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

pass arbitrary number of vertices to the shader execution cycle

Browse Source
This commit is contained in:
Zack Rusin
2008-04-12 15:45:28 -04:00
committed by Keith Whitwell
parent 4f550ab821
commit aadbb1d7fb
4 changed files with 148 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/gallium/auxiliary/draw/draw_private.h
View File

@@ -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.

4
src/gallium/auxiliary/draw/draw_vertex_shader.c
View File

@@ -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;

64
src/gallium/auxiliary/draw/draw_vs_exec.c
View File

@@ -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);
@@ -92,7 +92,9 @@ 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 */
@@ -100,7 +102,7 @@ vs_exec_run( struct draw_vertex_shader *shader,
} }
/* store machine results */ /* store machine results */
for (j = 0; j < count; j++) { for (j = 0; j < max_vertices; j++) {
unsigned slot; unsigned slot;
float x, y, z, w; float x, y, z, w;
@@ -110,13 +112,14 @@ vs_exec_run( struct draw_vertex_shader *shader,
* program as a set of DP4 instructions appended to the * program as a set of DP4 instructions appended to the
* user-provided code. * user-provided code.
*/ */
x = vOut[j]->clip[0] = machine->Outputs[0].xyzw[0].f[j]; x = vOut[i + j]->clip[0] = machine->Outputs[0].xyzw[0].f[j];
y = vOut[j]->clip[1] = machine->Outputs[0].xyzw[1].f[j]; y = vOut[i + j]->clip[1] = machine->Outputs[0].xyzw[1].f[j];
z = vOut[j]->clip[2] = machine->Outputs[0].xyzw[2].f[j]; z = vOut[i + j]->clip[2] = machine->Outputs[0].xyzw[2].f[j];
w = vOut[j]->clip[3] = machine->Outputs[0].xyzw[3].f[j]; w = vOut[i + j]->clip[3] = machine->Outputs[0].xyzw[3].f[j];
if (!draw->rasterizer->bypass_clipping) { if (!draw->rasterizer->bypass_clipping) {
vOut[j]->clipmask = compute_clipmask(vOut[j]->clip, draw->plane, draw->nr_planes); vOut[i + j]->clipmask = compute_clipmask(vOut[i + j]->clip, draw->plane,
draw->nr_planes);
/* divide by w */ /* divide by w */
w = 1.0f / w; w = 1.0f / w;
@@ -125,47 +128,46 @@ vs_exec_run( struct draw_vertex_shader *shader,
z *= w; z *= w;
} }
else { else {
vOut[j]->clipmask = 0; vOut[i + j]->clipmask = 0;
} }
vOut[j]->edgeflag = 1; vOut[i + j]->edgeflag = 1;
if (!draw->identity_viewport) { if (!draw->identity_viewport) {
/* Viewport mapping */ /* Viewport mapping */
vOut[j]->data[0][0] = x * scale[0] + trans[0]; vOut[i + j]->data[0][0] = x * scale[0] + trans[0];
vOut[j]->data[0][1] = y * scale[1] + trans[1]; vOut[i + j]->data[0][1] = y * scale[1] + trans[1];
vOut[j]->data[0][2] = z * scale[2] + trans[2]; vOut[i + j]->data[0][2] = z * scale[2] + trans[2];
vOut[j]->data[0][3] = w; vOut[i + j]->data[0][3] = w;
} }
else { else {
vOut[j]->data[0][0] = x; vOut[i + j]->data[0][0] = x;
vOut[j]->data[0][1] = y; vOut[i + j]->data[0][1] = y;
vOut[j]->data[0][2] = z; vOut[i + j]->data[0][2] = z;
vOut[j]->data[0][3] = w; vOut[i + j]->data[0][3] = w;
} }
/* Remaining attributes are packed into sequential post-transform /* Remaining attributes are packed into sequential post-transform
* vertex attrib slots. * vertex attrib slots.
*/ */
for (slot = 1; slot < draw->num_vs_outputs; slot++) { for (slot = 1; slot < draw->num_vs_outputs; slot++) {
vOut[j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j]; vOut[i + j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j];
vOut[j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j]; vOut[i + j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j];
vOut[j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j]; vOut[i + j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j];
vOut[j]->data[slot][3] = machine->Outputs[slot].xyzw[3].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 */
}
} }

51
src/gallium/auxiliary/draw/draw_vs_sse.c
View File

@@ -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);
@@ -108,14 +108,14 @@ 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) {
unsigned int max_vertices = MIN2(SSE_MAX_VERTICES, count - i);
/* Fetch vertices. This may at some point be integrated into the /* Fetch vertices. This may at some point be integrated into the
* compiled shader -- that would require a reorganization where * compiled shader -- that would require a reorganization where
* multiple versions of the compiled shader might exist, * multiple versions of the compiled shader might exist,
* specialized for each fetch state. * specialized for each fetch state.
*/ */
draw->vertex_fetch.fetch_func( draw, machine, elts, count ); draw->vertex_fetch.fetch_func(draw, machine, &elts[i], max_vertices);
if (!draw->rasterizer->bypass_vs) { if (!draw->rasterizer->bypass_vs) {
/* run compiled shader /* run compiled shader
@@ -127,22 +127,22 @@ vs_sse_run( struct draw_vertex_shader *base,
shader->immediates); shader->immediates);
} }
/* XXX: Computing the clipmask and emitting results should be done /* XXX: Computing the clipmask and emitting results should be done
* in the vertex program as a set of instructions appended to * in the vertex program as a set of instructions appended to
* the user-provided code. * the user-provided code.
*/ */
for (j = 0; j < count; j++) { for (j = 0; j < max_vertices; j++) {
unsigned slot; unsigned slot;
float x, y, z, w; float x, y, z, w;
x = vOut[j]->clip[0] = machine->Outputs[0].xyzw[0].f[j]; x = vOut[i + j]->clip[0] = machine->Outputs[0].xyzw[0].f[j];
y = vOut[j]->clip[1] = machine->Outputs[0].xyzw[1].f[j]; y = vOut[i + j]->clip[1] = machine->Outputs[0].xyzw[1].f[j];
z = vOut[j]->clip[2] = machine->Outputs[0].xyzw[2].f[j]; z = vOut[i + j]->clip[2] = machine->Outputs[0].xyzw[2].f[j];
w = vOut[j]->clip[3] = machine->Outputs[0].xyzw[3].f[j]; w = vOut[i + j]->clip[3] = machine->Outputs[0].xyzw[3].f[j];
if (!draw->rasterizer->bypass_clipping) { if (!draw->rasterizer->bypass_clipping) {
vOut[j]->clipmask = compute_clipmask(vOut[j]->clip, draw->plane, draw->nr_planes); vOut[i + j]->clipmask = compute_clipmask(vOut[i + j]->clip, draw->plane,
draw->nr_planes);
/* divide by w */ /* divide by w */
w = 1.0f / w; w = 1.0f / w;
@@ -151,32 +151,33 @@ vs_sse_run( struct draw_vertex_shader *base,
z *= w; z *= w;
} }
else { else {
vOut[j]->clipmask = 0; vOut[i + j]->clipmask = 0;
} }
vOut[j]->edgeflag = 1; vOut[j]->edgeflag = 1;
if (!draw->identity_viewport) { if (!draw->identity_viewport) {
/* Viewport mapping */ /* Viewport mapping */
vOut[j]->data[0][0] = x * scale[0] + trans[0]; vOut[i + j]->data[0][0] = x * scale[0] + trans[0];
vOut[j]->data[0][1] = y * scale[1] + trans[1]; vOut[i + j]->data[0][1] = y * scale[1] + trans[1];
vOut[j]->data[0][2] = z * scale[2] + trans[2]; vOut[i + j]->data[0][2] = z * scale[2] + trans[2];
vOut[j]->data[0][3] = w; vOut[i + j]->data[0][3] = w;
} }
else { else {
vOut[j]->data[0][0] = x; vOut[i + j]->data[0][0] = x;
vOut[j]->data[0][1] = y; vOut[i + j]->data[0][1] = y;
vOut[j]->data[0][2] = z; vOut[i + j]->data[0][2] = z;
vOut[j]->data[0][3] = w; vOut[i + j]->data[0][3] = w;
} }
/* Remaining attributes are packed into sequential post-transform /* Remaining attributes are packed into sequential post-transform
* vertex attrib slots. * vertex attrib slots.
*/ */
for (slot = 1; slot < draw->num_vs_outputs; slot++) { for (slot = 1; slot < draw->num_vs_outputs; slot++) {
vOut[j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j]; vOut[i + j]->data[slot][0] = machine->Outputs[slot].xyzw[0].f[j];
vOut[j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j]; vOut[i + j]->data[slot][1] = machine->Outputs[slot].xyzw[1].f[j];
vOut[j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j]; vOut[i + j]->data[slot][2] = machine->Outputs[slot].xyzw[2].f[j];
vOut[j]->data[slot][3] = machine->Outputs[slot].xyzw[3].f[j]; vOut[i + j]->data[slot][3] = machine->Outputs[slot].xyzw[3].f[j];
}
} }
} }
} }