#include "nine_debug.h"
#include "nine_state.h"
+#include "util/macros.h"
#include "util/u_memory.h"
#include "util/u_inlines.h"
#include "pipe/p_shader_tokens.h"
if (ureg_dst_is_undef(tx->regs.oDepth))
tx->regs.oDepth =
ureg_DECL_output_masked(tx->ureg, TGSI_SEMANTIC_POSITION, 0,
- TGSI_WRITEMASK_Z);
+ TGSI_WRITEMASK_Z, 0, 1);
dst = tx->regs.oDepth; /* XXX: must write .z component */
break;
case D3DSPR_PREDICATE:
tx->info->position_t = TRUE;
assert(sem.reg.idx < Elements(tx->regs.o));
tx->regs.o[sem.reg.idx] = ureg_DECL_output_masked(
- ureg, tgsi.Name, tgsi.Index, sem.reg.mask);
+ ureg, tgsi.Name, tgsi.Index, sem.reg.mask, 0, 1);
if (tgsi.Name == TGSI_SEMANTIC_PSIZE)
tx->regs.oPts = tx->regs.o[sem.reg.idx];
ureg, tgsi.Name, tgsi.Index,
nine_tgsi_to_interp_mode(&tgsi),
0, /* cylwrap */
- sem.reg.mod & NINED3DSPDM_CENTROID);
+ sem.reg.mod & NINED3DSPDM_CENTROID, 0, 1);
} else
if (!is_input && 0) { /* declare in COLOROUT/DEPTHOUT case */
/* FragColor or FragDepth */
assert(sem.reg.mask != 0);
- ureg_DECL_output_masked(ureg, tgsi.Name, tgsi.Index, sem.reg.mask);
+ ureg_DECL_output_masked(ureg, tgsi.Name, tgsi.Index, sem.reg.mask,
+ 0, 1);
}
}
return D3D_OK;
return D3D_OK;
}
+DECL_SPECIAL(LIT)
+{
+ struct ureg_program *ureg = tx->ureg;
+ struct ureg_dst tmp = tx_scratch(tx);
+ struct ureg_dst dst = tx_dst_param(tx, &tx->insn.dst[0]);
+ struct ureg_src src = tx_src_param(tx, &tx->insn.src[0]);
+ ureg_LIT(ureg, tmp, src);
+ /* d3d9 LIT is the same than gallium LIT. One difference is that d3d9
+ * states that dst.z is 0 when src.y <= 0. Gallium definition can assign
+ * it 0^0 if src.w=0, which value is driver dependent. */
+ ureg_CMP(ureg, ureg_writemask(dst, TGSI_WRITEMASK_Z),
+ ureg_negate(ureg_scalar(src, TGSI_SWIZZLE_Y)),
+ ureg_src(tmp), ureg_imm1f(ureg, 0.0f));
+ ureg_MOV(ureg, ureg_writemask(dst, TGSI_WRITEMASK_XYW), ureg_src(tmp));
+ return D3D_OK;
+}
+
DECL_SPECIAL(NRM)
{
struct ureg_program *ureg = tx->ureg;
ureg_CMP(ureg, ureg_writemask(tmp, TGSI_WRITEMASK_X), ureg_negate(ureg_abs(ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_Y))),
ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X), ureg_imm1f(ureg, 1.0f));
/* replace the depth for depth testing with the result */
- tx->regs.oDepth = ureg_DECL_output_masked(ureg, TGSI_SEMANTIC_POSITION, 0, TGSI_WRITEMASK_Z);
+ tx->regs.oDepth = ureg_DECL_output_masked(ureg, TGSI_SEMANTIC_POSITION, 0,
+ TGSI_WRITEMASK_Z, 0, 1);
ureg_MOV(ureg, tx->regs.oDepth, ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X));
/* note that we write nothing to the destination, since it's disallowed to use it afterward */
return D3D_OK;
ureg_CMP(ureg, ureg_writemask(r5, TGSI_WRITEMASK_X), ureg_negate(ureg_abs(r5g)),
r5r, ureg_imm1f(ureg, 1.0f));
/* replace the depth for depth testing with the result */
- tx->regs.oDepth = ureg_DECL_output_masked(ureg, TGSI_SEMANTIC_POSITION, 0, TGSI_WRITEMASK_Z);
+ tx->regs.oDepth = ureg_DECL_output_masked(ureg, TGSI_SEMANTIC_POSITION, 0,
+ TGSI_WRITEMASK_Z, 0, 1);
ureg_MOV(ureg, tx->regs.oDepth, r5r);
return D3D_OK;
tx_src_param(tx, &tx->insn.src[2]),
tx_src_param(tx, &tx->insn.src[3])
};
- assert(tx->insn.src[3].idx >= 0 &&
- tx->insn.src[3].idx < Elements(tx->sampler_targets));
+ assert(tx->insn.src[1].idx >= 0 &&
+ tx->insn.src[1].idx < Elements(tx->sampler_targets));
target = tx->sampler_targets[tx->insn.src[1].idx];
ureg_TXD(tx->ureg, dst, target, src[0], src[2], src[3], src[1]);
tx_src_param(tx, &tx->insn.src[0]),
tx_src_param(tx, &tx->insn.src[1])
};
- assert(tx->insn.src[3].idx >= 0 &&
- tx->insn.src[3].idx < Elements(tx->sampler_targets));
+ assert(tx->insn.src[1].idx >= 0 &&
+ tx->insn.src[1].idx < Elements(tx->sampler_targets));
target = tx->sampler_targets[tx->insn.src[1].idx];
ureg_TXL(tx->ureg, dst, target, src[0], src[1]);
_OPI(SGE, SGE, V(0,0), V(3,0), V(0,0), V(3,0), 1, 2, NULL), /* 13 */
_OPI(EXP, EX2, V(0,0), V(3,0), V(0,0), V(3,0), 1, 1, NULL), /* 14 */
_OPI(LOG, LG2, V(0,0), V(3,0), V(0,0), V(3,0), 1, 1, SPECIAL(LOG)), /* 15 */
- _OPI(LIT, LIT, V(0,0), V(3,0), V(0,0), V(0,0), 1, 1, NULL), /* 16 */
+ _OPI(LIT, LIT, V(0,0), V(3,0), V(0,0), V(0,0), 1, 1, SPECIAL(LIT)), /* 16 */
_OPI(DST, DST, V(0,0), V(3,0), V(0,0), V(3,0), 1, 2, NULL), /* 17 */
_OPI(LRP, LRP, V(0,0), V(3,0), V(0,0), V(3,0), 1, 3, NULL), /* 18 */
_OPI(FRC, FRC, V(0,0), V(3,0), V(0,0), V(3,0), 1, 1, NULL), /* 19 */
HRESULT hr = D3D_OK;
const unsigned processor = tgsi_processor_from_type(info->type);
unsigned s, slot_max;
+ unsigned max_const_f;
user_assert(processor != ~0, D3DERR_INVALIDCALL);
if (tx->indirect_const_access) /* vs only */
info->const_float_slots = device->max_vs_const_f;
+ max_const_f = IS_VS ? device->max_vs_const_f : device->max_ps_const_f;
slot_max = info->const_bool_slots > 0 ?
- device->max_vs_const_f + NINE_MAX_CONST_I
- + info->const_bool_slots :
+ max_const_f + NINE_MAX_CONST_I
+ + DIV_ROUND_UP(info->const_bool_slots, 4) :
info->const_int_slots > 0 ?
- device->max_vs_const_f + info->const_int_slots :
+ max_const_f + info->const_int_slots :
info->const_float_slots;
info->const_used_size = sizeof(float[4]) * slot_max; /* slots start from 1 */