[clang] [HLSL] Implement D3DCOLORtoUBYTE4 intrinsic (PR #122202)

[Deric Cheung via cfe-commits]

https://github.com/Icohedron created https://github.com/llvm/llvm-project/pull/122202

Fixes #99092.

1. Defines the function `D3DCOLORtoUBYTE4` in `clang/lib/Headers/hlsl/hlsl_intrinsics.h`.
2. Implements the function `D3DCOLORtoUBYTE4` as `d3d_color_to_ubyte4` in `clang/lib/Headers/hlsl/hlsl_detail.h`
3. Adds a HLSL codegen test to `clang/test/CodeGenHLSL/builtins/D3DCOLORtoUBYTE4.hlsl`
4. Adds error tests to `clang/test/SemaHLSL/BuiltIns/D3DCOLORtoUBYTE4-errors.hlsl`

>From 0ef5e0217c04aa16c2f54b5f0edf0a6dc4cdc28d Mon Sep 17 00:00:00 2001
From: Icohedron <cheung.deric at gmail.com>
Date: Thu, 9 Jan 2025 01:14:52 +0000
Subject: [PATCH] Implement D3DCOLORtoUBYTE4 intrinsic

---
 clang/lib/Headers/hlsl/hlsl_detail.h            |  8 ++++++++
 clang/lib/Headers/hlsl/hlsl_intrinsics.h        | 17 +++++++++++++++++
 .../CodeGenHLSL/builtins/D3DCOLORtoUBYTE4.hlsl  | 12 ++++++++++++
 .../BuiltIns/D3DCOLORtoUBYTE4-errors.hlsl       | 13 +++++++++++++
 4 files changed, 50 insertions(+)
 create mode 100644 clang/test/CodeGenHLSL/builtins/D3DCOLORtoUBYTE4.hlsl
 create mode 100644 clang/test/SemaHLSL/BuiltIns/D3DCOLORtoUBYTE4-errors.hlsl

diff --git a/clang/lib/Headers/hlsl/hlsl_detail.h b/clang/lib/Headers/hlsl/hlsl_detail.h
index 8d5fd941331531..470fa4214a12f8 100644
--- a/clang/lib/Headers/hlsl/hlsl_detail.h
+++ b/clang/lib/Headers/hlsl/hlsl_detail.h
@@ -33,6 +33,14 @@ constexpr enable_if_t<sizeof(U) == sizeof(T), U> bit_cast(T F) {
   return __builtin_bit_cast(U, F);
 }
 
+constexpr vector<uint, 4> d3d_color_to_ubyte4(vector<float, 4> V) {
+  // Use the same scaling factor used by FXC (i.e., 255.001953)
+  // Excerpt from stackoverflow discussion:
+  // "Built-in rounding, necessary because of truncation. 0.001953 * 256 = 0.5"
+  // https://stackoverflow.com/questions/52103720/why-does-d3dcolortoubyte4-multiplies-components-by-255-001953f
+  return V.zyxw * 255.001953f;
+}
+
 } // namespace __detail
 } // namespace hlsl
 #endif //_HLSL_HLSL_DETAILS_H_
diff --git a/clang/lib/Headers/hlsl/hlsl_intrinsics.h b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
index b745997f1d5a2b..e44403c6c802e0 100644
--- a/clang/lib/Headers/hlsl/hlsl_intrinsics.h
+++ b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
@@ -1857,6 +1857,23 @@ half3 cross(half3, half3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_cross)
 float3 cross(float3, float3);
 
+//===----------------------------------------------------------------------===//
+// D3DCOLORtoUBYTE4 builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn T D3DCOLORtoUBYTE4(T x)
+/// \brief Converts a floating-point, 4D vector set by a D3DCOLOR to a UBYTE4.
+/// \param x [in] The floating-point vector4 to convert.
+///
+/// The return value is the UBYTE4 representation of the \a x parameter.
+///
+/// This function swizzles and scales components of the \a x parameter. Use this
+/// function to compensate for the lack of UBYTE4 support in some hardware.
+
+constexpr vector<uint, 4> D3DCOLORtoUBYTE4(vector<float, 4> V) {
+  return __detail::d3d_color_to_ubyte4(V);
+}
+
 //===----------------------------------------------------------------------===//
 // rcp builtins
 //===----------------------------------------------------------------------===//
diff --git a/clang/test/CodeGenHLSL/builtins/D3DCOLORtoUBYTE4.hlsl b/clang/test/CodeGenHLSL/builtins/D3DCOLORtoUBYTE4.hlsl
new file mode 100644
index 00000000000000..6e48800dae6698
--- /dev/null
+++ b/clang/test/CodeGenHLSL/builtins/D3DCOLORtoUBYTE4.hlsl
@@ -0,0 +1,12 @@
+// RUN: %clang_cc1 -finclude-default-header -triple \
+// RUN:   dxil-pc-shadermodel6.3-library %s -fnative-half-type \
+// RUN:   -emit-llvm -O1 -o - | FileCheck %s --check-prefixes=CHECK
+
+// CHECK-LABEL: D3DCOLORtoUBYTE4
+int4 test_D3DCOLORtoUBYTE4 ( float4 p1 ) {
+  // CHECK: %[[SCALED:.*]] = fmul <4 x float> %{{.*}}, splat (float 0x406FE01000000000)
+  // CHECK: %[[CONVERTED:.*]] = fptoui <4 x float> %[[SCALED]] to <4 x i32>
+  // CHECK: %[[SHUFFLED:.*]] = shufflevector <4 x i32> %{{.*}}, <4 x i32> poison, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+  // CHECK: ret <4 x i32> %[[SHUFFLED]]
+  return D3DCOLORtoUBYTE4 ( p1 );
+}
diff --git a/clang/test/SemaHLSL/BuiltIns/D3DCOLORtoUBYTE4-errors.hlsl b/clang/test/SemaHLSL/BuiltIns/D3DCOLORtoUBYTE4-errors.hlsl
new file mode 100644
index 00000000000000..fb41c212bd0be3
--- /dev/null
+++ b/clang/test/SemaHLSL/BuiltIns/D3DCOLORtoUBYTE4-errors.hlsl
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.6-library %s -emit-llvm-only -disable-llvm-passes -verify
+
+int4 test_too_few_arg() {
+  return D3DCOLORtoUBYTE4();
+  // expected-error at -1 {{no matching function for call to 'D3DCOLORtoUBYTE4'}}
+  // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires single argument 'V', but no arguments were provided}}
+}
+
+int4 test_too_many_arg(float4 v) {
+  return D3DCOLORtoUBYTE4(v, v);
+  // expected-error at -1 {{no matching function for call to 'D3DCOLORtoUBYTE4'}}
+  // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires single argument 'V', but 2 arguments were provided}}
+}