static nir_ssa_def *
build_atan(nir_builder *b, nir_ssa_def *y_over_x)
{
nir_ssa_def *abs_y_over_x = nir_fabs(b, y_over_x);
nir_ssa_def *one = nir_imm_float(b, 1.0f);
/*
* range-reduction, first step:
*
* / y_over_x if |y_over_x| <= 1.0;
* x = <
* \ 1.0 / y_over_x otherwise
*/
nir_ssa_def *x = nir_fdiv(b, nir_fmin(b, abs_y_over_x, one),
nir_fmax(b, abs_y_over_x, one));
/*
* approximate atan by evaluating polynomial:
*
* x * 0.9999793128310355 - x^3 * 0.3326756418091246 +
* x^5 * 0.1938924977115610 - x^7 * 0.1173503194786851 +
* x^9 * 0.0536813784310406 - x^11 * 0.0121323213173444
*/
nir_ssa_def *x_2 = nir_fmul(b, x, x);
nir_ssa_def *x_3 = nir_fmul(b, x_2, x);
nir_ssa_def *x_5 = nir_fmul(b, x_3, x_2);
nir_ssa_def *x_7 = nir_fmul(b, x_5, x_2);
nir_ssa_def *x_9 = nir_fmul(b, x_7, x_2);
nir_ssa_def *x_11 = nir_fmul(b, x_9, x_2);
nir_ssa_def *polynomial_terms[] = {
nir_fmul(b, x, nir_imm_float(b, 0.9999793128310355f)),
nir_fmul(b, x_3, nir_imm_float(b, -0.3326756418091246f)),
nir_fmul(b, x_5, nir_imm_float(b, 0.1938924977115610f)),
nir_fmul(b, x_7, nir_imm_float(b, -0.1173503194786851f)),
nir_fmul(b, x_9, nir_imm_float(b, 0.0536813784310406f)),
nir_fmul(b, x_11, nir_imm_float(b, -0.0121323213173444f)),
};
nir_ssa_def *tmp =
build_fsum(b, polynomial_terms, ARRAY_SIZE(polynomial_terms));
/* range-reduction fixup */
tmp = nir_fadd(b, tmp,
nir_fmul(b,
nir_b2f(b, nir_flt(b, one, abs_y_over_x)),
nir_fadd(b, nir_fmul(b, tmp,
nir_imm_float(b, -2.0f)),
nir_imm_float(b, M_PI_2f))));
/* sign fixup */
return nir_fmul(b, tmp, nir_fsign(b, y_over_x));
}
static void
saturate_src(nir_builder *b, nir_tex_instr *tex, unsigned sat_mask)
{
b->cursor = nir_before_instr(&tex->instr);
/* Walk through the sources saturating the requested arguments. */
for (unsigned i = 0; i < tex->num_srcs; i++) {
if (tex->src[i].src_type != nir_tex_src_coord)
continue;
nir_ssa_def *src =
nir_ssa_for_src(b, tex->src[i].src, tex->coord_components);
/* split src into components: */
nir_ssa_def *comp[4];
for (unsigned j = 0; j < tex->coord_components; j++)
comp[j] = nir_channel(b, src, j);
/* clamp requested components, array index does not get clamped: */
unsigned ncomp = tex->coord_components;
if (tex->is_array)
ncomp--;
for (unsigned j = 0; j < ncomp; j++) {
if ((1 << j) & sat_mask) {
if (tex->sampler_dim == GLSL_SAMPLER_DIM_RECT) {
/* non-normalized texture coords, so clamp to texture
* size rather than [0.0, 1.0]
*/
nir_ssa_def *txs = get_texture_size(b, tex);
comp[j] = nir_fmax(b, comp[j], nir_imm_float(b, 0.0));
comp[j] = nir_fmin(b, comp[j], nir_channel(b, txs, j));
} else {
comp[j] = nir_fsat(b, comp[j]);
}
}
}
/* and move the result back into a single vecN: */
src = nir_vec(b, comp, tex->coord_components);
nir_instr_rewrite_src(&tex->instr,
&tex->src[i].src,
nir_src_for_ssa(src));
}
}
static inline nir_ssa_def *
build_fclamp(nir_builder *b,
nir_ssa_def *x, nir_ssa_def *min_val, nir_ssa_def *max_val)
{
return nir_fmin(b, nir_fmax(b, x, min_val), max_val);
}
