pass arbitrary number of vertices to the shader execution cycle
This commit is contained in:

committed by
Keith Whitwell

parent
4f550ab821
commit
aadbb1d7fb
@@ -56,6 +56,8 @@ struct gallivm_cpu_engine;
|
|||||||
struct draw_pt_middle_end;
|
struct draw_pt_middle_end;
|
||||||
struct draw_pt_front_end;
|
struct draw_pt_front_end;
|
||||||
|
|
||||||
|
#define MAX_SHADER_VERTICES 128
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Basic vertex info.
|
* Basic vertex info.
|
||||||
* Carry some useful information around with the vertices in the prim pipe.
|
* Carry some useful information around with the vertices in the prim pipe.
|
||||||
|
@@ -37,8 +37,6 @@
|
|||||||
#include "draw_context.h"
|
#include "draw_context.h"
|
||||||
#include "draw_vs.h"
|
#include "draw_vs.h"
|
||||||
|
|
||||||
#define MAX_SHADER_VERTICES 4
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Run the vertex shader on all vertices in the vertex queue.
|
* Run the vertex shader on all vertices in the vertex queue.
|
||||||
* Called by the draw module when the vertx cache needs to be flushed.
|
* Called by the draw module when the vertx cache needs to be flushed.
|
||||||
@@ -61,7 +59,7 @@ draw_vertex_shader_queue_flush(struct draw_context *draw)
|
|||||||
for (i = 0; i < draw->vs.queue_nr; i += MAX_SHADER_VERTICES) {
|
for (i = 0; i < draw->vs.queue_nr; i += MAX_SHADER_VERTICES) {
|
||||||
struct vertex_header *dests[MAX_SHADER_VERTICES];
|
struct vertex_header *dests[MAX_SHADER_VERTICES];
|
||||||
unsigned elts[MAX_SHADER_VERTICES];
|
unsigned elts[MAX_SHADER_VERTICES];
|
||||||
int j, n = MIN2(MAX_SHADER_VERTICES, - i);
|
int j, n = MIN2(MAX_SHADER_VERTICES, draw->vs.queue_nr - i);
|
||||||
|
|
||||||
for (j = 0; j < n; j++) {
|
for (j = 0; j < n; j++) {
|
||||||
elts[j] = draw->vs.queue[i + j].elt;
|
elts[j] = draw->vs.queue[i + j].elt;
|
||||||
|
@@ -40,6 +40,7 @@
|
|||||||
|
|
||||||
#include "tgsi/util/tgsi_parse.h"
|
#include "tgsi/util/tgsi_parse.h"
|
||||||
|
|
||||||
|
#define MAX_TGSI_VERTICES 4
|
||||||
|
|
||||||
static void
|
static void
|
||||||
vs_exec_prepare( struct draw_vertex_shader *shader,
|
vs_exec_prepare( struct draw_vertex_shader *shader,
|
||||||
@@ -71,14 +72,13 @@ vs_exec_run( struct draw_vertex_shader *shader,
|
|||||||
struct vertex_header *vOut[] )
|
struct vertex_header *vOut[] )
|
||||||
{
|
{
|
||||||
struct tgsi_exec_machine *machine = &draw->machine;
|
struct tgsi_exec_machine *machine = &draw->machine;
|
||||||
unsigned int j;
|
unsigned int i, j;
|
||||||
|
|
||||||
ALIGN16_DECL(struct tgsi_exec_vector, inputs, PIPE_MAX_ATTRIBS);
|
ALIGN16_DECL(struct tgsi_exec_vector, inputs, PIPE_MAX_ATTRIBS);
|
||||||
ALIGN16_DECL(struct tgsi_exec_vector, outputs, PIPE_MAX_ATTRIBS);
|
ALIGN16_DECL(struct tgsi_exec_vector, outputs, PIPE_MAX_ATTRIBS);
|
||||||
const float *scale = draw->viewport.scale;
|
const float *scale = draw->viewport.scale;
|
||||||
const float *trans = draw->viewport.translate;
|
const float *trans = draw->viewport.translate;
|
||||||
|
|
||||||
assert(count <= 4);
|
|
||||||
assert(draw->vertex_shader->info.output_semantic_name[0]
|
assert(draw->vertex_shader->info.output_semantic_name[0]
|
||||||
== TGSI_SEMANTIC_POSITION);
|
== TGSI_SEMANTIC_POSITION);
|
||||||
|
|
||||||
@@ -92,80 +92,82 @@ vs_exec_run( struct draw_vertex_shader *shader,
|
|||||||
machine->Outputs = ALIGN16_ASSIGN(outputs);
|
machine->Outputs = ALIGN16_ASSIGN(outputs);
|
||||||
}
|
}
|
||||||
|
|
||||||
draw->vertex_fetch.fetch_func( draw, machine, elts, count );
|
for (i = 0; i < count; i += MAX_TGSI_VERTICES) {
|
||||||
|
unsigned int max_vertices = MIN2(MAX_TGSI_VERTICES, count - i);
|
||||||
|
draw->vertex_fetch.fetch_func( draw, machine, &elts[i], max_vertices );
|
||||||
|
|
||||||
if (!draw->rasterizer->bypass_vs) {
|
if (!draw->rasterizer->bypass_vs) {
|
||||||
/* run interpreter */
|
/* run interpreter */
|
||||||
tgsi_exec_machine_run( machine );
|
tgsi_exec_machine_run( machine );
|
||||||
}
|
|
||||||
|
|
||||||
/* store machine results */
|
|
||||||
for (j = 0; j < count; j++) {
|
|
||||||
unsigned slot;
|
|
||||||
float x, y, z, w;
|
|
||||||
|
|
||||||
/* Handle attr[0] (position) specially:
|
|
||||||
*
|
|
||||||
* XXX: Computing the clipmask should be done in the vertex
|
|
||||||
* program as a set of DP4 instructions appended to the
|
|
||||||
* user-provided code.
|
|
||||||
*/
|
|
||||||
x = vOut[j]->clip[0] = machine->Outputs[0].xyzw[0].f[j];
|
|
||||||
y = vOut[j]->clip[1] = machine->Outputs[0].xyzw[1].f[j];
|
|
||||||
z = vOut[j]->clip[2] = machine->Outputs[0].xyzw[2].f[j];
|
|
||||||
w = vOut[j]->clip[3] = machine->Outputs[0].xyzw[3].f[j];
|
|
||||||
|
|
||||||
if (!draw->rasterizer->bypass_clipping) {
|
|
||||||
vOut[j]->clipmask = compute_clipmask(vOut[j]->clip, draw->plane, draw->nr_planes);
|
|
||||||
|
|
||||||
/* divide by w */
|
|
||||||
w = 1.0f / w;
|
|
||||||
x *= w;
|
|
||||||
y *= w;
|
|
||||||
z *= w;
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
vOut[j]->clipmask = 0;
|
|
||||||
}
|
|
||||||
vOut[j]->edgeflag = 1;
|
|
||||||
|
|
||||||
if (!draw->identity_viewport) {
|
|
||||||
/* Viewport mapping */
|
|
||||||
vOut[j]->data[0][0] = x * scale[0] + trans[0];
|
|
||||||
vOut[j]->data[0][1] = y * scale[1] + trans[1];
|
|
||||||
vOut[j]->data[0][2] = z * scale[2] + trans[2];
|
|
||||||
vOut[j]->data[0][3] = w;
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
vOut[j]->data[0][0] = x;
|
|
||||||
vOut[j]->data[0][1] = y;
|
|
||||||
vOut[j]->data[0][2] = z;
|
|
||||||
vOut[j]->data[0][3] = w;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Remaining attributes are packed into sequential post-transform
|
/* store machine results */
|
||||||
* vertex attrib slots.
|
for (j = 0; j < max_vertices; j++) {
|
||||||
*/
|
unsigned slot;
|
||||||
for (slot = 1; slot < draw->num_vs_outputs; slot++) {
|
float x, y, z, w;
|
||||||
vOut[j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j];
|
|
||||||
vOut[j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j];
|
/* Handle attr[0] (position) specially:
|
||||||
vOut[j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j];
|
*
|
||||||
vOut[j]->data[slot][3] = machine->Outputs[slot].xyzw[3].f[j];
|
* XXX: Computing the clipmask should be done in the vertex
|
||||||
}
|
* program as a set of DP4 instructions appended to the
|
||||||
|
* user-provided code.
|
||||||
|
*/
|
||||||
|
x = vOut[i + j]->clip[0] = machine->Outputs[0].xyzw[0].f[j];
|
||||||
|
y = vOut[i + j]->clip[1] = machine->Outputs[0].xyzw[1].f[j];
|
||||||
|
z = vOut[i + j]->clip[2] = machine->Outputs[0].xyzw[2].f[j];
|
||||||
|
w = vOut[i + j]->clip[3] = machine->Outputs[0].xyzw[3].f[j];
|
||||||
|
|
||||||
|
if (!draw->rasterizer->bypass_clipping) {
|
||||||
|
vOut[i + j]->clipmask = compute_clipmask(vOut[i + j]->clip, draw->plane,
|
||||||
|
draw->nr_planes);
|
||||||
|
|
||||||
|
/* divide by w */
|
||||||
|
w = 1.0f / w;
|
||||||
|
x *= w;
|
||||||
|
y *= w;
|
||||||
|
z *= w;
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
vOut[i + j]->clipmask = 0;
|
||||||
|
}
|
||||||
|
vOut[i + j]->edgeflag = 1;
|
||||||
|
|
||||||
|
if (!draw->identity_viewport) {
|
||||||
|
/* Viewport mapping */
|
||||||
|
vOut[i + j]->data[0][0] = x * scale[0] + trans[0];
|
||||||
|
vOut[i + j]->data[0][1] = y * scale[1] + trans[1];
|
||||||
|
vOut[i + j]->data[0][2] = z * scale[2] + trans[2];
|
||||||
|
vOut[i + j]->data[0][3] = w;
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
vOut[i + j]->data[0][0] = x;
|
||||||
|
vOut[i + j]->data[0][1] = y;
|
||||||
|
vOut[i + j]->data[0][2] = z;
|
||||||
|
vOut[i + j]->data[0][3] = w;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Remaining attributes are packed into sequential post-transform
|
||||||
|
* vertex attrib slots.
|
||||||
|
*/
|
||||||
|
for (slot = 1; slot < draw->num_vs_outputs; slot++) {
|
||||||
|
vOut[i + j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j];
|
||||||
|
vOut[i + j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j];
|
||||||
|
vOut[i + j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j];
|
||||||
|
vOut[i + j]->data[slot][3] = machine->Outputs[slot].xyzw[3].f[j];
|
||||||
|
}
|
||||||
|
|
||||||
#if 0 /*DEBUG*/
|
#if 0 /*DEBUG*/
|
||||||
printf("Post xform vert:\n");
|
printf("%d) Post xform vert:\n", i + j);
|
||||||
for (slot = 0; slot < draw->num_vs_outputs; slot++) {
|
for (slot = 0; slot < draw->num_vs_outputs; slot++) {
|
||||||
printf("%d: %f %f %f %f\n", slot,
|
printf("\t%d: %f %f %f %f\n", slot,
|
||||||
vOut[j]->data[slot][0],
|
vOut[i + j]->data[slot][0],
|
||||||
vOut[j]->data[slot][1],
|
vOut[i + j]->data[slot][1],
|
||||||
vOut[j]->data[slot][2],
|
vOut[i + j]->data[slot][2],
|
||||||
vOut[j]->data[slot][3]);
|
vOut[i + j]->data[slot][3]);
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
||||||
|
} /* loop over vertices */
|
||||||
|
}
|
||||||
} /* loop over vertices */
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
@@ -45,6 +45,7 @@
|
|||||||
#include "tgsi/exec/tgsi_sse2.h"
|
#include "tgsi/exec/tgsi_sse2.h"
|
||||||
#include "tgsi/util/tgsi_parse.h"
|
#include "tgsi/util/tgsi_parse.h"
|
||||||
|
|
||||||
|
#define SSE_MAX_VERTICES 4
|
||||||
|
|
||||||
typedef void (XSTDCALL *codegen_function) (
|
typedef void (XSTDCALL *codegen_function) (
|
||||||
const struct tgsi_exec_vector *input,
|
const struct tgsi_exec_vector *input,
|
||||||
@@ -86,14 +87,13 @@ vs_sse_run( struct draw_vertex_shader *base,
|
|||||||
{
|
{
|
||||||
struct draw_sse_vertex_shader *shader = (struct draw_sse_vertex_shader *)base;
|
struct draw_sse_vertex_shader *shader = (struct draw_sse_vertex_shader *)base;
|
||||||
struct tgsi_exec_machine *machine = &draw->machine;
|
struct tgsi_exec_machine *machine = &draw->machine;
|
||||||
unsigned int j;
|
unsigned int i, j;
|
||||||
|
|
||||||
ALIGN16_DECL(struct tgsi_exec_vector, inputs, PIPE_MAX_ATTRIBS);
|
ALIGN16_DECL(struct tgsi_exec_vector, inputs, PIPE_MAX_ATTRIBS);
|
||||||
ALIGN16_DECL(struct tgsi_exec_vector, outputs, PIPE_MAX_ATTRIBS);
|
ALIGN16_DECL(struct tgsi_exec_vector, outputs, PIPE_MAX_ATTRIBS);
|
||||||
const float *scale = draw->viewport.scale;
|
const float *scale = draw->viewport.scale;
|
||||||
const float *trans = draw->viewport.translate;
|
const float *trans = draw->viewport.translate;
|
||||||
|
|
||||||
assert(count <= 4);
|
|
||||||
assert(draw->vertex_shader->info.output_semantic_name[0]
|
assert(draw->vertex_shader->info.output_semantic_name[0]
|
||||||
== TGSI_SEMANTIC_POSITION);
|
== TGSI_SEMANTIC_POSITION);
|
||||||
|
|
||||||
@@ -108,75 +108,76 @@ vs_sse_run( struct draw_vertex_shader *base,
|
|||||||
machine->Outputs = ALIGN16_ASSIGN(outputs);
|
machine->Outputs = ALIGN16_ASSIGN(outputs);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
for (i = 0; i < count; i += SSE_MAX_VERTICES) {
|
||||||
/* Fetch vertices. This may at some point be integrated into the
|
unsigned int max_vertices = MIN2(SSE_MAX_VERTICES, count - i);
|
||||||
* compiled shader -- that would require a reorganization where
|
/* Fetch vertices. This may at some point be integrated into the
|
||||||
* multiple versions of the compiled shader might exist,
|
* compiled shader -- that would require a reorganization where
|
||||||
* specialized for each fetch state.
|
* multiple versions of the compiled shader might exist,
|
||||||
*/
|
* specialized for each fetch state.
|
||||||
draw->vertex_fetch.fetch_func( draw, machine, elts, count );
|
|
||||||
|
|
||||||
|
|
||||||
if (!draw->rasterizer->bypass_vs) {
|
|
||||||
/* run compiled shader
|
|
||||||
*/
|
*/
|
||||||
shader->func(machine->Inputs,
|
draw->vertex_fetch.fetch_func(draw, machine, &elts[i], max_vertices);
|
||||||
machine->Outputs,
|
|
||||||
machine->Consts,
|
|
||||||
machine->Temps,
|
|
||||||
shader->immediates);
|
|
||||||
}
|
|
||||||
|
|
||||||
|
if (!draw->rasterizer->bypass_vs) {
|
||||||
/* XXX: Computing the clipmask and emitting results should be done
|
/* run compiled shader
|
||||||
* in the vertex program as a set of instructions appended to
|
*/
|
||||||
* the user-provided code.
|
shader->func(machine->Inputs,
|
||||||
*/
|
machine->Outputs,
|
||||||
for (j = 0; j < count; j++) {
|
machine->Consts,
|
||||||
unsigned slot;
|
machine->Temps,
|
||||||
float x, y, z, w;
|
shader->immediates);
|
||||||
|
|
||||||
x = vOut[j]->clip[0] = machine->Outputs[0].xyzw[0].f[j];
|
|
||||||
y = vOut[j]->clip[1] = machine->Outputs[0].xyzw[1].f[j];
|
|
||||||
z = vOut[j]->clip[2] = machine->Outputs[0].xyzw[2].f[j];
|
|
||||||
w = vOut[j]->clip[3] = machine->Outputs[0].xyzw[3].f[j];
|
|
||||||
|
|
||||||
if (!draw->rasterizer->bypass_clipping) {
|
|
||||||
vOut[j]->clipmask = compute_clipmask(vOut[j]->clip, draw->plane, draw->nr_planes);
|
|
||||||
|
|
||||||
/* divide by w */
|
|
||||||
w = 1.0f / w;
|
|
||||||
x *= w;
|
|
||||||
y *= w;
|
|
||||||
z *= w;
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
vOut[j]->clipmask = 0;
|
|
||||||
}
|
|
||||||
vOut[j]->edgeflag = 1;
|
|
||||||
|
|
||||||
if (!draw->identity_viewport) {
|
|
||||||
/* Viewport mapping */
|
|
||||||
vOut[j]->data[0][0] = x * scale[0] + trans[0];
|
|
||||||
vOut[j]->data[0][1] = y * scale[1] + trans[1];
|
|
||||||
vOut[j]->data[0][2] = z * scale[2] + trans[2];
|
|
||||||
vOut[j]->data[0][3] = w;
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
vOut[j]->data[0][0] = x;
|
|
||||||
vOut[j]->data[0][1] = y;
|
|
||||||
vOut[j]->data[0][2] = z;
|
|
||||||
vOut[j]->data[0][3] = w;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Remaining attributes are packed into sequential post-transform
|
/* XXX: Computing the clipmask and emitting results should be done
|
||||||
* vertex attrib slots.
|
* in the vertex program as a set of instructions appended to
|
||||||
|
* the user-provided code.
|
||||||
*/
|
*/
|
||||||
for (slot = 1; slot < draw->num_vs_outputs; slot++) {
|
for (j = 0; j < max_vertices; j++) {
|
||||||
vOut[j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j];
|
unsigned slot;
|
||||||
vOut[j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j];
|
float x, y, z, w;
|
||||||
vOut[j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j];
|
|
||||||
vOut[j]->data[slot][3] = machine->Outputs[slot].xyzw[3].f[j];
|
x = vOut[i + j]->clip[0] = machine->Outputs[0].xyzw[0].f[j];
|
||||||
|
y = vOut[i + j]->clip[1] = machine->Outputs[0].xyzw[1].f[j];
|
||||||
|
z = vOut[i + j]->clip[2] = machine->Outputs[0].xyzw[2].f[j];
|
||||||
|
w = vOut[i + j]->clip[3] = machine->Outputs[0].xyzw[3].f[j];
|
||||||
|
|
||||||
|
if (!draw->rasterizer->bypass_clipping) {
|
||||||
|
vOut[i + j]->clipmask = compute_clipmask(vOut[i + j]->clip, draw->plane,
|
||||||
|
draw->nr_planes);
|
||||||
|
|
||||||
|
/* divide by w */
|
||||||
|
w = 1.0f / w;
|
||||||
|
x *= w;
|
||||||
|
y *= w;
|
||||||
|
z *= w;
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
vOut[i + j]->clipmask = 0;
|
||||||
|
}
|
||||||
|
vOut[j]->edgeflag = 1;
|
||||||
|
|
||||||
|
if (!draw->identity_viewport) {
|
||||||
|
/* Viewport mapping */
|
||||||
|
vOut[i + j]->data[0][0] = x * scale[0] + trans[0];
|
||||||
|
vOut[i + j]->data[0][1] = y * scale[1] + trans[1];
|
||||||
|
vOut[i + j]->data[0][2] = z * scale[2] + trans[2];
|
||||||
|
vOut[i + j]->data[0][3] = w;
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
vOut[i + j]->data[0][0] = x;
|
||||||
|
vOut[i + j]->data[0][1] = y;
|
||||||
|
vOut[i + j]->data[0][2] = z;
|
||||||
|
vOut[i + j]->data[0][3] = w;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Remaining attributes are packed into sequential post-transform
|
||||||
|
* vertex attrib slots.
|
||||||
|
*/
|
||||||
|
for (slot = 1; slot < draw->num_vs_outputs; slot++) {
|
||||||
|
vOut[i + j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j];
|
||||||
|
vOut[i + j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j];
|
||||||
|
vOut[i + j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j];
|
||||||
|
vOut[i + j]->data[slot][3] = machine->Outputs[slot].xyzw[3].f[j];
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
Reference in New Issue
Block a user