Merge branch 'outputswritten64'
Add a GLbitfield64 type and several macros to operate on 64-bit fields. The OutputsWritten field of gl_program is changed to use that type. This results in a fair amount of fallout in drivers that use programs. No changes are strictly necessary at this point as all bits used are below the 32-bit boundary. Fairly soon several bits will be added for clip distances written by a vertex shader. This will cause several bits used for varyings to be pushed above the 32-bit boundary. This will affect any drivers that support GLSL. At this point, only the i965 driver has been modified to support this eventuality. I did this as a "squash" merge. There were several places through the outputswritten64 branch where things were broken. I foresee this causing difficulties later for bisecting. The history is still available in the branch. Conflicts: src/mesa/drivers/dri/i965/brw_wm.h
This commit is contained in:
@@ -78,7 +78,7 @@ static void compile_clip_prog( struct brw_context *brw,
|
||||
delta = REG_SIZE;
|
||||
|
||||
for (i = 0; i < VERT_RESULT_MAX; i++)
|
||||
if (c.key.attrs & (1<<i)) {
|
||||
if (c.key.attrs & BITFIELD64_BIT(i)) {
|
||||
c.offset[i] = delta;
|
||||
delta += ATTR_SIZE;
|
||||
}
|
||||
|
@@ -42,7 +42,7 @@
|
||||
* up polygon offset and flatshading at this point:
|
||||
*/
|
||||
struct brw_clip_prog_key {
|
||||
GLuint attrs:32;
|
||||
GLbitfield64 attrs;
|
||||
GLuint primitive:4;
|
||||
GLuint nr_userclip:3;
|
||||
GLuint do_flat_shading:1;
|
||||
|
@@ -231,7 +231,7 @@ struct brw_vs_prog_data {
|
||||
GLuint curb_read_length;
|
||||
GLuint urb_read_length;
|
||||
GLuint total_grf;
|
||||
GLuint outputs_written;
|
||||
GLbitfield64 outputs_written;
|
||||
GLuint nr_params; /**< number of float params/constants */
|
||||
|
||||
GLuint inputs_read;
|
||||
@@ -742,9 +742,5 @@ brw_fragment_program_const(const struct gl_fragment_program *p)
|
||||
return (const struct brw_fragment_program *) p;
|
||||
}
|
||||
|
||||
|
||||
|
||||
#define DO_SETUP_BITS ((1<<(FRAG_ATTRIB_MAX)) - 1)
|
||||
|
||||
#endif
|
||||
|
||||
|
@@ -40,7 +40,7 @@
|
||||
#define MAX_GS_VERTS (4)
|
||||
|
||||
struct brw_gs_prog_key {
|
||||
GLuint attrs:32;
|
||||
GLbitfield64 attrs;
|
||||
GLuint primitive:4;
|
||||
GLuint hint_gs_always:1;
|
||||
GLuint pv_first:1;
|
||||
|
@@ -61,7 +61,7 @@ static void compile_sf_prog( struct brw_context *brw,
|
||||
c.key = *key;
|
||||
c.nr_attrs = brw_count_bits(c.key.attrs);
|
||||
c.nr_attr_regs = (c.nr_attrs+1)/2;
|
||||
c.nr_setup_attrs = brw_count_bits(c.key.attrs & DO_SETUP_BITS);
|
||||
c.nr_setup_attrs = brw_count_bits(c.key.attrs);
|
||||
c.nr_setup_regs = (c.nr_setup_attrs+1)/2;
|
||||
|
||||
c.prog_data.urb_read_length = c.nr_attr_regs;
|
||||
@@ -70,7 +70,7 @@ static void compile_sf_prog( struct brw_context *brw,
|
||||
/* Construct map from attribute number to position in the vertex.
|
||||
*/
|
||||
for (i = idx = 0; i < VERT_RESULT_MAX; i++)
|
||||
if (c.key.attrs & (1<<i)) {
|
||||
if (c.key.attrs & BITFIELD64_BIT(i)) {
|
||||
c.attr_to_idx[i] = idx;
|
||||
c.idx_to_attr[idx] = i;
|
||||
if (i >= VERT_RESULT_TEX0 && i <= VERT_RESULT_TEX7) {
|
||||
@@ -147,7 +147,7 @@ static void upload_sf_prog(struct brw_context *brw)
|
||||
* edgeflag testing here, it is already done in the clip
|
||||
* program.
|
||||
*/
|
||||
if (key.attrs & (1<<VERT_RESULT_EDGE))
|
||||
if (key.attrs & BITFIELD64_BIT(VERT_RESULT_EDGE))
|
||||
key.primitive = SF_UNFILLED_TRIS;
|
||||
else
|
||||
key.primitive = SF_TRIANGLES;
|
||||
|
@@ -45,7 +45,7 @@
|
||||
#define SF_UNFILLED_TRIS 3
|
||||
|
||||
struct brw_sf_prog_key {
|
||||
GLuint attrs:32;
|
||||
GLbitfield64 attrs;
|
||||
GLuint primitive:2;
|
||||
GLuint do_twoside_color:1;
|
||||
GLuint do_flat_shading:1;
|
||||
|
@@ -56,7 +56,7 @@ static struct brw_reg get_vert_attr(struct brw_sf_compile *c,
|
||||
static GLboolean have_attr(struct brw_sf_compile *c,
|
||||
GLuint attr)
|
||||
{
|
||||
return (c->key.attrs & (1<<attr)) ? 1 : 0;
|
||||
return (c->key.attrs & BITFIELD64_BIT(attr)) ? 1 : 0;
|
||||
}
|
||||
|
||||
/***********************************************************************
|
||||
@@ -122,8 +122,8 @@ static void do_twoside_color( struct brw_sf_compile *c )
|
||||
* Flat shading
|
||||
*/
|
||||
|
||||
#define VERT_RESULT_COLOR_BITS ((1<<VERT_RESULT_COL0) | \
|
||||
(1<<VERT_RESULT_COL1))
|
||||
#define VERT_RESULT_COLOR_BITS (BITFIELD64_BIT(VERT_RESULT_COL0) | \
|
||||
BITFIELD64_BIT(VERT_RESULT_COL1))
|
||||
|
||||
static void copy_colors( struct brw_sf_compile *c,
|
||||
struct brw_reg dst,
|
||||
@@ -312,8 +312,8 @@ static GLboolean calculate_masks( struct brw_sf_compile *c,
|
||||
GLushort *pc_linear)
|
||||
{
|
||||
GLboolean is_last_attr = (reg == c->nr_setup_regs - 1);
|
||||
GLuint persp_mask;
|
||||
GLuint linear_mask;
|
||||
GLbitfield64 persp_mask;
|
||||
GLbitfield64 linear_mask;
|
||||
|
||||
if (c->key.do_flat_shading || c->key.linear_color)
|
||||
persp_mask = c->key.attrs & ~(FRAG_BIT_WPOS |
|
||||
@@ -331,10 +331,10 @@ static GLboolean calculate_masks( struct brw_sf_compile *c,
|
||||
*pc_linear = 0;
|
||||
*pc = 0xf;
|
||||
|
||||
if (persp_mask & (1 << c->idx_to_attr[reg*2]))
|
||||
if (persp_mask & BITFIELD64_BIT(c->idx_to_attr[reg*2]))
|
||||
*pc_persp = 0xf;
|
||||
|
||||
if (linear_mask & (1 << c->idx_to_attr[reg*2]))
|
||||
if (linear_mask & BITFIELD64_BIT(c->idx_to_attr[reg*2]))
|
||||
*pc_linear = 0xf;
|
||||
|
||||
/* Maybe only processs one attribute on the final round:
|
||||
@@ -342,10 +342,10 @@ static GLboolean calculate_masks( struct brw_sf_compile *c,
|
||||
if (reg*2+1 < c->nr_setup_attrs) {
|
||||
*pc |= 0xf0;
|
||||
|
||||
if (persp_mask & (1 << c->idx_to_attr[reg*2+1]))
|
||||
if (persp_mask & BITFIELD64_BIT(c->idx_to_attr[reg*2+1]))
|
||||
*pc_persp |= 0xf0;
|
||||
|
||||
if (linear_mask & (1 << c->idx_to_attr[reg*2+1]))
|
||||
if (linear_mask & BITFIELD64_BIT(c->idx_to_attr[reg*2+1]))
|
||||
*pc_linear |= 0xf0;
|
||||
}
|
||||
|
||||
|
@@ -35,7 +35,7 @@
|
||||
#include "brw_util.h"
|
||||
#include "brw_defines.h"
|
||||
|
||||
GLuint brw_count_bits( GLuint val )
|
||||
GLuint brw_count_bits(uint64_t val)
|
||||
{
|
||||
GLuint i;
|
||||
for (i = 0; val ; val >>= 1)
|
||||
|
@@ -35,7 +35,7 @@
|
||||
|
||||
#include "main/mtypes.h"
|
||||
|
||||
extern GLuint brw_count_bits( GLuint val );
|
||||
extern GLuint brw_count_bits(uint64_t val);
|
||||
extern GLuint brw_parameter_list_state_flags(struct gl_program_parameter_list *paramList);
|
||||
extern GLuint brw_translate_blend_factor( GLenum factor );
|
||||
extern GLuint brw_translate_blend_equation( GLenum mode );
|
||||
|
@@ -56,7 +56,7 @@ static void do_vs_prog( struct brw_context *brw,
|
||||
c.prog_data.inputs_read = vp->program.Base.InputsRead;
|
||||
|
||||
if (c.key.copy_edgeflag) {
|
||||
c.prog_data.outputs_written |= 1<<VERT_RESULT_EDGE;
|
||||
c.prog_data.outputs_written |= BITFIELD64_BIT(VERT_RESULT_EDGE);
|
||||
c.prog_data.inputs_read |= 1<<VERT_ATTRIB_EDGEFLAG;
|
||||
}
|
||||
|
||||
|
@@ -147,7 +147,7 @@ static void brw_vs_alloc_regs( struct brw_vs_compile *c )
|
||||
mrf = 4;
|
||||
|
||||
for (i = 0; i < VERT_RESULT_MAX; i++) {
|
||||
if (c->prog_data.outputs_written & (1 << i)) {
|
||||
if (c->prog_data.outputs_written & BITFIELD64_BIT(i)) {
|
||||
c->nr_outputs++;
|
||||
assert(i < Elements(c->regs[PROGRAM_OUTPUT]));
|
||||
if (i == VERT_RESULT_HPOS) {
|
||||
@@ -1124,7 +1124,7 @@ static void emit_vertex_write( struct brw_vs_compile *c)
|
||||
/* Update the header for point size, user clipping flags, and -ve rhw
|
||||
* workaround.
|
||||
*/
|
||||
if ((c->prog_data.outputs_written & (1<<VERT_RESULT_PSIZ)) ||
|
||||
if ((c->prog_data.outputs_written & BITFIELD64_BIT(VERT_RESULT_PSIZ)) ||
|
||||
c->key.nr_userclip || BRW_IS_965(p->brw))
|
||||
{
|
||||
struct brw_reg header1 = retype(get_tmp(c), BRW_REGISTER_TYPE_UD);
|
||||
@@ -1134,7 +1134,7 @@ static void emit_vertex_write( struct brw_vs_compile *c)
|
||||
|
||||
brw_set_access_mode(p, BRW_ALIGN_16);
|
||||
|
||||
if (c->prog_data.outputs_written & (1<<VERT_RESULT_PSIZ)) {
|
||||
if (c->prog_data.outputs_written & BITFIELD64_BIT(VERT_RESULT_PSIZ)) {
|
||||
struct brw_reg psiz = c->regs[PROGRAM_OUTPUT][VERT_RESULT_PSIZ];
|
||||
brw_MUL(p, brw_writemask(header1, WRITEMASK_W), brw_swizzle1(psiz, 0), brw_imm_f(1<<11));
|
||||
brw_AND(p, brw_writemask(header1, WRITEMASK_W), header1, brw_imm_ud(0x7ff<<8));
|
||||
@@ -1224,7 +1224,7 @@ static void emit_vertex_write( struct brw_vs_compile *c)
|
||||
*/
|
||||
GLuint i, mrf = 0;
|
||||
for (i = c->first_overflow_output; i < VERT_RESULT_MAX; i++) {
|
||||
if (c->prog_data.outputs_written & (1 << i)) {
|
||||
if (c->prog_data.outputs_written & BITFIELD64_BIT(i)) {
|
||||
/* move from GRF to MRF */
|
||||
brw_MOV(p, brw_message_reg(4+mrf), c->regs[PROGRAM_OUTPUT][i]);
|
||||
mrf++;
|
||||
|
@@ -231,7 +231,7 @@ static void brw_wm_populate_key( struct brw_context *brw,
|
||||
ctx->Color.AlphaEnabled)
|
||||
lookup |= IZ_PS_KILL_ALPHATEST_BIT;
|
||||
|
||||
if (fp->program.Base.OutputsWritten & (1<<FRAG_RESULT_DEPTH))
|
||||
if (fp->program.Base.OutputsWritten & BITFIELD64_BIT(FRAG_RESULT_DEPTH))
|
||||
lookup |= IZ_PS_COMPUTES_DEPTH_BIT;
|
||||
|
||||
/* _NEW_DEPTH */
|
||||
@@ -347,7 +347,7 @@ static void brw_wm_populate_key( struct brw_context *brw,
|
||||
key->nr_color_regions = brw->state.nr_color_regions;
|
||||
|
||||
/* CACHE_NEW_VS_PROG */
|
||||
key->vp_outputs_written = brw->vs.prog_data->outputs_written & DO_SETUP_BITS;
|
||||
key->vp_outputs_written = brw->vs.prog_data->outputs_written;
|
||||
|
||||
/* The unique fragment program ID */
|
||||
key->program_string_id = fp->id;
|
||||
|
@@ -79,7 +79,7 @@ struct brw_wm_prog_key {
|
||||
GLuint program_string_id:32;
|
||||
GLushort origin_x, origin_y;
|
||||
GLushort drawable_height;
|
||||
GLuint vp_outputs_written;
|
||||
GLbitfield64 vp_outputs_written;
|
||||
};
|
||||
|
||||
|
||||
|
@@ -986,7 +986,7 @@ static void emit_render_target_writes( struct brw_wm_compile *c )
|
||||
}
|
||||
else {
|
||||
/* if gl_FragData[0] is written, use it, else use gl_FragColor */
|
||||
if (c->fp->program.Base.OutputsWritten & (1 << FRAG_RESULT_DATA0))
|
||||
if (c->fp->program.Base.OutputsWritten & BITFIELD64_BIT(FRAG_RESULT_DATA0))
|
||||
outcolor = src_reg(PROGRAM_OUTPUT, FRAG_RESULT_DATA0);
|
||||
else
|
||||
outcolor = src_reg(PROGRAM_OUTPUT, FRAG_RESULT_COLOR);
|
||||
|
@@ -371,7 +371,7 @@ static void prealloc_reg(struct brw_wm_compile *c)
|
||||
for (j = 0; j < 4; j++)
|
||||
set_reg(c, PROGRAM_PAYLOAD, fp_input, j, reg);
|
||||
}
|
||||
if (c->key.vp_outputs_written & (1 << i)) {
|
||||
if (c->key.vp_outputs_written & BITFIELD64_BIT(i)) {
|
||||
reg_index += 2;
|
||||
}
|
||||
}
|
||||
|
@@ -82,8 +82,8 @@ static void init_registers( struct brw_wm_compile *c )
|
||||
for (j = 0; j < c->nr_creg; j++)
|
||||
prealloc_reg(c, &c->creg[j], i++);
|
||||
|
||||
for (j = 0; j < FRAG_ATTRIB_MAX; j++) {
|
||||
if (c->key.vp_outputs_written & (1<<j)) {
|
||||
for (j = 0; j < VERT_RESULT_MAX; j++) {
|
||||
if (c->key.vp_outputs_written & BITFIELD64_BIT(j)) {
|
||||
int fp_index;
|
||||
|
||||
if (j >= VERT_RESULT_VAR0)
|
||||
|
@@ -106,7 +106,7 @@ wm_unit_populate_key(struct brw_context *brw, struct brw_wm_unit_key *key)
|
||||
|
||||
/* as far as we can tell */
|
||||
key->computes_depth =
|
||||
(fp->Base.OutputsWritten & (1 << FRAG_RESULT_DEPTH)) != 0;
|
||||
(fp->Base.OutputsWritten & BITFIELD64_BIT(FRAG_RESULT_DEPTH)) != 0;
|
||||
/* BRW_NEW_DEPTH_BUFFER
|
||||
* Override for NULL depthbuffer case, required by the Pixel Shader Computed
|
||||
* Depth field.
|
||||
|
@@ -509,25 +509,26 @@ static GLboolean r200_run_tcl_render( GLcontext *ctx,
|
||||
prog to a not enabled output however, so just don't mess with it.
|
||||
We only need to change compsel. */
|
||||
GLuint out_compsel = 0;
|
||||
GLuint vp_out = rmesa->curr_vp_hw->mesa_program.Base.OutputsWritten;
|
||||
const GLbitfield64 vp_out =
|
||||
rmesa->curr_vp_hw->mesa_program.Base.OutputsWritten;
|
||||
|
||||
vimap_rev = &rmesa->curr_vp_hw->inputmap_rev[0];
|
||||
assert(vp_out & (1 << VERT_RESULT_HPOS));
|
||||
assert(vp_out & BITFIELD64_BIT(VERT_RESULT_HPOS));
|
||||
out_compsel = R200_OUTPUT_XYZW;
|
||||
if (vp_out & (1 << VERT_RESULT_COL0)) {
|
||||
if (vp_out & BITFIELD64_BIT(VERT_RESULT_COL0)) {
|
||||
out_compsel |= R200_OUTPUT_COLOR_0;
|
||||
}
|
||||
if (vp_out & (1 << VERT_RESULT_COL1)) {
|
||||
if (vp_out & BITFIELD64_BIT(VERT_RESULT_COL1)) {
|
||||
out_compsel |= R200_OUTPUT_COLOR_1;
|
||||
}
|
||||
if (vp_out & (1 << VERT_RESULT_FOGC)) {
|
||||
if (vp_out & BITFIELD64_BIT(VERT_RESULT_FOGC)) {
|
||||
out_compsel |= R200_OUTPUT_DISCRETE_FOG;
|
||||
}
|
||||
if (vp_out & (1 << VERT_RESULT_PSIZ)) {
|
||||
if (vp_out & BITFIELD64_BIT(VERT_RESULT_PSIZ)) {
|
||||
out_compsel |= R200_OUTPUT_PT_SIZE;
|
||||
}
|
||||
for (i = VERT_RESULT_TEX0; i < VERT_RESULT_TEX6; i++) {
|
||||
if (vp_out & (1 << i)) {
|
||||
if (vp_out & BITFIELD64_BIT(i)) {
|
||||
out_compsel |= R200_OUTPUT_TEX_0 << (i - VERT_RESULT_TEX0);
|
||||
}
|
||||
}
|
||||
|
@@ -205,7 +205,7 @@
|
||||
#define MAX_VARYING 16 /**< number of float[4] vectors */
|
||||
#define MAX_SAMPLERS MAX_TEXTURE_IMAGE_UNITS
|
||||
#define MAX_PROGRAM_INPUTS 32
|
||||
#define MAX_PROGRAM_OUTPUTS 32
|
||||
#define MAX_PROGRAM_OUTPUTS 64
|
||||
/*@}*/
|
||||
|
||||
/** For GL_ARB_vertex_program */
|
||||
|
@@ -601,9 +601,11 @@ _mesa_init_constants(GLcontext *ctx)
|
||||
ASSERT(MAX_NV_VERTEX_PROGRAM_INPUTS <= VERT_ATTRIB_MAX);
|
||||
ASSERT(MAX_NV_VERTEX_PROGRAM_OUTPUTS <= VERT_RESULT_MAX);
|
||||
|
||||
/* check that we don't exceed various 32-bit bitfields */
|
||||
ASSERT(VERT_RESULT_MAX <= 32);
|
||||
ASSERT(FRAG_ATTRIB_MAX <= 32);
|
||||
/* check that we don't exceed the size of various bitfields */
|
||||
ASSERT(VERT_RESULT_MAX <=
|
||||
(8 * sizeof(ctx->VertexProgram._Current->Base.OutputsWritten)));
|
||||
ASSERT(FRAG_ATTRIB_MAX <=
|
||||
(8 * sizeof(ctx->FragmentProgram._Current->Base.InputsRead)));
|
||||
}
|
||||
|
||||
|
||||
|
@@ -438,7 +438,7 @@ static struct ureg register_input( struct tnl_program *p, GLuint input )
|
||||
*/
|
||||
static struct ureg register_output( struct tnl_program *p, GLuint output )
|
||||
{
|
||||
p->program->Base.OutputsWritten |= (1<<output);
|
||||
p->program->Base.OutputsWritten |= BITFIELD64_BIT(output);
|
||||
return make_ureg(PROGRAM_OUTPUT, output);
|
||||
}
|
||||
|
||||
|
@@ -78,6 +78,31 @@
|
||||
#endif
|
||||
|
||||
|
||||
/**
|
||||
* \name 64-bit extension of GLbitfield.
|
||||
*/
|
||||
/*@{*/
|
||||
typedef GLuint64 GLbitfield64;
|
||||
|
||||
#define BITFIELD64_ONE 1ULL
|
||||
#define BITFIELD64_ALLONES ~0ULL
|
||||
|
||||
/** Set a single bit */
|
||||
#define BITFIELD64_BIT(b) (BITFIELD64_ONE << (b))
|
||||
|
||||
/** Set a mask of the least significant \c b bits */
|
||||
#define BITFIELD64_MASK(b) (((b) >= 64) ? BITFIELD64_ALLONES : \
|
||||
(BITFIELD64_BIT(b) - 1))
|
||||
|
||||
/**
|
||||
* Set all bits from l (low bit) to h (high bit), inclusive.
|
||||
*
|
||||
* \note \C BITFIELD_64_RANGE(0, 63) return 64 set bits.
|
||||
*/
|
||||
#define BITFIELD64_RANGE(l, h) (BITFIELD64_MASK((h) + 1) & ~BITFIELD64_MASK(l))
|
||||
/*@}*/
|
||||
|
||||
|
||||
/**
|
||||
* \name Some forward type declarations
|
||||
*/
|
||||
@@ -1670,7 +1695,7 @@ struct gl_program
|
||||
struct prog_instruction *Instructions;
|
||||
|
||||
GLbitfield InputsRead; /**< Bitmask of which input regs are read */
|
||||
GLbitfield OutputsWritten; /**< Bitmask of which output regs are written to */
|
||||
GLbitfield64 OutputsWritten; /**< Bitmask of which output regs are written */
|
||||
GLbitfield InputFlags[MAX_PROGRAM_INPUTS]; /**< PROG_PARAM_BIT_x flags */
|
||||
GLbitfield OutputFlags[MAX_PROGRAM_OUTPUTS]; /**< PROG_PARAM_BIT_x flags */
|
||||
GLbitfield TexturesUsed[MAX_TEXTURE_UNITS]; /**< TEXTURE_x_BIT bitmask */
|
||||
|
@@ -367,7 +367,7 @@ static GLbitfield get_fp_input_mask( GLcontext *ctx )
|
||||
else {
|
||||
/* calculate from vp->outputs */
|
||||
struct gl_vertex_program *vprog;
|
||||
GLbitfield vp_outputs;
|
||||
GLbitfield64 vp_outputs;
|
||||
|
||||
/* Choose GLSL vertex shader over ARB vertex program. Need this
|
||||
* since vertex shader state validation comes after fragment state
|
||||
|
@@ -826,11 +826,11 @@ _mesa_print_program(const struct gl_program *prog)
|
||||
* XXX move to imports.[ch] if useful elsewhere.
|
||||
*/
|
||||
static const char *
|
||||
binary(GLbitfield val)
|
||||
binary(GLbitfield64 val)
|
||||
{
|
||||
static char buf[50];
|
||||
static char buf[80];
|
||||
GLint i, len = 0;
|
||||
for (i = 31; i >= 0; --i) {
|
||||
for (i = 63; i >= 0; --i) {
|
||||
if (val & (1 << i))
|
||||
buf[len++] = '1';
|
||||
else if (len > 0 || i == 0)
|
||||
|
@@ -2622,7 +2622,7 @@ yyreduce:
|
||||
YYERROR;
|
||||
}
|
||||
|
||||
state->prog->OutputsWritten |= (1U << (yyval.dst_reg).Index);
|
||||
state->prog->OutputsWritten |= BITFIELD64_BIT((yyval.dst_reg).Index);
|
||||
}
|
||||
;}
|
||||
break;
|
||||
|
@@ -643,7 +643,7 @@ maskedDstReg: dstReg optionalMask optionalCcMask
|
||||
YYERROR;
|
||||
}
|
||||
|
||||
state->prog->OutputsWritten |= (1U << $$.Index);
|
||||
state->prog->OutputsWritten |= BITFIELD64_BIT($$.Index);
|
||||
}
|
||||
}
|
||||
;
|
||||
|
@@ -109,7 +109,7 @@ _mesa_insert_mvp_dp4_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
vprog->Base.Instructions = newInst;
|
||||
vprog->Base.NumInstructions = newLen;
|
||||
vprog->Base.InputsRead |= VERT_BIT_POS;
|
||||
vprog->Base.OutputsWritten |= (1 << VERT_RESULT_HPOS);
|
||||
vprog->Base.OutputsWritten |= BITFIELD64_BIT(VERT_RESULT_HPOS);
|
||||
}
|
||||
|
||||
|
||||
@@ -211,7 +211,7 @@ _mesa_insert_mvp_mad_code(GLcontext *ctx, struct gl_vertex_program *vprog)
|
||||
vprog->Base.Instructions = newInst;
|
||||
vprog->Base.NumInstructions = newLen;
|
||||
vprog->Base.InputsRead |= VERT_BIT_POS;
|
||||
vprog->Base.OutputsWritten |= (1 << VERT_RESULT_HPOS);
|
||||
vprog->Base.OutputsWritten |= BITFIELD64_BIT(VERT_RESULT_HPOS);
|
||||
}
|
||||
|
||||
|
||||
@@ -613,7 +613,7 @@ _mesa_nop_fragment_program(GLcontext *ctx, struct gl_fragment_program *prog)
|
||||
prog->Base.Instructions = inst;
|
||||
prog->Base.NumInstructions = 2;
|
||||
prog->Base.InputsRead = 1 << inputAttr;
|
||||
prog->Base.OutputsWritten = 1 << FRAG_RESULT_COLOR;
|
||||
prog->Base.OutputsWritten = BITFIELD64_BIT(FRAG_RESULT_COLOR);
|
||||
}
|
||||
|
||||
|
||||
@@ -657,7 +657,7 @@ _mesa_nop_vertex_program(GLcontext *ctx, struct gl_vertex_program *prog)
|
||||
prog->Base.Instructions = inst;
|
||||
prog->Base.NumInstructions = 2;
|
||||
prog->Base.InputsRead = 1 << inputAttr;
|
||||
prog->Base.OutputsWritten = 1 << VERT_RESULT_COL0;
|
||||
prog->Base.OutputsWritten = BITFIELD64_BIT(VERT_RESULT_COL0);
|
||||
|
||||
/*
|
||||
* Now insert code to do standard modelview/projection transformation.
|
||||
|
@@ -515,7 +515,7 @@ _slang_update_inputs_outputs(struct gl_program *prog)
|
||||
}
|
||||
|
||||
if (inst->DstReg.File == PROGRAM_OUTPUT) {
|
||||
prog->OutputsWritten |= 1 << inst->DstReg.Index;
|
||||
prog->OutputsWritten |= BITFIELD64_BIT(inst->DstReg.Index);
|
||||
if (inst->DstReg.RelAddr) {
|
||||
/* If the output attribute is indexed with relative addressing
|
||||
* we know that it must be a varying or texcoord such as
|
||||
@@ -528,14 +528,17 @@ _slang_update_inputs_outputs(struct gl_program *prog)
|
||||
if (prog->Target == GL_VERTEX_PROGRAM_ARB) {
|
||||
if (inst->DstReg.Index == VERT_RESULT_TEX0) {
|
||||
/* mark all texcoord outputs as written */
|
||||
const GLbitfield mask =
|
||||
((1 << MAX_TEXTURE_COORD_UNITS) - 1) << VERT_RESULT_TEX0;
|
||||
const GLbitfield64 mask =
|
||||
BITFIELD64_RANGE(VERT_RESULT_TEX0,
|
||||
(VERT_RESULT_TEX0
|
||||
+ MAX_TEXTURE_COORD_UNITS - 1));
|
||||
prog->OutputsWritten |= mask;
|
||||
}
|
||||
else if (inst->DstReg.Index == VERT_RESULT_VAR0) {
|
||||
/* mark all generic varying outputs as written */
|
||||
const GLbitfield mask =
|
||||
((1 << MAX_VARYING) - 1) << VERT_RESULT_VAR0;
|
||||
const GLbitfield64 mask =
|
||||
BITFIELD64_RANGE(VERT_RESULT_VAR0,
|
||||
(VERT_RESULT_VAR0 + MAX_VARYING - 1));
|
||||
prog->OutputsWritten |= mask;
|
||||
}
|
||||
}
|
||||
@@ -807,7 +810,8 @@ _slang_link(GLcontext *ctx,
|
||||
if (shProg->VertexProgram) {
|
||||
_slang_update_inputs_outputs(&shProg->VertexProgram->Base);
|
||||
_slang_count_temporaries(&shProg->VertexProgram->Base);
|
||||
if (!(shProg->VertexProgram->Base.OutputsWritten & (1 << VERT_RESULT_HPOS))) {
|
||||
if (!(shProg->VertexProgram->Base.OutputsWritten
|
||||
& BITFIELD64_BIT(VERT_RESULT_HPOS))) {
|
||||
/* the vertex program did not compute a vertex position */
|
||||
link_error(shProg,
|
||||
"gl_Position was not written by vertex shader\n");
|
||||
@@ -825,7 +829,7 @@ _slang_link(GLcontext *ctx,
|
||||
if (shProg->FragmentProgram) {
|
||||
const GLbitfield varyingRead
|
||||
= shProg->FragmentProgram->Base.InputsRead >> FRAG_ATTRIB_VAR0;
|
||||
const GLbitfield varyingWritten = shProg->VertexProgram ?
|
||||
const GLbitfield64 varyingWritten = shProg->VertexProgram ?
|
||||
shProg->VertexProgram->Base.OutputsWritten >> VERT_RESULT_VAR0 : 0x0;
|
||||
if ((varyingRead & varyingWritten) != varyingRead) {
|
||||
link_error(shProg,
|
||||
@@ -836,9 +840,10 @@ _slang_link(GLcontext *ctx,
|
||||
|
||||
/* check that gl_FragColor and gl_FragData are not both written to */
|
||||
if (shProg->FragmentProgram) {
|
||||
GLbitfield outputsWritten = shProg->FragmentProgram->Base.OutputsWritten;
|
||||
if ((outputsWritten & ((1 << FRAG_RESULT_COLOR))) &&
|
||||
(outputsWritten >= (1 << FRAG_RESULT_DATA0))) {
|
||||
const GLbitfield64 outputsWritten =
|
||||
shProg->FragmentProgram->Base.OutputsWritten;
|
||||
if ((outputsWritten & BITFIELD64_BIT(FRAG_RESULT_COLOR)) &&
|
||||
(outputsWritten >= BITFIELD64_BIT(FRAG_RESULT_DATA0))) {
|
||||
link_error(shProg, "Fragment program cannot write both gl_FragColor"
|
||||
" and gl_FragData[].\n");
|
||||
return;
|
||||
|
@@ -176,7 +176,7 @@ find_translated_vp(struct st_context *st,
|
||||
/* See if we need to translate vertex program to TGSI form */
|
||||
if (xvp->serialNo != stvp->serialNo) {
|
||||
GLuint outAttr;
|
||||
const GLbitfield outputsWritten = stvp->Base.Base.OutputsWritten;
|
||||
const GLbitfield64 outputsWritten = stvp->Base.Base.OutputsWritten;
|
||||
GLuint numVpOuts = 0;
|
||||
GLboolean emitPntSize = GL_FALSE, emitBFC0 = GL_FALSE, emitBFC1 = GL_FALSE;
|
||||
GLbitfield usedGenerics = 0x0;
|
||||
|
@@ -469,7 +469,7 @@ st_translate_fragment_program(struct st_context *st,
|
||||
*/
|
||||
{
|
||||
uint numColors = 0;
|
||||
GLbitfield outputsWritten = stfp->Base.Base.OutputsWritten;
|
||||
GLbitfield64 outputsWritten = stfp->Base.Base.OutputsWritten;
|
||||
|
||||
/* if z is written, emit that first */
|
||||
if (outputsWritten & (1 << FRAG_RESULT_DEPTH)) {
|
||||
|
@@ -190,7 +190,7 @@ run_program(GLcontext *ctx, SWspan *span, GLuint start, GLuint end)
|
||||
{
|
||||
SWcontext *swrast = SWRAST_CONTEXT(ctx);
|
||||
const struct gl_fragment_program *program = ctx->FragmentProgram._Current;
|
||||
const GLbitfield outputsWritten = program->Base.OutputsWritten;
|
||||
const GLbitfield64 outputsWritten = program->Base.OutputsWritten;
|
||||
struct gl_program_machine *machine = &swrast->FragProgMachine;
|
||||
GLuint i;
|
||||
|
||||
@@ -201,7 +201,7 @@ run_program(GLcontext *ctx, SWspan *span, GLuint start, GLuint end)
|
||||
if (_mesa_execute_program(ctx, &program->Base, machine)) {
|
||||
|
||||
/* Store result color */
|
||||
if (outputsWritten & (1 << FRAG_RESULT_COLOR)) {
|
||||
if (outputsWritten & BITFIELD64_BIT(FRAG_RESULT_COLOR)) {
|
||||
COPY_4V(span->array->attribs[FRAG_ATTRIB_COL0][i],
|
||||
machine->Outputs[FRAG_RESULT_COLOR]);
|
||||
}
|
||||
@@ -212,7 +212,7 @@ run_program(GLcontext *ctx, SWspan *span, GLuint start, GLuint end)
|
||||
*/
|
||||
GLuint buf;
|
||||
for (buf = 0; buf < ctx->DrawBuffer->_NumColorDrawBuffers; buf++) {
|
||||
if (outputsWritten & (1 << (FRAG_RESULT_DATA0 + buf))) {
|
||||
if (outputsWritten & BITFIELD64_BIT(FRAG_RESULT_DATA0 + buf)) {
|
||||
COPY_4V(span->array->attribs[FRAG_ATTRIB_COL0 + buf][i],
|
||||
machine->Outputs[FRAG_RESULT_DATA0 + buf]);
|
||||
}
|
||||
@@ -220,7 +220,7 @@ run_program(GLcontext *ctx, SWspan *span, GLuint start, GLuint end)
|
||||
}
|
||||
|
||||
/* Store result depth/z */
|
||||
if (outputsWritten & (1 << FRAG_RESULT_DEPTH)) {
|
||||
if (outputsWritten & BITFIELD64_BIT(FRAG_RESULT_DEPTH)) {
|
||||
const GLfloat depth = machine->Outputs[FRAG_RESULT_DEPTH][2];
|
||||
if (depth <= 0.0)
|
||||
span->array->z[i] = 0;
|
||||
@@ -256,12 +256,12 @@ _swrast_exec_fragment_program( GLcontext *ctx, SWspan *span )
|
||||
|
||||
run_program(ctx, span, 0, span->end);
|
||||
|
||||
if (program->Base.OutputsWritten & (1 << FRAG_RESULT_COLOR)) {
|
||||
if (program->Base.OutputsWritten & BITFIELD64_BIT(FRAG_RESULT_COLOR)) {
|
||||
span->interpMask &= ~SPAN_RGBA;
|
||||
span->arrayMask |= SPAN_RGBA;
|
||||
}
|
||||
|
||||
if (program->Base.OutputsWritten & (1 << FRAG_RESULT_DEPTH)) {
|
||||
if (program->Base.OutputsWritten & BITFIELD64_BIT(FRAG_RESULT_DEPTH)) {
|
||||
span->interpMask &= ~SPAN_Z;
|
||||
span->arrayMask |= SPAN_Z;
|
||||
}
|
||||
|
@@ -171,7 +171,7 @@ _tnl_InvalidateState( GLcontext *ctx, GLuint new_state )
|
||||
if (vp) {
|
||||
GLuint i;
|
||||
for (i = 0; i < MAX_VARYING; i++) {
|
||||
if (vp->Base.OutputsWritten & (1 << (VERT_RESULT_VAR0 + i))) {
|
||||
if (vp->Base.OutputsWritten & BITFIELD64_BIT(VERT_RESULT_VAR0 + i)) {
|
||||
RENDERINPUTS_SET(tnl->render_inputs_bitset,
|
||||
_TNL_ATTRIB_GENERIC(i));
|
||||
}
|
||||
|
@@ -329,7 +329,7 @@ run_vp( GLcontext *ctx, struct tnl_pipeline_stage *stage )
|
||||
/* make list of outputs to save some time below */
|
||||
numOutputs = 0;
|
||||
for (i = 0; i < VERT_RESULT_MAX; i++) {
|
||||
if (program->Base.OutputsWritten & (1 << i)) {
|
||||
if (program->Base.OutputsWritten & BITFIELD64_BIT(i)) {
|
||||
outputs[numOutputs++] = i;
|
||||
}
|
||||
}
|
||||
@@ -407,14 +407,14 @@ run_vp( GLcontext *ctx, struct tnl_pipeline_stage *stage )
|
||||
/* Fixup fog and point size results if needed */
|
||||
if (program->IsNVProgram) {
|
||||
if (ctx->Fog.Enabled &&
|
||||
(program->Base.OutputsWritten & (1 << VERT_RESULT_FOGC)) == 0) {
|
||||
(program->Base.OutputsWritten & BITFIELD64_BIT(VERT_RESULT_FOGC)) == 0) {
|
||||
for (i = 0; i < VB->Count; i++) {
|
||||
store->results[VERT_RESULT_FOGC].data[i][0] = 1.0;
|
||||
}
|
||||
}
|
||||
|
||||
if (ctx->VertexProgram.PointSizeEnabled &&
|
||||
(program->Base.OutputsWritten & (1 << VERT_RESULT_PSIZ)) == 0) {
|
||||
(program->Base.OutputsWritten & BITFIELD64_BIT(VERT_RESULT_PSIZ)) == 0) {
|
||||
for (i = 0; i < VB->Count; i++) {
|
||||
store->results[VERT_RESULT_PSIZ].data[i][0] = ctx->Point.Size;
|
||||
}
|
||||
@@ -472,7 +472,7 @@ run_vp( GLcontext *ctx, struct tnl_pipeline_stage *stage )
|
||||
}
|
||||
|
||||
for (i = 0; i < ctx->Const.MaxVarying; i++) {
|
||||
if (program->Base.OutputsWritten & (1 << (VERT_RESULT_VAR0 + i))) {
|
||||
if (program->Base.OutputsWritten & BITFIELD64_BIT(VERT_RESULT_VAR0 + i)) {
|
||||
/* Note: varying results get put into the generic attributes */
|
||||
VB->AttribPtr[VERT_ATTRIB_GENERIC0+i]
|
||||
= &store->results[VERT_RESULT_VAR0 + i];
|
||||
|
Reference in New Issue
Block a user