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

Revert "Redoing the way we handle vertex shaders for the draw module."

Browse Source 
This reverts commit 6dcfddb8e2.
This commit is contained in:
Zack Rusin
2007-09-28 12:28:16 -04:00
parent f2a33a63f1
commit 901577e07f
17 changed files with 141 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/mesa/pipe/draw/draw_context.c
View File

@@ -155,6 +155,14 @@ void draw_set_viewport_state( struct draw_context *draw,
}
void
draw_set_vertex_shader(struct draw_context *draw,
const struct pipe_shader_state *shader)
{
draw_flush( draw );
draw->vertex_shader = *shader;
}
void
draw_set_vertex_buffer(struct draw_context *draw,

7
src/mesa/pipe/draw/draw_context.h
View File

@@ -92,12 +92,9 @@ void draw_set_rasterize_stage( struct draw_context *draw,
struct draw_stage *stage );
void * draw_create_vertex_shader(struct draw_context *draw,
void
draw_set_vertex_shader(struct draw_context *draw,
const struct pipe_shader_state *shader);
void draw_bind_vertex_shader(struct draw_context *draw,
void *vcso);
void draw_delete_vertex_shader(struct draw_context *draw,
void *vcso);
void

12
src/mesa/pipe/draw/draw_private.h
View File

@@ -46,7 +46,6 @@
#include "draw_vertex.h"
#include "x86/rtasm/x86sse.h"
/**
* Basic vertex info.
@@ -117,15 +116,6 @@ struct draw_stage
#define VCACHE_OVERFLOW 4
#define VS_QUEUE_LENGTH (VCACHE_SIZE + VCACHE_OVERFLOW + 1) /* can never fill up */
/**
* Private version of the compiled vertex_shader
*/
struct draw_vertex_shader {
const struct pipe_shader_state *state;
#if defined(__i386__) || defined(__386__)
struct x86_function sse2_program;
#endif
};
/**
* Private context for the drawing module.
@@ -155,7 +145,7 @@ struct draw_context
struct pipe_viewport_state viewport;
struct pipe_vertex_buffer vertex_buffer[PIPE_ATTRIB_MAX];
struct pipe_vertex_element vertex_element[PIPE_ATTRIB_MAX];
const struct draw_vertex_shader *vertex_shader;
struct pipe_shader_state vertex_shader;
struct pipe_vertex_buffer feedback_buffer[PIPE_ATTRIB_MAX];
struct pipe_vertex_element feedback_element[PIPE_ATTRIB_MAX];

2
src/mesa/pipe/draw/draw_vertex_fetch.c
View File

@@ -85,7 +85,7 @@ void draw_vertex_fetch( struct draw_context *draw,
/*printf("fetch vertex %u: \n", j);*/
/* loop over vertex attributes (vertex shader inputs) */
for (attr = 0; attr < draw->vertex_shader->state->num_inputs; attr++) {
for (attr = 0; attr < draw->vertex_shader.num_inputs; attr++) {
unsigned buf = draw->vertex_element[attr].vertex_buffer_index;
const void *src

50
src/mesa/pipe/draw/draw_vertex_shader.c
View File

@@ -36,8 +36,6 @@
#include "draw_context.h"
#include "draw_vertex.h"
#include "x86/rtasm/x86sse.h"
#include "pipe/tgsi/exec/tgsi_core.h"
static INLINE unsigned
@@ -72,7 +70,6 @@ typedef void (XSTDCALL *codegen_function) (
float (*constant)[4],
struct tgsi_exec_vector *temporary );
/**
* Transform vertices with the current vertex program/shader
* Up to four vertices can be shaded at a time.
@@ -95,7 +92,7 @@ run_vertex_program(struct draw_context *draw,
const float *trans = draw->viewport.translate;
assert(count <= 4);
assert(draw->vertex_shader->state->output_semantic_name[0]
assert(draw->vertex_shader.output_semantic_name[0]
== TGSI_SEMANTIC_POSITION);
#ifdef DEBUG
@@ -104,7 +101,7 @@ run_vertex_program(struct draw_context *draw,
/* init machine state */
tgsi_exec_machine_init(&machine,
draw->vertex_shader->state->tokens,
draw->vertex_shader.tokens,
PIPE_MAX_SAMPLERS,
NULL /*samplers*/ );
@@ -117,8 +114,8 @@ run_vertex_program(struct draw_context *draw,
draw_vertex_fetch( draw, &machine, elts, count );
/* run shader */
if( draw->vertex_shader->state->executable != NULL ) {
codegen_function func = (codegen_function) draw->vertex_shader->state->executable;
if( draw->vertex_shader.executable != NULL ) {
codegen_function func = (codegen_function) draw->vertex_shader.executable;
func(
machine.Inputs,
machine.Outputs,
@@ -209,42 +206,3 @@ void draw_vertex_shader_queue_flush( struct draw_context *draw )
draw->vs.queue_nr = 0;
}
void *
draw_create_vertex_shader(struct draw_context *draw,
const struct pipe_shader_state *shader)
{
struct draw_vertex_shader *vs = calloc(1, sizeof(struct draw_vertex_shader));
vs->state = shader;
#if defined(__i386__) || defined(__386__)
x86_init_func(&vs->sse2_program);
tgsi_emit_sse2(shader->tokens, &vs->sse2_program);
((struct pipe_shader_state*)(vs->state))->executable =
x86_get_func(&vs->sse2_program);
#endif
return vs;
}
void draw_bind_vertex_shader(struct draw_context *draw,
void *vcso)
{
draw_flush(draw);
draw->vertex_shader = (struct draw_vertex_shader*)(vcso);
}
void draw_delete_vertex_shader(struct draw_context *draw,
void *vcso)
{
struct draw_vertex_shader *vs = (struct draw_vertex_shader*)(vcso);
#if defined(__i386__) || defined(__386__)
x86_release_func(&vs->sse2_program);
#endif
free(vcso);
}

54
src/mesa/pipe/i915simple/i915_state.c
View File

@@ -443,13 +443,16 @@ static void i915_set_polygon_stipple( struct pipe_context *pipe,
{
}
static void * i915_create_fs_state(struct pipe_context *pipe,
static void *
i915_create_shader_state(struct pipe_context *pipe,
const struct pipe_shader_state *templ)
{
return 0;
}
static void i915_bind_fs_state(struct pipe_context *pipe, void *fs)
static void i915_bind_fs_state( struct pipe_context *pipe,
void *fs )
{
struct i915_context *i915 = i915_context(pipe);
@@ -458,37 +461,22 @@ static void i915_bind_fs_state(struct pipe_context *pipe, void *fs)
i915->dirty |= I915_NEW_FS;
}
static void i915_delete_fs_state(struct pipe_context *pipe, void *shader)
static void i915_bind_vs_state(struct pipe_context *pipe,
void *vs)
{
struct i915_context *i915 = i915_context(pipe);
/* just pass-through to draw module */
draw_set_vertex_shader(i915->draw, (const struct pipe_shader_state *)vs);
}
static void i915_delete_shader_state(struct pipe_context *pipe,
void *shader)
{
/*do nothing*/
}
static void *
i915_create_vs_state(struct pipe_context *pipe,
const struct pipe_shader_state *templ)
{
struct i915_context *i915 = i915_context(pipe);
/* just pass-through to draw module */
return draw_create_vertex_shader(i915->draw, templ);
}
static void i915_bind_vs_state(struct pipe_context *pipe, void *vs)
{
struct i915_context *i915 = i915_context(pipe);
/* just pass-through to draw module */
draw_bind_vertex_shader(i915->draw, vs);
}
static void i915_delete_vs_state(struct pipe_context *pipe, void *shader)
{
struct i915_context *i915 = i915_context(pipe);
/* just pass-through to draw module */
draw_delete_vertex_shader(i915->draw, shader);
}
static void i915_set_constant_buffer(struct pipe_context *pipe,
uint shader, uint index,
const struct pipe_constant_buffer *buf)
@@ -719,12 +707,12 @@ i915_init_state_functions( struct i915_context *i915 )
i915->pipe.create_rasterizer_state = i915_create_rasterizer_state;
i915->pipe.bind_rasterizer_state = i915_bind_rasterizer_state;
i915->pipe.delete_rasterizer_state = i915_delete_rasterizer_state;
i915->pipe.create_fs_state = i915_create_fs_state;
i915->pipe.create_fs_state = i915_create_shader_state;
i915->pipe.bind_fs_state = i915_bind_fs_state;
i915->pipe.delete_fs_state = i915_delete_fs_state;
i915->pipe.create_vs_state = i915_create_vs_state;
i915->pipe.delete_fs_state = i915_delete_shader_state;
i915->pipe.create_vs_state = i915_create_shader_state;
i915->pipe.bind_vs_state = i915_bind_vs_state;
i915->pipe.delete_vs_state = i915_delete_vs_state;
i915->pipe.delete_vs_state = i915_delete_shader_state;
i915->pipe.set_blend_color = i915_set_blend_color;
i915->pipe.set_clip_state = i915_set_clip_state;

8
src/mesa/pipe/softpipe/sp_context.c
View File

@@ -275,12 +275,12 @@ struct pipe_context *softpipe_create( struct pipe_winsys *pipe_winsys,
softpipe->pipe.create_rasterizer_state = softpipe_create_rasterizer_state;
softpipe->pipe.bind_rasterizer_state = softpipe_bind_rasterizer_state;
softpipe->pipe.delete_rasterizer_state = softpipe_delete_rasterizer_state;
softpipe->pipe.create_fs_state = softpipe_create_fs_state;
softpipe->pipe.create_fs_state = softpipe_create_shader_state;
softpipe->pipe.bind_fs_state = softpipe_bind_fs_state;
softpipe->pipe.delete_fs_state = softpipe_delete_fs_state;
softpipe->pipe.create_vs_state = softpipe_create_vs_state;
softpipe->pipe.delete_fs_state = softpipe_delete_shader_state;
softpipe->pipe.create_vs_state = softpipe_create_shader_state;
softpipe->pipe.bind_vs_state = softpipe_bind_vs_state;
softpipe->pipe.delete_vs_state = softpipe_delete_vs_state;
softpipe->pipe.delete_vs_state = softpipe_delete_shader_state;
softpipe->pipe.set_blend_color = softpipe_set_blend_color;
softpipe->pipe.set_clip_state = softpipe_set_clip_state;

6
src/mesa/pipe/softpipe/sp_context.h
View File

@@ -62,10 +62,6 @@ struct draw_stage;
#define SP_NEW_VS 0x2000
#define SP_NEW_CONSTANTS 0x4000
struct sp_vertex_shader_state {
const struct pipe_shader_state *state;
void *draw_data;
};
struct softpipe_context {
struct pipe_context pipe; /**< base class */
@@ -80,7 +76,7 @@ struct softpipe_context {
const struct pipe_depth_stencil_state *depth_stencil;
const struct pipe_rasterizer_state *rasterizer;
const struct pipe_shader_state *fs;
const struct sp_vertex_shader_state *vs;
const struct pipe_shader_state *vs;
struct pipe_blend_color blend_color;
struct pipe_clear_color_state clear_color;

14
src/mesa/pipe/softpipe/sp_state.h
View File

@@ -87,14 +87,12 @@ void softpipe_set_constant_buffer(struct pipe_context *,
void softpipe_set_feedback_state( struct pipe_context *,
const struct pipe_feedback_state * );
void *softpipe_create_fs_state(struct pipe_context *,
const struct pipe_shader_state *);
void softpipe_bind_fs_state(struct pipe_context *, void *);
void softpipe_delete_fs_state(struct pipe_context *, void *);
void *softpipe_create_vs_state(struct pipe_context *,
const struct pipe_shader_state *);
void softpipe_bind_vs_state(struct pipe_context *, void *);
void softpipe_delete_vs_state(struct pipe_context *, void *);
void *
softpipe_create_shader_state( struct pipe_context *,
const struct pipe_shader_state * );
void softpipe_bind_fs_state( struct pipe_context *, void * );
void softpipe_bind_vs_state( struct pipe_context *, void * );
void softpipe_delete_shader_state( struct pipe_context *, void * );
void softpipe_set_polygon_stipple( struct pipe_context *,
const struct pipe_poly_stipple * );

2
src/mesa/pipe/softpipe/sp_state_derived.c
View File

@@ -43,7 +43,7 @@
*/
static void calculate_vertex_layout( struct softpipe_context *softpipe )
{
const struct pipe_shader_state *vs = softpipe->vs->state;
const struct pipe_shader_state *vs = softpipe->vs;
const struct pipe_shader_state *fs = softpipe->fs;
const interp_mode colorInterp
= softpipe->rasterizer->flatshade ? INTERP_CONSTANT : INTERP_LINEAR;

47
src/mesa/pipe/softpipe/sp_state_fs.c
View File

@@ -33,13 +33,10 @@
#include "pipe/draw/draw_context.h"
void * softpipe_create_fs_state(struct pipe_context *pipe,
void * softpipe_create_shader_state(struct pipe_context *pipe,
const struct pipe_shader_state *templ)
{
/* Decide whether we'll be codegenerating this shader and if so do
* that now.
*/
/* we just want the pipe_shader_state template in the bind calls */
return 0;
}
@@ -52,51 +49,25 @@ void softpipe_bind_fs_state(struct pipe_context *pipe, void *fs)
softpipe->dirty |= SP_NEW_FS;
}
void softpipe_delete_fs_state(struct pipe_context *pipe,
void *shader)
{
}
void * softpipe_create_vs_state(struct pipe_context *pipe,
const struct pipe_shader_state *templ)
{
struct softpipe_context *softpipe = softpipe_context(pipe);
struct sp_vertex_shader_state *state =
malloc(sizeof(struct sp_vertex_shader_state));
state->state = templ;
state->draw_data = draw_create_vertex_shader(softpipe->draw,
state->state);
return state;
}
void softpipe_bind_vs_state(struct pipe_context *pipe, void *vs)
{
struct softpipe_context *softpipe = softpipe_context(pipe);
softpipe->vs = (const struct sp_vertex_shader_state *)vs;
draw_bind_vertex_shader(softpipe->draw, softpipe->vs->draw_data);
softpipe->vs = (struct pipe_shader_state *)vs;
softpipe->dirty |= SP_NEW_VS;
draw_set_vertex_shader(softpipe->draw, (struct pipe_shader_state *)vs);
}
void softpipe_delete_vs_state(struct pipe_context *pipe,
void *vs)
void softpipe_delete_shader_state( struct pipe_context *pipe,
void *shader )
{
struct softpipe_context *softpipe = softpipe_context(pipe);
struct sp_vertex_shader_state *state =
(struct sp_vertex_shader_state *)vs;
draw_delete_vertex_shader(softpipe->draw, state->draw_data);
free(state);
/* do nothing */
}
void softpipe_set_constant_buffer(struct pipe_context *pipe,
uint shader, uint index,
const struct pipe_constant_buffer *buf)

7
src/mesa/state_tracker/st_cb_program.c
View File

@@ -86,6 +86,10 @@ static struct gl_program *st_new_program( GLcontext *ctx,
prog->serialNo = 1;
#if defined(__i386__) || defined(__386__)
x86_init_func( &prog->sse2_program );
#endif
return _mesa_init_vertex_program( ctx,
&prog->Base,
target,
@@ -125,6 +129,9 @@ static void st_delete_program( GLcontext *ctx,
case GL_VERTEX_PROGRAM_ARB:
{
struct st_vertex_program *stvp = (struct st_vertex_program *) prog;
#if defined(__i386__) || defined(__386__)
x86_release_func( &stvp->sse2_program );
#endif
st_remove_vertex_program(st, stvp);
}
break;

2
src/mesa/state_tracker/st_draw.c
View File

@@ -405,7 +405,7 @@ st_feedback_draw_vbo(GLcontext *ctx,
draw_set_viewport_state(draw, &st->state.viewport);
draw_set_clip_state(draw, &st->state.clip);
draw_set_rasterizer_state(draw, &st->state.rasterizer->state);
draw_bind_vertex_shader(draw, st->state.vs->data);
draw_set_vertex_shader(draw, &st->state.vs->state);
/* XXX need to set vertex info too */

8
src/mesa/state_tracker/st_program.c
View File

@@ -253,6 +253,14 @@ st_translate_vertex_program(struct st_context *st,
if (TGSI_DEBUG)
tgsi_dump( tokensOut, 0 );
#if defined(__i386__) || defined(__386__)
if (stvp->sse2_program.csr == stvp->sse2_program.store)
tgsi_emit_sse2( tokensOut, &stvp->sse2_program );
if (!cso->state.executable)
((struct cso_vertex_shader*)cso)->state.executable = (void *) x86_get_func( &stvp->sse2_program );
#endif
return cso;
}

4
src/mesa/state_tracker/st_program.h
View File

@@ -79,6 +79,10 @@ struct st_vertex_program
/** The program in TGSI format */
struct tgsi_token tokens[ST_FP_MAX_TOKENS];
#if defined(__i386__) || defined(__386__)
struct x86_function sse2_program;
#endif
/** Pointer to the corresponding cached shader */
const struct cso_vertex_shader *vs;

68
src/mesa/x86/rtasm/x86sse.c
View File

@@ -6,22 +6,22 @@
#define DISASSEM 0
#define X86_TWOB 0x0f
static unsigned char *cptr( void (*label)() )
static GLubyte *cptr( void (*label)() )
{
return (unsigned char *)(unsigned long)label;
return (char *)(unsigned long)label;
}
/* Emit bytes to the instruction stream:
*/
static void emit_1b( struct x86_function *p, char b0 )
static void emit_1b( struct x86_function *p, GLbyte b0 )
{
*(char *)(p->csr++) = b0;
*(GLbyte *)(p->csr++) = b0;
}
static void emit_1i( struct x86_function *p, int i0 )
static void emit_1i( struct x86_function *p, GLint i0 )
{
*(int *)(p->csr) = i0;
*(GLint *)(p->csr) = i0;
p->csr += 4;
}
@@ -35,20 +35,20 @@ static void disassem( struct x86_function *p, const char *fn )
#endif
}
static void emit_1ub_fn( struct x86_function *p, unsigned char b0, const char *fn )
static void emit_1ub_fn( struct x86_function *p, GLubyte b0, const char *fn )
{
disassem(p, fn);
*(p->csr++) = b0;
}
static void emit_2ub_fn( struct x86_function *p, unsigned char b0, unsigned char b1, const char *fn )
static void emit_2ub_fn( struct x86_function *p, GLubyte b0, GLubyte b1, const char *fn )
{
disassem(p, fn);
*(p->csr++) = b0;
*(p->csr++) = b1;
}
static void emit_3ub_fn( struct x86_function *p, unsigned char b0, unsigned char b1, unsigned char b2, const char *fn )
static void emit_3ub_fn( struct x86_function *p, GLubyte b0, GLubyte b1, GLubyte b2, const char *fn )
{
disassem(p, fn);
*(p->csr++) = b0;
@@ -69,7 +69,7 @@ static void emit_modrm( struct x86_function *p,
struct x86_reg reg,
struct x86_reg regmem )
{
unsigned char val = 0;
GLubyte val = 0;
assert(reg.mod == mod_REG);
@@ -104,7 +104,7 @@ static void emit_modrm( struct x86_function *p,
static void emit_modrm_noreg( struct x86_function *p,
unsigned op,
GLuint op,
struct x86_reg regmem )
{
struct x86_reg dummy = x86_make_reg(file_REG32, op);
@@ -117,8 +117,8 @@ static void emit_modrm_noreg( struct x86_function *p,
* the arguments presented.
*/
static void emit_op_modrm( struct x86_function *p,
unsigned char op_dst_is_reg,
unsigned char op_dst_is_mem,
GLubyte op_dst_is_reg,
GLubyte op_dst_is_mem,
struct x86_reg dst,
struct x86_reg src )
{
@@ -162,7 +162,7 @@ struct x86_reg x86_make_reg( enum x86_reg_file file,
}
struct x86_reg x86_make_disp( struct x86_reg reg,
int disp )
GLint disp )
{
assert(reg.file == file_REG32);
@@ -191,7 +191,7 @@ struct x86_reg x86_get_base_reg( struct x86_reg reg )
return x86_make_reg( reg.file, reg.idx );
}
unsigned char *x86_get_label( struct x86_function *p )
GLubyte *x86_get_label( struct x86_function *p )
{
return p->csr;
}
@@ -205,13 +205,13 @@ unsigned char *x86_get_label( struct x86_function *p )
void x86_jcc( struct x86_function *p,
enum x86_cc cc,
unsigned char *label )
GLubyte *label )
{
int offset = label - (x86_get_label(p) + 2);
GLint offset = label - (x86_get_label(p) + 2);
if (offset <= 127 && offset >= -128) {
emit_1ub(p, 0x70 + cc);
emit_1b(p, (char) offset);
emit_1b(p, (GLbyte) offset);
}
else {
offset = label - (x86_get_label(p) + 6);
@@ -222,7 +222,7 @@ void x86_jcc( struct x86_function *p,
/* Always use a 32bit offset for forward jumps:
*/
unsigned char *x86_jcc_forward( struct x86_function *p,
GLubyte *x86_jcc_forward( struct x86_function *p,
enum x86_cc cc )
{
emit_2ub(p, 0x0f, 0x80 + cc);
@@ -230,14 +230,14 @@ unsigned char *x86_jcc_forward( struct x86_function *p,
return x86_get_label(p);
}
unsigned char *x86_jmp_forward( struct x86_function *p)
GLubyte *x86_jmp_forward( struct x86_function *p)
{
emit_1ub(p, 0xe9);
emit_1i(p, 0);
return x86_get_label(p);
}
unsigned char *x86_call_forward( struct x86_function *p)
GLubyte *x86_call_forward( struct x86_function *p)
{
emit_1ub(p, 0xe8);
emit_1i(p, 0);
@@ -247,12 +247,12 @@ unsigned char *x86_call_forward( struct x86_function *p)
/* Fixup offset from forward jump:
*/
void x86_fixup_fwd_jump( struct x86_function *p,
unsigned char *fixup )
GLubyte *fixup )
{
*(int *)(fixup - 4) = x86_get_label(p) - fixup;
}
void x86_jmp( struct x86_function *p, unsigned char *label)
void x86_jmp( struct x86_function *p, GLubyte *label)
{
emit_1ub(p, 0xe9);
emit_1i(p, label - x86_get_label(p) - 4);
@@ -268,7 +268,7 @@ void x86_call( struct x86_function *p, void (*label)())
* Temporary. As I need immediate operands, and dont want to mess with the codegen,
* I load the immediate into general purpose register and use it.
*/
void x86_mov_reg_imm( struct x86_function *p, struct x86_reg dst, int imm )
void x86_mov_reg_imm( struct x86_function *p, struct x86_reg dst, GLint imm )
{
assert(dst.mod == mod_REG);
emit_1ub(p, 0xb8 + dst.idx);
@@ -595,7 +595,7 @@ void sse_cvtps2pi( struct x86_function *p,
void sse_shufps( struct x86_function *p,
struct x86_reg dest,
struct x86_reg arg0,
unsigned char shuf)
GLubyte shuf)
{
emit_2ub(p, X86_TWOB, 0xC6);
emit_modrm(p, dest, arg0);
@@ -605,7 +605,7 @@ void sse_shufps( struct x86_function *p,
void sse_cmpps( struct x86_function *p,
struct x86_reg dest,
struct x86_reg arg0,
unsigned char cc)
GLubyte cc)
{
emit_2ub(p, X86_TWOB, 0xC2);
emit_modrm(p, dest, arg0);
@@ -630,7 +630,7 @@ void sse_pmovmskb( struct x86_function *p,
void sse2_pshufd( struct x86_function *p,
struct x86_reg dest,
struct x86_reg arg0,
unsigned char shuf)
GLubyte shuf)
{
emit_3ub(p, 0x66, X86_TWOB, 0x70);
emit_modrm(p, dest, arg0);
@@ -772,11 +772,11 @@ void x87_fclex( struct x86_function *p )
static void x87_arith_op( struct x86_function *p, struct x86_reg dst, struct x86_reg arg,
unsigned char dst0ub0,
unsigned char dst0ub1,
unsigned char arg0ub0,
unsigned char arg0ub1,
unsigned char argmem_noreg)
GLubyte dst0ub0,
GLubyte dst0ub1,
GLubyte arg0ub0,
GLubyte arg0ub1,
GLubyte argmem_noreg)
{
assert(dst.file == file_x87);
@@ -1116,7 +1116,7 @@ void mmx_movq( struct x86_function *p,
* account any push/pop activity:
*/
struct x86_reg x86_fn_arg( struct x86_function *p,
unsigned arg )
GLuint arg )
{
return x86_make_disp(x86_make_reg(file_REG32, reg_SP),
p->stack_offset + arg * 4); /* ??? */
@@ -1128,7 +1128,7 @@ void x86_init_func( struct x86_function *p )
x86_init_func_size(p, 1024);
}
void x86_init_func_size( struct x86_function *p, unsigned code_size )
void x86_init_func_size( struct x86_function *p, GLuint code_size )
{
p->store = _mesa_exec_malloc(code_size);
p->csr = p->store;

49
src/mesa/x86/rtasm/x86sse.h
View File

@@ -4,22 +4,24 @@
#if defined(__i386__) || defined(__386__)
#include "glheader.h"
/* It is up to the caller to ensure that instructions issued are
* suitable for the host cpu. There are no checks made in this module
* for mmx/sse/sse2 support on the cpu.
*/
struct x86_reg {
unsigned file:3;
unsigned idx:3;
unsigned mod:2; /* mod_REG if this is just a register */
int disp:24; /* only +/- 23bits of offset - should be enough... */
GLuint file:3;
GLuint idx:3;
GLuint mod:2; /* mod_REG if this is just a register */
GLint disp:24; /* only +/- 23bits of offset - should be enough... */
};
struct x86_function {
unsigned char *store;
unsigned char *csr;
unsigned stack_offset;
int need_emms;
GLubyte *store;
GLubyte *csr;
GLuint stack_offset;
GLint need_emms;
const char *fn;
};
@@ -79,7 +81,7 @@ enum sse_cc {
void x86_init_func( struct x86_function *p );
void x86_init_func_size( struct x86_function *p, unsigned code_size );
void x86_init_func_size( struct x86_function *p, GLuint code_size );
void x86_release_func( struct x86_function *p );
void (*x86_get_func( struct x86_function *p ))( void );
@@ -91,7 +93,7 @@ struct x86_reg x86_make_reg( enum x86_reg_file file,
enum x86_reg_name idx );
struct x86_reg x86_make_disp( struct x86_reg reg,
int disp );
GLint disp );
struct x86_reg x86_deref( struct x86_reg reg );
@@ -100,23 +102,23 @@ struct x86_reg x86_get_base_reg( struct x86_reg reg );
/* Labels, jumps and fixup:
*/
unsigned char *x86_get_label( struct x86_function *p );
GLubyte *x86_get_label( struct x86_function *p );
void x86_jcc( struct x86_function *p,
enum x86_cc cc,
unsigned char *label );
GLubyte *label );
unsigned char *x86_jcc_forward( struct x86_function *p,
GLubyte *x86_jcc_forward( struct x86_function *p,
enum x86_cc cc );
unsigned char *x86_jmp_forward( struct x86_function *p);
GLubyte *x86_jmp_forward( struct x86_function *p);
unsigned char *x86_call_forward( struct x86_function *p);
GLubyte *x86_call_forward( struct x86_function *p);
void x86_fixup_fwd_jump( struct x86_function *p,
unsigned char *fixup );
GLubyte *fixup );
void x86_jmp( struct x86_function *p, unsigned char *label );
void x86_jmp( struct x86_function *p, GLubyte *label );
void x86_call( struct x86_function *p, void (*label)() );
@@ -124,7 +126,7 @@ void x86_call( struct x86_function *p, void (*label)() );
* Temporary. As I need immediate operands, and dont want to mess with the codegen,
* I load the immediate into general purpose register and use it.
*/
void x86_mov_reg_imm( struct x86_function *p, struct x86_reg dst, int imm );
void x86_mov_reg_imm( struct x86_function *p, struct x86_reg dst, GLint imm );
/* Macro for sse_shufps() and sse2_pshufd():
@@ -145,8 +147,7 @@ void sse2_movd( struct x86_function *p, struct x86_reg dst, struct x86_reg src )
void sse2_packssdw( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse2_packsswb( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse2_packuswb( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse2_pshufd( struct x86_function *p, struct x86_reg dest, struct x86_reg arg0,
unsigned char shuf );
void sse2_pshufd( struct x86_function *p, struct x86_reg dest, struct x86_reg arg0, GLubyte shuf );
void sse2_rcpps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse2_rcpss( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
@@ -156,8 +157,7 @@ void sse_cvtps2pi( struct x86_function *p, struct x86_reg dst, struct x86_reg sr
void sse_divss( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_andnps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_andps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_cmpps( struct x86_function *p, struct x86_reg dst, struct x86_reg src,
unsigned char cc );
void sse_cmpps( struct x86_function *p, struct x86_reg dst, struct x86_reg src, GLubyte cc );
void sse_maxps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_maxss( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_minps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
@@ -175,8 +175,7 @@ void sse_xorps( struct x86_function *p, struct x86_reg dst, struct x86_reg src )
void sse_subps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_rsqrtps( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_rsqrtss( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
void sse_shufps( struct x86_function *p, struct x86_reg dest, struct x86_reg arg0,
unsigned char shuf );
void sse_shufps( struct x86_function *p, struct x86_reg dest, struct x86_reg arg0, GLubyte shuf );
void sse_pmovmskb( struct x86_function *p, struct x86_reg dest, struct x86_reg src );
void x86_add( struct x86_function *p, struct x86_reg dst, struct x86_reg src );
@@ -248,7 +247,7 @@ void x87_fucom( struct x86_function *p, struct x86_reg arg );
* account any push/pop activity. Note - doesn't track explict
* manipulation of ESP by other instructions.
*/
struct x86_reg x86_fn_arg( struct x86_function *p, unsigned arg );
struct x86_reg x86_fn_arg( struct x86_function *p, GLuint arg );
#endif
#endif