[HLSL][SPIRV][DXIL] Implement dot4add_i8packed intrinsic

    - create a clang built-in in Builtins.td
    - link dot4add_i8packed in hlsl_intrinsics.h
    - add lowering to spirv backend through expansion of operation as
      OPSDot is missing up to SPIRV 1.6 in SPIRVInstructionSelector.cpp
    - add dot4add_i8packed intrinsic to IntrinsicsDirectX.td and mapping
      to DXIL.td op Dot4AddI8Packed

    - add tests for HLSL intrinsic lowering to dx/spv intrinsic in
      dot4add_i8packed.hlsl
    - add tests for sema checks in dot4add_i8packed-errors.hlsl
    - add test of spir-v lowering in SPIRV/dot4add_i8packed.ll
    - add test to dxil lowering in DirectX/dot4add_i8packed.ll

Author: inbelic

clang/include/clang/Basic/Builtins.td

@@ -4792,6 +4792,12 @@ def HLSLDotProduct : LangBuiltin<"HLSL_LANG"> {
   let Prototype = "void(...)";
 }
 
+def HLSLDot4AddI8Packed : LangBuiltin<"HLSL_LANG"> {
+  let Spellings = ["__builtin_hlsl_dot4add_i8packed"];
+  let Attributes = [NoThrow, Const];
+  let Prototype = "int(unsigned int, unsigned int, int)";
+}
+
 def HLSLFrac : LangBuiltin<"HLSL_LANG"> {
   let Spellings = ["__builtin_hlsl_elementwise_frac"];
   let Attributes = [NoThrow, Const];

clang/lib/CodeGen/CGBuiltin.cpp

@@ -18722,7 +18722,17 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned BuiltinID,
         /*ReturnType=*/T0->getScalarType(),
         getDotProductIntrinsic(CGM.getHLSLRuntime(), VecTy0->getElementType()),
         ArrayRef<Value *>{Op0, Op1}, nullptr, "hlsl.dot");
-  } break;
+  }
+  case Builtin::BI__builtin_hlsl_dot4add_i8packed: {
+    Value *A = EmitScalarExpr(E->getArg(0));
+    Value *B = EmitScalarExpr(E->getArg(1));
+    Value *C = EmitScalarExpr(E->getArg(2));
+
+    Intrinsic::ID ID = CGM.getHLSLRuntime().getDot4AddI8PackedIntrinsic();
+    return Builder.CreateIntrinsic(
+        /*ReturnType=*/C->getType(), ID,
+        ArrayRef<Value *>{A, B, C}, nullptr, "hlsl.dot4add.i8packed");
+  }
   case Builtin::BI__builtin_hlsl_lerp: {
     Value *X = EmitScalarExpr(E->getArg(0));
     Value *Y = EmitScalarExpr(E->getArg(1));

clang/lib/CodeGen/CGHLSLRuntime.h

@@ -89,6 +89,7 @@ class CGHLSLRuntime {
   GENERATE_HLSL_INTRINSIC_FUNCTION(FDot, fdot)
   GENERATE_HLSL_INTRINSIC_FUNCTION(SDot, sdot)
   GENERATE_HLSL_INTRINSIC_FUNCTION(UDot, udot)
+  GENERATE_HLSL_INTRINSIC_FUNCTION(Dot4AddI8Packed, dot4add_i8packed)
   GENERATE_HLSL_INTRINSIC_FUNCTION(WaveIsFirstLane, wave_is_first_lane)
   GENERATE_HLSL_INTRINSIC_FUNCTION(WaveReadLaneAt, wave_readlane)
 

clang/lib/Headers/hlsl/hlsl_intrinsics.h

@@ -894,6 +894,16 @@ uint64_t dot(uint64_t3, uint64_t3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_dot)
 uint64_t dot(uint64_t4, uint64_t4);
 
+//===----------------------------------------------------------------------===//
+// dot4add builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn int dot4add_i8packed(uint A, uint B, int C)
+
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.4)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_dot4add_i8packed)
+int dot4add_i8packed(unsigned int, unsigned int, int);
+
 //===----------------------------------------------------------------------===//
 // exp builtins
 //===----------------------------------------------------------------------===//

clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl

@@ -0,0 +1,17 @@
+// 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 -DTARGET=dx
+// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \
+// RUN:   spirv-pc-vulkan-compute %s -emit-llvm -disable-llvm-passes -o - | \
+// RUN:   FileCheck %s -DTARGET=spv
+
+// Test basic lowering to runtime function call.
+
+// CHECK-LABEL: test
+int test(uint a, uint b, int c) {
+  // CHECK:  %[[RET:.*]] = call [[TY:i32]] @llvm.[[TARGET]].dot4add.i8packed([[TY]] %[[#]], [[TY]] %[[#]], [[TY]] %[[#]])
+  // CHECK:  ret [[TY]] %[[RET]]
+  return dot4add_i8packed(a, b, c);
+}
+
+// CHECK: declare [[TY]] @llvm.[[TARGET]].dot4add.i8packed([[TY]], [[TY]], [[TY]])

clang/test/SemaHLSL/BuiltIns/dot4add_i8packed-errors.hlsl

@@ -0,0 +1,28 @@
+// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.6-library %s -emit-llvm-only -disable-llvm-passes -verify
+
+int test_too_few_arg0() {
+  return __builtin_hlsl_dot4add_i8packed();
+  // expected-error@-1 {{too few arguments to function call, expected 3, have 0}}
+}
+
+int test_too_few_arg1(int p0) {
+  return __builtin_hlsl_dot4add_i8packed(p0);
+  // expected-error@-1 {{too few arguments to function call, expected 3, have 1}}
+}
+
+int test_too_few_arg2(int p0) {
+  return __builtin_hlsl_dot4add_i8packed(p0, p0);
+  // expected-error@-1 {{too few arguments to function call, expected 3, have 2}}
+}
+
+int test_too_many_arg(int p0) {
+  return __builtin_hlsl_dot4add_i8packed(p0, p0, p0, p0);
+  // expected-error@-1 {{too many arguments to function call, expected 3, have 4}}
+}
+
+struct S { float f; };
+
+int test_expr_struct_type_check(S p0, int p1) {
+  return __builtin_hlsl_dot4add_i8packed(p0, p1, p1);
+  // expected-error@-1 {{no viable conversion from 'S' to 'unsigned int'}}
+}

llvm/include/llvm/IR/IntrinsicsDirectX.td

@@ -69,6 +69,7 @@ def int_dx_udot :
     DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
     [llvm_anyint_ty, LLVMScalarOrSameVectorWidth<0, LLVMVectorElementType<0>>],
     [IntrNoMem, Commutative] >;
+  def int_dx_dot4add_i8packed : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem, Commutative] >;
 
 def int_dx_frac  : DefaultAttrsIntrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem]>;
 def int_dx_degrees : DefaultAttrsIntrinsic<[LLVMMatchType<0>], [llvm_anyfloat_ty], [IntrNoMem]>;

llvm/include/llvm/IR/IntrinsicsSPIRV.td

@@ -83,6 +83,7 @@ let TargetPrefix = "spv" in {
     DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],
     [llvm_anyint_ty, LLVMScalarOrSameVectorWidth<0, LLVMVectorElementType<0>>],
     [IntrNoMem, Commutative] >;
+  def int_spv_dot4add_i8packed : DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem, Commutative] >;
   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]>;
   def int_spv_sign : DefaultAttrsIntrinsic<[LLVMScalarOrSameVectorWidth<0, llvm_i32_ty>], [llvm_any_ty], [IntrNoMem]>;

llvm/lib/Target/DirectX/DXIL.td

@@ -779,6 +779,16 @@ def FlattenedThreadIdInGroup :  DXILOp<96, flattenedThreadIdInGroup> {
   let attributes = [Attributes<DXIL1_0, [ReadNone]>];
 }
 
+def Dot4AddI8Packed : DXILOp<163, dot4AddPacked> {
+  let Doc = "signed dot product of 4 x i8 vectors packed into i32, with "
+            "accumulate to i32";
+  let LLVMIntrinsic = int_dx_dot4add_i8packed;
+  let arguments = [Int32Ty, Int32Ty, Int32Ty];
+  let result = Int32Ty;
+  let attributes = [Attributes<DXIL1_0, [ReadNone]>];
+  let stages = [Stages<DXIL1_0, [all_stages]>];
+}
+
 def AnnotateHandle : DXILOp<217, annotateHandle> {
   let Doc = "annotate handle with resource properties";
   let arguments = [HandleTy, ResPropsTy];

llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp

@@ -164,6 +164,10 @@ class SPIRVInstructionSelector : public InstructionSelector {
   bool selectIntegerDot(Register ResVReg, const SPIRVType *ResType,
                         MachineInstr &I) const;
 
+  template <bool Signed>
+  bool selectDot4AddPacked(Register ResVReg, const SPIRVType *ResType,
+                           MachineInstr &I) const;
+
   void renderImm32(MachineInstrBuilder &MIB, const MachineInstr &I,
                    int OpIdx) const;
   void renderFImm64(MachineInstrBuilder &MIB, const MachineInstr &I,
@@ -1694,6 +1698,84 @@ bool SPIRVInstructionSelector::selectIntegerDot(Register ResVReg,
   return Result;
 }
 
+// Since pre-1.6 SPIRV has no DotProductInput4x8BitPacked implementation,
+// extract the elements of the packed inputs, multiply them and add the result
+// to the accumulator.
+template <bool Signed>
+bool SPIRVInstructionSelector::selectDot4AddPacked(Register ResVReg,
+                                                   const SPIRVType *ResType,
+                                                   MachineInstr &I) const {
+  assert(I.getNumOperands() == 5);
+  assert(I.getOperand(2).isReg());
+  assert(I.getOperand(3).isReg());
+  assert(I.getOperand(4).isReg());
+  MachineBasicBlock &BB = *I.getParent();
+
+  bool Result = false;
+
+  // Acc = C
+  Register Acc = I.getOperand(4).getReg();
+  SPIRVType *EltType = GR.getOrCreateSPIRVIntegerType(8, I, TII);
+  auto ExtractOp =
+      Signed ? SPIRV::OpBitFieldSExtract : SPIRV::OpBitFieldUExtract;
+
+  // Extract the i8 element, multiply and add it to the accumulator
+  for (unsigned i = 0; i < 4; i++) {
+    // A[i]
+    Register AElt = MRI->createVirtualRegister(&SPIRV::IDRegClass);
+    Result |= BuildMI(BB, I, I.getDebugLoc(), TII.get(ExtractOp))
+                  .addDef(AElt)
+                  .addUse(GR.getSPIRVTypeID(ResType))
+                  .addUse(I.getOperand(2).getReg())
+                  .addUse(GR.getOrCreateConstInt(i * 8, I, EltType, TII))
+                  .addImm(8)
+                  .constrainAllUses(TII, TRI, RBI);
+
+    // B[i]
+    Register BElt = MRI->createVirtualRegister(&SPIRV::IDRegClass);
+    Result |= BuildMI(BB, I, I.getDebugLoc(), TII.get(ExtractOp))
+                  .addDef(BElt)
+                  .addUse(GR.getSPIRVTypeID(ResType))
+                  .addUse(I.getOperand(3).getReg())
+                  .addUse(GR.getOrCreateConstInt(i * 8, I, EltType, TII))
+                  .addImm(8)
+                  .constrainAllUses(TII, TRI, RBI);
+
+    // A[i] * B[i]
+    Register Mul = MRI->createVirtualRegister(&SPIRV::IDRegClass);
+    Result |= BuildMI(BB, I, I.getDebugLoc(), TII.get(SPIRV::OpIMulS))
+                  .addDef(Mul)
+                  .addUse(GR.getSPIRVTypeID(ResType))
+                  .addUse(AElt)
+                  .addUse(BElt)
+                  .constrainAllUses(TII, TRI, RBI);
+
+    // Discard 24 highest-bits so that stored i32 register is i8 equivalent
+    Register MaskMul = MRI->createVirtualRegister(&SPIRV::IDRegClass);
+    Result |= BuildMI(BB, I, I.getDebugLoc(), TII.get(ExtractOp))
+                  .addDef(MaskMul)
+                  .addUse(GR.getSPIRVTypeID(ResType))
+                  .addUse(Mul)
+                  .addUse(GR.getOrCreateConstInt(0, I, EltType, TII))
+                  .addImm(8)
+                  .constrainAllUses(TII, TRI, RBI);
+
+    // Acc = Acc + A[i] * B[i]
+    Register Sum =
+        i < 3 ? MRI->createVirtualRegister(&SPIRV::IDRegClass) : ResVReg;
+    Result |= BuildMI(BB, I, I.getDebugLoc(), TII.get(SPIRV::OpIAddS))
+                  .addDef(Sum)
+                  .addUse(GR.getSPIRVTypeID(ResType))
+                  .addUse(Acc)
+                  .addUse(MaskMul)
+                  .constrainAllUses(TII, TRI, RBI);
+
+    Acc = Sum;
+  }
+
+  return Result;
+}
+
 /// Transform saturate(x) to clamp(x, 0.0f, 1.0f) as SPIRV
 /// does not have a saturate builtin.
 bool SPIRVInstructionSelector::selectSaturate(Register ResVReg,
@@ -2527,6 +2609,8 @@ bool SPIRVInstructionSelector::selectIntrinsic(Register ResVReg,
   case Intrinsic::spv_udot:
   case Intrinsic::spv_sdot:
     return selectIntegerDot(ResVReg, ResType, I);
+  case Intrinsic::spv_dot4add_i8packed:
+    return selectDot4AddPacked<true>(ResVReg, ResType, I);
   case Intrinsic::spv_all:
     return selectAll(ResVReg, ResType, I);
   case Intrinsic::spv_any:

llvm/test/CodeGen/DirectX/dot4add_i8packed.ll

@@ -0,0 +1,10 @@
+; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s | FileCheck %s
+
+define void @main(i32 %a, i32 %b, i32 %c) {
+entry:
+; CHECK: call i32 @dx.op.dot4AddPacked(i32 163, i32 %a, i32 %b, i32 %c)
+  %0 = call i32 @llvm.dx.dot4add.i8packed(i32 %a, i32 %b, i32 %c)
+  ret void
+}
+
+declare i32 @llvm.dx.dot4add.i8packed(i32, i32, i32)

llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_i8packed.ll

@@ -0,0 +1,48 @@
+; RUN: llc -O0 -mtriple=spirv32v1.3-vulkan-unknown %s -o - | FileCheck %s
+; RUN: %if spirv-tools %{ llc -O0 -mtriple=spirv32v1.3-vulkan-unknown %s -o - -filetype=obj | spirv-val %}
+
+; CHECK-DAG: %[[#int_32:]] = OpTypeInt 32 0
+; CHECK-DAG: %[[#int_8:]] = OpTypeInt 8 0
+; CHECK-DAG: %[[#zero:]] = OpConstantNull %[[#int_8]]
+; CHECK-DAG: %[[#eight:]] = OpConstant %[[#int_8]] 8
+; CHECK-DAG: %[[#sixteen:]] = OpConstant %[[#int_8]] 16
+; CHECK-DAG: %[[#twentyfour:]] = OpConstant %[[#int_8]] 24
+; CHECK-LABEL: Begin function test_dot
+define noundef i32 @test_dot(i32 noundef %a, i32 noundef %b, i32 noundef %c) {
+entry:
+; CHECK: %[[#A:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#B:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#C:]] = OpFunctionParameter %[[#int_32]]
+
+; First element of the packed vector
+; CHECK: %[[#A0:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#zero]] 8
+; CHECK: %[[#B0:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#zero]] 8
+; CHECK: %[[#MUL0:]] = OpIMul %[[#int_32]] %[[#A0]] %[[#B0]]
+; CHECK: %[[#MASK0:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL0]] %[[#zero]] 8
+; CHECK: %[[#ACC0:]] = OpIAdd %[[#int_32]] %[[#C]] %[[#MASK0]]
+
+; Second element of the packed vector
+; CHECK: %[[#A1:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#eight]] 8
+; CHECK: %[[#B1:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#eight]] 8
+; CHECK: %[[#MUL1:]] = OpIMul %[[#int_32]] %[[#A1]] %[[#B1]]
+; CHECK: %[[#MASK1:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL1]] %[[#zero]] 8
+; CHECK: %[[#ACC1:]] = OpIAdd %[[#int_32]] %[[#ACC0]] %[[#MASK1]]
+
+; Third element of the packed vector
+; CHECK: %[[#A2:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#sixteen]] 8
+; CHECK: %[[#B2:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#sixteen]] 8
+; CHECK: %[[#MUL2:]] = OpIMul %[[#int_32]] %[[#A2]] %[[#B2]]
+; CHECK: %[[#MASK2:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL2]] %[[#zero]] 8
+; CHECK: %[[#ACC2:]] = OpIAdd %[[#int_32]] %[[#ACC1]] %[[#MASK2]]
+
+; Fourth element of the packed vector
+; CHECK: %[[#A3:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#twentyfour]] 8
+; CHECK: %[[#B3:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#twentyfour]] 8
+; CHECK: %[[#MUL3:]] = OpIMul %[[#int_32]] %[[#A3]] %[[#B3]]
+; CHECK: %[[#MASK3:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL3]] %[[#zero]] 8
+; CHECK: %[[#ACC3:]] = OpIAdd %[[#int_32]] %[[#ACC2]] %[[#MASK3]]
+
+; CHECK: OpReturnValue %[[#ACC3]]
+  %spv.dot = call i32 @llvm.spv.dot4add.i8packed(i32 %a, i32 %b, i32 %c)
+  ret i32 %spv.dot
+}