mesa: more complete fix for transform_invarient glitches
Add a new flag mvp_with_dp4 in the context, and use that to switch both ffvertex.c and programopt.c vertex transformation code to either DP4 or MUL/MAD implementations.
This commit is contained in:
@@ -1522,4 +1522,17 @@ _mesa_Flush(void)
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Set mvp_with_dp4 flag. If a driver has a preference for DP4 over
|
||||
* MUL/MAD, or vice versa, call this function to register that.
|
||||
* Otherwise we default to MUL/MAD.
|
||||
*/
|
||||
void
|
||||
_mesa_set_mvp_with_dp4( GLcontext *ctx,
|
||||
GLboolean flag )
|
||||
{
|
||||
ctx->mvp_with_dp4 = flag;
|
||||
}
|
||||
|
||||
|
||||
/*@}*/
|
||||
|
@@ -151,6 +151,10 @@ extern struct _glapi_table *
|
||||
_mesa_get_dispatch(GLcontext *ctx);
|
||||
|
||||
|
||||
void
|
||||
_mesa_set_mvp_with_dp4( GLcontext *ctx,
|
||||
GLboolean flag );
|
||||
|
||||
|
||||
/** \name Miscellaneous */
|
||||
/*@{*/
|
||||
|
@@ -315,12 +315,6 @@ static void make_state_key( GLcontext *ctx, struct state_key *key )
|
||||
*/
|
||||
#define DISASSEM 0
|
||||
|
||||
/* Should be tunable by the driver - do we want to do matrix
|
||||
* multiplications with DP4's or with MUL/MAD's? SSE works better
|
||||
* with the latter, drivers may differ.
|
||||
*/
|
||||
#define PREFER_DP4 1
|
||||
|
||||
|
||||
/* Use uregs to represent registers internally, translate to Mesa's
|
||||
* expected formats on emit.
|
||||
@@ -348,6 +342,7 @@ struct tnl_program {
|
||||
const struct state_key *state;
|
||||
struct gl_vertex_program *program;
|
||||
GLint max_inst; /** number of instructions allocated for program */
|
||||
GLboolean mvp_with_dp4;
|
||||
|
||||
GLuint temp_in_use;
|
||||
GLuint temp_reserved;
|
||||
@@ -775,7 +770,7 @@ static struct ureg get_eye_position( struct tnl_program *p )
|
||||
|
||||
p->eye_position = reserve_temp(p);
|
||||
|
||||
if (PREFER_DP4) {
|
||||
if (p->mvp_with_dp4) {
|
||||
register_matrix_param5( p, STATE_MODELVIEW_MATRIX, 0, 0, 3,
|
||||
0, modelview );
|
||||
|
||||
@@ -881,7 +876,7 @@ static void build_hpos( struct tnl_program *p )
|
||||
struct ureg hpos = register_output( p, VERT_RESULT_HPOS );
|
||||
struct ureg mvp[4];
|
||||
|
||||
if (PREFER_DP4) {
|
||||
if (p->mvp_with_dp4) {
|
||||
register_matrix_param5( p, STATE_MVP_MATRIX, 0, 0, 3,
|
||||
0, mvp );
|
||||
emit_matrix_transform_vec4( p, hpos, mvp, pos );
|
||||
@@ -1574,7 +1569,7 @@ static void build_texture_transform( struct tnl_program *p )
|
||||
struct ureg in = (!is_undef(out_texgen) ?
|
||||
out_texgen :
|
||||
register_input(p, VERT_ATTRIB_TEX0+i));
|
||||
if (PREFER_DP4) {
|
||||
if (p->mvp_with_dp4) {
|
||||
register_matrix_param5( p, STATE_TEXTURE_MATRIX, i, 0, 3,
|
||||
0, texmat );
|
||||
emit_matrix_transform_vec4( p, out, texmat, in );
|
||||
@@ -1708,6 +1703,7 @@ static void build_tnl_program( struct tnl_program *p )
|
||||
static void
|
||||
create_new_program( const struct state_key *key,
|
||||
struct gl_vertex_program *program,
|
||||
GLboolean mvp_with_dp4,
|
||||
GLuint max_temps)
|
||||
{
|
||||
struct tnl_program p;
|
||||
@@ -1721,6 +1717,7 @@ create_new_program( const struct state_key *key,
|
||||
p.transformed_normal = undef;
|
||||
p.identity = undef;
|
||||
p.temp_in_use = 0;
|
||||
p.mvp_with_dp4 = mvp_with_dp4;
|
||||
|
||||
if (max_temps >= sizeof(int) * 8)
|
||||
p.temp_reserved = 0;
|
||||
@@ -1776,6 +1773,7 @@ _mesa_get_fixed_func_vertex_program(GLcontext *ctx)
|
||||
return NULL;
|
||||
|
||||
create_new_program( &key, prog,
|
||||
ctx->mvp_with_dp4,
|
||||
ctx->Const.VertexProgram.MaxTemps );
|
||||
|
||||
#if 0
|
||||
|
@@ -2977,6 +2977,12 @@ struct __GLcontextRec
|
||||
/** software compression/decompression supported or not */
|
||||
GLboolean Mesa_DXTn;
|
||||
|
||||
/**
|
||||
* Use dp4 (rather than mul/mad) instructions for position
|
||||
* transformation?
|
||||
*/
|
||||
GLboolean mvp_with_dp4;
|
||||
|
||||
/** Core tnl module support */
|
||||
struct gl_tnl_module TnlModule;
|
||||
|
||||
|
@@ -45,8 +45,8 @@
|
||||
* into a vertex program.
|
||||
* May be used to implement the position_invariant option.
|
||||
*/
|
||||
void
|
||||
_mesa_insert_mvp_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
static void
|
||||
_mesa_insert_mvp_dp4_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
{
|
||||
struct prog_instruction *newInst;
|
||||
const GLuint origLen = vprog->Base.NumInstructions;
|
||||
@@ -113,6 +113,121 @@ _mesa_insert_mvp_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
}
|
||||
|
||||
|
||||
static void
|
||||
_mesa_insert_mvp_mad_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
{
|
||||
struct prog_instruction *newInst;
|
||||
const GLuint origLen = vprog->Base.NumInstructions;
|
||||
const GLuint newLen = origLen + 4;
|
||||
GLuint hposTemp;
|
||||
GLuint i;
|
||||
|
||||
/*
|
||||
* Setup state references for the modelview/projection matrix.
|
||||
* XXX we should check if these state vars are already declared.
|
||||
*/
|
||||
static const gl_state_index mvpState[4][STATE_LENGTH] = {
|
||||
{ STATE_MVP_MATRIX, 0, 0, 0, STATE_MATRIX_TRANSPOSE },
|
||||
{ STATE_MVP_MATRIX, 0, 1, 1, STATE_MATRIX_TRANSPOSE },
|
||||
{ STATE_MVP_MATRIX, 0, 2, 2, STATE_MATRIX_TRANSPOSE },
|
||||
{ STATE_MVP_MATRIX, 0, 3, 3, STATE_MATRIX_TRANSPOSE },
|
||||
};
|
||||
GLint mvpRef[4];
|
||||
|
||||
for (i = 0; i < 4; i++) {
|
||||
mvpRef[i] = _mesa_add_state_reference(vprog->Base.Parameters,
|
||||
mvpState[i]);
|
||||
}
|
||||
|
||||
/* Alloc storage for new instructions */
|
||||
newInst = _mesa_alloc_instructions(newLen);
|
||||
if (!newInst) {
|
||||
_mesa_error(ctx, GL_OUT_OF_MEMORY,
|
||||
"glProgramString(inserting position_invariant code)");
|
||||
return;
|
||||
}
|
||||
|
||||
/* TEMP hposTemp; */
|
||||
hposTemp = vprog->Base.NumTemporaries++;
|
||||
|
||||
/*
|
||||
* Generated instructions:
|
||||
* emit_op2(p, OPCODE_MUL, tmp, 0, swizzle1(src,X), mat[0]);
|
||||
* emit_op3(p, OPCODE_MAD, tmp, 0, swizzle1(src,Y), mat[1], tmp);
|
||||
* emit_op3(p, OPCODE_MAD, tmp, 0, swizzle1(src,Z), mat[2], tmp);
|
||||
* emit_op3(p, OPCODE_MAD, dest, 0, swizzle1(src,W), mat[3], tmp);
|
||||
*/
|
||||
_mesa_init_instructions(newInst, 4);
|
||||
|
||||
newInst[0].Opcode = OPCODE_MUL;
|
||||
newInst[0].DstReg.File = PROGRAM_TEMPORARY;
|
||||
newInst[0].DstReg.Index = hposTemp;
|
||||
newInst[0].DstReg.WriteMask = WRITEMASK_XYZW;
|
||||
newInst[0].SrcReg[0].File = PROGRAM_INPUT;
|
||||
newInst[0].SrcReg[0].Index = VERT_ATTRIB_POS;
|
||||
newInst[0].SrcReg[0].Swizzle = SWIZZLE_XXXX;
|
||||
newInst[0].SrcReg[1].File = PROGRAM_STATE_VAR;
|
||||
newInst[0].SrcReg[1].Index = mvpRef[0];
|
||||
newInst[0].SrcReg[1].Swizzle = SWIZZLE_NOOP;
|
||||
|
||||
for (i = 1; i <= 2; i++) {
|
||||
newInst[i].Opcode = OPCODE_MAD;
|
||||
newInst[i].DstReg.File = PROGRAM_TEMPORARY;
|
||||
newInst[i].DstReg.Index = hposTemp;
|
||||
newInst[i].DstReg.WriteMask = WRITEMASK_XYZW;
|
||||
newInst[i].SrcReg[0].File = PROGRAM_INPUT;
|
||||
newInst[i].SrcReg[0].Index = VERT_ATTRIB_POS;
|
||||
newInst[i].SrcReg[0].Swizzle = MAKE_SWIZZLE4(i,i,i,i);
|
||||
newInst[i].SrcReg[1].File = PROGRAM_STATE_VAR;
|
||||
newInst[i].SrcReg[1].Index = mvpRef[i];
|
||||
newInst[i].SrcReg[1].Swizzle = SWIZZLE_NOOP;
|
||||
newInst[i].SrcReg[2].File = PROGRAM_TEMPORARY;
|
||||
newInst[i].SrcReg[2].Index = hposTemp;
|
||||
newInst[1].SrcReg[2].Swizzle = SWIZZLE_NOOP;
|
||||
}
|
||||
|
||||
newInst[3].Opcode = OPCODE_MAD;
|
||||
newInst[3].DstReg.File = PROGRAM_OUTPUT;
|
||||
newInst[3].DstReg.Index = VERT_RESULT_HPOS;
|
||||
newInst[3].DstReg.WriteMask = WRITEMASK_XYZW;
|
||||
newInst[3].SrcReg[0].File = PROGRAM_INPUT;
|
||||
newInst[3].SrcReg[0].Index = VERT_ATTRIB_POS;
|
||||
newInst[3].SrcReg[0].Swizzle = SWIZZLE_WWWW;
|
||||
newInst[3].SrcReg[1].File = PROGRAM_STATE_VAR;
|
||||
newInst[3].SrcReg[1].Index = mvpRef[3];
|
||||
newInst[3].SrcReg[1].Swizzle = SWIZZLE_NOOP;
|
||||
newInst[3].SrcReg[2].File = PROGRAM_TEMPORARY;
|
||||
newInst[3].SrcReg[2].Index = hposTemp;
|
||||
newInst[3].SrcReg[2].Swizzle = SWIZZLE_NOOP;
|
||||
|
||||
|
||||
/* Append original instructions after new instructions */
|
||||
_mesa_copy_instructions (newInst + 4, vprog->Base.Instructions, origLen);
|
||||
|
||||
/* free old instructions */
|
||||
_mesa_free_instructions(vprog->Base.Instructions, origLen);
|
||||
|
||||
/* install new instructions */
|
||||
vprog->Base.Instructions = newInst;
|
||||
vprog->Base.NumInstructions = newLen;
|
||||
vprog->Base.InputsRead |= VERT_BIT_POS;
|
||||
vprog->Base.OutputsWritten |= (1 << VERT_RESULT_HPOS);
|
||||
}
|
||||
|
||||
|
||||
void
|
||||
_mesa_insert_mvp_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
{
|
||||
if (ctx->mvp_with_dp4)
|
||||
_mesa_insert_mvp_dp4_code( ctx, vprog );
|
||||
else
|
||||
_mesa_insert_mvp_mad_code( ctx, vprog );
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* Append extra instructions onto the given fragment program to implement
|
||||
|
@@ -177,6 +177,12 @@ struct st_context *st_create_context(struct pipe_context *pipe,
|
||||
|
||||
ctx = _mesa_create_context(visual, shareCtx, &funcs, NULL);
|
||||
|
||||
/* XXX: need a capability bit in gallium to query if the pipe
|
||||
* driver prefers DP4 or MUL/MAD for vertex transformation.
|
||||
*/
|
||||
if (debug_get_bool_option("MESA_MVP_DP4", FALSE))
|
||||
_mesa_set_mvp_with_dp4( ctx, GL_TRUE );
|
||||
|
||||
return st_create_context_priv(ctx, pipe);
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user