llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang-codegen Author: Sietze Riemersma (KungFuDonkey) <details> <summary>Changes</summary> Adds the WaveActiveMin intrinsic from #<!-- -->99169. I think I did all of the required things on the checklist: [x] Implement `WaveActiveMin` clang builtin, [x] Link `WaveActiveMin` clang builtin with `hlsl_intrinsics.h` [x] Add sema checks for `WaveActiveMin` to `CheckHLSLBuiltinFunctionCall` in `SemaChecking.cpp` [x] Add codegen for `WaveActiveMin` to `EmitHLSLBuiltinExpr` in `CGBuiltin.cpp` [x] Add codegen tests to `clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl` [x] Add sema tests to `clang/test/SemaHLSL/BuiltIns/WaveActiveMin-errors.hlsl` [x] Create the `int_dx_WaveActiveMin` intrinsic in `IntrinsicsDirectX.td` [x] Create the `DXILOpMapping` of `int_dx_WaveActiveMin` to `119` in `DXIL.td` [x] Create the `WaveActiveMin.ll` and `WaveActiveMin_errors.ll` tests in `llvm/test/CodeGen/DirectX/` [x] Create the `int_spv_WaveActiveMin` intrinsic in `IntrinsicsSPIRV.td` [x] In SPIRVInstructionSelector.cpp create the `WaveActiveMin` lowering and map it to `int_spv_WaveActiveMin` in `SPIRVInstructionSelector::selectIntrinsic`. [x] Create SPIR-V backend test case in `llvm/test/CodeGen/SPIRV/hlsl-intrinsics/WaveActiveMin.ll But as some of the filenames have changed and were moved around (E.G. `CGBuiltin.cpp` -> `CGHLSLBuiltins.cpp`) I mostly followed how `WaveActiveMax()` is implemented. I have not been able to run the tests myself as I am unsure which project runs the correct test. Any guidance on how I can test myself would be helpful. Also added some tests to the offload-test-suite https://github.com/llvm/offload-test-suite/pull/478 --- Patch is 29.72 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/164385.diff 13 Files Affected: - (modified) clang/include/clang/Basic/Builtins.td (+6) - (modified) clang/lib/CodeGen/CGHLSLBuiltins.cpp (+31-1) - (modified) clang/lib/Headers/hlsl/hlsl_alias_intrinsics.h (+123) - (modified) clang/lib/Sema/SemaHLSL.cpp (+1) - (added) clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl (+46) - (added) clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl (+29) - (modified) llvm/include/llvm/IR/IntrinsicsDirectX.td (+2) - (modified) llvm/include/llvm/IR/IntrinsicsSPIRV.td (+3-1) - (modified) llvm/lib/Target/DirectX/DXIL.td (+10) - (modified) llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp (+1) - (modified) llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp (+36) - (added) llvm/test/CodeGen/DirectX/WaveActiveMin.ll (+143) - (added) llvm/test/CodeGen/SPIRV/hlsl-intrinsics/WaveActiveMin.ll (+57) ``````````diff diff --git a/clang/include/clang/Basic/Builtins.td b/clang/include/clang/Basic/Builtins.td index 792e2e07ec594..5c81dc4159801 100644 --- a/clang/include/clang/Basic/Builtins.td +++ b/clang/include/clang/Basic/Builtins.td @@ -5011,6 +5011,12 @@ def HLSLWaveActiveMax : LangBuiltin<"HLSL_LANG"> { let Prototype = "void (...)"; } +def HLSLWaveActiveMin : LangBuiltin<"HLSL_LANG"> { + let Spellings = ["__builtin_hlsl_wave_active_min"]; + let Attributes = [NoThrow, Const]; + let Prototype = "void (...)"; +} + def HLSLWaveActiveSum : LangBuiltin<"HLSL_LANG"> { let Spellings = ["__builtin_hlsl_wave_active_sum"]; let Attributes = [NoThrow, Const]; diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp b/clang/lib/CodeGen/CGHLSLBuiltins.cpp index 4f2f5a761f197..700c506200390 100644 --- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp +++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp @@ -196,7 +196,7 @@ static Intrinsic::ID getWaveActiveSumIntrinsic(llvm::Triple::ArchType Arch, } } -// Return wave active sum that corresponds to the QT scalar type +// Return wave active max that corresponds to the QT scalar type static Intrinsic::ID getWaveActiveMaxIntrinsic(llvm::Triple::ArchType Arch, CGHLSLRuntime &RT, QualType QT) { switch (Arch) { @@ -215,6 +215,25 @@ static Intrinsic::ID getWaveActiveMaxIntrinsic(llvm::Triple::ArchType Arch, } } +// Return wave active min that corresponds to the QT scalar type +static Intrinsic::ID getWaveActiveMinIntrinsic(llvm::Triple::ArchType Arch, + CGHLSLRuntime &RT, QualType QT) { + switch (Arch) { + case llvm::Triple::spirv: + if (QT->isUnsignedIntegerType()) + return Intrinsic::spv_wave_reduce_umin; + return Intrinsic::spv_wave_reduce_min; + case llvm::Triple::dxil: { + if (QT->isUnsignedIntegerType()) + return Intrinsic::dx_wave_reduce_umin; + return Intrinsic::dx_wave_reduce_min; + } + default: + llvm_unreachable("Intrinsic WaveActiveMin" + " not supported by target architecture"); + } +} + // Returns the mangled name for a builtin function that the SPIR-V backend // will expand into a spec Constant. static std::string getSpecConstantFunctionName(clang::QualType SpecConstantType, @@ -719,6 +738,17 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned BuiltinID, &CGM.getModule(), IID, {OpExpr->getType()}), ArrayRef{OpExpr}, "hlsl.wave.active.max"); } + case Builtin::BI__builtin_hlsl_wave_active_min: { + // Due to the use of variadic arguments, explicitly retreive argument + Value *OpExpr = EmitScalarExpr(E->getArg(0)); + Intrinsic::ID IID = getWaveActiveMinIntrinsic( + getTarget().getTriple().getArch(), CGM.getHLSLRuntime(), + E->getArg(0)->getType()); + + return EmitRuntimeCall(Intrinsic::getOrInsertDeclaration( + &CGM.getModule(), IID, {OpExpr->getType()}), + ArrayRef{OpExpr}, "hlsl.wave.active.min"); + } case Builtin::BI__builtin_hlsl_wave_get_lane_index: { // We don't define a SPIR-V intrinsic, instead it is a SPIR-V built-in // defined in SPIRVBuiltins.td. So instead we manually get the matching name diff --git a/clang/lib/Headers/hlsl/hlsl_alias_intrinsics.h b/clang/lib/Headers/hlsl/hlsl_alias_intrinsics.h index d973371312701..1d440f49af6c4 100644 --- a/clang/lib/Headers/hlsl/hlsl_alias_intrinsics.h +++ b/clang/lib/Headers/hlsl/hlsl_alias_intrinsics.h @@ -2597,6 +2597,129 @@ __attribute__((convergent)) double3 WaveActiveMax(double3); _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) __attribute__((convergent)) double4 WaveActiveMax(double4); +//===----------------------------------------------------------------------===// +// WaveActiveMax builtins +//===----------------------------------------------------------------------===// + +_HLSL_16BIT_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) half WaveActiveMin(half); +_HLSL_16BIT_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) half2 WaveActiveMin(half2); +_HLSL_16BIT_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) half3 WaveActiveMin(half3); +_HLSL_16BIT_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) half4 WaveActiveMin(half4); + +#ifdef __HLSL_ENABLE_16_BIT +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int16_t WaveActiveMin(int16_t); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int16_t2 WaveActiveMin(int16_t2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int16_t3 WaveActiveMin(int16_t3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int16_t4 WaveActiveMin(int16_t4); + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint16_t WaveActiveMin(uint16_t); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint16_t2 WaveActiveMin(uint16_t2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint16_t3 WaveActiveMin(uint16_t3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint16_t4 WaveActiveMin(uint16_t4); +#endif + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int WaveActiveMin(int); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int2 WaveActiveMin(int2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int3 WaveActiveMin(int3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int4 WaveActiveMin(int4); + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint WaveActiveMin(uint); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint2 WaveActiveMin(uint2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint3 WaveActiveMin(uint3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint4 WaveActiveMin(uint4); + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int64_t WaveActiveMin(int64_t); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int64_t2 WaveActiveMin(int64_t2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int64_t3 WaveActiveMin(int64_t3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) int64_t4 WaveActiveMin(int64_t4); + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint64_t WaveActiveMin(uint64_t); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint64_t2 WaveActiveMin(uint64_t2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint64_t3 WaveActiveMin(uint64_t3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) uint64_t4 WaveActiveMin(uint64_t4); + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) float WaveActiveMin(float); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) float2 WaveActiveMin(float2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) float3 WaveActiveMin(float3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) float4 WaveActiveMin(float4); + +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) double WaveActiveMin(double); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) double2 WaveActiveMin(double2); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) double3 WaveActiveMin(double3); +_HLSL_AVAILABILITY(shadermodel, 6.0) +_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_active_max) +__attribute__((convergent)) double4 WaveActiveMin(double4); + //===----------------------------------------------------------------------===// // WaveActiveSum builtins //===----------------------------------------------------------------------===// diff --git a/clang/lib/Sema/SemaHLSL.cpp b/clang/lib/Sema/SemaHLSL.cpp index f34706677b59f..680036b8ca241 100644 --- a/clang/lib/Sema/SemaHLSL.cpp +++ b/clang/lib/Sema/SemaHLSL.cpp @@ -3197,6 +3197,7 @@ bool SemaHLSL::CheckBuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) { break; } case Builtin::BI__builtin_hlsl_wave_active_max: + case Builtin::BI__builtin_hlsl_wave_active_min: case Builtin::BI__builtin_hlsl_wave_active_sum: { if (SemaRef.checkArgCount(TheCall, 1)) return true; diff --git a/clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl b/clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl new file mode 100644 index 0000000000000..1194f842deed6 --- /dev/null +++ b/clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl @@ -0,0 +1,46 @@ +// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \ +// RUN: dxil-pc-shadermodel6.3-compute %s -emit-llvm -disable-llvm-passes -o - | \ +// RUN: FileCheck %s --check-prefixes=CHECK,CHECK-DXIL +// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \ +// RUN: spirv-pc-vulkan-compute %s -emit-llvm -disable-llvm-passes -o - | \ +// RUN: FileCheck %s --check-prefixes=CHECK,CHECK-SPIRV + +// Test basic lowering to runtime function call. + +// CHECK-LABEL: test_int +int test_int(int expr) { + // CHECK-SPIRV: %[[RET:.*]] = call spir_func [[TY:.*]] @llvm.spv.wave.reduce.min.i32([[TY]] %[[#]]) + // CHECK-DXIL: %[[RET:.*]] = call [[TY:.*]] @llvm.dx.wave.reduce.min.i32([[TY]] %[[#]]) + // CHECK: ret [[TY]] %[[RET]] + return WaveActiveMin(expr); +} + +// CHECK-DXIL: declare [[TY]] @llvm.dx.wave.reduce.min.i32([[TY]]) #[[#attr:]] +// CHECK-SPIRV: declare [[TY]] @llvm.spv.wave.reduce.min.i32([[TY]]) #[[#attr:]] + +// CHECK-LABEL: test_uint64_t +uint64_t test_uint64_t(uint64_t expr) { + // CHECK-SPIRV: %[[RET:.*]] = call spir_func [[TY:.*]] @llvm.spv.wave.reduce.umin.i64([[TY]] %[[#]]) + // CHECK-DXIL: %[[RET:.*]] = call [[TY:.*]] @llvm.dx.wave.reduce.umin.i64([[TY]] %[[#]]) + // CHECK: ret [[TY]] %[[RET]] + return WaveActiveMin(expr); +} + +// CHECK-DXIL: declare [[TY]] @llvm.dx.wave.reduce.umin.i64([[TY]]) #[[#attr:]] +// CHECK-SPIRV: declare [[TY]] @llvm.spv.wave.reduce.umin.i64([[TY]]) #[[#attr:]] + +// Test basic lowering to runtime function call with array and float value. + +// CHECK-LABEL: test_floatv4 +float4 test_floatv4(float4 expr) { + // CHECK-SPIRV: %[[RET1:.*]] = call reassoc nnan ninf nsz arcp afn spir_func [[TY1:.*]] @llvm.spv.wave.reduce.min.v4f32([[TY1]] %[[#]] + // CHECK-DXIL: %[[RET1:.*]] = call reassoc nnan ninf nsz arcp afn [[TY1:.*]] @llvm.dx.wave.reduce.min.v4f32([[TY1]] %[[#]]) + // CHECK: ret [[TY1]] %[[RET1]] + return WaveActiveMin(expr); +} + +// CHECK-DXIL: declare [[TY1]] @llvm.dx.wave.reduce.min.v4f32([[TY1]]) #[[#attr]] +// CHECK-SPIRV: declare [[TY1]] @llvm.spv.wave.reduce.min.v4f32([[TY1]]) #[[#attr]] + +// CHECK: attributes #[[#attr]] = {{{.*}} convergent {{.*}}} + diff --git a/clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl b/clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl new file mode 100644 index 0000000000000..3b12faf8d9978 --- /dev/null +++ b/clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl @@ -0,0 +1,29 @@ +// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.6-library %s -emit-llvm-only -disable-llvm-passes -verify + +int test_too_few_arg() { + return __builtin_hlsl_wave_active_min(); + // expected-error@-1 {{too few arguments to function call, expected 1, have 0}} +} + +float2 test_too_many_arg(float2 p0) { + return __builtin_hlsl_wave_active_min(p0, p0); + // expected-error@-1 {{too many arguments to function call, expected 1, have 2}} +} + +bool test_expr_bool_type_check(bool p0) { + return __builtin_hlsl_wave_active_min(p0); + // expected-error@-1 {{invalid operand of type 'bool'}} +} + +bool2 test_expr_bool_vec_type_check(bool2 p0) { + return __builtin_hlsl_wave_active_min(p0); + // expected-error@-1 {{invalid operand of type 'bool2' (aka 'vector<bool, 2>')}} +} + +struct S { float f; }; + +S test_expr_struct_type_check(S p0) { + return __builtin_hlsl_wave_active_min(p0); + // expected-error@-1 {{invalid operand of type 'S' where a scalar or vector is required}} +} + diff --git a/llvm/include/llvm/IR/IntrinsicsDirectX.td b/llvm/include/llvm/IR/IntrinsicsDirectX.td index 3b7077c52db21..dbec8e72fad19 100644 --- a/llvm/include/llvm/IR/IntrinsicsDirectX.td +++ b/llvm/include/llvm/IR/IntrinsicsDirectX.td @@ -153,6 +153,8 @@ def int_dx_wave_any : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_i1_ty], [IntrCon def int_dx_wave_getlaneindex : DefaultAttrsIntrinsic<[llvm_i32_ty], [], [IntrConvergent, IntrNoMem]>; def int_dx_wave_reduce_max : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_dx_wave_reduce_umax : DefaultAttrsIntrinsic<[llvm_anyint_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; +def int_dx_wave_reduce_min : DefaultAttrsIntrinsic<[llvm_anyint_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; +def int_dx_wave_reduce_umin : DefaultAttrsIntrinsic<[llvm_anyint_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_dx_wave_reduce_sum : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_dx_wave_reduce_usum : DefaultAttrsIntrinsic<[llvm_anyint_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_dx_wave_is_first_lane : DefaultAttrsIntrinsic<[llvm_i1_ty], [], [IntrConvergent]>; diff --git a/llvm/include/llvm/IR/IntrinsicsSPIRV.td b/llvm/include/llvm/IR/IntrinsicsSPIRV.td index 49a182be98acd..bc51fb639fd75 100644 --- a/llvm/include/llvm/IR/IntrinsicsSPIRV.td +++ b/llvm/include/llvm/IR/IntrinsicsSPIRV.td @@ -122,6 +122,8 @@ def int_spv_rsqrt : DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty] def int_spv_wave_any : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_i1_ty], [IntrConvergent, IntrNoMem]>; def int_spv_wave_reduce_umax : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_spv_wave_reduce_max : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; + def int_spv_wave_reduce_min : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; + def int_spv_wave_reduce_umin : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_spv_wave_reduce_sum : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>], [IntrConvergent, IntrNoMem]>; def int_spv_wave_is_first_lane : DefaultAttrsIntrinsic<[llvm_i1_ty], [], [IntrConvergent]>; def int_spv_wave_readlane : DefaultAttrsIntrinsic<[llvm_any_ty], [LLVMMatchType<0>, llvm_i32_ty], [IntrConvergent, IntrNoMem]>; @@ -136,7 +138,7 @@ def int_spv_rsqrt : DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty] def int_spv_sclamp : DefaultAttrsIntrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>; def int_spv_nclamp : DefaultAttrsIntrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>; - // Create resource handle given the binding information. Returns a + // Create resource handle given the binding information. Returns a // type appropriate for the kind of resource given the set id, binding id, // array size of the binding, as well as an index and an indicator // whether that index may be non-uniform. diff --git a/llvm/lib/Target/DirectX/DXIL.td b/llvm/lib/Target/DirectX/DXIL.td index 44c48305f2832..3986f62d47cb8 100644 --- a/llvm/lib/Target/DirectX/DXIL.td +++ b/llvm/lib/Target/DirectX/DXIL.td @@ -1058,6 +1058,16 @@ def WaveActiveOp : DXILOp<119, waveActiveOp> { IntrinArgIndex<0>, IntrinArgI8<WaveOpKind_Max>, IntrinArgI8<SignedOpKind_Unsigned> ]>, + IntrinSelect<int_dx_wave_reduce_min, + [ + IntrinArgIndex<0>, IntrinArgI8<WaveOpKind_Max>, + IntrinArgI8<SignedOpKind_Signed> + ]>, + IntrinSelect<int_dx_wave_reduce_umin, + [ + IntrinArgIndex<0>, IntrinArgI8<WaveOpKind_Max>, + IntrinArgI8<SignedOpKind_Unsigned> + ]>, ]; let arguments = [OverloadTy, Int8Ty, Int8Ty]; diff --git a/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp b/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp index 68fd3e0bc74c7..96a9285767aa6 100644 --- a/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp +++ b/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp @@ -55,6 +55,7 @@ bool DirectXTTIImpl::isTargetIntrinsicTriviallyScalarizable( case Intrinsic::dx_splitdouble: case Intrinsic::dx_wave_readlane: case Intrinsic::dx_wave_reduce_max: + case Intrinsic::dx_wave_reduce_min: case Intrinsic::dx_wave_reduce_sum: case Intrinsic::dx_wave_reduce_umax: case Intrinsic::dx_wave_reduce_usum: diff --git a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp index a0cff4d82b500..0719efed5e6a8 100644 --- a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp +++ b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp @@ -222,6 +222,9 @@ class SPIRVInstructionSelector : public InstructionSelector { bool selectWaveReduceMax(Register ResVReg, const SPIRVType *ResType, MachineInstr &I, bool IsUnsigned) const; + bool selectWaveActiveMin(Register ResVReg, const SPIRVType *ResType, + MachineInstr &I, bool IsUnsigned) const; + bool selectWaveReduceSum(Register ResVReg, const SPIRVType *ResType, MachineInstr &I) const; @@ -2456,6 +2459,35 @@ bool SPIRVInstructionSelector::selectWaveReduceMax(Register ResVReg, .constrainAllUses(TII, TRI, RBI); } +bool SPIRVInstructionSelector::selectWaveActiveMin(Register ResVReg, + const SPIRVType *ResType, + MachineInstr &I, + bool IsUnsigned) const { + assert(I.getNumOperands() == 3); + assert(I.getOperand(2).isReg()); + MachineBasicBlock &BB = *I.getParent(); + Register InputRegister = I.getOperand(2).getReg(); + SPIRVType *InputType = GR.getSPIRVTypeForVReg(InputRegister); + + if (!InputType) + report_fatal_error("Input Type could not be determined."); + + SPIRVType *IntTy = GR.getOrCreateSPIRVIntegerType(32, I, TII); + // Retreive the operation to use based on input type + bool IsFloatTy = GR.isScalarOrVectorOfType(InputRegister, SPIRV::OpTypeFloat); + auto IntegerOpcodeType = + IsUnsigned ? SPIRV::OpGroupNonUniformUMin : SPIRV::OpGroupNonUniformSMin; + auto Opcode = IsFlo... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/164385 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
