[SPIRV]Added support for the extension SPV_INTEL_blocking_pipes

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_blocking_pipes``
+     - Adds new pipe read and write functions that have blocking semantics instead of the non-blocking semantics of the existing pipe read/write functions.
 
 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:
 

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);
@@ -2296,6 +2297,19 @@ static bool generateExtendedBitOpsInst(const SPIRV::IncomingCall *Call,
   return buildExtendedBitOpsInst(Call, Opcode, MIRBuilder, GR);
 }
 
+static bool generateBlockingPipesInst(const SPIRV::IncomingCall *Call,
+                                      MachineIRBuilder &MIRBuilder,
+                                      SPIRVGlobalRegistry *GR) {
+  const SPIRV::DemangledBuiltin *Builtin = Call->Builtin;
+  unsigned Opcode =
+      SPIRV::lookupNativeBuiltin(Builtin->Name, Builtin->Set)->Opcode;
+
+  auto MIB = MIRBuilder.buildInstr(Opcode);
+  for (unsigned i = 0; i < Call->Arguments.size(); ++i)
+    MIB.addUse(Call->Arguments[i]);
+  return true;
+}
+
 static bool generateBindlessImageINTELInst(const SPIRV::IncomingCall *Call,
                                            MachineIRBuilder &MIRBuilder,
                                            SPIRVGlobalRegistry *GR) {
@@ -2900,6 +2914,8 @@ std::optional<bool> lowerBuiltin(const StringRef DemangledCall,
     return generateExtendedBitOpsInst(Call.get(), MIRBuilder, GR);
   case SPIRV::BindlessINTEL:
     return generateBindlessImageINTELInst(Call.get(), MIRBuilder, GR);
+  case SPIRV::BlockingPipes:
+    return generateBlockingPipesInst(Call.get(), MIRBuilder, GR);
   case SPIRV::TernaryBitwiseINTEL:
     return generateTernaryBitwiseFunctionINTELInst(Call.get(), MIRBuilder, GR);
   }

llvm/lib/Target/SPIRV/SPIRVBuiltins.td

@@ -68,6 +68,7 @@ def ICarryBorrow : BuiltinGroup;
 def ExtendedBitOps : BuiltinGroup;
 def BindlessINTEL : BuiltinGroup;
 def TernaryBitwiseINTEL : BuiltinGroup;
+def BlockingPipes : BuiltinGroup;
 
 //===----------------------------------------------------------------------===//
 // Class defining a demangled builtin record. The information in the record
@@ -1136,6 +1137,10 @@ 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_blocking_pipes
+defm : DemangledNativeBuiltin<"__spirv_WritePipeBlockingINTEL", OpenCL_std, BlockingPipes, 0, 0, OpWritePipeBlockingINTEL>;
+defm : DemangledNativeBuiltin<"__spirv_ReadPipeBlockingINTEL", OpenCL_std, BlockingPipes, 0, 0, OpReadPipeBlockingINTEL>;
+
 //===----------------------------------------------------------------------===//
 // Class defining an atomic instruction on floating-point numbers.
 //

llvm/lib/Target/SPIRV/SPIRVCommandLine.cpp

@@ -97,7 +97,9 @@ 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_blocking_pipes",
+         SPIRV::Extension::Extension::SPV_INTEL_blocking_pipes}};
 
 bool SPIRVExtensionsParser::parse(cl::Option &O, StringRef ArgName,
                                   StringRef ArgValue,

llvm/lib/Target/SPIRV/SPIRVInstrInfo.td

@@ -936,3 +936,9 @@ 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 $lut_index">;
+
+//SPV_INTEL_blocking_pipes
+def OpReadPipeBlockingINTEL :Op<5946, (outs), (ins ID:$pipe, ID:$pointer, ID:$packetSize, ID:$packetAlignment),
+                   "OpReadPipeBlockingINTEL $pipe $pointer $packetSize $packetAlignment">;
+def OpWritePipeBlockingINTEL :Op<5946, (outs), (ins ID:$pipe, ID:$pointer, ID:$packetSize, ID:$packetAlignment),
+                   "OpWritePipeBlockingINTEL $pipe $pointer $packetSize $packetAlignment">;

llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp

@@ -1719,6 +1719,13 @@ void addInstrRequirements(const MachineInstr &MI,
     Reqs.addCapability(
         SPIRV::Capability::CooperativeMatrixCheckedInstructionsINTEL);
     break;
+  case SPIRV::OpReadPipeBlockingINTEL:
+  case SPIRV::OpWritePipeBlockingINTEL:
+    if (ST.canUseExtension(SPIRV::Extension::SPV_INTEL_blocking_pipes)) {
+      Reqs.addExtension(SPIRV::Extension::SPV_INTEL_blocking_pipes);
+      Reqs.addCapability(SPIRV::Capability::BlockingPipesINTEL);
+    }
+    break;
   case SPIRV::OpCooperativeMatrixGetElementCoordINTEL:
     if (!ST.canUseExtension(SPIRV::Extension::SPV_INTEL_joint_matrix))
       report_fatal_error("OpCooperativeMatrixGetElementCoordINTEL requires the "

llvm/lib/Target/SPIRV/SPIRVSymbolicOperands.td

@@ -515,6 +515,7 @@ defm LongCompositesINTEL : CapabilityOperand<6089, 0, 0, [SPV_INTEL_long_composi
 defm BindlessImagesINTEL : CapabilityOperand<6528, 0, 0, [SPV_INTEL_bindless_images], []>;
 defm MemoryAccessAliasingINTEL : CapabilityOperand<5910, 0, 0, [SPV_INTEL_memory_access_aliasing], []>;
 defm FPMaxErrorINTEL : CapabilityOperand<6169, 0, 0, [SPV_INTEL_fp_max_error], []>;
+defm BlockingPipesINTEL : CapabilityOperand<5945, 0, 0, [SPV_INTEL_blocking_pipes], []>;
 defm TernaryBitwiseFunctionINTEL : CapabilityOperand<6241, 0, 0, [SPV_INTEL_ternary_bitwise_function], []>;
 defm SubgroupMatrixMultiplyAccumulateINTEL : CapabilityOperand<6236, 0, 0, [SPV_INTEL_subgroup_matrix_multiply_accumulate], []>;
 

llvm/test/CodeGen/SPIRV/extensions/SPV_INTEL_blocking_pipes/PipeBlocking.ll

@@ -0,0 +1,114 @@
+; RUN: llc -verify-machineinstrs -O0 -mtriple=spirv32-unknown-unknown --spirv-ext=+SPV_INTEL_blocking_pipes %s -o - | FileCheck %s --check-prefixes=CHECK-SPIRV
+; TODO: %if spirv-tools %{ llc -O0 -mtriple=spirv64-unknown-unknown --spirv-ext=+SPV_INTEL_blocking_pipes %s -o - -filetype=obj | spirv-val %}
+
+%opencl.pipe_ro_t = type opaque
+%opencl.pipe_wo_t = type opaque
+
+; CHECK-SPIRV: OpCapability BlockingPipesINTEL
+; CHECK-SPIRV: OpExtension "SPV_INTEL_blocking_pipes"
+; CHECK-SPIRV: %[[PipeRTy:[0-9]+]] = OpTypePipe ReadOnly
+; CHECK-SPIRV: %[[PipeWTy:[0-9]+]] = OpTypePipe WriteOnly
+; CHECK-SPIRV: %[[PipeR1:[0-9]+]] = OpLoad %[[PipeRTy]] %[[#]] Aligned 8
+; CHECK-SPIRV: OpReadPipeBlockingINTEL %[[PipeR1]] %[[#]] %[[#]] %[[#]]
+; CHECK-SPIRV: %[[PipeR2:[0-9]+]] = OpLoad %[[PipeRTy]] %[[#]] Aligned 8
+; CHECK-SPIRV: OpReadPipeBlockingINTEL %[[PipeR2]] %[[#]]  %[[#]] %[[#]]
+; CHECK-SPIRV: %[[PipeW1:[0-9]+]] = OpLoad %[[PipeWTy]] %[[#]] Aligned 8
+; CHECK-SPIRV: OpWritePipeBlockingINTEL %[[PipeW1]] %[[#]]  %[[#]] %[[#]]
+; CHECK-SPIRV: %[[PipeW2:[0-9]+]] = OpLoad %[[PipeWTy]] %[[#]] Aligned 8
+; CHECK-SPIRV: OpWritePipeBlockingINTEL %[[PipeW2]] %[[#]] %[[#]] %[[#]]
+
+
+; Function Attrs: convergent noinline nounwind optnone
+define spir_func void @foo(target("spirv.Pipe", 0) %p, ptr addrspace(1) %ptr) #0 {
+entry:
+  %p.addr = alloca target("spirv.Pipe", 0), align 8
+  %ptr.addr = alloca ptr addrspace(1), align 8
+  store target("spirv.Pipe", 0) %p, target("spirv.Pipe", 0)* %p.addr, align 8
+  store ptr addrspace(1) %ptr, ptr %ptr.addr, align 8
+  %0 = load target("spirv.Pipe", 0), target("spirv.Pipe", 0)* %p.addr, align 8
+  %1 = load ptr addrspace(1), ptr %ptr.addr, align 8
+  %2 = addrspacecast ptr addrspace(1) %1 to ptr addrspace(4)
+  call spir_func void @_Z29__spirv_ReadPipeBlockingINTELIiEv8ocl_pipePiii(target("spirv.Pipe", 0) %0, ptr addrspace(4) %2, i32 4, i32 4)
+  ret void
+}
+
+declare dso_local spir_func void @_Z29__spirv_ReadPipeBlockingINTELIiEv8ocl_pipePiii(target("spirv.Pipe", 0), ptr addrspace(4), i32, i32)
+
+; Function Attrs: convergent noinline nounwind optnone
+define spir_func void @bar(target("spirv.Pipe", 0) %p, ptr addrspace(1) %ptr) #0 {
+entry:
+  %p.addr = alloca target("spirv.Pipe", 0), align 8
+  %ptr.addr = alloca ptr addrspace(1), align 8
+  store target("spirv.Pipe", 0) %p, target("spirv.Pipe", 0)* %p.addr, align 8
+  store ptr addrspace(1) %ptr, ptr %ptr.addr, align 8
+  %0 = load target("spirv.Pipe", 0), target("spirv.Pipe", 0)* %p.addr, align 8
+  %1 = load ptr addrspace(1), ptr %ptr.addr, align 8
+  %2 = addrspacecast ptr addrspace(1) %1 to ptr addrspace(4)
+  call spir_func void @_Z29__spirv_ReadPipeBlockingINTELIiEv8ocl_pipePvii(target("spirv.Pipe", 0) %0, ptr addrspace(4) %2, i32 4, i32 4)
+  ret void
+}
+
+declare dso_local spir_func void @_Z29__spirv_ReadPipeBlockingINTELIiEv8ocl_pipePvii(target("spirv.Pipe", 0), ptr addrspace(4), i32, i32)
+
+; Function Attrs: convergent noinline nounwind optnone
+define spir_func void @boo(target("spirv.Pipe", 1) %p, ptr addrspace(1) %ptr) #0 {
+entry:
+  %p.addr = alloca target("spirv.Pipe", 1), align 8
+  %ptr.addr = alloca ptr addrspace(1), align 8
+  store target("spirv.Pipe", 1) %p, target("spirv.Pipe", 1)* %p.addr, align 8
+  store ptr addrspace(1) %ptr, ptr %ptr.addr, align 8
+  %0 = load target("spirv.Pipe", 1), target("spirv.Pipe", 1)* %p.addr, align 8
+  %1 = load ptr addrspace(1), ptr %ptr.addr, align 8
+  %2 = addrspacecast ptr addrspace(1) %1 to ptr addrspace(4)
+  call spir_func void @_Z30__spirv_WritePipeBlockingINTELIKiEv8ocl_pipePiii(target("spirv.Pipe", 1) %0, ptr addrspace(4) %2, i32 4, i32 4)
+  ret void
+}
+
+declare dso_local spir_func void @_Z30__spirv_WritePipeBlockingINTELIKiEv8ocl_pipePiii(target("spirv.Pipe", 1), ptr addrspace(4), i32, i32)
+
+; Function Attrs: convergent noinline nounwind optnone
+define spir_func void @baz(target("spirv.Pipe", 1) %p, ptr addrspace(1) %ptr) #0 {
+entry:
+  %p.addr = alloca target("spirv.Pipe", 1), align 8
+  %ptr.addr = alloca ptr addrspace(1), align 8
+  store target("spirv.Pipe", 1) %p, target("spirv.Pipe", 1)* %p.addr, align 8
+  store ptr addrspace(1) %ptr, ptr %ptr.addr, align 8
+  %0 = load target("spirv.Pipe", 1), target("spirv.Pipe", 1)* %p.addr, align 8
+  %1 = load ptr addrspace(1), ptr %ptr.addr, align 8
+  %2 = addrspacecast ptr addrspace(1) %1 to ptr addrspace(4)
+  call spir_func void @_Z30__spirv_WritePipeBlockingINTELIKiEv8ocl_pipePvii(target("spirv.Pipe", 1) %0, ptr addrspace(4) %2, i32 4, i32 4)
+  ret void
+}
+
+declare dso_local spir_func void @_Z30__spirv_WritePipeBlockingINTELIKiEv8ocl_pipePvii(target("spirv.Pipe", 1), ptr addrspace(4), i32, i32)
+
+; CHECK-LLVM: declare spir_func void @__read_pipe_2_bl(ptr addrspace(1), ptr addrspace(4), i32, i32)
+; CHECK-LLVM: declare spir_func void @__write_pipe_2_bl(ptr addrspace(1), ptr addrspace(4), i32, i32)
+
+; Function Attrs: convergent mustprogress norecurse nounwind
+define linkonce_odr dso_local spir_func void @WritePipeBLockingi9Pointer(ptr addrspace(4) align 2 dereferenceable(2) %_Data) {
+entry:
+  %_Data.addr = alloca ptr addrspace(4), align 8
+  %_WPipe = alloca target("spirv.Pipe", 1), align 8
+  %_Data.addr.ascast = addrspacecast ptr %_Data.addr to ptr addrspace(4)
+  %_WPipe.ascast = addrspacecast target("spirv.Pipe", 1)* %_WPipe to target("spirv.Pipe", 1) addrspace(4)*
+  store ptr addrspace(4) %_Data, ptr addrspace(4) %_Data.addr.ascast, align 8
+  %0 = bitcast target("spirv.Pipe", 1)* %_WPipe to ptr
+  %1 = load target("spirv.Pipe", 1), target("spirv.Pipe", 1) addrspace(4)* %_WPipe.ascast, align 8
+  %2 = load ptr addrspace(4), ptr addrspace(4) %_Data.addr.ascast, align 8
+  call spir_func void @_Z30__spirv_WritePipeBlockingINTELIDU9_Ev8ocl_pipePKT_ii(target("spirv.Pipe", 1) %1, ptr addrspace(4) %2, i32 2, i32 2)
+  ret void
+}
+
+declare dso_local spir_func void @_Z30__spirv_WritePipeBlockingINTELIDU9_Ev8ocl_pipePKT_ii(target("spirv.Pipe", 1), ptr addrspace(4), i32, i32)
+
+attributes #0 = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "denorms-are-zero"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0}
+!opencl.ocl.version = !{!1}
+!opencl.spir.version = !{!1}
+!llvm.ident = !{!2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 2, i32 0}
+!2 = !{!"clang version 9.0.0 (https://github.com/MrSidims/llvm.git c627b787284c5bcc917ea9742908baa1b856e176)"}