[clang] Hlsl dst function (PR #133828)
via cfe-commits
cfe-commits at lists.llvm.org
Mon Mar 31 17:02:22 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: None (metkarpoonam)
<details>
<summary>Changes</summary>
Implement dst algorithm in the hlsl_intrinsics.h and added test cases for HLSL codegen and sema
fixes: https://github.com/llvm/llvm-project/issues/99108
---
Full diff: https://github.com/llvm/llvm-project/pull/133828.diff
4 Files Affected:
- (modified) clang/lib/Headers/hlsl/hlsl_intrinsic_helpers.h (+6)
- (modified) clang/lib/Headers/hlsl/hlsl_intrinsics.h (+25)
- (added) clang/test/CodeGenHLSL/builtins/dst.hlsl (+48)
- (added) clang/test/SemaHLSL/BuiltIns/dst-error.hlsl (+37)
``````````diff
diff --git a/clang/lib/Headers/hlsl/hlsl_intrinsic_helpers.h b/clang/lib/Headers/hlsl/hlsl_intrinsic_helpers.h
index 8cdd63d7e07bb..5ea8faf169380 100644
--- a/clang/lib/Headers/hlsl/hlsl_intrinsic_helpers.h
+++ b/clang/lib/Headers/hlsl/hlsl_intrinsic_helpers.h
@@ -35,6 +35,12 @@ length_vec_impl(vector<T, N> X) {
#endif
}
+template <typename T>
+constexpr vector<T, 4> dst_impl(vector<T, 4> src0, vector<T, 4> src1) {
+ vector<T, 4> dest = {1, src0[1] * src1[1], src0[2], src1[3]};
+ return dest;
+}
+
template <typename T> constexpr T distance_impl(T X, T Y) {
return length_impl(X - Y);
}
diff --git a/clang/lib/Headers/hlsl/hlsl_intrinsics.h b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
index fd799b8d874ae..7ae94731234f9 100644
--- a/clang/lib/Headers/hlsl/hlsl_intrinsics.h
+++ b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
@@ -174,6 +174,31 @@ const inline float distance(__detail::HLSL_FIXED_VECTOR<float, N> X,
__detail::HLSL_FIXED_VECTOR<float, N> Y) {
return __detail::distance_vec_impl(X, Y);
}
+//===----------------------------------------------------------------------===//
+// dst builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn fvector dst( fvector, fvector)
+/// \brief Returns the length of a vector
+/// \param src0 [in] The first vector contain {_, d*d, d*d, _}
+/// \param src1 [in] The second vector contain {_, 1/d, _, 1/d}
+///
+/// Return the computed distance vector contain {1, d, d*d, 1/d}
+
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
+const inline vector<half, 4> dst(vector<half, 4> src0, vector<half, 4> src1) {
+ return __detail::dst_impl(src0, src1);
+}
+
+const inline vector<float, 4> dst(vector<float, 4> src0,
+ vector<float, 4> src1) {
+ return __detail::dst_impl(src0, src1);
+}
+
+const inline vector<double, 4> dst(vector<double, 4> src0,
+ vector<double, 4> src1) {
+ return __detail::dst_impl(src0, src1);
+}
//===----------------------------------------------------------------------===//
// fmod builtins
diff --git a/clang/test/CodeGenHLSL/builtins/dst.hlsl b/clang/test/CodeGenHLSL/builtins/dst.hlsl
new file mode 100644
index 0000000000000..c62c9be5b0c1d
--- /dev/null
+++ b/clang/test/CodeGenHLSL/builtins/dst.hlsl
@@ -0,0 +1,48 @@
+// RUN: %clang_cc1 -finclude-default-header -x hlsl -triple dxil-pc-shadermodel6.2-library %s -fnative-half-type -emit-llvm -O1 -o - | FileCheck %s
+
+
+// CHECK-LABEL: define noundef nofpclass(nan inf) <4 x float> @_Z12dstWithFloatDv4_fS_(
+// CHECK-SAME: <4 x float> noundef nofpclass(nan inf) [[P:%.*]], <4 x float> noundef nofpclass(nan inf) [[Q:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[VECEXT:%.*]] = extractelement <4 x float> [[P]], i64 1
+// CHECK-NEXT: [[VECEXT1:%.*]] = extractelement <4 x float> [[Q]], i64 1
+// CHECK-NEXT: [[MULRES:%.*]] = fmul reassoc nnan ninf nsz arcp afn float [[VECEXT1]], [[VECEXT]]
+// CHECK-NEXT: [[VECINIT:%.*]] = insertelement <4 x float> <float 1.000000e+00, float poison, float poison, float poison>, float [[MULRES]], i64 1
+// CHECK-NEXT: [[VECINIT3:%.*]] = shufflevector <4 x float> [[VECINIT]], <4 x float> [[P]], <4 x i32> <i32 0, i32 1, i32 6, i32 poison>
+// CHECK-NEXT: [[VECINIT5:%.*]] = shufflevector <4 x float> [[VECINIT3]], <4 x float> [[Q]], <4 x i32> <i32 0, i32 1, i32 2, i32 7>
+// CHECK-NEXT: ret <4 x float> [[VECINIT5]]
+
+float4 dstWithFloat(float4 p1, float4 p2)
+{
+ return dst(p1, p2);
+}
+
+// CHECK-LABEL: define noundef nofpclass(nan inf) <4 x half> @_Z11dstwithHalfDv4_DhS_(
+// CHECK-SAME: <4 x half> noundef nofpclass(nan inf) [[P:%.*]], <4 x half> noundef nofpclass(nan inf) [[Q:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[VECEXT:%.*]] = extractelement <4 x half> [[P]], i64 1
+// CHECK-NEXT: [[VECEXT1:%.*]] = extractelement <4 x half> [[Q]], i64 1
+// CHECK-NEXT: [[MULRES:%.*]] = fmul reassoc nnan ninf nsz arcp afn half [[VECEXT1]], [[VECEXT]]
+// CHECK-NEXT: [[VECINIT:%.*]] = insertelement <4 x half> <half 0xH3C00, half poison, half poison, half poison>, half [[MULRES]], i64 1
+// CHECK-NEXT: [[VECINIT3:%.*]] = shufflevector <4 x half> [[VECINIT]], <4 x half> [[P]], <4 x i32> <i32 0, i32 1, i32 6, i32 poison>
+// CHECK-NEXT: [[VECINIT5:%.*]] = shufflevector <4 x half> [[VECINIT3]], <4 x half> [[Q]], <4 x i32> <i32 0, i32 1, i32 2, i32 7>
+// CHECK-NEXT: ret <4 x half> [[VECINIT5]]
+half4 dstwithHalf(half4 p1, half4 p2)
+{
+ return dst(p1, p2);
+}
+
+// CHECK-LABEL: define noundef nofpclass(nan inf) <4 x double> @_Z13dstWithDoubleDv4_dS_(
+// CHECK-SAME: <4 x double> noundef nofpclass(nan inf) [[P:%.*]], <4 x double> noundef nofpclass(nan inf) [[Q:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[VECEXT:%.*]] = extractelement <4 x double> [[P]], i64 1
+// CHECK-NEXT: [[VECEXT1:%.*]] = extractelement <4 x double> [[Q]], i64 1
+// CHECK-NEXT: [[MULRES:%.*]] = fmul reassoc nnan ninf nsz arcp afn double [[VECEXT1]], [[VECEXT]]
+// CHECK-NEXT: [[VECINIT:%.*]] = insertelement <4 x double> <double 1.000000e+00, double poison, double poison, double poison>, double [[MULRES]], i64 1
+// CHECK-NEXT: [[VECINIT3:%.*]] = shufflevector <4 x double> [[VECINIT]], <4 x double> [[P]], <4 x i32> <i32 0, i32 1, i32 6, i32 poison>
+// CHECK-NEXT: [[VECINIT5:%.*]] = shufflevector <4 x double> [[VECINIT3]], <4 x double> [[Q]], <4 x i32> <i32 0, i32 1, i32 2, i32 7>
+// CHECK-NEXT: ret <4 x double> [[VECINIT5]]
+double4 dstWithDouble(double4 p1, double4 p2)
+{
+ return dst(p1, p2);
+}
diff --git a/clang/test/SemaHLSL/BuiltIns/dst-error.hlsl b/clang/test/SemaHLSL/BuiltIns/dst-error.hlsl
new file mode 100644
index 0000000000000..6bff46ffc223b
--- /dev/null
+++ b/clang/test/SemaHLSL/BuiltIns/dst-error.hlsl
@@ -0,0 +1,37 @@
+// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.6-library %s -fnative-half-type -emit-llvm-only -disable-llvm-passes -verify
+
+float4 test_too_many_arg(float4 p0)
+{
+ dst(p0, p0, p0);
+ // expected-error at -1 {{no matching function for call to 'dst'}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 3 were provided}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 3 were provided}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 3 were provided}}
+}
+
+float4 test_no_second_arg(float4 p0)
+{
+ return dst(p0);
+ // expected-error at -1 {{no matching function for call to 'dst'}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 1 was provided}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 1 was provided}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 1 was provided}}
+}
+
+float4 test_no_args()
+{
+ return dst();
+ // expected-error at -1 {{no matching function for call to 'dst'}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 0 were provided}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 0 were provided}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: requires 2 arguments, but 0 were provided}}
+}
+
+float4 test_3_components(float3 p0, float3 p1)
+{
+ return dst(p0, p1);
+ // expected-error at -1 {{no matching function for call to 'dst'}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: no known conversion from 'vector<[...], 3>' to 'vector<[...], 4>' for 1st argument}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: no known conversion from 'vector<float, 3>' to 'vector<half, 4>' for 1st argument}}
+ // expected-note at hlsl/hlsl_intrinsics.h:* {{candidate function not viable: no known conversion from 'vector<float, 3>' to 'vector<double, 4>' for 1st argument}}
+}
``````````
</details>
https://github.com/llvm/llvm-project/pull/133828
More information about the cfe-commits
mailing list