python3kgae updated this revision to Diff 439463.
python3kgae marked 3 inline comments as done.
python3kgae added a comment.
Cleanup comments.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D124790/new/
https://reviews.llvm.org/D124790
Files:
clang/include/clang/Driver/Options.td
clang/lib/AST/ASTContext.cpp
clang/lib/AST/MicrosoftMangle.cpp
clang/lib/Basic/LangOptions.cpp
clang/lib/Basic/Targets/DirectX.h
clang/lib/Driver/ToolChains/Clang.cpp
clang/lib/Driver/ToolChains/HLSL.cpp
clang/test/CodeGenHLSL/basic_types.hlsl
clang/test/CodeGenHLSL/half.hlsl
Index: clang/test/CodeGenHLSL/half.hlsl
===================================================================
--- /dev/null
+++ clang/test/CodeGenHLSL/half.hlsl
@@ -0,0 +1,15 @@
+// RUN: %clang_dxc -Tlib_6_7 -fcgl -Fo - %s | FileCheck %s --check-prefix=FLOAT
+// RUN: %clang_dxc -Tlib_6_7 -enable-16bit-types -fcgl -Fo - %s | FileCheck %s --check-prefix=HALF
+
+// Make sure use float when not enable-16bit-types.
+// FLOAT:define {{.*}}float @"?foo@@YA$halff@$halff@0@Z"(float{{[^,]+}}, float{{[^,)]+}})
+// FLOAT-NOT:half
+// FLOAT:ret float %
+
+// Make sure use half when enable-16bit-types.
+// HALF:define {{.*}}half @"?foo@@YA$f16@$f16@0@Z"(half{{[^,]+}}, half{{[^,)]+}})
+// HALF-NOT:float
+// HALF:ret half %
+half foo(half a, half b) {
+ return a+b;
+}
Index: clang/test/CodeGenHLSL/basic_types.hlsl
===================================================================
--- clang/test/CodeGenHLSL/basic_types.hlsl
+++ clang/test/CodeGenHLSL/basic_types.hlsl
@@ -2,27 +2,27 @@
// FIXME: check 16bit types once enable-16bit-types is ready.
-// CHECK:@uint_Val = global i32 0, align 4
-// CHECK:@uint64_t_Val = global i64 0, align 8
-// CHECK:@int64_t_Val = global i64 0, align 8
-// CHECK:@int2_Val = global <2 x i32> zeroinitializer, align 8
-// CHECK:@int3_Val = global <3 x i32> zeroinitializer, align 16
-// CHECK:@int4_Val = global <4 x i32> zeroinitializer, align 16
-// CHECK:@uint2_Val = global <2 x i32> zeroinitializer, align 8
-// CHECK:@uint3_Val = global <3 x i32> zeroinitializer, align 16
-// CHECK:@uint4_Val = global <4 x i32> zeroinitializer, align 16
-// CHECK:@int64_t2_Val = global <2 x i64> zeroinitializer, align 16
-// CHECK:@int64_t3_Val = global <3 x i64> zeroinitializer, align 32
-// CHECK:@int64_t4_Val = global <4 x i64> zeroinitializer, align 32
-// CHECK:@uint64_t2_Val = global <2 x i64> zeroinitializer, align 16
-// CHECK:@uint64_t3_Val = global <3 x i64> zeroinitializer, align 32
-// CHECK:@uint64_t4_Val = global <4 x i64> zeroinitializer, align 32
-// CHECK:@float2_Val = global <2 x float> zeroinitializer, align 8
-// CHECK:@float3_Val = global <3 x float> zeroinitializer, align 16
-// CHECK:@float4_Val = global <4 x float> zeroinitializer, align 16
-// CHECK:@double2_Val = global <2 x double> zeroinitializer, align 16
-// CHECK:@double3_Val = global <3 x double> zeroinitializer, align 32
-// CHECK:@double4_Val = global <4 x double> zeroinitializer, align 32
+// CHECK:"?uint_Val@@3IA" = global i32 0, align 4
+// CHECK:"?uint64_t_Val@@3KA" = global i64 0, align 8
+// CHECK:"?int64_t_Val@@3JA" = global i64 0, align 8
+// CHECK:"?int2_Val@@3T?$__vector@H$01@__clang@@A" = global <2 x i32> zeroinitializer, align 8
+// CHECK:"?int3_Val@@3T?$__vector@H$02@__clang@@A" = global <3 x i32> zeroinitializer, align 16
+// CHECK:"?int4_Val@@3T?$__vector@H$03@__clang@@A" = global <4 x i32> zeroinitializer, align 16
+// CHECK:"?uint2_Val@@3T?$__vector@I$01@__clang@@A" = global <2 x i32> zeroinitializer, align 8
+// CHECK:"?uint3_Val@@3T?$__vector@I$02@__clang@@A" = global <3 x i32> zeroinitializer, align 16
+// CHECK:"?uint4_Val@@3T?$__vector@I$03@__clang@@A" = global <4 x i32> zeroinitializer, align 16
+// CHECK:"?int64_t2_Val@@3T?$__vector@J$01@__clang@@A" = global <2 x i64> zeroinitializer, align 16
+// CHECK:"?int64_t3_Val@@3T?$__vector@J$02@__clang@@A" = global <3 x i64> zeroinitializer, align 32
+// CHECK:"?int64_t4_Val@@3T?$__vector@J$03@__clang@@A" = global <4 x i64> zeroinitializer, align 32
+// CHECK:"?uint64_t2_Val@@3T?$__vector@K$01@__clang@@A" = global <2 x i64> zeroinitializer, align 16
+// CHECK:"?uint64_t3_Val@@3T?$__vector@K$02@__clang@@A" = global <3 x i64> zeroinitializer, align 32
+// CHECK:"?uint64_t4_Val@@3T?$__vector@K$03@__clang@@A" = global <4 x i64> zeroinitializer, align 32
+// CHECK:"?float2_Val@@3T?$__vector@M$01@__clang@@A" = global <2 x float> zeroinitializer, align 8
+// CHECK:"?float3_Val@@3T?$__vector@M$02@__clang@@A" = global <3 x float> zeroinitializer, align 16
+// CHECK:"?float4_Val@@3T?$__vector@M$03@__clang@@A" = global <4 x float> zeroinitializer, align 16
+// CHECK:"?double2_Val@@3T?$__vector@N$01@__clang@@A" = global <2 x double> zeroinitializer, align 16
+// CHECK:"?double3_Val@@3T?$__vector@N$02@__clang@@A" = global <3 x double> zeroinitializer, align 32
+// CHECK:"?double4_Val@@3T?$__vector@N$03@__clang@@A" = global <4 x double> zeroinitializer, align 32
#define TYPE_DECL(T) T T##_Val
Index: clang/lib/Driver/ToolChains/HLSL.cpp
===================================================================
--- clang/lib/Driver/ToolChains/HLSL.cpp
+++ clang/lib/Driver/ToolChains/HLSL.cpp
@@ -177,5 +177,7 @@
Opts.getOption(options::OPT_dxil_validator_version),
DefaultValidatorVer);
}
+ // FIXME: add validation for enable_16bit_types should be after HLSL 2018 and
+ // shader model 6.2.
return DAL;
}
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -3479,9 +3479,12 @@
static void RenderHLSLOptions(const ArgList &Args, ArgStringList &CmdArgs,
types::ID InputType) {
- const unsigned ForwardedArguments[] = {
- options::OPT_dxil_validator_version, options::OPT_D, options::OPT_S,
- options::OPT_emit_llvm, options::OPT_disable_llvm_passes};
+ const unsigned ForwardedArguments[] = {options::OPT_dxil_validator_version,
+ options::OPT_D,
+ options::OPT_S,
+ options::OPT_emit_llvm,
+ options::OPT_disable_llvm_passes,
+ options::OPT_fnative_half_type};
for (const auto &Arg : ForwardedArguments)
if (const auto *A = Args.getLastArg(Arg))
@@ -3489,6 +3492,7 @@
// Add the default headers if dxc_no_stdinc is not set.
if (!Args.hasArg(options::OPT_dxc_no_stdinc))
CmdArgs.push_back("-finclude-default-header");
+ CmdArgs.push_back("-fallow-half-arguments-and-returns");
}
static void RenderARCMigrateToolOptions(const Driver &D, const ArgList &Args,
Index: clang/lib/Basic/Targets/DirectX.h
===================================================================
--- clang/lib/Basic/Targets/DirectX.h
+++ clang/lib/Basic/Targets/DirectX.h
@@ -57,8 +57,9 @@
NoAsmVariants = true;
resetDataLayout("e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-f32:"
"32-f64:64-n8:16:32:64");
+ TheCXXABI.set(TargetCXXABI::Microsoft);
}
-
+ bool useFP16ConversionIntrinsics() const override { return false; }
void getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const override;
Index: clang/lib/Basic/LangOptions.cpp
===================================================================
--- clang/lib/Basic/LangOptions.cpp
+++ clang/lib/Basic/LangOptions.cpp
@@ -195,8 +195,8 @@
// OpenCL, C++ and C2x have bool, true, false keywords.
Opts.Bool = Opts.OpenCL || Opts.CPlusPlus || Opts.C2x;
- // OpenCL has half keyword
- Opts.Half = Opts.OpenCL;
+ // OpenCL and HLSL have half keyword
+ Opts.Half = Opts.OpenCL || Opts.HLSL;
}
FPOptions FPOptions::defaultWithoutTrailingStorage(const LangOptions &LO) {
Index: clang/lib/AST/MicrosoftMangle.cpp
===================================================================
--- clang/lib/AST/MicrosoftMangle.cpp
+++ clang/lib/AST/MicrosoftMangle.cpp
@@ -2461,7 +2461,12 @@
break;
case BuiltinType::Half:
- mangleArtificialTagType(TTK_Struct, "_Half", {"__clang"});
+ if (!getASTContext().getLangOpts().HLSL)
+ mangleArtificialTagType(TTK_Struct, "_Half", {"__clang"});
+ else if (getASTContext().getLangOpts().NativeHalfType)
+ Out << "$f16@";
+ else
+ Out << "$halff@";
break;
#define SVE_TYPE(Name, Id, SingletonId) \
Index: clang/lib/AST/ASTContext.cpp
===================================================================
--- clang/lib/AST/ASTContext.cpp
+++ clang/lib/AST/ASTContext.cpp
@@ -1707,8 +1707,17 @@
case BuiltinType::BFloat16:
return Target->getBFloat16Format();
case BuiltinType::Float16:
- case BuiltinType::Half:
return Target->getHalfFormat();
+ case BuiltinType::Half:
+ // For HLSL, when the native half type is disabled, half will be treat as
+ // float.
+ if (getLangOpts().HLSL)
+ if (getLangOpts().NativeHalfType)
+ return Target->getHalfFormat();
+ else
+ return Target->getFloatFormat();
+ else
+ return Target->getHalfFormat();
case BuiltinType::Float: return Target->getFloatFormat();
case BuiltinType::Double: return Target->getDoubleFormat();
case BuiltinType::Ibm128:
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -6847,3 +6847,6 @@
HelpText<"Emit pristine LLVM IR from the frontend by not running any LLVM passes at all."
"Same as -S + -emit-llvm + -disable-llvm-passes.">;
def fcgl : DXCFlag<"fcgl">, Alias<emit_pristine_llvm>;
+def enable_16bit_types : DXCFlag<"enable-16bit-types">, Alias<fnative_half_type>,
+ HelpText<"Enable 16-bit types and disable min precision types."
+ "Available in HLSL 2018 and shader model 6.2.">;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
