[HLSL] Implementation of the fmod intrinsic

This change implements the frontend for llvm#99118 Builtins.td - add the fmod builtin CGBuiltin.cpp - add the builtin to DirectX intrinsic mapping hlsl_intrinsics.h - add the fmod api SemaHLSL.cpp - add type checks for builtin IntrinsicsDirectX.td - add the fmod DirectX intrinsic
lizhengxing · Sep 13, 2024 · 565ec72 · 565ec72
1 parent ff1de24
commit 565ec72
Show file tree

Hide file tree

Showing 7 changed files with 231 additions and 0 deletions.
diff --git a/clang/include/clang/Basic/Builtins.td b/clang/include/clang/Basic/Builtins.td
@@ -4782,6 +4782,12 @@ def HLSLStep: LangBuiltin<"HLSL_LANG"> {
   let Prototype = "void(...)";
 }
 
+def HLSLFmod : LangBuiltin<"HLSL_LANG"> {
+  let Spellings = ["__builtin_hlsl_elementwise_fmod"];
+  let Attributes = [NoThrow, Const];
+  let Prototype = "void(...)";
+}
+
 // Builtins for XRay.
 def XRayCustomEvent : Builtin {
   let Spellings = ["__xray_customevent"];

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -18709,6 +18709,25 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned BuiltinID,
         CGM.getHLSLRuntime().getNormalizeIntrinsic(), ArrayRef<Value *>{X},
         nullptr, "hlsl.normalize");
   }
+  case Builtin::BI__builtin_hlsl_elementwise_fmod: {
+    Value *Op0 = EmitScalarExpr(E->getArg(0));
+    Value *Op1 = EmitScalarExpr(E->getArg(1));
+    if (!E->getArg(0)->getType()->hasFloatingRepresentation() ||
+        (E->getArg(0)->getType() != E->getArg(1)->getType()))
+      llvm_unreachable("fmod operands must have the same float representation");
+
+    llvm::Triple::ArchType Arch = CGM.getTarget().getTriple().getArch();
+    assert(((Arch == llvm::Triple::dxil) || (Arch == llvm::Triple::spirv)) &&
+           "Unknown target architecture");
+
+    if (CGM.getTarget().getTriple().getArch() == llvm::Triple::dxil)
+      return Builder.CreateIntrinsic(
+          /*ReturnType=*/Op0->getType(), Intrinsic::dx_fmod,
+          ArrayRef<Value *>{Op0, Op1}, nullptr, "dx.fmod");
+
+    // HLSL's Fmod builtin is equivalent to SPIRV's OpFRem instruction
+    return Builder.CreateFRem(Op0, Op1, "fmod");
+  }
   case Builtin::BI__builtin_hlsl_elementwise_frac: {
     Value *Op0 = EmitScalarExpr(E->getArg(0));
     if (!E->getArg(0)->getType()->hasFloatingRepresentation())

diff --git a/clang/lib/Headers/hlsl/hlsl_intrinsics.h b/clang/lib/Headers/hlsl/hlsl_intrinsics.h
@@ -807,6 +807,39 @@ float3 floor(float3);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_floor)
 float4 floor(float4);
 
+//===----------------------------------------------------------------------===//
+// fmod builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn T fmod(T x, T y)
+/// \brief Returns the linear interpolation of x to y.
+/// \param x [in] The dividend.
+/// \param y [in] The divisor.
+///
+/// Return the floating-point remainder of the x parameter divided by the y parameter.
+
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+half fmod(half, half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+half2 fmod(half2, half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+half3 fmod(half3, half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+half4 fmod(half4, half4);
+
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+float fmod(float, float);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+float2 fmod(float2, float2);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+float3 fmod(float3, float3);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_fmod)
+float4 fmod(float4, float4);
+
 //===----------------------------------------------------------------------===//
 // frac builtins
 //===----------------------------------------------------------------------===//

diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp
@@ -1649,6 +1649,18 @@ bool SemaHLSL::CheckBuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
       return true;
     break;
   }
+  case Builtin::BI__builtin_hlsl_elementwise_fmod: {
+    if (SemaRef.checkArgCount(TheCall, 2))
+      return true;
+    if (CheckFloatOrHalfRepresentations(&SemaRef, TheCall))
+      return true;
+
+    ExprResult A = TheCall->getArg(0);
+    QualType ArgTyA = A.get()->getType();
+    // return type is the same as the input type
+    TheCall->setType(ArgTyA);
+    break;
+  }
   case Builtin::BI__builtin_hlsl_select: {
     if (SemaRef.checkArgCount(TheCall, 3))
       return true;

diff --git a/clang/test/CodeGenHLSL/builtins/fmod.hlsl b/clang/test/CodeGenHLSL/builtins/fmod.hlsl
@@ -0,0 +1,122 @@
+// DirectX target:
+//
+// RUN: %clang_cc1 -finclude-default-header -x hlsl -triple \
+// RUN:   dxil-pc-shadermodel6.3-library %s -fnative-half-type \
+// RUN:   -emit-llvm -disable-llvm-passes -o - | FileCheck %s \
+// RUN:   --check-prefixes=DX-CHECK,DX-NATIVE_HALF
+
+// RUN: %clang_cc1 -finclude-default-header -x hlsl -triple \
+// RUN:   dxil-pc-shadermodel6.3-library %s -emit-llvm -disable-llvm-passes \
+// RUN:   -o - | FileCheck %s --check-prefixes=DX-CHECK,DX-NO_HALF 
+
+
+
+// Spirv target:
+//
+// RUN: %clang_cc1 -finclude-default-header -x hlsl -triple \
+// RUN:   spirv-unknown-vulkan-compute %s -fnative-half-type \
+// RUN:   -emit-llvm -disable-llvm-passes -o - | FileCheck %s \
+// RUN:   --check-prefixes=SPV-CHECK,SPV-NATIVE_HALF
+
+// RUN: %clang_cc1 -finclude-default-header -x hlsl -triple \
+// RUN:   spirv-unknown-vulkan-compute %s -emit-llvm -disable-llvm-passes \
+// RUN:   -o - | FileCheck %s --check-prefixes=SPV-CHECK,SPV-NO_HALF
+
+
+
+// DX-NATIVE_HALF: define noundef half @
+// DX-NATIVE_HALF: %dx.fmod = call half @llvm.dx.fmod.f16(
+// DX-NATIVE_HALF: ret half %dx.fmod
+// DX-NO_HALF: define noundef float @
+// DX-NO_HALF: %dx.fmod = call float @llvm.dx.fmod.f32(
+// DX-NO_HALF: ret float %dx.fmod
+//
+// SPV-NATIVE_HALF: define spir_func noundef half @
+// SPV-NATIVE_HALF: %fmod = frem half
+// SPV-NATIVE_HALF: ret half %fmod
+// SPV-NO_HALF: define spir_func noundef float @
+// SPV-NO_HALF: %fmod = frem float
+// SPV-NO_HALF: ret float %fmod
+half test_fmod_half(half p0, half p1) { return fmod(p0, p1); }
+
+// DX-NATIVE_HALF: define noundef <2 x half> @
+// DX-NATIVE_HALF: %dx.fmod = call <2 x half> @llvm.dx.fmod.v2f16
+// DX-NATIVE_HALF: ret <2 x half> %dx.fmod
+// DX-NO_HALF: define noundef <2 x float> @
+// DX-NO_HALF: %dx.fmod = call <2 x float> @llvm.dx.fmod.v2f32(
+// DX-NO_HALF: ret <2 x float> %dx.fmod
+//
+// SPV-NATIVE_HALF: define spir_func noundef <2 x half> @
+// SPV-NATIVE_HALF: %fmod = frem <2 x half>
+// SPV-NATIVE_HALF: ret <2 x half> %fmod
+// SPV-NO_HALF: define spir_func noundef <2 x float> @
+// SPV-NO_HALF: %fmod = frem <2 x float>
+// SPV-NO_HALF: ret <2 x float> %fmod
+half2 test_fmod_half2(half2 p0, half2 p1) { return fmod(p0, p1); }
+
+// DX-NATIVE_HALF: define noundef <3 x half> @
+// DX-NATIVE_HALF: %dx.fmod = call <3 x half> @llvm.dx.fmod.v3f16
+// DX-NATIVE_HALF: ret <3 x half> %dx.fmod
+// DX-NO_HALF: define noundef <3 x float> @
+// DX-NO_HALF: %dx.fmod = call <3 x float> @llvm.dx.fmod.v3f32(
+// DX-NO_HALF: ret <3 x float> %dx.fmod
+//
+// SPV-NATIVE_HALF: define spir_func noundef <3 x half> @
+// SPV-NATIVE_HALF: %fmod = frem <3 x half>
+// SPV-NATIVE_HALF: ret <3 x half> %fmod
+// SPV-NO_HALF: define spir_func noundef <3 x float> @
+// SPV-NO_HALF: %fmod = frem <3 x float>
+// SPV-NO_HALF: ret <3 x float> %fmod
+half3 test_fmod_half3(half3 p0, half3 p1) { return fmod(p0, p1); }
+
+// DX-NATIVE_HALF: define noundef <4 x half> @
+// DX-NATIVE_HALF: %dx.fmod = call <4 x half> @llvm.dx.fmod.v4f16
+// DX-NATIVE_HALF: ret <4 x half> %dx.fmod
+// DX-NO_HALF: define noundef <4 x float> @
+// DX-NO_HALF: %dx.fmod = call <4 x float> @llvm.dx.fmod.v4f32(
+// DX-NO_HALF: ret <4 x float> %dx.fmod
+//
+// SPV-NATIVE_HALF: define spir_func noundef <4 x half> @
+// SPV-NATIVE_HALF: %fmod = frem <4 x half>
+// SPV-NATIVE_HALF: ret <4 x half> %fmod
+// SPV-NO_HALF: define spir_func noundef <4 x float> @
+// SPV-NO_HALF: %fmod = frem <4 x float>
+// SPV-NO_HALF: ret <4 x float> %fmod
+half4 test_fmod_half4(half4 p0, half4 p1) { return fmod(p0, p1); }
+
+// DX-CHECK: define noundef float @
+// DX-CHECK: %dx.fmod = call float @llvm.dx.fmod.f32(
+// DX-CHECK: ret float %dx.fmod
+//
+// SPV-CHECK: define spir_func noundef float @
+// SPV-CHECK: %fmod = frem float
+// SPV-CHECK: ret float %fmod
+float test_fmod_float(float p0, float p1) { return fmod(p0, p1); }
+
+// DX-CHECK: define noundef <2 x float> @
+// DX-CHECK: %dx.fmod = call <2 x float> @llvm.dx.fmod.v2f32
+// DX-CHECK: ret <2 x float> %dx.fmod
+//
+// SPV-CHECK: define spir_func noundef <2 x float> @
+// SPV-CHECK: %fmod = frem <2 x float>
+// SPV-CHECK: ret <2 x float> %fmod
+float2 test_fmod_float2(float2 p0, float2 p1) { return fmod(p0, p1); }
+
+// DX-CHECK: define noundef <3 x float> @
+// DX-CHECK: %dx.fmod = call <3 x float> @llvm.dx.fmod.v3f32
+// DX-CHECK: ret <3 x float> %dx.fmod
+//
+// SPV-CHECK: define spir_func noundef <3 x float> @
+// SPV-CHECK: %fmod = frem <3 x float>
+// SPV-CHECK: ret <3 x float> %fmod
+float3 test_fmod_float3(float3 p0, float3 p1) { return fmod(p0, p1); }
+
+// DX-CHECK: define noundef <4 x float> @
+// DX-CHECK: %dx.fmod = call <4 x float> @llvm.dx.fmod.v4f32
+// DX-CHECK: ret <4 x float> %dx.fmod
+//
+// SPV-CHECK: define spir_func noundef <4 x float> @
+// SPV-CHECK: %fmod = frem <4 x float>
+// SPV-CHECK: ret <4 x float> %fmod
+float4 test_fmod_float4(float4 p0, float4 p1) { return fmod(p0, p1); }
+
diff --git a/clang/test/SemaHLSL/BuiltIns/fmod-errors.hlsl b/clang/test/SemaHLSL/BuiltIns/fmod-errors.hlsl
@@ -0,0 +1,38 @@
+
+// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.6-library %s -fnative-half-type -emit-llvm-only -disable-llvm-passes -verify -verify-ignore-unexpected
+
+float test_too_few_arg() {
+  return __builtin_hlsl_elementwise_fmod();
+  // expected-error@-1 {{too few arguments to function call, expected 2, have 0}}
+}
+
+float2 test_too_many_arg(float2 p0, float2 p1, float2 p3) {
+  return __builtin_hlsl_elementwise_fmod(p0, p1, p3);
+  // expected-error@-1 {{too many arguments to function call, expected 2, have 3}}
+}
+
+float builtin_bool_to_float_type_promotion(bool p1, bool p2) {
+  return __builtin_hlsl_elementwise_fmod(p1, p2);
+  // expected-error@-1 {{passing 'bool' to parameter of incompatible type 'float'}}
+}
+
+float builtin_fmod_int_to_float_promotion(int p1, int p2) {
+  return __builtin_hlsl_elementwise_fmod(p1, p2);
+  // expected-error@-1 {{passing 'int' to parameter of incompatible type 'float'}}
+}
+
+float2 builtin_fmod_int2_to_float2_promotion(int2 p1, int2 p2) {
+  return __builtin_hlsl_elementwise_fmod(p1, p2);
+  // expected-error@-1 {{passing 'int2' (aka 'vector<int, 2>') to parameter of incompatible type '__attribute__((__vector_size__(2 * sizeof(float)))) float' (vector of 2 'float' values)}}
+}
+
+// builtins are variadic functions and so are subject to DefaultVariadicArgumentPromotion
+half builtin_fmod_half_scalar (half p0, half p1) {
+  return __builtin_hlsl_elementwise_fmod(p0, p1);
+  // expected-error@-1 {{passing 'double' to parameter of incompatible type 'float'}}
+}
+
+float builtin_fmod_float_scalar (float p0, float p1) {
+  return __builtin_hlsl_elementwise_fmod (p0, p1);
+  // expected-error@-1 {{passing 'double' to parameter of incompatible type 'float'}}
+}
diff --git a/llvm/include/llvm/IR/IntrinsicsDirectX.td b/llvm/include/llvm/IR/IntrinsicsDirectX.td
@@ -90,4 +90,5 @@ def int_dx_rsqrt  : DefaultAttrsIntrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>]
 def int_dx_wave_is_first_lane : DefaultAttrsIntrinsic<[llvm_i1_ty], [], [IntrConvergent]>;
 def int_dx_sign : DefaultAttrsIntrinsic<[LLVMScalarOrSameVectorWidth<0, llvm_i32_ty>], [llvm_any_ty]>;
 def int_dx_step : DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty, LLVMMatchType<0>]>;
+def int_dx_fmod : DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty, LLVMMatchType<0>]>;
 }