From 086791eca2260c03c7bbdd37a53626d16656f0ca Mon Sep 17 00:00:00 2001 From: Richard Sandiford Date: Tue, 10 Dec 2013 10:36:34 +0000 Subject: [PATCH] Add TargetLowering::prepareVolatileOrAtomicLoad One unusual feature of the z architecture is that the result of a previous load can be reused indefinitely for subsequent loads, even if a cache-coherent store to that location is performed by another CPU. A special serializing instruction must be used if you want to force a load to be reattempted. Since volatile loads are not supposed to be omitted in this way, we should insert a serializing instruction before each such load. The same goes for atomic loads. The patch implements this at the IR->DAG boundary, in a similar way to atomic fences. It is a no-op for targets other than SystemZ. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@196905 91177308-0d34-0410-b5e6-96231b3b80d8 --- include/llvm/Target/TargetLowering.h | 12 +++++++++++ .../SelectionDAG/SelectionDAGBuilder.cpp | 7 ++++++- lib/Target/SystemZ/SystemZAsmPrinter.cpp | 9 ++++++++ lib/Target/SystemZ/SystemZISelLowering.cpp | 6 ++++++ lib/Target/SystemZ/SystemZISelLowering.h | 7 +++++++ lib/Target/SystemZ/SystemZInstrInfo.td | 2 ++ lib/Target/SystemZ/SystemZOperators.td | 3 +++ lib/Target/SystemZ/SystemZProcessors.td | 9 ++++++-- lib/Target/SystemZ/SystemZSubtarget.cpp | 2 +- lib/Target/SystemZ/SystemZSubtarget.h | 4 ++++ test/CodeGen/SystemZ/Large/branch-range-01.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-02.py | 2 +- test/CodeGen/SystemZ/Large/branch-range-03.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-04.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-05.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-06.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-09.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-10.py | 4 ++-- test/CodeGen/SystemZ/Large/branch-range-11.py | 8 +++---- test/CodeGen/SystemZ/Large/branch-range-12.py | 8 +++---- test/CodeGen/SystemZ/frame-13.ll | 13 ++---------- test/CodeGen/SystemZ/frame-14.ll | 14 ++----------- test/CodeGen/SystemZ/serialize-01.ll | 21 +++++++++++++++++++ test/CodeGen/SystemZ/spill-01.ll | 2 +- 24 files changed, 106 insertions(+), 51 deletions(-) create mode 100644 test/CodeGen/SystemZ/serialize-01.ll diff --git a/include/llvm/Target/TargetLowering.h b/include/llvm/Target/TargetLowering.h index 53eea3b50f4..57e142139b4 100644 --- a/include/llvm/Target/TargetLowering.h +++ b/include/llvm/Target/TargetLowering.h @@ -2082,6 +2082,18 @@ public: return NULL; } + /// This callback is used to prepare for a volatile or atomic load. + /// It takes a chain node as input and returns the chain for the load itself. + /// + /// Having a callback like this is necessary for targets like SystemZ, + /// which allows a CPU to reuse the result of a previous load indefinitely, + /// even if a cache-coherent store is performed by another CPU. The default + /// implementation does nothing. + virtual SDValue prepareVolatileOrAtomicLoad(SDValue Chain, SDLoc DL, + SelectionDAG &DAG) const { + return Chain; + } + /// This callback is invoked by the type legalizer to legalize nodes with an /// illegal operand type but legal result types. It replaces the /// LowerOperation callback in the type Legalizer. The reason we can not do diff --git a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp index 34b7df59acd..c63a88b9d77 100644 --- a/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp +++ b/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp @@ -3400,7 +3400,7 @@ void SelectionDAGBuilder::visitLoad(const LoadInst &I) { SDValue Root; bool ConstantMemory = false; - if (I.isVolatile() || NumValues > MaxParallelChains) + if (isVolatile || NumValues > MaxParallelChains) // Serialize volatile loads with other side effects. Root = getRoot(); else if (AA->pointsToConstantMemory( @@ -3413,6 +3413,10 @@ void SelectionDAGBuilder::visitLoad(const LoadInst &I) { Root = DAG.getRoot(); } + const TargetLowering *TLI = TM.getTargetLowering(); + if (isVolatile) + Root = TLI->prepareVolatileOrAtomicLoad(Root, getCurSDLoc(), DAG); + SmallVector Values(NumValues); SmallVector Chains(std::min(unsigned(MaxParallelChains), NumValues)); @@ -3637,6 +3641,7 @@ void SelectionDAGBuilder::visitAtomicLoad(const LoadInst &I) { if (I.getAlignment() < VT.getSizeInBits() / 8) report_fatal_error("Cannot generate unaligned atomic load"); + InChain = TLI->prepareVolatileOrAtomicLoad(InChain, dl, DAG); SDValue L = DAG.getAtomic(ISD::ATOMIC_LOAD, dl, VT, VT, InChain, getValue(I.getPointerOperand()), diff --git a/lib/Target/SystemZ/SystemZAsmPrinter.cpp b/lib/Target/SystemZ/SystemZAsmPrinter.cpp index 75cbda4958a..0960b0dbe7a 100644 --- a/lib/Target/SystemZ/SystemZAsmPrinter.cpp +++ b/lib/Target/SystemZ/SystemZAsmPrinter.cpp @@ -151,6 +151,15 @@ void SystemZAsmPrinter::EmitInstruction(const MachineInstr *MI) { #undef LOWER_HIGH + case SystemZ::Serialize: + if (Subtarget->hasFastSerialization()) + LoweredMI = MCInstBuilder(SystemZ::AsmBCR) + .addImm(14).addReg(SystemZ::R0D); + else + LoweredMI = MCInstBuilder(SystemZ::AsmBCR) + .addImm(15).addReg(SystemZ::R0D); + break; + default: Lower.lower(MI, LoweredMI); break; diff --git a/lib/Target/SystemZ/SystemZISelLowering.cpp b/lib/Target/SystemZ/SystemZISelLowering.cpp index f4a6b2406cb..af5b52f1aee 100644 --- a/lib/Target/SystemZ/SystemZISelLowering.cpp +++ b/lib/Target/SystemZ/SystemZISelLowering.cpp @@ -970,6 +970,11 @@ SystemZTargetLowering::LowerReturn(SDValue Chain, RetOps.data(), RetOps.size()); } +SDValue SystemZTargetLowering:: +prepareVolatileOrAtomicLoad(SDValue Chain, SDLoc DL, SelectionDAG &DAG) const { + return DAG.getNode(SystemZISD::SERIALIZE, DL, MVT::Other, Chain); +} + // CC is a comparison that will be implemented using an integer or // floating-point comparison. Return the condition code mask for // a branch on true. In the integer case, CCMASK_CMP_UO is set for @@ -2257,6 +2262,7 @@ const char *SystemZTargetLowering::getTargetNodeName(unsigned Opcode) const { OPCODE(STPCPY); OPCODE(SEARCH_STRING); OPCODE(IPM); + OPCODE(SERIALIZE); OPCODE(ATOMIC_SWAPW); OPCODE(ATOMIC_LOADW_ADD); OPCODE(ATOMIC_LOADW_SUB); diff --git a/lib/Target/SystemZ/SystemZISelLowering.h b/lib/Target/SystemZ/SystemZISelLowering.h index c6dcca6982a..0b36f9fc7fe 100644 --- a/lib/Target/SystemZ/SystemZISelLowering.h +++ b/lib/Target/SystemZ/SystemZISelLowering.h @@ -132,6 +132,9 @@ namespace SystemZISD { // Store the CC value in bits 29 and 28 of an integer. IPM, + // Perform a serialization operation. (BCR 15,0 or BCR 14,0.) + SERIALIZE, + // Wrappers around the inner loop of an 8- or 16-bit ATOMIC_SWAP or // ATOMIC_LOAD_. // @@ -244,6 +247,9 @@ public: const SmallVectorImpl &Outs, const SmallVectorImpl &OutVals, SDLoc DL, SelectionDAG &DAG) const LLVM_OVERRIDE; + virtual SDValue prepareVolatileOrAtomicLoad(SDValue Chain, SDLoc DL, + SelectionDAG &DAG) const + LLVM_OVERRIDE; private: const SystemZSubtarget &Subtarget; @@ -273,6 +279,7 @@ private: SDValue lowerATOMIC_LOAD(SDValue Op, SelectionDAG &DAG, unsigned Opcode) const; SDValue lowerATOMIC_CMP_SWAP(SDValue Op, SelectionDAG &DAG) const; + SDValue lowerLOAD_SEQUENCE_POINT(SDValue Op, SelectionDAG &DAG) const; SDValue lowerSTACKSAVE(SDValue Op, SelectionDAG &DAG) const; SDValue lowerSTACKRESTORE(SDValue Op, SelectionDAG &DAG) const; SDValue lowerPREFETCH(SDValue Op, SelectionDAG &DAG) const; diff --git a/lib/Target/SystemZ/SystemZInstrInfo.td b/lib/Target/SystemZ/SystemZInstrInfo.td index 6524e442b63..00cb7d2c362 100644 --- a/lib/Target/SystemZ/SystemZInstrInfo.td +++ b/lib/Target/SystemZ/SystemZInstrInfo.td @@ -1195,6 +1195,8 @@ def PFDRL : PrefetchRILPC<"pfdrl", 0xC62, z_prefetch>; // Atomic operations //===----------------------------------------------------------------------===// +def Serialize : Alias<2, (outs), (ins), [(z_serialize)]>; + def ATOMIC_SWAPW : AtomicLoadWBinaryReg; def ATOMIC_SWAP_32 : AtomicLoadBinaryReg32; def ATOMIC_SWAP_64 : AtomicLoadBinaryReg64; diff --git a/lib/Target/SystemZ/SystemZOperators.td b/lib/Target/SystemZ/SystemZOperators.td index 31cabaa3413..771fbc32f3c 100644 --- a/lib/Target/SystemZ/SystemZOperators.td +++ b/lib/Target/SystemZ/SystemZOperators.td @@ -119,6 +119,9 @@ def z_sdivrem64 : SDNode<"SystemZISD::SDIVREM64", SDT_ZGR128Binary64>; def z_udivrem32 : SDNode<"SystemZISD::UDIVREM32", SDT_ZGR128Binary32>; def z_udivrem64 : SDNode<"SystemZISD::UDIVREM64", SDT_ZGR128Binary64>; +def z_serialize : SDNode<"SystemZISD::SERIALIZE", SDTNone, + [SDNPHasChain, SDNPMayStore]>; + class AtomicWOp : SDNode<"SystemZISD::"##name, profile, [SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand]>; diff --git a/lib/Target/SystemZ/SystemZProcessors.td b/lib/Target/SystemZ/SystemZProcessors.td index f241fb0c222..9aed4f9edff 100644 --- a/lib/Target/SystemZ/SystemZProcessors.td +++ b/lib/Target/SystemZ/SystemZProcessors.td @@ -36,11 +36,16 @@ def FeatureFPExtension : SystemZFeature< "Assume that the floating-point extension facility is installed" >; +def FeatureFastSerialization : SystemZFeature< + "fast-serialization", "FastSerialization", + "Assume that the fast-serialization facility is installed" +>; + def : Processor<"generic", NoItineraries, []>; def : Processor<"z10", NoItineraries, []>; def : Processor<"z196", NoItineraries, [FeatureDistinctOps, FeatureLoadStoreOnCond, FeatureHighWord, - FeatureFPExtension]>; + FeatureFPExtension, FeatureFastSerialization]>; def : Processor<"zEC12", NoItineraries, [FeatureDistinctOps, FeatureLoadStoreOnCond, FeatureHighWord, - FeatureFPExtension]>; + FeatureFPExtension, FeatureFastSerialization]>; diff --git a/lib/Target/SystemZ/SystemZSubtarget.cpp b/lib/Target/SystemZ/SystemZSubtarget.cpp index 3971d5e2a5f..333db2536e7 100644 --- a/lib/Target/SystemZ/SystemZSubtarget.cpp +++ b/lib/Target/SystemZ/SystemZSubtarget.cpp @@ -26,7 +26,7 @@ SystemZSubtarget::SystemZSubtarget(const std::string &TT, const std::string &FS) : SystemZGenSubtargetInfo(TT, CPU, FS), HasDistinctOps(false), HasLoadStoreOnCond(false), HasHighWord(false), HasFPExtension(false), - TargetTriple(TT) { + HasFastSerialization(false), TargetTriple(TT) { std::string CPUName = CPU; if (CPUName.empty()) CPUName = "generic"; diff --git a/lib/Target/SystemZ/SystemZSubtarget.h b/lib/Target/SystemZ/SystemZSubtarget.h index 5817491d458..6823c1432cd 100644 --- a/lib/Target/SystemZ/SystemZSubtarget.h +++ b/lib/Target/SystemZ/SystemZSubtarget.h @@ -32,6 +32,7 @@ protected: bool HasLoadStoreOnCond; bool HasHighWord; bool HasFPExtension; + bool HasFastSerialization; private: Triple TargetTriple; @@ -58,6 +59,9 @@ public: // Return true if the target has the floating-point extension facility. bool hasFPExtension() const { return HasFPExtension; } + // Return true if the target has the fast-serialization facility. + bool hasFastSerialization() const { return HasFastSerialization; } + // Return true if GV can be accessed using LARL for reloc model RM // and code model CM. bool isPC32DBLSymbol(const GlobalValue *GV, Reloc::Model RM, diff --git a/test/CodeGen/SystemZ/Large/branch-range-01.py b/test/CodeGen/SystemZ/Large/branch-range-01.py index 552c9ca0ea8..edb631d8c6d 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-01.py +++ b/test/CodeGen/SystemZ/Large/branch-range-01.py @@ -79,7 +79,7 @@ for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i print ' %%bstop%d = getelementptr i32 *%%stop, i64 %d' % (i, i) - print ' %%bcur%d = load volatile i32 *%%bstop%d' % (i, i) + print ' %%bcur%d = load i32 *%%bstop%d' % (i, i) print ' %%btest%d = icmp eq i32 %%limit, %%bcur%d' % (i, i) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) print '' @@ -95,7 +95,7 @@ for i in xrange(0, main_size, 6): for i in xrange(branch_blocks): print ' %%astop%d = getelementptr i32 *%%stop, i64 %d' % (i, i + 25) - print ' %%acur%d = load volatile i32 *%%astop%d' % (i, i) + print ' %%acur%d = load i32 *%%astop%d' % (i, i) print ' %%atest%d = icmp eq i32 %%limit, %%acur%d' % (i, i) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) print '' diff --git a/test/CodeGen/SystemZ/Large/branch-range-02.py b/test/CodeGen/SystemZ/Large/branch-range-02.py index 0b21ced99a1..743e12de0f1 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-02.py +++ b/test/CodeGen/SystemZ/Large/branch-range-02.py @@ -72,7 +72,7 @@ for i in xrange(blocks): print 'b%d:' % i print ' store volatile i8 %d, i8 *%%base' % value print ' %%astop%d = getelementptr i32 *%%stop, i64 %d' % (i, i) - print ' %%acur%d = load volatile i32 *%%astop%d' % (i, i) + print ' %%acur%d = load i32 *%%astop%d' % (i, i) print ' %%atest%d = icmp eq i32 %%limit, %%acur%d' % (i, i) print ' br i1 %%atest%d, label %%%s, label %%%s' % (i, other, next) diff --git a/test/CodeGen/SystemZ/Large/branch-range-03.py b/test/CodeGen/SystemZ/Large/branch-range-03.py index 75cdf247c6f..5c9a93b87f7 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-03.py +++ b/test/CodeGen/SystemZ/Large/branch-range-03.py @@ -79,7 +79,7 @@ for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i print ' %%bstop%d = getelementptr i8 *%%stop, i64 %d' % (i, i) - print ' %%bcur%d = load volatile i8 *%%bstop%d' % (i, i) + print ' %%bcur%d = load i8 *%%bstop%d' % (i, i) print ' %%bext%d = sext i8 %%bcur%d to i32' % (i, i) print ' %%btest%d = icmp eq i32 %%limit, %%bext%d' % (i, i) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -96,7 +96,7 @@ for i in xrange(0, main_size, 6): for i in xrange(branch_blocks): print ' %%astop%d = getelementptr i8 *%%stop, i64 %d' % (i, i + 25) - print ' %%acur%d = load volatile i8 *%%astop%d' % (i, i) + print ' %%acur%d = load i8 *%%astop%d' % (i, i) print ' %%aext%d = sext i8 %%acur%d to i32' % (i, i) print ' %%atest%d = icmp eq i32 %%limit, %%aext%d' % (i, i) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-04.py b/test/CodeGen/SystemZ/Large/branch-range-04.py index 3ae3ae9c37f..2c9090fa206 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-04.py +++ b/test/CodeGen/SystemZ/Large/branch-range-04.py @@ -83,7 +83,7 @@ for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i print ' %%bstop%d = getelementptr i8 *%%stop, i64 %d' % (i, i) - print ' %%bcur%d = load volatile i8 *%%bstop%d' % (i, i) + print ' %%bcur%d = load i8 *%%bstop%d' % (i, i) print ' %%bext%d = sext i8 %%bcur%d to i64' % (i, i) print ' %%btest%d = icmp eq i64 %%limit, %%bext%d' % (i, i) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -100,7 +100,7 @@ for i in xrange(0, main_size, 6): for i in xrange(branch_blocks): print ' %%astop%d = getelementptr i8 *%%stop, i64 %d' % (i, i + 25) - print ' %%acur%d = load volatile i8 *%%astop%d' % (i, i) + print ' %%acur%d = load i8 *%%astop%d' % (i, i) print ' %%aext%d = sext i8 %%acur%d to i64' % (i, i) print ' %%atest%d = icmp eq i64 %%limit, %%aext%d' % (i, i) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-05.py b/test/CodeGen/SystemZ/Large/branch-range-05.py index 6928b8fc21d..52f4a961c88 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-05.py +++ b/test/CodeGen/SystemZ/Large/branch-range-05.py @@ -82,7 +82,7 @@ print '' for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i - print ' %%bcur%d = load volatile i8 *%%stop' % i + print ' %%bcur%d = load i8 *%%stop' % i print ' %%bext%d = sext i8 %%bcur%d to i32' % (i, i) print ' %%btest%d = icmp slt i32 %%bext%d, %d' % (i, i, i + 50) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -98,7 +98,7 @@ for i in xrange(0, main_size, 6): print ' store volatile i8 %d, i8 *%%ptr%d' % (value, i) for i in xrange(branch_blocks): - print ' %%acur%d = load volatile i8 *%%stop' % i + print ' %%acur%d = load i8 *%%stop' % i print ' %%aext%d = sext i8 %%acur%d to i32' % (i, i) print ' %%atest%d = icmp slt i32 %%aext%d, %d' % (i, i, i + 100) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-06.py b/test/CodeGen/SystemZ/Large/branch-range-06.py index aabc72fa6ec..c34ebac4ce3 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-06.py +++ b/test/CodeGen/SystemZ/Large/branch-range-06.py @@ -82,7 +82,7 @@ print '' for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i - print ' %%bcur%d = load volatile i8 *%%stop' % i + print ' %%bcur%d = load i8 *%%stop' % i print ' %%bext%d = sext i8 %%bcur%d to i64' % (i, i) print ' %%btest%d = icmp slt i64 %%bext%d, %d' % (i, i, i + 50) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -98,7 +98,7 @@ for i in xrange(0, main_size, 6): print ' store volatile i8 %d, i8 *%%ptr%d' % (value, i) for i in xrange(branch_blocks): - print ' %%acur%d = load volatile i8 *%%stop' % i + print ' %%acur%d = load i8 *%%stop' % i print ' %%aext%d = sext i8 %%acur%d to i64' % (i, i) print ' %%atest%d = icmp slt i64 %%aext%d, %d' % (i, i, i + 100) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-09.py b/test/CodeGen/SystemZ/Large/branch-range-09.py index b3fd81324da..bc712cb164e 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-09.py +++ b/test/CodeGen/SystemZ/Large/branch-range-09.py @@ -79,7 +79,7 @@ for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i print ' %%bstop%d = getelementptr i8 *%%stop, i64 %d' % (i, i) - print ' %%bcur%d = load volatile i8 *%%bstop%d' % (i, i) + print ' %%bcur%d = load i8 *%%bstop%d' % (i, i) print ' %%bext%d = sext i8 %%bcur%d to i32' % (i, i) print ' %%btest%d = icmp ult i32 %%limit, %%bext%d' % (i, i) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -96,7 +96,7 @@ for i in xrange(0, main_size, 6): for i in xrange(branch_blocks): print ' %%astop%d = getelementptr i8 *%%stop, i64 %d' % (i, i + 25) - print ' %%acur%d = load volatile i8 *%%astop%d' % (i, i) + print ' %%acur%d = load i8 *%%astop%d' % (i, i) print ' %%aext%d = sext i8 %%acur%d to i32' % (i, i) print ' %%atest%d = icmp ult i32 %%limit, %%aext%d' % (i, i) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-10.py b/test/CodeGen/SystemZ/Large/branch-range-10.py index 3aeea3ebccd..8c483c33724 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-10.py +++ b/test/CodeGen/SystemZ/Large/branch-range-10.py @@ -83,7 +83,7 @@ for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i print ' %%bstop%d = getelementptr i8 *%%stop, i64 %d' % (i, i) - print ' %%bcur%d = load volatile i8 *%%bstop%d' % (i, i) + print ' %%bcur%d = load i8 *%%bstop%d' % (i, i) print ' %%bext%d = sext i8 %%bcur%d to i64' % (i, i) print ' %%btest%d = icmp ult i64 %%limit, %%bext%d' % (i, i) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -100,7 +100,7 @@ for i in xrange(0, main_size, 6): for i in xrange(branch_blocks): print ' %%astop%d = getelementptr i8 *%%stop, i64 %d' % (i, i + 25) - print ' %%acur%d = load volatile i8 *%%astop%d' % (i, i) + print ' %%acur%d = load i8 *%%astop%d' % (i, i) print ' %%aext%d = sext i8 %%acur%d to i64' % (i, i) print ' %%atest%d = icmp ult i64 %%limit, %%aext%d' % (i, i) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-11.py b/test/CodeGen/SystemZ/Large/branch-range-11.py index 034902c4a34..054610380e3 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-11.py +++ b/test/CodeGen/SystemZ/Large/branch-range-11.py @@ -98,8 +98,8 @@ print '' for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i - print ' %%bcur%da = load volatile i32 *%%stopa' % i - print ' %%bcur%db = load volatile i32 *%%stopb' % i + print ' %%bcur%da = load i32 *%%stopa' % i + print ' %%bcur%db = load i32 *%%stopb' % i print ' %%bsub%d = sub i32 %%bcur%da, %%bcur%db' % (i, i, i) print ' %%btest%d = icmp ult i32 %%bsub%d, %d' % (i, i, i + 50) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -115,8 +115,8 @@ for i in xrange(0, main_size, 6): print ' store volatile i8 %d, i8 *%%ptr%d' % (value, i) for i in xrange(branch_blocks): - print ' %%acur%da = load volatile i32 *%%stopa' % i - print ' %%acur%db = load volatile i32 *%%stopb' % i + print ' %%acur%da = load i32 *%%stopa' % i + print ' %%acur%db = load i32 *%%stopb' % i print ' %%asub%d = sub i32 %%acur%da, %%acur%db' % (i, i, i) print ' %%atest%d = icmp ult i32 %%asub%d, %d' % (i, i, i + 100) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/Large/branch-range-12.py b/test/CodeGen/SystemZ/Large/branch-range-12.py index 007d477e214..626c8998d5d 100644 --- a/test/CodeGen/SystemZ/Large/branch-range-12.py +++ b/test/CodeGen/SystemZ/Large/branch-range-12.py @@ -98,8 +98,8 @@ print '' for i in xrange(branch_blocks): next = 'before%d' % (i + 1) if i + 1 < branch_blocks else 'main' print 'before%d:' % i - print ' %%bcur%da = load volatile i64 *%%stopa' % i - print ' %%bcur%db = load volatile i64 *%%stopb' % i + print ' %%bcur%da = load i64 *%%stopa' % i + print ' %%bcur%db = load i64 *%%stopb' % i print ' %%bsub%d = sub i64 %%bcur%da, %%bcur%db' % (i, i, i) print ' %%btest%d = icmp ult i64 %%bsub%d, %d' % (i, i, i + 50) print ' br i1 %%btest%d, label %%after0, label %%%s' % (i, next) @@ -115,8 +115,8 @@ for i in xrange(0, main_size, 6): print ' store volatile i8 %d, i8 *%%ptr%d' % (value, i) for i in xrange(branch_blocks): - print ' %%acur%da = load volatile i64 *%%stopa' % i - print ' %%acur%db = load volatile i64 *%%stopb' % i + print ' %%acur%da = load i64 *%%stopa' % i + print ' %%acur%db = load i64 *%%stopb' % i print ' %%asub%d = sub i64 %%acur%da, %%acur%db' % (i, i, i) print ' %%atest%d = icmp ult i64 %%asub%d, %d' % (i, i, i + 100) print ' br i1 %%atest%d, label %%main, label %%after%d' % (i, i) diff --git a/test/CodeGen/SystemZ/frame-13.ll b/test/CodeGen/SystemZ/frame-13.ll index 393850fbf61..58dee1da58b 100644 --- a/test/CodeGen/SystemZ/frame-13.ll +++ b/test/CodeGen/SystemZ/frame-13.ll @@ -243,8 +243,8 @@ define void @f10(i32 *%vptr) { ; And again with maximum register pressure. The only spill slots that the ; NOFP case needs are the emergency ones, so the offsets are the same as for f2. -; However, the FP case uses %r11 as the frame pointer and must therefore -; spill a second register. This leads to an extra displacement of 8. +; The FP case needs to spill an extra register and is too dependent on +; register allocation heuristics for a stable test. define void @f11(i32 *%vptr) { ; CHECK-NOFP-LABEL: f11: ; CHECK-NOFP: stmg %r6, %r15, @@ -254,15 +254,6 @@ define void @f11(i32 *%vptr) { ; CHECK-NOFP: lg [[REGISTER]], [[OFFSET]](%r15) ; CHECK-NOFP: lmg %r6, %r15, ; CHECK-NOFP: br %r14 -; -; CHECK-FP-LABEL: f11: -; CHECK-FP: stmg %r6, %r15, -; CHECK-FP: stg [[REGISTER:%r[1-9][0-4]?]], [[OFFSET:160|168]](%r11) -; CHECK-FP: lay [[REGISTER]], 4096(%r11) -; CHECK-FP: mvhi 8([[REGISTER]]), 42 -; CHECK-FP: lg [[REGISTER]], [[OFFSET]](%r11) -; CHECK-FP: lmg %r6, %r15, -; CHECK-FP: br %r14 %i0 = load volatile i32 *%vptr %i1 = load volatile i32 *%vptr %i3 = load volatile i32 *%vptr diff --git a/test/CodeGen/SystemZ/frame-14.ll b/test/CodeGen/SystemZ/frame-14.ll index 3b48179c40b..24169cf61f0 100644 --- a/test/CodeGen/SystemZ/frame-14.ll +++ b/test/CodeGen/SystemZ/frame-14.ll @@ -266,8 +266,8 @@ define void @f10(i32 *%vptr) { ; And again with maximum register pressure. The only spill slots that the ; NOFP case needs are the emergency ones, so the offsets are the same as for f4. -; However, the FP case uses %r11 as the frame pointer and must therefore -; spill a second register. This leads to an extra displacement of 8. +; The FP case needs to spill an extra register and is too dependent on +; register allocation heuristics for a stable test. define void @f11(i32 *%vptr) { ; CHECK-NOFP-LABEL: f11: ; CHECK-NOFP: stmg %r6, %r15, @@ -278,16 +278,6 @@ define void @f11(i32 *%vptr) { ; CHECK-NOFP: lg [[REGISTER]], [[OFFSET]](%r15) ; CHECK-NOFP: lmg %r6, %r15, ; CHECK-NOFP: br %r14 -; -; CHECK-FP-LABEL: f11: -; CHECK-FP: stmg %r6, %r15, -; CHECK-FP: stg [[REGISTER:%r[1-9][0-4]?]], [[OFFSET:160|168]](%r11) -; CHECK-FP: llilh [[REGISTER]], 8 -; CHECK-FP: agr [[REGISTER]], %r11 -; CHECK-FP: mvi 8([[REGISTER]]), 42 -; CHECK-FP: lg [[REGISTER]], [[OFFSET]](%r11) -; CHECK-FP: lmg %r6, %r15, -; CHECK-FP: br %r14 %i0 = load volatile i32 *%vptr %i1 = load volatile i32 *%vptr %i3 = load volatile i32 *%vptr diff --git a/test/CodeGen/SystemZ/serialize-01.ll b/test/CodeGen/SystemZ/serialize-01.ll new file mode 100644 index 00000000000..7801fac8d47 --- /dev/null +++ b/test/CodeGen/SystemZ/serialize-01.ll @@ -0,0 +1,21 @@ +; Test serialization instructions. +; +; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 | \ +; RUN: FileCheck %s -check-prefix=CHECK-FULL +; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z196 | \ +; RUN: FileCheck %s -check-prefix=CHECK-FAST + +; Check that volatile loads produce a serialisation. +define i32 @f1(i32 *%src) { +; CHECK-FULL-LABEL: f1: +; CHECK-FULL: bcr 15, %r0 +; CHECK-FULL: l %r2, 0(%r2) +; CHECK-FULL: br %r14 +; +; CHECK-FAST-LABEL: f1: +; CHECK-FAST: bcr 14, %r0 +; CHECK-FAST: l %r2, 0(%r2) +; CHECK-FAST: br %r14 + %val = load volatile i32 *%src + ret i32 %val +} diff --git a/test/CodeGen/SystemZ/spill-01.ll b/test/CodeGen/SystemZ/spill-01.ll index ca64a88f2a0..c1f780c55d3 100644 --- a/test/CodeGen/SystemZ/spill-01.ll +++ b/test/CodeGen/SystemZ/spill-01.ll @@ -400,6 +400,7 @@ define void @f10() { ; CHECK: stgrl [[REG]], h8 ; CHECK: br %r14 entry: + %val8 = load volatile i64 *@h8 %val0 = load volatile i64 *@h0 %val1 = load volatile i64 *@h1 %val2 = load volatile i64 *@h2 @@ -408,7 +409,6 @@ entry: %val5 = load volatile i64 *@h5 %val6 = load volatile i64 *@h6 %val7 = load volatile i64 *@h7 - %val8 = load volatile i64 *@h8 %val9 = load volatile i64 *@h9 call void @foo() -- 2.34.1