aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/Target/DirectX
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Target/DirectX')
-rw-r--r--llvm/lib/Target/DirectX/DXIL.td19
-rw-r--r--llvm/lib/Target/DirectX/DXILOpBuilder.cpp4
-rw-r--r--llvm/lib/Target/DirectX/DXILOpLowering.cpp60
-rw-r--r--llvm/lib/Target/DirectX/DXILResourceAccess.cpp13
-rw-r--r--llvm/lib/Target/DirectX/DXILWriter/DXILBitcodeWriter.cpp8
5 files changed, 90 insertions, 14 deletions
diff --git a/llvm/lib/Target/DirectX/DXIL.td b/llvm/lib/Target/DirectX/DXIL.td
index 5d865a3..62b5b70 100644
--- a/llvm/lib/Target/DirectX/DXIL.td
+++ b/llvm/lib/Target/DirectX/DXIL.td
@@ -42,8 +42,10 @@ def FloatTy : DXILOpParamType;
def DoubleTy : DXILOpParamType;
def ResRetHalfTy : DXILOpParamType;
def ResRetFloatTy : DXILOpParamType;
+def ResRetDoubleTy : DXILOpParamType;
def ResRetInt16Ty : DXILOpParamType;
def ResRetInt32Ty : DXILOpParamType;
+def ResRetInt64Ty : DXILOpParamType;
def HandleTy : DXILOpParamType;
def ResBindTy : DXILOpParamType;
def ResPropsTy : DXILOpParamType;
@@ -890,6 +892,23 @@ def SplitDouble : DXILOp<102, splitDouble> {
let attributes = [Attributes<DXIL1_0, [ReadNone]>];
}
+def RawBufferLoad : DXILOp<139, rawBufferLoad> {
+ let Doc = "reads from a raw buffer and structured buffer";
+ // Handle, Coord0, Coord1, Mask, Alignment
+ let arguments = [HandleTy, Int32Ty, Int32Ty, Int8Ty, Int32Ty];
+ let result = OverloadTy;
+ let overloads = [
+ Overloads<DXIL1_2,
+ [ResRetHalfTy, ResRetFloatTy, ResRetInt16Ty, ResRetInt32Ty]>,
+ Overloads<DXIL1_3,
+ [
+ ResRetHalfTy, ResRetFloatTy, ResRetDoubleTy, ResRetInt16Ty,
+ ResRetInt32Ty, ResRetInt64Ty
+ ]>
+ ];
+ let stages = [Stages<DXIL1_2, [all_stages]>];
+}
+
def Dot4AddI8Packed : DXILOp<163, dot4AddPacked> {
let Doc = "signed dot product of 4 x i8 vectors packed into i32, with "
"accumulate to i32";
diff --git a/llvm/lib/Target/DirectX/DXILOpBuilder.cpp b/llvm/lib/Target/DirectX/DXILOpBuilder.cpp
index 5d5bb3e..9f88ccd 100644
--- a/llvm/lib/Target/DirectX/DXILOpBuilder.cpp
+++ b/llvm/lib/Target/DirectX/DXILOpBuilder.cpp
@@ -263,10 +263,14 @@ static Type *getTypeFromOpParamType(OpParamType Kind, LLVMContext &Ctx,
return getResRetType(Type::getHalfTy(Ctx));
case OpParamType::ResRetFloatTy:
return getResRetType(Type::getFloatTy(Ctx));
+ case OpParamType::ResRetDoubleTy:
+ return getResRetType(Type::getDoubleTy(Ctx));
case OpParamType::ResRetInt16Ty:
return getResRetType(Type::getInt16Ty(Ctx));
case OpParamType::ResRetInt32Ty:
return getResRetType(Type::getInt32Ty(Ctx));
+ case OpParamType::ResRetInt64Ty:
+ return getResRetType(Type::getInt64Ty(Ctx));
case OpParamType::HandleTy:
return getHandleType(Ctx);
case OpParamType::ResBindTy:
diff --git a/llvm/lib/Target/DirectX/DXILOpLowering.cpp b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
index 4e01dd1..f43815b 100644
--- a/llvm/lib/Target/DirectX/DXILOpLowering.cpp
+++ b/llvm/lib/Target/DirectX/DXILOpLowering.cpp
@@ -415,8 +415,16 @@ public:
}
}
- OldResult = cast<Instruction>(
- IRB.CreateExtractValue(Op, 0, OldResult->getName()));
+ if (OldResult->use_empty()) {
+ // Only the check bit was used, so we're done here.
+ OldResult->eraseFromParent();
+ return Error::success();
+ }
+
+ assert(OldResult->hasOneUse() &&
+ isa<ExtractValueInst>(*OldResult->user_begin()) &&
+ "Expected only use to be extract of first element");
+ OldResult = cast<Instruction>(*OldResult->user_begin());
OldTy = ST->getElementType(0);
}
@@ -534,6 +542,48 @@ public:
});
}
+ [[nodiscard]] bool lowerRawBufferLoad(Function &F) {
+ Triple TT(Triple(M.getTargetTriple()));
+ VersionTuple DXILVersion = TT.getDXILVersion();
+ const DataLayout &DL = F.getDataLayout();
+ IRBuilder<> &IRB = OpBuilder.getIRB();
+ Type *Int8Ty = IRB.getInt8Ty();
+ Type *Int32Ty = IRB.getInt32Ty();
+
+ return replaceFunction(F, [&](CallInst *CI) -> Error {
+ IRB.SetInsertPoint(CI);
+
+ Type *OldTy = cast<StructType>(CI->getType())->getElementType(0);
+ Type *ScalarTy = OldTy->getScalarType();
+ Type *NewRetTy = OpBuilder.getResRetType(ScalarTy);
+
+ Value *Handle =
+ createTmpHandleCast(CI->getArgOperand(0), OpBuilder.getHandleType());
+ Value *Index0 = CI->getArgOperand(1);
+ Value *Index1 = CI->getArgOperand(2);
+ uint64_t NumElements =
+ DL.getTypeSizeInBits(OldTy) / DL.getTypeSizeInBits(ScalarTy);
+ Value *Mask = ConstantInt::get(Int8Ty, ~(~0U << NumElements));
+ Value *Align =
+ ConstantInt::get(Int32Ty, DL.getPrefTypeAlign(ScalarTy).value());
+
+ Expected<CallInst *> OpCall =
+ DXILVersion >= VersionTuple(1, 2)
+ ? OpBuilder.tryCreateOp(OpCode::RawBufferLoad,
+ {Handle, Index0, Index1, Mask, Align},
+ CI->getName(), NewRetTy)
+ : OpBuilder.tryCreateOp(OpCode::BufferLoad,
+ {Handle, Index0, Index1}, CI->getName(),
+ NewRetTy);
+ if (Error E = OpCall.takeError())
+ return E;
+ if (Error E = replaceResRetUses(CI, *OpCall, /*HasCheckBit=*/true))
+ return E;
+
+ return Error::success();
+ });
+ }
+
[[nodiscard]] bool lowerUpdateCounter(Function &F) {
IRBuilder<> &IRB = OpBuilder.getIRB();
Type *Int32Ty = IRB.getInt32Ty();
@@ -723,14 +773,14 @@ public:
HasErrors |= lowerGetPointer(F);
break;
case Intrinsic::dx_resource_load_typedbuffer:
- HasErrors |= lowerTypedBufferLoad(F, /*HasCheckBit=*/false);
- break;
- case Intrinsic::dx_resource_loadchecked_typedbuffer:
HasErrors |= lowerTypedBufferLoad(F, /*HasCheckBit=*/true);
break;
case Intrinsic::dx_resource_store_typedbuffer:
HasErrors |= lowerTypedBufferStore(F);
break;
+ case Intrinsic::dx_resource_load_rawbuffer:
+ HasErrors |= lowerRawBufferLoad(F);
+ break;
case Intrinsic::dx_resource_updatecounter:
HasErrors |= lowerUpdateCounter(F);
break;
diff --git a/llvm/lib/Target/DirectX/DXILResourceAccess.cpp b/llvm/lib/Target/DirectX/DXILResourceAccess.cpp
index 1ff8f09..8376249 100644
--- a/llvm/lib/Target/DirectX/DXILResourceAccess.cpp
+++ b/llvm/lib/Target/DirectX/DXILResourceAccess.cpp
@@ -30,6 +30,9 @@ static void replaceTypedBufferAccess(IntrinsicInst *II,
"Unexpected typed buffer type");
Type *ContainedType = HandleType->getTypeParameter(0);
+ Type *LoadType =
+ StructType::get(ContainedType, Type::getInt1Ty(II->getContext()));
+
// We need the size of an element in bytes so that we can calculate the offset
// in elements given a total offset in bytes later.
Type *ScalarType = ContainedType->getScalarType();
@@ -81,13 +84,15 @@ static void replaceTypedBufferAccess(IntrinsicInst *II,
// We're storing a scalar, so we need to load the current value and only
// replace the relevant part.
auto *Load = Builder.CreateIntrinsic(
- ContainedType, Intrinsic::dx_resource_load_typedbuffer,
+ LoadType, Intrinsic::dx_resource_load_typedbuffer,
{II->getOperand(0), II->getOperand(1)});
+ auto *Struct = Builder.CreateExtractValue(Load, {0});
+
// If we have an offset from seeing a GEP earlier, use it.
Value *IndexOp = Current.Index
? Current.Index
: ConstantInt::get(Builder.getInt32Ty(), 0);
- V = Builder.CreateInsertElement(Load, V, IndexOp);
+ V = Builder.CreateInsertElement(Struct, V, IndexOp);
} else {
llvm_unreachable("Store to typed resource has invalid type");
}
@@ -101,8 +106,10 @@ static void replaceTypedBufferAccess(IntrinsicInst *II,
} else if (auto *LI = dyn_cast<LoadInst>(Current.Access)) {
IRBuilder<> Builder(LI);
Value *V = Builder.CreateIntrinsic(
- ContainedType, Intrinsic::dx_resource_load_typedbuffer,
+ LoadType, Intrinsic::dx_resource_load_typedbuffer,
{II->getOperand(0), II->getOperand(1)});
+ V = Builder.CreateExtractValue(V, {0});
+
if (Current.Index)
V = Builder.CreateExtractElement(V, Current.Index);
diff --git a/llvm/lib/Target/DirectX/DXILWriter/DXILBitcodeWriter.cpp b/llvm/lib/Target/DirectX/DXILWriter/DXILBitcodeWriter.cpp
index 45aadac..be68d46 100644
--- a/llvm/lib/Target/DirectX/DXILWriter/DXILBitcodeWriter.cpp
+++ b/llvm/lib/Target/DirectX/DXILWriter/DXILBitcodeWriter.cpp
@@ -749,8 +749,8 @@ uint64_t DXILBitcodeWriter::getOptimizationFlags(const Value *V) {
if (PEO->isExact())
Flags |= 1 << bitc::PEO_EXACT;
} else if (const auto *FPMO = dyn_cast<FPMathOperator>(V)) {
- if (FPMO->hasAllowReassoc())
- Flags |= bitc::AllowReassoc;
+ if (FPMO->hasAllowReassoc() || FPMO->hasAllowContract())
+ Flags |= bitc::UnsafeAlgebra;
if (FPMO->hasNoNaNs())
Flags |= bitc::NoNaNs;
if (FPMO->hasNoInfs())
@@ -759,10 +759,6 @@ uint64_t DXILBitcodeWriter::getOptimizationFlags(const Value *V) {
Flags |= bitc::NoSignedZeros;
if (FPMO->hasAllowReciprocal())
Flags |= bitc::AllowReciprocal;
- if (FPMO->hasAllowContract())
- Flags |= bitc::AllowContract;
- if (FPMO->hasApproxFunc())
- Flags |= bitc::ApproxFunc;
}
return Flags;
generated by cgit v1.1 at 2025-09-27 16:09:46 +0000