletions

View File

@@ -67,6 +67,10 @@ fetch_attrib4(const void *ptr, unsigned format, float attrib[4])
}
}
/**
* Fetch vertex attributes for 'count' vertices.
*/
void draw_vertex_fetch( struct draw_context *draw,
struct tgsi_exec_machine *machine,
const unsigned *elts,
@@ -74,12 +78,12 @@ void draw_vertex_fetch( struct draw_context *draw,
{
unsigned j;
/* load machine inputs */
/* loop over vertices */
for (j = 0; j < count; j++) {
unsigned attr;
for (attr = 0; attr < 16; attr++) {
if (draw->vertex_shader.inputs_read & (1 << attr)) {
uint attr;
/* loop over vertex attributes (vertex shader inputs) */
for (attr = 0; attr < draw->vertex_shader.num_inputs; attr++) {
unsigned buf = draw->vertex_element[attr].vertex_buffer_index;
const void *src
= (const void *) ((const ubyte *) draw->mapped_vbuffer[buf]
@@ -96,6 +100,5 @@ void draw_vertex_fetch( struct draw_context *draw,
machine->Inputs[attr].xyzw[3].f[j] = p[3]; /*W*/
}
}
}
}

View File

@@ -114,7 +114,6 @@ run_vertex_program(struct draw_context *draw,
draw_vertex_fetch( draw, &machine, elts, count );
/* run shader */
if( draw->vertex_shader.executable != NULL ) {
#if defined(USE_X86_ASM) || defined(SLANG_X86)
@@ -159,14 +158,23 @@ run_vertex_program(struct draw_context *draw,
vOut[j]->data[0][2] = z * scale[2] + trans[2];
vOut[j]->data[0][3] = w;
/* remaining attributes are packed into sequential post-transform
/* Remaining attributes are packed into sequential post-transform
* vertex attrib slots.
* Skip 0 since we just did it above.
* Subtract two because of the VERTEX_HEADER, CLIP_POS attribs.
*/
for (slot = 1; slot < draw->vertex_info.num_attribs; slot++) {
for (slot = 1; slot < draw->vertex_info.num_attribs - 2; slot++) {
vOut[j]->data[slot][0] = machine.Outputs[slot].xyzw[0].f[j];
vOut[j]->data[slot][1] = machine.Outputs[slot].xyzw[1].f[j];
vOut[j]->data[slot][2] = machine.Outputs[slot].xyzw[2].f[j];
vOut[j]->data[slot][3] = machine.Outputs[slot].xyzw[3].f[j];
/*
printf("output %d: %f %f %f %f\n", slot,
vOut[j]->data[slot][0],
vOut[j]->data[slot][1],
vOut[j]->data[slot][2],
vOut[j]->data[slot][3]);
*/
}
} /* loop over vertices */
}

View File

@@ -144,6 +144,9 @@ struct pipe_shader_state {
unsigned outputs_written; /**< TGSI_ATTRIB_ bits */
const struct tgsi_token *tokens;
void *executable;
uint num_inputs;
uint num_outputs;
};
struct pipe_depth_stencil_state

View File

@@ -448,6 +448,14 @@ static void tri_persp_coeff( struct setup_stage *setup,
float a = setup->ebot.dy * majda - botda * setup->emaj.dy;
float b = setup->emaj.dx * botda - majda * setup->ebot.dx;
/*
printf("tri persp %d,%d: %f %f %f\n", slot, i,
setup->vmin->data[slot][i],
setup->vmid->data[slot][i],
setup->vmax->data[slot][i]
);
*/
assert(slot < TGSI_ATTRIB_MAX);
assert(i <= 3);

View File

@@ -211,6 +211,7 @@ tgsi_mesa_translate_fragment_output(GLuint attrib)
}
#if 01
uint
tgsi_mesa_translate_vertex_input_mask(GLbitfield mask)
{
@@ -224,7 +225,7 @@ tgsi_mesa_translate_vertex_input_mask(GLbitfield mask)
}
return tgsiMask;
}
#endif
uint
tgsi_mesa_translate_vertex_output_mask(GLbitfield mask)
@@ -318,7 +319,9 @@ map_register_file_index(
GLuint processor,
GLuint file,
GLuint index,
GLbitfield usage_bitmask )
GLbitfield usage_bitmask,
const GLuint inputMapping[],
const GLuint outputMapping[])
{
GLuint mapped_index;
GLuint i;
@@ -337,6 +340,12 @@ map_register_file_index(
* etc.
*/
assert( index < 32 );
if (inputMapping) {
printf("New map %d input %d to %d\n", processor, index,
inputMapping[index]);
return inputMapping[index];
}
assert( usage_bitmask & (1 << index) );
mapped_index = 0;
for( i = 0; i < index; i++ ) {
@@ -344,7 +353,7 @@ map_register_file_index(
mapped_index++;
}
}
printf("Map input %d to %d\n", index, mapped_index);
printf("Map %d input %d to %d\n", processor, index, mapped_index);
break;
case TGSI_FILE_OUTPUT:
@@ -372,6 +381,8 @@ map_register_file_index(
mapped_index++;
}
}
printf("Map VP output from %d to %d\n", index, mapped_index);
assert(outputMapping[index] == mapped_index);
}
break;
@@ -443,6 +454,8 @@ compile_instruction(
struct tgsi_full_instruction *fullinst,
GLuint inputs_read,
GLuint outputs_written,
const GLuint inputMapping[],
const GLuint outputMapping[],
GLuint preamble_size,
GLuint processor )
{
@@ -462,7 +475,9 @@ compile_instruction(
processor,
fulldst->DstRegister.File,
inst->DstReg.Index,
outputs_written
outputs_written,
NULL,
outputMapping
);
fulldst->DstRegister.WriteMask = convert_writemask( inst->DstReg.WriteMask );
@@ -475,7 +490,9 @@ compile_instruction(
processor,
fullsrc->SrcRegister.File,
inst->SrcReg[i].Index,
inputs_read );
inputs_read,
inputMapping,
outputMapping );
for( j = 0; j < 4; j++ ) {
GLuint swz;
@@ -789,9 +806,20 @@ make_frag_output_decl(
return decl;
}
/**
* Convert Mesa fragment program to TGSI format.
* \param inputMapping array to map original Mesa fragment program inputs
* registers to TGSI generic input indexes
* \param interpMode array[FRAG_ATTRIB_x] of TGSI_INTERPOLATE_LINEAR/PERSP.
*
*/
GLboolean
tgsi_mesa_compile_fp_program(
const struct gl_fragment_program *program,
const GLuint inputMapping[],
const GLuint interpMode[],
const GLuint outputMapping[],
struct tgsi_token *tokens,
GLuint maxTokens )
{
@@ -800,8 +828,10 @@ tgsi_mesa_compile_fp_program(
struct tgsi_processor *processor;
struct tgsi_full_declaration fulldecl;
struct tgsi_full_instruction fullinst;
/*
struct tgsi_full_dst_register *fulldst;
struct tgsi_full_src_register *fullsrc;
*/
GLuint inputs_read;
GLboolean reads_wpos;
GLuint preamble_size = 0;
@@ -822,7 +852,7 @@ tgsi_mesa_compile_fp_program(
/*
* Declare input attributes. Note that we do not interpolate fragment position.
*/
reads_wpos = 1;
/* Fragment position. */
if( reads_wpos ) {
fulldecl = make_frag_input_decl(
@@ -853,20 +883,16 @@ tgsi_mesa_compile_fp_program(
for( i = 1; i < 32; i++ ) {
if( inputs_read & (1 << i) ) {
count++;
}
}
if( count > 0 ) {
fulldecl = make_frag_input_decl(
1,
1 + count - 1,
TGSI_INTERPOLATE_PERSPECTIVE,
fulldecl = make_frag_input_decl(count,
count,
interpMode[i],
TGSI_WRITEMASK_XYZW );
ti += tgsi_build_full_declaration(
&fulldecl,
ti += tgsi_build_full_declaration(&fulldecl,
&tokens[ti],
header,
maxTokens - ti );
}
}
/*
* Declare output attributes.
@@ -932,6 +958,8 @@ tgsi_mesa_compile_fp_program(
&fullinst,
inputs_read,
~0, /*outputs_written*/
inputMapping,
outputMapping,
preamble_size,
TGSI_PROCESSOR_FRAGMENT ) ) {
assert( i == program->Base.NumInstructions - 1 );
@@ -955,8 +983,10 @@ tgsi_mesa_compile_fp_program(
GLboolean
tgsi_mesa_compile_vp_program(
const struct gl_vertex_program *program,
const GLuint inputMapping[],
const GLuint outputMapping[],
struct tgsi_token *tokens,
GLuint maxTokens )
GLuint maxTokens)
{
GLuint i, ti;
struct tgsi_header *header;
@@ -983,6 +1013,8 @@ tgsi_mesa_compile_vp_program(
&fullinst,
inputs_read,
outputs_written,
inputMapping,
outputMapping,
0,
TGSI_PROCESSOR_VERTEX ) ) {
assert( i == program->Base.NumInstructions - 1 );

View File

@@ -10,12 +10,17 @@ struct tgsi_token;
GLboolean
tgsi_mesa_compile_fp_program(
const struct gl_fragment_program *program,
const GLuint inputMapping[],
const GLuint interpMode[],
const GLuint outputMapping[],
struct tgsi_token *tokens,
GLuint maxTokens );
GLboolean
tgsi_mesa_compile_vp_program(
const struct gl_vertex_program *program,
const GLuint inputMapping[],
const GLuint outputMapping[],
struct tgsi_token *tokens,
GLuint maxTokens );

View File

@@ -42,17 +42,34 @@
#include "st_atom.h"
#include "st_program.h"
#define TGSI_DEBUG 0
#define TGSI_DEBUG 1
static void compile_fs( struct st_context *st )
{
/* Map FRAG_RESULT_COLR to output 1, map FRAG_RESULT_DEPR to output 0 */
static const GLuint outputMapping[2] = {1, 0};
struct st_fragment_program *fp = st->fp;
struct pipe_shader_state fs;
struct pipe_shader_state *cached;
GLuint interpMode[16]; /* XXX size? */
GLuint i;
for (i = 0; i < 16; i++) {
if (fp->Base.Base.InputsRead & (1 << i)) {
if (i == FRAG_ATTRIB_COL0 || i == FRAG_ATTRIB_COL1) {
interpMode[i] = TGSI_INTERPOLATE_LINEAR;
}
else {
interpMode[i] = TGSI_INTERPOLATE_PERSPECTIVE;
}
}
}
/* XXX: fix static allocation of tokens:
*/
tgsi_mesa_compile_fp_program( &fp->Base, fp->tokens, ST_FP_MAX_TOKENS );
tgsi_mesa_compile_fp_program( &fp->Base, NULL, interpMode,
outputMapping,
fp->tokens, ST_FP_MAX_TOKENS );
memset(&fs, 0, sizeof(fs));
fs.inputs_read
@@ -64,7 +81,7 @@ static void compile_fs( struct st_context *st )
fp->fsx = cached;
if (TGSI_DEBUG)
tgsi_dump( fp->tokens, TGSI_DUMP_VERBOSE );
tgsi_dump( fp->tokens, 0/*TGSI_DUMP_VERBOSE*/ );
fp->dirty = 0;
}

View File

@@ -51,25 +51,61 @@
/* translate shader to TGSI format
*/
/**
* Translate Mesa shader to TGSI format
*/
static void compile_vs( struct st_context *st )
{
struct st_vertex_program *vp = st->vp;
struct pipe_shader_state vs;
struct pipe_shader_state *cached;
/* XXX: fix static allocation of tokens:
*/
tgsi_mesa_compile_vp_program( &vp->Base, vp->tokens, ST_FP_MAX_TOKENS );
GLuint i;
memset(&vs, 0, sizeof(vs));
/*
* Determine how many inputs there are.
* Also, compute two look-up tables that map between Mesa VERT_ATTRIB_x
* values and TGSI generic input indexes.
*/
for (i = 0; i < MAX_VERTEX_PROGRAM_ATTRIBS; i++) {
if (vp->Base.Base.InputsRead & (1 << i)) {
vp->input_to_index[i] = vs.num_inputs;
vp->index_to_input[vs.num_inputs] = i;
vs.num_inputs++;
}
}
/*
* Determine output register mapping.
*/
for (i = 0; i < VERT_RESULT_MAX; i++) {
if (vp->Base.Base.OutputsWritten & (1 << i)) {
vp->output_to_index[i] = vs.num_outputs;
vp->index_to_output[vs.num_outputs] = i;
vs.num_outputs++;
}
}
/* XXX: fix static allocation of tokens:
*/
tgsi_mesa_compile_vp_program( &vp->Base,
vp->input_to_index,
vp->output_to_index,
vp->tokens, ST_FP_MAX_TOKENS );
#if 01
vs.inputs_read
= tgsi_mesa_translate_vertex_input_mask(vp->Base.Base.InputsRead);
#endif
vs.outputs_written
= tgsi_mesa_translate_vertex_output_mask(vp->Base.Base.OutputsWritten);
vs.tokens = &vp->tokens[0];
cached = st_cached_shader_state(st, &vs);
vp->vs = cached;
if (TGSI_DEBUG)
@@ -121,7 +157,7 @@ static void update_vs( struct st_context *st )
const struct st_tracked_state st_update_vs = {
.name = "st_update_vs",
.dirty = {
.mesa = 0,
.mesa = _NEW_PROGRAM,
.st = ST_NEW_VERTEX_PROGRAM,
},
.update = update_vs

View File

@@ -119,12 +119,19 @@ is_depth_stencil_format(GLuint pipeFormat)
* Create a simple fragment shader that just passes through the fragment color.
*/
static struct st_fragment_program *
make_color_shader(struct st_context *st)
make_frag_shader(struct st_context *st)
{
static const GLuint outputMapping[] = { 1, 0 };
GLcontext *ctx = st->ctx;
struct st_fragment_program *stfp;
struct gl_program *p;
GLboolean b;
GLuint interpMode[16];
GLuint i;
/* XXX temporary */
for (i = 0; i < 16; i++)
interpMode[i] = TGSI_INTERPOLATE_LINEAR;
p = ctx->Driver.NewProgram(ctx, GL_FRAGMENT_PROGRAM_ARB, 0);
if (!p)
@@ -151,7 +158,8 @@ make_color_shader(struct st_context *st)
stfp = (struct st_fragment_program *) p;
/* compile into tgsi format */
b = tgsi_mesa_compile_fp_program(&stfp->Base,
b = tgsi_mesa_compile_fp_program(&stfp->Base, NULL, interpMode,
outputMapping,
stfp->tokens, ST_FP_MAX_TOKENS);
assert(b);
@@ -166,6 +174,11 @@ make_color_shader(struct st_context *st)
static struct st_vertex_program *
make_vertex_shader(struct st_context *st)
{
/* Map VERT_ATTRIB_POS to 0, VERT_ATTRIB_COLOR0 to 1 */
static const GLuint inputMapping[4] = { 0, 0, 0, 1 };
/* Map VERT_RESULT_HPOS to 0, VERT_RESULT_COL0 to 1 */
static const GLuint outputMapping[2] = { 0, 1 };
GLcontext *ctx = st->ctx;
struct st_vertex_program *stvp;
struct gl_program *p;
@@ -204,6 +217,8 @@ make_vertex_shader(struct st_context *st)
stvp = (struct st_vertex_program *) p;
/* compile into tgsi format */
b = tgsi_mesa_compile_vp_program(&stvp->Base,
inputMapping,
outputMapping,
stvp->tokens, ST_FP_MAX_TOKENS);
assert(b);
@@ -349,7 +364,7 @@ clear_with_quad(GLcontext *ctx,
struct pipe_shader_state fs;
const struct pipe_shader_state *cached;
if (!stfp) {
stfp = make_color_shader(st);
stfp = make_frag_shader(st);
}
memset(&fs, 0, sizeof(fs));
fs.inputs_read = tgsi_mesa_translate_fragment_input_mask(stfp->Base.Base.InputsRead);

View File

@@ -56,10 +56,17 @@
static struct st_fragment_program *
make_fragment_shader(struct st_context *st)
{
static const GLuint outputMapping[2] = { 1, 0 };
GLcontext *ctx = st->ctx;
struct st_fragment_program *stfp;
struct gl_program *p;
GLboolean b;
GLuint interpMode[16];
GLuint i;
/* XXX temporary */
for (i = 0; i < 16; i++)
interpMode[i] = TGSI_INTERPOLATE_LINEAR;
p = ctx->Driver.NewProgram(ctx, GL_FRAGMENT_PROGRAM_ARB, 0);
if (!p)
@@ -88,7 +95,8 @@ make_fragment_shader(struct st_context *st)
stfp = (struct st_fragment_program *) p;
/* compile into tgsi format */
b = tgsi_mesa_compile_fp_program(&stfp->Base,
b = tgsi_mesa_compile_fp_program(&stfp->Base, NULL, interpMode,
outputMapping,
stfp->tokens, ST_FP_MAX_TOKENS);
assert(b);
@@ -103,6 +111,8 @@ make_fragment_shader(struct st_context *st)
static struct st_vertex_program *
make_vertex_shader(struct st_context *st)
{
/* Map VERT_RESULT_HPOS to 0, VERT_RESULT_TEX0 to 1 */
static const GLuint outputMapping[] = { 0, 0, 0, 0, 1 };
GLcontext *ctx = st->ctx;
struct st_vertex_program *stvp;
struct gl_program *p;
@@ -140,7 +150,8 @@ make_vertex_shader(struct st_context *st)
stvp = (struct st_vertex_program *) p;
/* compile into tgsi format */
b = tgsi_mesa_compile_vp_program(&stvp->Base,
b = tgsi_mesa_compile_vp_program(&stvp->Base, NULL,
outputMapping,
stvp->tokens, ST_FP_MAX_TOKENS);
assert(b);

View File

@@ -37,10 +37,12 @@
#include "tnl/t_vp_build.h"
#include "st_context.h"
#include "st_atom.h"
#include "st_draw.h"
#include "st_context.h"
#include "st_cb_bufferobjects.h"
#include "st_draw.h"
#include "st_program.h"
#include "pipe/p_context.h"
#include "pipe/p_defines.h"
#include "pipe/p_winsys.h"
@@ -185,18 +187,22 @@ st_draw_vbo(GLcontext *ctx,
GLuint max_index)
{
struct pipe_context *pipe = ctx->st->pipe;
GLuint attr, i;
GLbitfield attrsNeeded;
const struct st_vertex_program *vp = ctx->st->vp;
const struct pipe_shader_state *vs;
const unsigned attr0_offset = (unsigned) arrays[0]->Ptr;
GLboolean needDefaultAttribs = GL_FALSE;
GLuint attr;
st_validate_state(ctx->st);
update_default_attribs_buffer(ctx);
/* this must be after state validation */
attrsNeeded = ctx->st->state.vs->inputs_read;
/* must do this after state validation! */
vs = ctx->st->state.vs;
/* loop over TGSI shader inputs */
for (attr = 0; attr < vs->num_inputs; attr++) {
const GLuint mesaAttr = vp->index_to_input[attr];
struct gl_buffer_object *bufobj = arrays[mesaAttr]->BufferObj;
/* tell pipe about the vertex array element/attributes */
for (attr = 0; attr < 16; attr++) {
struct pipe_vertex_buffer vbuffer;
struct pipe_vertex_element velement;
@@ -206,10 +212,6 @@ st_draw_vbo(GLcontext *ctx,
velement.vertex_buffer_index = 0;
velement.src_format = 0;
if (attrsNeeded & (1 << attr)) {
const GLuint mesaAttr = tgsi_attrib_to_mesa_attrib(attr);
struct gl_buffer_object *bufobj = arrays[mesaAttr]->BufferObj;
if (bufobj && bufobj->Name) {
struct st_buffer_object *stobj = st_buffer_object(bufobj);
/* Recall that for VBOs, the gl_client_array->Ptr field is
@@ -233,17 +235,18 @@ st_draw_vbo(GLcontext *ctx,
}
else {
/* use the default attribute buffer */
needDefaultAttribs = GL_TRUE;
vbuffer.buffer = ctx->st->default_attrib_buffer;
vbuffer.buffer_offset = 0;
vbuffer.pitch = 0; /* must be zero! */
vbuffer.max_index = 1;
velement.src_offset = attr * 4 * sizeof(GLfloat);
velement.src_offset = mesaAttr * 4 * sizeof(GLfloat);
velement.vertex_buffer_index = attr;
velement.dst_offset = 0;
velement.src_format = PIPE_FORMAT_R32G32B32A32_FLOAT;
}
}
if (attr == 0)
assert(vbuffer.buffer);
@@ -252,12 +255,17 @@ st_draw_vbo(GLcontext *ctx,
pipe->set_vertex_element(pipe, attr, &velement);
}
if (needDefaultAttribs) {
update_default_attribs_buffer(ctx);
}
/* do actual drawing */
if (ib) {
/* indexed primitive */
struct gl_buffer_object *bufobj = ib->obj;
struct pipe_buffer_handle *bh = NULL;
unsigned indexSize;
unsigned indexSize, i;
if (bufobj && bufobj->Name) {
/* elements/indexes are in a real VBO */
@@ -285,6 +293,7 @@ st_draw_vbo(GLcontext *ctx,
}
else {
/* non-indexed */
GLuint i;
for (i = 0; i < nr_prims; i++) {
pipe->draw_arrays(pipe, prims[i].mode, prims[i].start, prims[i].count);
}

View File

@@ -61,13 +61,20 @@ struct st_fragment_program
struct st_vertex_program
{
struct gl_vertex_program Base;
GLboolean error; /* If program is malformed for any reason. */
struct gl_vertex_program Base; /**< The Mesa vertex program */
GLboolean error; /**< Set if program is malformed for any reason. */
GLuint id; /* String id, for tracking
* ProgramStringNotify changes.
*/
GLuint id; /**< String id, for tracking ProgramStringNotify changes. */
/** maps a Mesa VERT_ATTRIB_x to a packed TGSI input index */
GLuint input_to_index[MAX_VERTEX_PROGRAM_ATTRIBS];
/** maps a TGSI input index back to a Mesa VERT_ATTRIB_x */
GLuint index_to_input[MAX_VERTEX_PROGRAM_ATTRIBS];
GLuint output_to_index[MAX_VERTEX_PROGRAM_ATTRIBS];
GLuint index_to_output[MAX_VERTEX_PROGRAM_ATTRIBS];
/** The program in TGSI format */
struct tgsi_token tokens[ST_FP_MAX_TOKENS];
GLboolean dirty;