vkd3d-shader/hlsl: Implement acos and asin trig intrinsics.

Tests have already been implemented in 92044d5e; this commit also reduces
the scope of some of the todos (because now they're implemented!).

Wine-Bug: https://bugs.winehq.org/show_bug.cgi?id=55154
This commit is contained in:
Petrichor Park 2024-02-11 11:06:01 -06:00 committed by Alexandre Julliard
parent d4223a03c8
commit 69294c290b
Notes: Alexandre Julliard 2024-02-21 23:33:43 +01:00
Approved-by: Giovanni Mascellani (@giomasce)
Approved-by: Zebediah Figura (@zfigura)
Approved-by: Henri Verbeet (@hverbeet)
Approved-by: Alexandre Julliard (@julliard)
Merge-Request: https://gitlab.winehq.org/wine/vkd3d/-/merge_requests/364
2 changed files with 69 additions and 12 deletions

View File

@ -2666,6 +2666,55 @@ static bool intrinsic_abs(struct hlsl_ctx *ctx,
return !!add_unary_arithmetic_expr(ctx, params->instrs, HLSL_OP1_ABS, params->args[0], loc); return !!add_unary_arithmetic_expr(ctx, params->instrs, HLSL_OP1_ABS, params->args[0], loc);
} }
static bool write_acos_or_asin(struct hlsl_ctx *ctx,
const struct parse_initializer *params, const struct vkd3d_shader_location *loc, bool asin_mode)
{
struct hlsl_ir_function_decl *func;
struct hlsl_type *type;
char *body;
static const char template[] =
"%s %s(%s x)\n"
"{\n"
" %s abs_arg = abs(x);\n"
" %s poly_approx = (((-0.018729\n"
" * abs_arg + 0.074261)\n"
" * abs_arg - 0.212114)\n"
" * abs_arg + 1.570729);\n"
" %s correction = sqrt(1.0 - abs_arg);\n"
" %s zero_flip = (x < 0.0) * (-2.0 * correction * poly_approx + 3.141593);\n"
" %s result = poly_approx * correction + zero_flip;\n"
" return %s;\n"
"}";
static const char fn_name_acos[] = "acos";
static const char fn_name_asin[] = "asin";
static const char return_stmt_acos[] = "result";
static const char return_stmt_asin[] = "-result + 1.570796";
const char *fn_name = asin_mode ? fn_name_asin : fn_name_acos;
type = params->args[0]->data_type;
type = hlsl_get_numeric_type(ctx, type->class, HLSL_TYPE_FLOAT, type->dimx, type->dimy);
if (!(body = hlsl_sprintf_alloc(ctx, template,
type->name, fn_name, type->name,
type->name, type->name, type->name, type->name, type->name,
(asin_mode ? return_stmt_asin : return_stmt_acos))))
return false;
func = hlsl_compile_internal_function(ctx, fn_name, body);
vkd3d_free(body);
if (!func)
return false;
return add_user_call(ctx, func, params, loc);
}
static bool intrinsic_acos(struct hlsl_ctx *ctx,
const struct parse_initializer *params, const struct vkd3d_shader_location *loc)
{
return write_acos_or_asin(ctx, params, loc, false);
}
static bool intrinsic_all(struct hlsl_ctx *ctx, static bool intrinsic_all(struct hlsl_ctx *ctx,
const struct parse_initializer *params, const struct vkd3d_shader_location *loc) const struct parse_initializer *params, const struct vkd3d_shader_location *loc)
{ {
@ -2743,6 +2792,12 @@ static bool intrinsic_any(struct hlsl_ctx *ctx,
return false; return false;
} }
static bool intrinsic_asin(struct hlsl_ctx *ctx,
const struct parse_initializer *params, const struct vkd3d_shader_location *loc)
{
return write_acos_or_asin(ctx, params, loc, true);
}
/* Find the type corresponding to the given source type, with the same /* Find the type corresponding to the given source type, with the same
* dimensions but a different base type. */ * dimensions but a different base type. */
static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx, static struct hlsl_type *convert_numeric_type(const struct hlsl_ctx *ctx,
@ -3970,9 +4025,11 @@ intrinsic_functions[] =
/* Note: these entries should be kept in alphabetical order. */ /* Note: these entries should be kept in alphabetical order. */
{"D3DCOLORtoUBYTE4", 1, true, intrinsic_d3dcolor_to_ubyte4}, {"D3DCOLORtoUBYTE4", 1, true, intrinsic_d3dcolor_to_ubyte4},
{"abs", 1, true, intrinsic_abs}, {"abs", 1, true, intrinsic_abs},
{"acos", 1, true, intrinsic_acos},
{"all", 1, true, intrinsic_all}, {"all", 1, true, intrinsic_all},
{"any", 1, true, intrinsic_any}, {"any", 1, true, intrinsic_any},
{"asfloat", 1, true, intrinsic_asfloat}, {"asfloat", 1, true, intrinsic_asfloat},
{"asin", 1, true, intrinsic_asin},
{"asuint", -1, true, intrinsic_asuint}, {"asuint", -1, true, intrinsic_asuint},
{"ceil", 1, true, intrinsic_ceil}, {"ceil", 1, true, intrinsic_ceil},
{"clamp", 3, true, intrinsic_clamp}, {"clamp", 3, true, intrinsic_clamp},

View File

@ -3,7 +3,7 @@
% implementations. DXIL defines intrinsics for inverse trig, to be implemented % implementations. DXIL defines intrinsics for inverse trig, to be implemented
% by the backend. % by the backend.
[pixel shader todo] [pixel shader todo(sm<4)]
uniform float4 a; uniform float4 a;
float4 main() : sv_target float4 main() : sv_target
@ -13,26 +13,26 @@ float4 main() : sv_target
[test] [test]
uniform 0 float4 -1.0 0.0 0.0 0.0 uniform 0 float4 -1.0 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (3.14159274, 0.0, 0.0, 0.0) 128 probe all rgba (3.14159274, 0.0, 0.0, 0.0) 128
uniform 0 float4 -0.5 0.0 0.0 0.0 uniform 0 float4 -0.5 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (2.094441441, 0.0, 0.0, 0.0) 256 probe all rgba (2.094441441, 0.0, 0.0, 0.0) 256
uniform 0 float4 0.0 0.0 0.0 0.0 uniform 0 float4 0.0 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (1.57072878, 0.0, 0.0, 0.0) 1024 probe all rgba (1.57072878, 0.0, 0.0, 0.0) 1024
uniform 0 float4 0.5 0.0 0.0 0.0 uniform 0 float4 0.5 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (1.04715133, 0.0, 0.0, 0.0) 512 probe all rgba (1.04715133, 0.0, 0.0, 0.0) 512
uniform 0 float4 1.0 0.0 0.0 0.0 uniform 0 float4 1.0 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (0.0, 0.0, 0.0, 0.0) 128 probe all rgba (0.0, 0.0, 0.0, 0.0) 128
[pixel shader todo] [pixel shader todo(sm<4)]
uniform float4 a; uniform float4 a;
float4 main() : sv_target float4 main() : sv_target
@ -44,7 +44,7 @@ float4 main() : sv_target
[test] [test]
uniform 0 float4 -1.0 0.0 0.0 0.0 uniform 0 float4 -1.0 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (-31416.0, 0.0, 0.0, 0.0) probe all rgba (-31416.0, 0.0, 0.0, 0.0)
[require] [require]
@ -52,15 +52,15 @@ shader model < 6.0
[test] [test]
uniform 0 float4 -0.5 0.0 0.0 0.0 uniform 0 float4 -0.5 0.0 0.0 0.0
todo draw quad todo(sm<4) draw quad
probe all rgba (-10473.0, 0.0, 0.0, 0.0) probe all rgba (-10473.0, 0.0, 0.0, 0.0)
uniform 0 float4 0.0 0.0 0.0 0.0 uniform 0 float4 0.0 0.0 0.0 0.0
todo draw quad todo(sm<4) draw quad
probe all rgba (1.0, 0.0, 0.0, 0.0) probe all rgba (1.0, 0.0, 0.0, 0.0)
uniform 0 float4 0.5 0.0 0.0 0.0 uniform 0 float4 0.5 0.0 0.0 0.0
todo draw quad todo(sm<4) draw quad
probe all rgba (10473.0, 0.0, 0.0, 0.0) probe all rgba (10473.0, 0.0, 0.0, 0.0)
[require] [require]
@ -88,7 +88,7 @@ probe all rgba (10472.0, 0.0, 0.0, 0.0) 4096
[test] [test]
uniform 0 float4 1.0 0.0 0.0 0.0 uniform 0 float4 1.0 0.0 0.0 0.0
todo(sm<6) draw quad todo(sm<4) draw quad
probe all rgba (31416.0, 0.0, 0.0, 0.0) probe all rgba (31416.0, 0.0, 0.0, 0.0)