state->OES_standard_derivatives_enable);
}
+static bool
+fs_derivative_control(const _mesa_glsl_parse_state *state)
+{
+ return state->stage == MESA_SHADER_FRAGMENT &&
+ (state->is_version(450, 0) ||
+ state->ARB_derivative_control_enable);
+}
+
static bool
tex1d_lod(const _mesa_glsl_parse_state *state)
{
ir_swizzle *matrix_elt(ir_variable *var, int col, int row);
ir_expression *asin_expr(ir_variable *x);
+ void do_atan(ir_factory &body, const glsl_type *type, ir_variable *res, operand y_over_x);
/**
* Call function \param f with parameters specified as the linked
B1(dFdx);
B1(dFdy);
B1(fwidth);
+ B1(dFdxCoarse);
+ B1(dFdyCoarse);
+ B1(fwidthCoarse);
+ B1(dFdxFine);
+ B1(dFdyFine);
+ B1(fwidthFine);
B1(noise1);
B1(noise2);
B1(noise3);
if (f == NULL)
return NULL;
- ir_function_signature *sig = f->matching_signature(state, actual_parameters);
+ ir_function_signature *sig =
+ f->matching_signature(state, actual_parameters, true);
if (sig == NULL)
return NULL;
NULL);
add_function("texture2DProjLod",
- _texture(ir_txl, v110_lod, glsl_type::vec4_type, glsl_type::sampler2D_type, glsl_type::vec3_type, TEX_PROJECT),
- _texture(ir_txl, v110_lod, glsl_type::vec4_type, glsl_type::sampler2D_type, glsl_type::vec4_type, TEX_PROJECT),
+ _texture(ir_txl, lod_exists_in_stage, glsl_type::vec4_type, glsl_type::sampler2D_type, glsl_type::vec3_type, TEX_PROJECT),
+ _texture(ir_txl, lod_exists_in_stage, glsl_type::vec4_type, glsl_type::sampler2D_type, glsl_type::vec4_type, TEX_PROJECT),
NULL);
add_function("texture3D",
NULL);
add_function("textureCubeLod",
- _texture(ir_txl, v110_lod, glsl_type::vec4_type, glsl_type::samplerCube_type, glsl_type::vec3_type),
+ _texture(ir_txl, lod_exists_in_stage, glsl_type::vec4_type, glsl_type::samplerCube_type, glsl_type::vec3_type),
NULL);
add_function("texture2DRect",
F(dFdx)
F(dFdy)
F(fwidth)
+ F(dFdxCoarse)
+ F(dFdyCoarse)
+ F(fwidthCoarse)
+ F(dFdxFine)
+ F(dFdyFine)
+ F(fwidthFine)
F(noise1)
F(noise2)
F(noise3)
ir_factory outer_then(&outer_if->then_instructions, mem_ctx);
/* Then...call atan(y/x) */
- ir_variable *y_over_x = outer_then.make_temp(glsl_type::float_type, "y_over_x");
- outer_then.emit(assign(y_over_x, div(y, x)));
- outer_then.emit(assign(r, mul(y_over_x, rsq(add(mul(y_over_x, y_over_x),
- imm(1.0f))))));
- outer_then.emit(assign(r, asin_expr(r)));
+ do_atan(body, glsl_type::float_type, r, div(y, x));
/* ...and fix it up: */
ir_if *inner_if = new(mem_ctx) ir_if(less(x, imm(0.0f)));
return sig;
}
+void
+builtin_builder::do_atan(ir_factory &body, const glsl_type *type, ir_variable *res, operand y_over_x)
+{
+ /*
+ * range-reduction, first step:
+ *
+ * / y_over_x if |y_over_x| <= 1.0;
+ * x = <
+ * \ 1.0 / y_over_x otherwise
+ */
+ ir_variable *x = body.make_temp(type, "atan_x");
+ body.emit(assign(x, div(min2(abs(y_over_x),
+ imm(1.0f)),
+ max2(abs(y_over_x),
+ imm(1.0f)))));
+
+ /*
+ * 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
+ */
+ ir_variable *tmp = body.make_temp(type, "atan_tmp");
+ body.emit(assign(tmp, mul(x, x)));
+ body.emit(assign(tmp, mul(add(mul(sub(mul(add(mul(sub(mul(add(mul(imm(-0.0121323213173444f),
+ tmp),
+ imm(0.0536813784310406f)),
+ tmp),
+ imm(0.1173503194786851f)),
+ tmp),
+ imm(0.1938924977115610f)),
+ tmp),
+ imm(0.3326756418091246f)),
+ tmp),
+ imm(0.9999793128310355f)),
+ x)));
+
+ /* range-reduction fixup */
+ body.emit(assign(tmp, add(tmp,
+ mul(b2f(greater(abs(y_over_x),
+ imm(1.0f, type->components()))),
+ add(mul(tmp,
+ imm(-2.0f)),
+ imm(M_PI_2f))))));
+
+ /* sign fixup */
+ body.emit(assign(res, mul(tmp, sign(y_over_x))));
+}
+
ir_function_signature *
builtin_builder::_atan(const glsl_type *type)
{
ir_variable *y_over_x = in_var(type, "y_over_x");
MAKE_SIG(type, always_available, 1, y_over_x);
- ir_variable *t = body.make_temp(type, "t");
- body.emit(assign(t, mul(y_over_x, rsq(add(mul(y_over_x, y_over_x),
- imm(1.0f))))));
-
- body.emit(ret(asin_expr(t)));
+ ir_variable *tmp = body.make_temp(type, "tmp");
+ do_atan(body, type, tmp, y_over_x);
+ body.emit(ret(tmp));
return sig;
}
}
UNOP(dFdx, ir_unop_dFdx, fs_oes_derivatives)
+UNOP(dFdxCoarse, ir_unop_dFdx_coarse, fs_derivative_control)
+UNOP(dFdxFine, ir_unop_dFdx_fine, fs_derivative_control)
UNOP(dFdy, ir_unop_dFdy, fs_oes_derivatives)
+UNOP(dFdyCoarse, ir_unop_dFdy_coarse, fs_derivative_control)
+UNOP(dFdyFine, ir_unop_dFdy_fine, fs_derivative_control)
ir_function_signature *
builtin_builder::_fwidth(const glsl_type *type)
return sig;
}
+ir_function_signature *
+builtin_builder::_fwidthCoarse(const glsl_type *type)
+{
+ ir_variable *p = in_var(type, "p");
+ MAKE_SIG(type, fs_derivative_control, 1, p);
+
+ body.emit(ret(add(abs(expr(ir_unop_dFdx_coarse, p)),
+ abs(expr(ir_unop_dFdy_coarse, p)))));
+
+ return sig;
+}
+
+ir_function_signature *
+builtin_builder::_fwidthFine(const glsl_type *type)
+{
+ ir_variable *p = in_var(type, "p");
+ MAKE_SIG(type, fs_derivative_control, 1, p);
+
+ body.emit(ret(add(abs(expr(ir_unop_dFdx_fine, p)),
+ abs(expr(ir_unop_dFdy_fine, p)))));
+
+ return sig;
+}
+
ir_function_signature *
builtin_builder::_noise1(const glsl_type *type)
{
sig->parameters.push_tail(in_var(glsl_type::int_type, "sample"));
/* Data arguments. */
- for (unsigned i = 0; i < num_arguments; ++i)
- sig->parameters.push_tail(in_var(data_type,
- ralloc_asprintf(NULL, "arg%d", i)));
+ for (unsigned i = 0; i < num_arguments; ++i) {
+ char *arg_name = ralloc_asprintf(NULL, "arg%d", i);
+ sig->parameters.push_tail(in_var(data_type, arg_name));
+ ralloc_free(arg_name);
+ }
/* Set the maximal set of qualifiers allowed for this image
* built-in. Function calls with arguments having fewer
* accept everything that needs to be accepted, and reject cases
* like loads from write-only or stores to read-only images.
*/
- image->data.image.read_only = flags & IMAGE_FUNCTION_READ_ONLY;
- image->data.image.write_only = flags & IMAGE_FUNCTION_WRITE_ONLY;
- image->data.image.coherent = true;
- image->data.image._volatile = true;
- image->data.image.restrict_flag = true;
+ image->data.image_read_only = (flags & IMAGE_FUNCTION_READ_ONLY) != 0;
+ image->data.image_write_only = (flags & IMAGE_FUNCTION_WRITE_ONLY) != 0;
+ image->data.image_coherent = true;
+ image->data.image_volatile = true;
+ image->data.image_restrict = true;
return sig;
}