From b5c0c9c22f3c646cfc3143b5d8e6200a9a45ab6f Mon Sep 17 00:00:00 2001
From: Nikolay Sivov <nsivov@codeweavers.com>
Date: Thu, 7 Sep 2023 02:09:36 +0200
Subject: [PATCH] vkd3d-shader/hlsl: Add fwidth() function.

Signed-off-by: Nikolay Sivov <nsivov@codeweavers.com>
---
 Makefile.am                   |  1 +
 libs/vkd3d-shader/hlsl.y      | 28 ++++++++++++++++++++++++++++
 tests/hlsl/fwidth.shader_test | 26 ++++++++++++++++++++++++++
 3 files changed, 55 insertions(+)
 create mode 100644 tests/hlsl/fwidth.shader_test

diff --git a/Makefile.am b/Makefile.am
index 744e4612..11df76ad 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -93,6 +93,7 @@ vkd3d_shader_tests = \
 	tests/hlsl/function-overload.shader_test \
 	tests/hlsl/function-return.shader_test \
 	tests/hlsl/function.shader_test \
+	tests/hlsl/fwidth.shader_test \
 	tests/hlsl/gather-offset.shader_test \
 	tests/hlsl/gather.shader_test \
 	tests/hlsl/getdimensions.shader_test \
diff --git a/libs/vkd3d-shader/hlsl.y b/libs/vkd3d-shader/hlsl.y
index a47246de..8c327c79 100644
--- a/libs/vkd3d-shader/hlsl.y
+++ b/libs/vkd3d-shader/hlsl.y
@@ -2961,6 +2961,33 @@ static bool intrinsic_frac(struct hlsl_ctx *ctx,
     return !!add_unary_arithmetic_expr(ctx, params->instrs, HLSL_OP1_FRACT, arg, loc);
 }
 
+static bool intrinsic_fwidth(struct hlsl_ctx *ctx,
+        const struct parse_initializer *params, const struct vkd3d_shader_location *loc)
+{
+    struct hlsl_ir_function_decl *func;
+    struct hlsl_type *type;
+    char *body;
+
+    static const char template[] =
+            "%s fwidth(%s x)\n"
+            "{\n"
+            "    return abs(ddx(x)) + abs(ddy(x));\n"
+            "}";
+
+    if (!elementwise_intrinsic_float_convert_args(ctx, params, loc))
+        return false;
+    type = params->args[0]->data_type;
+
+    if (!(body = hlsl_sprintf_alloc(ctx, template, type->name, type->name)))
+        return false;
+    func = hlsl_compile_internal_function(ctx, "fwidth", body);
+    vkd3d_free(body);
+    if (!func)
+        return false;
+
+    return add_user_call(ctx, func, params, loc);
+}
+
 static bool intrinsic_ldexp(struct hlsl_ctx *ctx,
         const struct parse_initializer *params, const struct vkd3d_shader_location *loc)
 {
@@ -3690,6 +3717,7 @@ intrinsic_functions[] =
     {"floor",                               1, true,  intrinsic_floor},
     {"fmod",                                2, true,  intrinsic_fmod},
     {"frac",                                1, true,  intrinsic_frac},
+    {"fwidth",                              1, true,  intrinsic_fwidth},
     {"ldexp",                               2, true,  intrinsic_ldexp},
     {"length",                              1, true,  intrinsic_length},
     {"lerp",                                3, true,  intrinsic_lerp},
diff --git a/tests/hlsl/fwidth.shader_test b/tests/hlsl/fwidth.shader_test
new file mode 100644
index 00000000..e302505f
--- /dev/null
+++ b/tests/hlsl/fwidth.shader_test
@@ -0,0 +1,26 @@
+[require]
+shader model >= 3.0
+
+[pixel shader]
+float4 main(float4 pos : sv_position) : sv_target
+{
+    // Shader models < 4 don't add 0.5 to sv_position, so this adjustment is required to get the
+    // same outputs.
+    pos.x = floor(pos.x) + 0.5;
+    pos.y = floor(pos.y) + 0.5;
+
+    pos /= 10.0;
+    float nonlinear = pos.x * pos.y - pos.x * (pos.x + 0.5);
+    float4 res = fwidth(nonlinear);
+
+    // Each device may use either the coarse or the fine derivate, so use quantization.
+    return round(30 * res);
+}
+
+[test]
+draw quad
+probe (10, 10) rgba (8.0, 8.0, 8.0, 8.0)
+probe (11, 10) rgba (8.0, 8.0, 8.0, 8.0)
+probe (12, 10) rgba (10.0, 10.0, 10.0, 10.0)
+probe (16, 16) rgba (12.0, 12.0, 12.0, 12.0)
+probe (150, 150) rgba (92.0, 92.0, 92.0, 92.0)