[llvm] [SPIRV]Added support for extension SPV_INTEL_arbitrary_precision_fixed_point (PR #136085)
Aadesh Premkumar via llvm-commits
llvm-commits at lists.llvm.org
Tue May 13 00:00:18 PDT 2025
https://github.com/aadeshps-mcw updated https://github.com/llvm/llvm-project/pull/136085
>From 6fb0d9c8ad5040072c037e7d77fc346a13d65a4c Mon Sep 17 00:00:00 2001
From: Aadesh PremKumar <aadesh.premkumar at multicorewareinc.com>
Date: Tue, 13 May 2025 11:59:12 +0530
Subject: [PATCH] --Updated the test file
---
llvm/docs/SPIRVUsage.rst | 2 +
llvm/lib/Target/SPIRV/SPIRVBuiltins.cpp | 76 +++++-
llvm/lib/Target/SPIRV/SPIRVBuiltins.td | 14 +
llvm/lib/Target/SPIRV/SPIRVCommandLine.cpp | 5 +-
llvm/lib/Target/SPIRV/SPIRVInstrInfo.td | 24 ++
llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp | 21 ++
.../lib/Target/SPIRV/SPIRVSymbolicOperands.td | 2 +
...arbitrary-precision-fixed-point-numbers.ll | 255 ++++++++++++++++++
8 files changed, 397 insertions(+), 2 deletions(-)
create mode 100644 llvm/test/CodeGen/SPIRV/extensions/SPV_INTEL_arbitrary_precision_fixed_point/capability-arbitrary-precision-fixed-point-numbers.ll
diff --git a/llvm/docs/SPIRVUsage.rst b/llvm/docs/SPIRVUsage.rst
index 6ff8034cac00c..7faa3b7ab2023 100644
--- a/llvm/docs/SPIRVUsage.rst
+++ b/llvm/docs/SPIRVUsage.rst
@@ -213,6 +213,8 @@ list of supported SPIR-V extensions, sorted alphabetically by their extension na
- Adds a bitwise instruction on three operands and a look-up table index for specifying the bitwise operation to perform.
* - ``SPV_INTEL_subgroup_matrix_multiply_accumulate``
- Adds an instruction to compute the matrix product of an M x K matrix with a K x N matrix and then add an M x N matrix.
+ * - ``SPV_INTEL_arbitrary_precision_fixed_point``
+ - Add instructions for fixed point arithmetic. The extension works without SPV_INTEL_arbitrary_precision_integers, but together they allow greater flexibility in representing arbitrary precision data types.
To enable multiple extensions, list them separated by comma. For example, to enable support for atomic operations on floating-point numbers and arbitrary precision integers, use:
diff --git a/llvm/lib/Target/SPIRV/SPIRVBuiltins.cpp b/llvm/lib/Target/SPIRV/SPIRVBuiltins.cpp
index c516be0297e66..71ee4776d8b7e 100644
--- a/llvm/lib/Target/SPIRV/SPIRVBuiltins.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVBuiltins.cpp
@@ -697,7 +697,8 @@ static bool buildAtomicStoreInst(const SPIRV::IncomingCall *Call,
MachineIRBuilder &MIRBuilder,
SPIRVGlobalRegistry *GR) {
if (Call->isSpirvOp())
- return buildOpFromWrapper(MIRBuilder, SPIRV::OpAtomicStore, Call, Register(0));
+ return buildOpFromWrapper(MIRBuilder, SPIRV::OpAtomicStore, Call,
+ Register(0));
Register ScopeRegister =
buildConstantIntReg32(SPIRV::Scope::Device, MIRBuilder, GR);
@@ -2307,6 +2308,77 @@ static bool generateBindlessImageINTELInst(const SPIRV::IncomingCall *Call,
return buildBindlessImageINTELInst(Call, Opcode, MIRBuilder, GR);
}
+static bool buildAPFixedPointInst(const SPIRV::IncomingCall *Call,
+ unsigned Opcode, MachineIRBuilder &MIRBuilder,
+ SPIRVGlobalRegistry *GR) {
+ MachineRegisterInfo *MRI = MIRBuilder.getMRI();
+ SmallVector<uint32_t, 1> ImmArgs;
+ Register InputReg = Call->Arguments[0];
+ const Type *RetTy = GR->getTypeForSPIRVType(Call->ReturnType);
+ bool IsSRet = RetTy->isVoidTy();
+
+ if (IsSRet) {
+ const LLT ValTy = MRI->getType(InputReg);
+ Register ActualRetValReg = MRI->createGenericVirtualRegister(ValTy);
+ SPIRVType *InstructionType =
+ GR->getPointeeType(GR->getSPIRVTypeForVReg(InputReg));
+ InputReg = Call->Arguments[1];
+ auto InputType = GR->getTypeForSPIRVType(GR->getSPIRVTypeForVReg(InputReg));
+ Register PtrInputReg;
+ if (InputType->getTypeID() == llvm::Type::TypeID::TypedPointerTyID) {
+ LLT InputLLT = MRI->getType(InputReg);
+ PtrInputReg = MRI->createGenericVirtualRegister(InputLLT);
+ SPIRVType *PtrType =
+ GR->getPointeeType(GR->getSPIRVTypeForVReg(InputReg));
+ MachineMemOperand *MMO1 = MIRBuilder.getMF().getMachineMemOperand(
+ MachinePointerInfo(), MachineMemOperand::MOLoad,
+ InputLLT.getSizeInBytes(), Align(4));
+ MIRBuilder.buildLoad(PtrInputReg, InputReg, *MMO1);
+ MRI->setRegClass(PtrInputReg, &SPIRV::iIDRegClass);
+ GR->assignSPIRVTypeToVReg(PtrType, PtrInputReg, MIRBuilder.getMF());
+ }
+
+ for (unsigned index = 2; index < 7; index++) {
+ ImmArgs.push_back(getConstFromIntrinsic(Call->Arguments[index], MRI));
+ }
+
+ // Emit the instruction
+ auto MIB = MIRBuilder.buildInstr(Opcode)
+ .addDef(ActualRetValReg)
+ .addUse(GR->getSPIRVTypeID(InstructionType));
+ if (PtrInputReg)
+ MIB.addUse(PtrInputReg);
+ else
+ MIB.addUse(InputReg);
+
+ for (uint32_t Imm : ImmArgs)
+ MIB.addImm(Imm);
+ unsigned Size = ValTy.getSizeInBytes();
+ // Store result to the pointer passed in Arg[0]
+ MachineMemOperand *MMO = MIRBuilder.getMF().getMachineMemOperand(
+ MachinePointerInfo(), MachineMemOperand::MOStore, Size, Align(4));
+ MRI->setRegClass(ActualRetValReg, &SPIRV::pIDRegClass);
+ MIRBuilder.buildStore(ActualRetValReg, Call->Arguments[0], *MMO);
+ return true;
+ } else {
+ for (unsigned index = 1; index < 6; index++)
+ ImmArgs.push_back(getConstFromIntrinsic(Call->Arguments[index], MRI));
+
+ return buildOpFromWrapper(MIRBuilder, Opcode, Call,
+ GR->getSPIRVTypeID(Call->ReturnType), ImmArgs);
+ }
+}
+
+static bool generateAPFixedPointInst(const SPIRV::IncomingCall *Call,
+ MachineIRBuilder &MIRBuilder,
+ SPIRVGlobalRegistry *GR) {
+ const SPIRV::DemangledBuiltin *Builtin = Call->Builtin;
+ unsigned Opcode =
+ SPIRV::lookupNativeBuiltin(Builtin->Name, Builtin->Set)->Opcode;
+
+ return buildAPFixedPointInst(Call, Opcode, MIRBuilder, GR);
+}
+
static bool
generateTernaryBitwiseFunctionINTELInst(const SPIRV::IncomingCall *Call,
MachineIRBuilder &MIRBuilder,
@@ -2900,6 +2972,8 @@ std::optional<bool> lowerBuiltin(const StringRef DemangledCall,
return generateExtendedBitOpsInst(Call.get(), MIRBuilder, GR);
case SPIRV::BindlessINTEL:
return generateBindlessImageINTELInst(Call.get(), MIRBuilder, GR);
+ case SPIRV::ArbitraryPrecisionFixedPoint:
+ return generateAPFixedPointInst(Call.get(), MIRBuilder, GR);
case SPIRV::TernaryBitwiseINTEL:
return generateTernaryBitwiseFunctionINTELInst(Call.get(), MIRBuilder, GR);
}
diff --git a/llvm/lib/Target/SPIRV/SPIRVBuiltins.td b/llvm/lib/Target/SPIRV/SPIRVBuiltins.td
index 59cd38126cc01..4a84369cb1d02 100644
--- a/llvm/lib/Target/SPIRV/SPIRVBuiltins.td
+++ b/llvm/lib/Target/SPIRV/SPIRVBuiltins.td
@@ -68,6 +68,7 @@ def ICarryBorrow : BuiltinGroup;
def ExtendedBitOps : BuiltinGroup;
def BindlessINTEL : BuiltinGroup;
def TernaryBitwiseINTEL : BuiltinGroup;
+def ArbitraryPrecisionFixedPoint : BuiltinGroup;
//===----------------------------------------------------------------------===//
// Class defining a demangled builtin record. The information in the record
@@ -1136,6 +1137,19 @@ defm : DemangledNativeBuiltin<"clock_read_hilo_device", OpenCL_std, KernelClock,
defm : DemangledNativeBuiltin<"clock_read_hilo_work_group", OpenCL_std, KernelClock, 0, 0, OpReadClockKHR>;
defm : DemangledNativeBuiltin<"clock_read_hilo_sub_group", OpenCL_std, KernelClock, 0, 0, OpReadClockKHR>;
+//SPV_INTEL_arbitrary_precision_fixed_point
+defm : DemangledNativeBuiltin<"__spirv_FixedSqrtINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedSqrtINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedRecipINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedRecipINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedRsqrtINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedRsqrtINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedSinINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedSinINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedCosINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedCosINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedSinCosINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedSinCosINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedSinPiINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedSinPiINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedCosPiINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedCosPiINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedSinCosPiINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedSinCosPiINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedLogINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedLogINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_FixedExpINTEL", OpenCL_std, ArbitraryPrecisionFixedPoint, 6 , 8, OpFixedExpINTEL>;
+
//===----------------------------------------------------------------------===//
// Class defining an atomic instruction on floating-point numbers.
//
diff --git a/llvm/lib/Target/SPIRV/SPIRVCommandLine.cpp b/llvm/lib/Target/SPIRV/SPIRVCommandLine.cpp
index 56cbd9414c9ee..9b16c86cb0de2 100644
--- a/llvm/lib/Target/SPIRV/SPIRVCommandLine.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVCommandLine.cpp
@@ -97,7 +97,10 @@ static const std::map<std::string, SPIRV::Extension::Extension, std::less<>>
SPIRV::Extension::Extension::
SPV_INTEL_subgroup_matrix_multiply_accumulate},
{"SPV_INTEL_ternary_bitwise_function",
- SPIRV::Extension::Extension::SPV_INTEL_ternary_bitwise_function}};
+ SPIRV::Extension::Extension::SPV_INTEL_ternary_bitwise_function},
+ {"SPV_INTEL_arbitrary_precision_fixed_point",
+ SPIRV::Extension::Extension::
+ SPV_INTEL_arbitrary_precision_fixed_point}};
bool SPIRVExtensionsParser::parse(cl::Option &O, StringRef ArgName,
StringRef ArgValue,
diff --git a/llvm/lib/Target/SPIRV/SPIRVInstrInfo.td b/llvm/lib/Target/SPIRV/SPIRVInstrInfo.td
index 6d8c84945d7d4..4cbed1e0de7dc 100644
--- a/llvm/lib/Target/SPIRV/SPIRVInstrInfo.td
+++ b/llvm/lib/Target/SPIRV/SPIRVInstrInfo.td
@@ -936,3 +936,27 @@ def OpAliasScopeListDeclINTEL: Op<5913, (outs ID:$res), (ins variable_ops),
// SPV_INTEL_ternary_bitwise_function
def OpBitwiseFunctionINTEL: Op<6242, (outs ID:$res), (ins TYPE:$type, ID:$a, ID:$b, ID:$c, ID:$lut_index),
"$res = OpBitwiseFunctionINTEL $type $a $b $c $lut_index">;
+
+//SPV_INTEL_arbitrary_precision_fixed_point
+def OpFixedSqrtINTEL: Op<5923, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedSqrtINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedRecipINTEL: Op<5924, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedRecipINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedRsqrtINTEL: Op<5925, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedRsqrtINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedSinINTEL: Op<5926, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedSinINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedCosINTEL: Op<5927, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedCosINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedSinCosINTEL: Op<5928, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedSinCosINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedSinPiINTEL: Op<5929, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedSinPiINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedCosPiINTEL: Op<5930, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedCosPiINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedSinCosPiINTEL: Op<5931, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedSinCosPiINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedLogINTEL: Op<5932, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedLogINTEL $result_type $input $sign $l $rl $q $o">;
+def OpFixedExpINTEL: Op<5933, (outs ID:$res), (ins TYPE:$result_type, ID:$input, i32imm:$sign, i32imm:$l, i32imm:$rl, i32imm:$q, i32imm:$o),
+ "$res = OpFixedExpINTEL $result_type $input $sign $l $rl $q $o">;
\ No newline at end of file
diff --git a/llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp b/llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp
index 6d2ecd563d200..4267b4478c9e8 100644
--- a/llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp
@@ -1516,6 +1516,27 @@ void addInstrRequirements(const MachineInstr &MI,
Reqs.addCapability(SPIRV::Capability::GroupNonUniformRotateKHR);
Reqs.addCapability(SPIRV::Capability::GroupNonUniform);
break;
+ case SPIRV::OpFixedCosINTEL:
+ case SPIRV::OpFixedSinINTEL:
+ case SPIRV::OpFixedCosPiINTEL:
+ case SPIRV::OpFixedSinPiINTEL:
+ case SPIRV::OpFixedExpINTEL:
+ case SPIRV::OpFixedLogINTEL:
+ case SPIRV::OpFixedRecipINTEL:
+ case SPIRV::OpFixedSqrtINTEL:
+ case SPIRV::OpFixedSinCosINTEL:
+ case SPIRV::OpFixedSinCosPiINTEL:
+ case SPIRV::OpFixedRsqrtINTEL:
+ if (!ST.canUseExtension(
+ SPIRV::Extension::SPV_INTEL_arbitrary_precision_fixed_point))
+ report_fatal_error("This instruction requires the "
+ "following SPIR-V extension: "
+ "SPV_INTEL_arbitrary_precision_fixed_point",
+ false);
+ Reqs.addExtension(
+ SPIRV::Extension::SPV_INTEL_arbitrary_precision_fixed_point);
+ Reqs.addCapability(SPIRV::Capability::ArbitraryPrecisionFixedPointINTEL);
+ break;
case SPIRV::OpGroupIMulKHR:
case SPIRV::OpGroupFMulKHR:
case SPIRV::OpGroupBitwiseAndKHR:
diff --git a/llvm/lib/Target/SPIRV/SPIRVSymbolicOperands.td b/llvm/lib/Target/SPIRV/SPIRVSymbolicOperands.td
index cc32200a0a261..48a7f1b993d83 100644
--- a/llvm/lib/Target/SPIRV/SPIRVSymbolicOperands.td
+++ b/llvm/lib/Target/SPIRV/SPIRVSymbolicOperands.td
@@ -315,6 +315,7 @@ defm SPV_INTEL_memory_access_aliasing : ExtensionOperand<118>;
defm SPV_INTEL_fp_max_error : ExtensionOperand<119>;
defm SPV_INTEL_ternary_bitwise_function : ExtensionOperand<120>;
defm SPV_INTEL_subgroup_matrix_multiply_accumulate : ExtensionOperand<121>;
+defm SPV_INTEL_arbitrary_precision_fixed_point : ExtensionOperand<122>;
//===----------------------------------------------------------------------===//
// Multiclass used to define Capabilities enum values and at the same time
@@ -517,6 +518,7 @@ defm MemoryAccessAliasingINTEL : CapabilityOperand<5910, 0, 0, [SPV_INTEL_memory
defm FPMaxErrorINTEL : CapabilityOperand<6169, 0, 0, [SPV_INTEL_fp_max_error], []>;
defm TernaryBitwiseFunctionINTEL : CapabilityOperand<6241, 0, 0, [SPV_INTEL_ternary_bitwise_function], []>;
defm SubgroupMatrixMultiplyAccumulateINTEL : CapabilityOperand<6236, 0, 0, [SPV_INTEL_subgroup_matrix_multiply_accumulate], []>;
+defm ArbitraryPrecisionFixedPointINTEL : CapabilityOperand<5922, 0, 0, [SPV_INTEL_arbitrary_precision_fixed_point], []>;
//===----------------------------------------------------------------------===//
// Multiclass used to define SourceLanguage enum values and at the same time
diff --git a/llvm/test/CodeGen/SPIRV/extensions/SPV_INTEL_arbitrary_precision_fixed_point/capability-arbitrary-precision-fixed-point-numbers.ll b/llvm/test/CodeGen/SPIRV/extensions/SPV_INTEL_arbitrary_precision_fixed_point/capability-arbitrary-precision-fixed-point-numbers.ll
new file mode 100644
index 0000000000000..0e003d217ace7
--- /dev/null
+++ b/llvm/test/CodeGen/SPIRV/extensions/SPV_INTEL_arbitrary_precision_fixed_point/capability-arbitrary-precision-fixed-point-numbers.ll
@@ -0,0 +1,255 @@
+; RUN: llc -verify-machineinstrs -O0 -mtriple=spirv64-unknown-unknown --spirv-ext=+SPV_INTEL_arbitrary_precision_fixed_point,+SPV_INTEL_arbitrary_precision_integers %s -o - | FileCheck %s
+; TODO: %if spirv-tools %{ llc -O0 -mtriple=spirv64-unknown-unknown --spirv-ext=+SPV_INTEL_arbitrary_precision_fixed_point,+SPV_INTEL_arbitrary_precision_integers %s -o - -filetype=obj | spirv-val %}
+
+
+; CHECK-DAG: OpCapability Kernel
+; CHECK-DAG: OpCapability ArbitraryPrecisionIntegersINTEL
+; CHECK-DAG: OpCapability ArbitraryPrecisionFixedPointINTEL
+; CHECK-DAG: OpExtension "SPV_INTEL_arbitrary_precision_fixed_point"
+; CHECK-DAG: OpExtension "SPV_INTEL_arbitrary_precision_integers"
+
+; CHECK-DAG: %[[Ty_8:[0-9]+]] = OpTypeInt 8 0
+; CHECK-DAG: %[[Ty_13:[0-9]+]] = OpTypeInt 13 0
+; CHECK-DAG: %[[Ty_5:[0-9]+]] = OpTypeInt 5 0
+; CHECK-DAG: %[[Ty_3:[0-9]+]] = OpTypeInt 3 0
+; CHECK-DAG: %[[Ty_11:[0-9]+]] = OpTypeInt 11 0
+; CHECK-DAG: %[[Ty_10:[0-9]+]] = OpTypeInt 10 0
+; CHECK-DAG: %[[Ty_17:[0-9]+]] = OpTypeInt 17 0
+; CHECK-DAG: %[[Ty_35:[0-9]+]] = OpTypeInt 35 0
+; CHECK-DAG: %[[Ty_28:[0-9]+]] = OpTypeInt 28 0
+; CHECK-DAG: %[[Ty_31:[0-9]+]] = OpTypeInt 31 0
+; CHECK-DAG: %[[Ty_40:[0-9]+]] = OpTypeInt 40 0
+; CHECK-DAG: %[[Ty_60:[0-9]+]] = OpTypeInt 60 0
+; CHECK-DAG: %[[Ty_16:[0-9]+]] = OpTypeInt 16 0
+; CHECK-DAG: %[[Ty_64:[0-9]+]] = OpTypeInt 64 0
+; CHECK-DAG: %[[Ty_44:[0-9]+]] = OpTypeInt 44 0
+; CHECK-DAG: %[[Ty_34:[0-9]+]] = OpTypeInt 34 0
+; CHECK-DAG: %[[Ty_51:[0-9]+]] = OpTypeInt 51 0
+
+; CHECK: %[[Sqrt_InId:[0-9]+]] = OpLoad %[[Ty_13]]
+; CHECK-NEXT: %[[#]] = OpFixedSqrtINTEL %[[Ty_5]] %[[Sqrt_InId]] 0 2 2 0 0
+
+; CHECK: %[[Recip_InId:[0-9]+]] = OpLoad %[[Ty_3]]
+; CHECK-NEXT: %[[#]] = OpFixedRecipINTEL %[[Ty_8]] %[[Recip_InId]] 1 4 4 0 0
+
+; CHECK: %[[Rsqrt_InId:[0-9]+]] = OpLoad %[[Ty_11]]
+; CHECK-NEXT: %[[#]] = OpFixedRsqrtINTEL %[[Ty_10]] %[[Rsqrt_InId]] 0 8 6 0 0
+
+; CHECK: %[[Sin_InId:[0-9]+]] = OpLoad %[[Ty_17]]
+; CHECK-NEXT: %[[#]] = OpFixedSinINTEL %[[Ty_11]] %[[Sin_InId]] 1 7 5 0 0
+
+; CHECK: %[[Cos_InId:[0-9]+]] = OpLoad %[[Ty_35]]
+; CHECK-NEXT: %[[#]] = OpFixedCosINTEL %[[Ty_28]] %[[Cos_InId]] 0 9 3 0 0
+
+; CHECK: %[[SinCos_InId:[0-9]+]] = OpLoad %[[Ty_31]]
+; CHECK-NEXT: %[[#]] = OpFixedSinCosINTEL %[[Ty_40]] %[[SinCos_InId]] 1 10 12 0 0
+
+; CHECK: %[[SinPi_InId:[0-9]+]] = OpLoad %[[Ty_60]]
+; CHECK-NEXT: %[[#]] = OpFixedSinPiINTEL %[[Ty_5]] %[[SinPi_InId]] 0 2 2 0 0
+
+; CHECK: %[[CosPi_InId:[0-9]+]] = OpLoad %[[Ty_28]]
+; CHECK-NEXT: %[[#]] = OpFixedCosPiINTEL %[[Ty_16]] %[[CosPi_InId]] 0 8 5 0 0
+
+; CHECK: %[[SinCosPi_InId:[0-9]+]] = OpLoad %[[Ty_13]]
+; CHECK-NEXT: %[[#]] = OpFixedSinCosPiINTEL %[[Ty_10]] %[[SinCosPi_InId]] 0 2 2 0 0
+
+; CHECK: %[[Log_InId:[0-9]+]] = OpLoad %[[Ty_64]]
+; CHECK-NEXT: %[[#]] = OpFixedLogINTEL %[[Ty_44]] %[[Log_InId]] 1 24 22 0 0
+
+; CHECK: %[[Exp_InId:[0-9]+]] = OpLoad %[[Ty_44]]
+; CHECK-NEXT: %[[#]] = OpFixedExpINTEL %[[Ty_34]] %[[Exp_InId]] 0 20 20 0 0
+
+; CHECK: %[[SinCos_InId:[0-9]+]] = OpLoad %[[Ty_34]]
+; CHECK-NEXT: %[[SinCos_ResultId:[0-9]+]] = OpFixedSinCosINTEL %[[Ty_51]] %[[SinCos_InId]] 1 3 2 0 0
+; CHECK-NEXT: OpStore %[[#]] %[[SinCos_ResultId]]
+
+; CHECK: %[[ResId:[0-9]+]] = OpLoad %[[Ty_51]]
+; CHECK-NEXT: OpStore %[[PtrId:[0-9]+]] %[[ResId]]
+; CHECK-NEXT: %[[ExpInId2:[0-9]+]] = OpLoad %[[Ty_51]] %[[PtrId]]
+; CHECK-NEXT: %[[#]] = OpFixedExpINTEL %[[Ty_51]] %[[ExpInId2]] 0 20 20 0 0
+
+%"class._ZTSZ4mainE3$_0.anon" = type { i8 }
+
+define dso_local spir_kernel void @_ZTSZ4mainE15kernel_function() !kernel_arg_addr_space !{} !kernel_arg_access_qual !{} !kernel_arg_type !{} !kernel_arg_base_type !{} !kernel_arg_type_qual !{} {
+entry:
+ %0 = alloca %"class._ZTSZ4mainE3$_0.anon", align 1
+ %1 = addrspacecast ptr %0 to ptr addrspace(4)
+ call spir_func void @"_ZZ4mainENK3$_0clEv"(ptr addrspace(4) %1)
+ ret void
+}
+
+define internal spir_func void @"_ZZ4mainENK3$_0clEv"(ptr addrspace(4) %this) align 2 {
+entry:
+ %this.addr = alloca ptr addrspace(4), align 8
+ store ptr addrspace(4) %this, ptr %this.addr, align 8
+ call spir_func void @_Z4sqrtILi13ELi5ELb0ELi2ELi2EEvv()
+ call spir_func void @_Z5recipILi3ELi8ELb1ELi4ELi4EEvv()
+ call spir_func void @_Z5rsqrtILi11ELi10ELb0ELi8ELi6EEvv()
+ call spir_func void @_Z3sinILi17ELi11ELb1ELi7ELi5EEvv()
+ call spir_func void @_Z3cosILi35ELi28ELb0ELi9ELi3EEvv()
+ call spir_func void @_Z7sin_cosILi31ELi20ELb1ELi10ELi12EEvv()
+ call spir_func void @_Z6sin_piILi60ELi5ELb0ELi2ELi2EEvv()
+ call spir_func void @_Z6cos_piILi28ELi16ELb0ELi8ELi5EEvv()
+ call spir_func void @_Z10sin_cos_piILi13ELi5ELb0ELi2ELi2EEvv()
+ call spir_func void @_Z3logILi64ELi44ELb1ELi24ELi22EEvv()
+ call spir_func void @_Z3expILi44ELi34ELb0ELi20ELi20EEvv()
+ call spir_func void @_Z7sin_cosILi31ELi20ELb1ELi10ELi12EEvv_()
+ call spir_func void @_Z3expILi51ELi51ELb0ELi20ELi20EEvv()
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z4sqrtILi13ELi5ELb0ELi2ELi2EEvv() {
+entry:
+ %in_ptr = alloca i13, align 2
+ %out_ptr = alloca i5, align 1
+ %in_val = load i13, ptr %in_ptr, align 2
+ %res = call spir_func signext i5 @_Z22__spirv_FixedSqrtINTELILi13ELi5EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i13 signext %in_val, i1 zeroext false, i32 2, i32 2, i32 0, i32 0)
+ store i5 %res, ptr %out_ptr, align 1
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z5recipILi3ELi8ELb1ELi4ELi4EEvv() {
+entry:
+ %in_ptr = alloca i3, align 1
+ %out_ptr = alloca i8, align 1
+ %in_val = load i3, ptr %in_ptr, align 1
+ %res = call spir_func signext i8 @_Z23__spirv_FixedRecipINTELILi3ELi8EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i3 signext %in_val, i1 zeroext true, i32 4, i32 4, i32 0, i32 0)
+ store i8 %res, ptr %out_ptr, align 1
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z5rsqrtILi11ELi10ELb0ELi8ELi6EEvv() {
+entry:
+ %in_ptr = alloca i11, align 2
+ %out_ptr = alloca i10, align 2
+ %in_val = load i11, ptr %in_ptr, align 2
+ %res = call spir_func signext i10 @_Z23__spirv_FixedRsqrtINTELILi11ELi10EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i11 signext %in_val, i1 zeroext false, i32 8, i32 6, i32 0, i32 0)
+ store i10 %res, ptr %out_ptr, align 2
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z3sinILi17ELi11ELb1ELi7ELi5EEvv() {
+entry:
+ %in_ptr = alloca i17, align 4
+ %out_ptr = alloca i11, align 2
+ %in_val = load i17, ptr %in_ptr, align 4
+ %res = call spir_func signext i11 @_Z21__spirv_FixedSinINTELILi17ELi11EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i17 signext %in_val, i1 zeroext true, i32 7, i32 5, i32 0, i32 0)
+ store i11 %res, ptr %out_ptr, align 2
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z3cosILi35ELi28ELb0ELi9ELi3EEvv() {
+entry:
+ %in_ptr = alloca i35, align 8
+ %out_ptr = alloca i28, align 4
+ %in_val = load i35, ptr %in_ptr, align 8
+ %res = call spir_func signext i28 @_Z21__spirv_FixedCosINTELILi35ELi28EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i35 signext %in_val, i1 zeroext false, i32 9, i32 3, i32 0, i32 0)
+ store i28 %res, ptr %out_ptr, align 4
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z7sin_cosILi31ELi20ELb1ELi10ELi12EEvv() {
+entry:
+ %in_ptr = alloca i31, align 4
+ %out_ptr = alloca i40, align 8
+ %in_val = load i31, ptr %in_ptr, align 4
+ %res = call spir_func i40 @_Z24__spirv_FixedSinCosINTELILi31ELi20EEU7_ExtIntIXmlLi2ET0_EEiU7_ExtIntIXT_EEibiiii(i31 signext %in_val, i1 zeroext true, i32 10, i32 12, i32 0, i32 0)
+ store i40 %res, ptr %out_ptr, align 8
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z6sin_piILi60ELi5ELb0ELi2ELi2EEvv() {
+entry:
+ %in_ptr = alloca i60, align 8
+ %out_ptr = alloca i5, align 1
+ %in_val = load i60, ptr %in_ptr, align 8
+ %res = call spir_func signext i5 @_Z23__spirv_FixedSinPiINTELILi60ELi5EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i60 signext %in_val, i1 zeroext false, i32 2, i32 2, i32 0, i32 0)
+ store i5 %res, ptr %out_ptr, align 1
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z6cos_piILi28ELi16ELb0ELi8ELi5EEvv() {
+entry:
+ %in_ptr = alloca i28, align 4
+ %out_ptr = alloca i16, align 2
+ %in_val = load i28, ptr %in_ptr, align 4
+ %res = call spir_func signext i16 @_Z23__spirv_FixedCosPiINTELILi28ELi16EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i28 signext %in_val, i1 zeroext false, i32 8, i32 5, i32 0, i32 0)
+ store i16 %res, ptr %out_ptr, align 2
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z10sin_cos_piILi13ELi5ELb0ELi2ELi2EEvv() {
+entry:
+ %in_ptr = alloca i13, align 2
+ %out_ptr = alloca i10, align 2
+ %in_val = load i13, ptr %in_ptr, align 2
+ %res = call spir_func signext i10 @_Z26__spirv_FixedSinCosPiINTELILi13ELi5EEU7_ExtIntIXmlLi2ET0_EEiU7_ExtIntIXT_EEibiiii(i13 signext %in_val, i1 zeroext false, i32 2, i32 2, i32 0, i32 0)
+ store i10 %res, ptr %out_ptr, align 2
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z3logILi64ELi44ELb1ELi24ELi22EEvv() {
+entry:
+ %in_ptr = alloca i64, align 8
+ %out_ptr = alloca i44, align 8
+ %in_val = load i64, ptr %in_ptr, align 8
+ %res = call spir_func i44 @_Z21__spirv_FixedLogINTELILi64ELi44EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i64 %in_val, i1 zeroext true, i32 24, i32 22, i32 0, i32 0)
+ store i44 %res, ptr %out_ptr, align 8
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z3expILi44ELi34ELb0ELi20ELi20EEvv() {
+entry:
+ %in_ptr = alloca i44, align 8
+ %out_ptr = alloca i34, align 8
+ %in_val = load i44, ptr %in_ptr, align 8
+ %res = call spir_func i34 @_Z21__spirv_FixedExpINTELILi44ELi34EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i44 %in_val, i1 zeroext false, i32 20, i32 20, i32 0, i32 0)
+ store i34 %res, ptr %out_ptr, align 8
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z7sin_cosILi31ELi20ELb1ELi10ELi12EEvv_() {
+entry:
+ %tmp = alloca i34, align 8
+ %out_ptr = alloca i51, align 8
+ %in_ptr = addrspacecast ptr %tmp to ptr addrspace(4)
+ %out_s = addrspacecast ptr %out_ptr to ptr addrspace(4)
+ %in_val = load i34, ptr addrspace(4) %in_ptr, align 8
+ call spir_func void @_Z24__spirv_FixedSinCosINTELILi34ELi51EEU7_ExtIntIXmlLi2ET0_EEiU7_ExtIntIXT_EEibiiii(ptr addrspace(4) sret(i51) align 8 %out_s, i34 %in_val, i1 zeroext true, i32 3, i32 2, i32 0, i32 0)
+ ret void
+}
+
+define linkonce_odr dso_local spir_func void @_Z3expILi51ELi51ELb0ELi20ELi20EEvv() {
+entry:
+ %a = alloca i51, align 8
+ %a.ascast = addrspacecast ptr %a to ptr addrspace(4)
+ %ap_fixed_Exp = alloca i51, align 8
+ %ap_fixed_Exp.ascast = addrspacecast ptr %ap_fixed_Exp to ptr addrspace(4)
+ %tmp = alloca i51, align 8
+ %tmp.ascast = addrspacecast ptr %tmp to ptr addrspace(4)
+ %indirect-arg-temp = alloca i51, align 8
+ %0 = load i51, ptr addrspace(4) %a.ascast, align 8
+ store i51 %0, ptr %indirect-arg-temp, align 8
+ call spir_func void @_Z21__spirv_FixedExpINTELILi51ELi51EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(
+ ptr addrspace(4) sret(i51) align 8 %tmp.ascast,
+ ptr byval(i64) align 8 %indirect-arg-temp,
+ i1 zeroext false, i32 20, i32 20, i32 0, i32 0)
+ %1 = load i51, ptr addrspace(4) %tmp.ascast, align 8
+ store i51 %1, ptr addrspace(4) %ap_fixed_Exp.ascast, align 8
+ ret void
+}
+
+declare dso_local spir_func signext i5 @_Z22__spirv_FixedSqrtINTELILi13ELi5EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i13 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i13 @_Z22__spirv_FixedSqrtINTELILi5ELi13EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i5 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i8 @_Z23__spirv_FixedRecipINTELILi3ELi8EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i3 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i10 @_Z23__spirv_FixedRsqrtINTELILi11ELi10EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i11 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i11 @_Z21__spirv_FixedSinINTELILi17ELi11EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i17 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i28 @_Z21__spirv_FixedCosINTELILi35ELi28EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i35, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func i40 @_Z24__spirv_FixedSinCosINTELILi31ELi20EEU7_ExtIntIXmlLi2ET0_EEiU7_ExtIntIXT_EEibiiii(i31 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i5 @_Z23__spirv_FixedSinPiINTELILi60ELi5EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i60, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i16 @_Z23__spirv_FixedCosPiINTELILi28ELi16EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i28 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func signext i10 @_Z26__spirv_FixedSinCosPiINTELILi13ELi5EEU7_ExtIntIXmlLi2ET0_EEiU7_ExtIntIXT_EEibiiii(i13 signext, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func i44 @_Z21__spirv_FixedLogINTELILi64ELi44EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i64, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func i34 @_Z21__spirv_FixedExpINTELILi44ELi34EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(i44, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func void @_Z24__spirv_FixedSinCosINTELILi34ELi51EEU7_ExtIntIXmlLi2ET0_EEiU7_ExtIntIXT_EEibiiii(ptr addrspace(4) sret(i51) align 8, i34, i1 zeroext, i32, i32, i32, i32)
+declare dso_local spir_func void @_Z21__spirv_FixedExpINTELILi51ELi51EEU7_ExtIntIXT0_EEiU7_ExtIntIXT_EEibiiii(ptr addrspace(4) sret(i51) align 8, ptr byval(i51) align 8, i1 zeroext, i32, i32, i32, i32)
More information about the llvm-commits
mailing list