llvm-6502/lib/Support/Triple.cpp

1170 lines
36 KiB
C++
Raw Normal View History

//===--- Triple.cpp - Target triple helper class --------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/Triple.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/ErrorHandling.h"
#include <cstring>
using namespace llvm;
const char *Triple::getArchTypeName(ArchType Kind) {
switch (Kind) {
case UnknownArch: return "unknown";
case aarch64: return "aarch64";
case aarch64_be: return "aarch64_be";
case arm: return "arm";
case armeb: return "armeb";
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
case bpf: return "bpf";
case hexagon: return "hexagon";
case mips: return "mips";
case mipsel: return "mipsel";
case mips64: return "mips64";
case mips64el: return "mips64el";
case msp430: return "msp430";
case ppc64: return "powerpc64";
case ppc64le: return "powerpc64le";
case ppc: return "powerpc";
case r600: return "r600";
case amdgcn: return "amdgcn";
case sparc: return "sparc";
case sparcv9: return "sparcv9";
case sparcel: return "sparcel";
case systemz: return "s390x";
case tce: return "tce";
case thumb: return "thumb";
case thumbeb: return "thumbeb";
case x86: return "i386";
case x86_64: return "x86_64";
case xcore: return "xcore";
case nvptx: return "nvptx";
case nvptx64: return "nvptx64";
case le32: return "le32";
case le64: return "le64";
case amdil: return "amdil";
case amdil64: return "amdil64";
case hsail: return "hsail";
case hsail64: return "hsail64";
case spir: return "spir";
case spir64: return "spir64";
case kalimba: return "kalimba";
}
llvm_unreachable("Invalid ArchType!");
}
const char *Triple::getArchTypePrefix(ArchType Kind) {
switch (Kind) {
default:
return nullptr;
case aarch64:
case aarch64_be: return "aarch64";
case arm:
case armeb:
case thumb:
case thumbeb: return "arm";
case ppc64:
case ppc64le:
case ppc: return "ppc";
case mips:
case mipsel:
case mips64:
case mips64el: return "mips";
case hexagon: return "hexagon";
case amdgcn:
case r600: return "amdgpu";
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
case bpf: return "bpf";
case sparcv9:
case sparcel:
case sparc: return "sparc";
[SystemZ] Support transactional execution on zEC12 The zEC12 provides the transactional-execution facility. This is exposed to users via a set of builtin routines on other compilers. This patch adds LLVM support to enable those builtins. In partciular, the patch: - adds the transactional-execution and processor-assist facilities - adds MC support for all instructions provided by those facilities - adds LLVM intrinsics for those instructions and hooks them up for CodeGen - adds CodeGen support to optimize CC return value checking Since this is first use of target-specific intrinsics on the platform, the patch creates the include/llvm/IR/IntrinsicsSystemZ.td file and hooks it up in Intrinsics.td. I've also changed Triple::getArchTypePrefix to return "s390" instead of "systemz", since the naming convention for GCC intrinsics uses "s390" on the platform, and it neemed more straight- forward to use the same convention for LLVM IR intrinsics. An associated clang patch makes the intrinsics (and command line switches) available at the source-language level. For reference, the transactional-execution instructions are documented in the z/Architecture Principles of Operation for the zEC12: http://publibfp.boulder.ibm.com/cgi-bin/bookmgr/download/DZ9ZR009.pdf The associated builtins are documented in the GCC manual: http://gcc.gnu.org/onlinedocs/gcc/S_002f390-System-z-Built-in-Functions.html Index: llvm-head/lib/Target/SystemZ/SystemZOperators.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZOperators.td +++ llvm-head/lib/Target/SystemZ/SystemZOperators.td @@ -79,6 +79,9 @@ def SDT_ZI32Intrinsic : SDTypeProf def SDT_ZPrefetch : SDTypeProfile<0, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<1>]>; +def SDT_ZTBegin : SDTypeProfile<0, 2, + [SDTCisPtrTy<0>, + SDTCisVT<1, i32>]>; //===----------------------------------------------------------------------===// // Node definitions @@ -180,6 +183,15 @@ def z_prefetch : SDNode<"System [SDNPHasChain, SDNPMayLoad, SDNPMayStore, SDNPMemOperand]>; +def z_tbegin : SDNode<"SystemZISD::TBEGIN", SDT_ZTBegin, + [SDNPHasChain, SDNPOutGlue, SDNPMayStore, + SDNPSideEffect]>; +def z_tbegin_nofloat : SDNode<"SystemZISD::TBEGIN_NOFLOAT", SDT_ZTBegin, + [SDNPHasChain, SDNPOutGlue, SDNPMayStore, + SDNPSideEffect]>; +def z_tend : SDNode<"SystemZISD::TEND", SDTNone, + [SDNPHasChain, SDNPOutGlue, SDNPSideEffect]>; + //===----------------------------------------------------------------------===// // Pattern fragments //===----------------------------------------------------------------------===// Index: llvm-head/lib/Target/SystemZ/SystemZInstrFormats.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZInstrFormats.td +++ llvm-head/lib/Target/SystemZ/SystemZInstrFormats.td @@ -473,6 +473,17 @@ class InstSS<bits<8> op, dag outs, dag i let Inst{15-0} = BD2; } +class InstS<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern> + : InstSystemZ<4, outs, ins, asmstr, pattern> { + field bits<32> Inst; + field bits<32> SoftFail = 0; + + bits<16> BD2; + + let Inst{31-16} = op; + let Inst{15-0} = BD2; +} + //===----------------------------------------------------------------------===// // Instruction definitions with semantics //===----------------------------------------------------------------------===// Index: llvm-head/lib/Target/SystemZ/SystemZInstrInfo.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZInstrInfo.td +++ llvm-head/lib/Target/SystemZ/SystemZInstrInfo.td @@ -1362,6 +1362,60 @@ let Defs = [CC] in { } //===----------------------------------------------------------------------===// +// Transactional execution +//===----------------------------------------------------------------------===// + +let Predicates = [FeatureTransactionalExecution] in { + // Transaction Begin + let hasSideEffects = 1, mayStore = 1, + usesCustomInserter = 1, Defs = [CC] in { + def TBEGIN : InstSIL<0xE560, + (outs), (ins bdaddr12only:$BD1, imm32zx16:$I2), + "tbegin\t$BD1, $I2", + [(z_tbegin bdaddr12only:$BD1, imm32zx16:$I2)]>; + def TBEGIN_nofloat : Pseudo<(outs), (ins bdaddr12only:$BD1, imm32zx16:$I2), + [(z_tbegin_nofloat bdaddr12only:$BD1, + imm32zx16:$I2)]>; + def TBEGINC : InstSIL<0xE561, + (outs), (ins bdaddr12only:$BD1, imm32zx16:$I2), + "tbeginc\t$BD1, $I2", + [(int_s390_tbeginc bdaddr12only:$BD1, + imm32zx16:$I2)]>; + } + + // Transaction End + let hasSideEffects = 1, Defs = [CC], BD2 = 0 in + def TEND : InstS<0xB2F8, (outs), (ins), "tend", [(z_tend)]>; + + // Transaction Abort + let hasSideEffects = 1, isTerminator = 1, isBarrier = 1 in + def TABORT : InstS<0xB2FC, (outs), (ins bdaddr12only:$BD2), + "tabort\t$BD2", + [(int_s390_tabort bdaddr12only:$BD2)]>; + + // Nontransactional Store + let hasSideEffects = 1 in + def NTSTG : StoreRXY<"ntstg", 0xE325, int_s390_ntstg, GR64, 8>; + + // Extract Transaction Nesting Depth + let hasSideEffects = 1 in + def ETND : InherentRRE<"etnd", 0xB2EC, GR32, (int_s390_etnd)>; +} + +//===----------------------------------------------------------------------===// +// Processor assist +//===----------------------------------------------------------------------===// + +let Predicates = [FeatureProcessorAssist] in { + let hasSideEffects = 1, R4 = 0 in + def PPA : InstRRF<0xB2E8, (outs), (ins GR64:$R1, GR64:$R2, imm32zx4:$R3), + "ppa\t$R1, $R2, $R3", []>; + def : Pat<(int_s390_ppa_txassist GR32:$src), + (PPA (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, subreg_l32), + 0, 1)>; +} + +//===----------------------------------------------------------------------===// // Miscellaneous Instructions. //===----------------------------------------------------------------------===// Index: llvm-head/lib/Target/SystemZ/SystemZProcessors.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZProcessors.td +++ llvm-head/lib/Target/SystemZ/SystemZProcessors.td @@ -60,6 +60,16 @@ def FeatureMiscellaneousExtensions : Sys "Assume that the miscellaneous-extensions facility is installed" >; +def FeatureTransactionalExecution : SystemZFeature< + "transactional-execution", "TransactionalExecution", + "Assume that the transactional-execution facility is installed" +>; + +def FeatureProcessorAssist : SystemZFeature< + "processor-assist", "ProcessorAssist", + "Assume that the processor-assist facility is installed" +>; + def : Processor<"generic", NoItineraries, []>; def : Processor<"z10", NoItineraries, []>; def : Processor<"z196", NoItineraries, @@ -70,4 +80,5 @@ def : Processor<"zEC12", NoItineraries, [FeatureDistinctOps, FeatureLoadStoreOnCond, FeatureHighWord, FeatureFPExtension, FeaturePopulationCount, FeatureFastSerialization, FeatureInterlockedAccess1, - FeatureMiscellaneousExtensions]>; + FeatureMiscellaneousExtensions, + FeatureTransactionalExecution, FeatureProcessorAssist]>; Index: llvm-head/lib/Target/SystemZ/SystemZSubtarget.cpp =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZSubtarget.cpp +++ llvm-head/lib/Target/SystemZ/SystemZSubtarget.cpp @@ -40,6 +40,7 @@ SystemZSubtarget::SystemZSubtarget(const HasLoadStoreOnCond(false), HasHighWord(false), HasFPExtension(false), HasPopulationCount(false), HasFastSerialization(false), HasInterlockedAccess1(false), HasMiscellaneousExtensions(false), + HasTransactionalExecution(false), HasProcessorAssist(false), TargetTriple(TT), InstrInfo(initializeSubtargetDependencies(CPU, FS)), TLInfo(TM, *this), TSInfo(*TM.getDataLayout()), FrameLowering() {} Index: llvm-head/lib/Target/SystemZ/SystemZSubtarget.h =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZSubtarget.h +++ llvm-head/lib/Target/SystemZ/SystemZSubtarget.h @@ -42,6 +42,8 @@ protected: bool HasFastSerialization; bool HasInterlockedAccess1; bool HasMiscellaneousExtensions; + bool HasTransactionalExecution; + bool HasProcessorAssist; private: Triple TargetTriple; @@ -102,6 +104,12 @@ public: return HasMiscellaneousExtensions; } + // Return true if the target has the transactional-execution facility. + bool hasTransactionalExecution() const { return HasTransactionalExecution; } + + // Return true if the target has the processor-assist facility. + bool hasProcessorAssist() const { return HasProcessorAssist; } + // 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, Index: llvm-head/lib/Support/Triple.cpp =================================================================== --- llvm-head.orig/lib/Support/Triple.cpp +++ llvm-head/lib/Support/Triple.cpp @@ -92,7 +92,7 @@ const char *Triple::getArchTypePrefix(Ar case sparcv9: case sparc: return "sparc"; - case systemz: return "systemz"; + case systemz: return "s390"; case x86: case x86_64: return "x86"; Index: llvm-head/include/llvm/IR/Intrinsics.td =================================================================== --- llvm-head.orig/include/llvm/IR/Intrinsics.td +++ llvm-head/include/llvm/IR/Intrinsics.td @@ -634,3 +634,4 @@ include "llvm/IR/IntrinsicsNVVM.td" include "llvm/IR/IntrinsicsMips.td" include "llvm/IR/IntrinsicsR600.td" include "llvm/IR/IntrinsicsBPF.td" +include "llvm/IR/IntrinsicsSystemZ.td" Index: llvm-head/include/llvm/IR/IntrinsicsSystemZ.td =================================================================== --- /dev/null +++ llvm-head/include/llvm/IR/IntrinsicsSystemZ.td @@ -0,0 +1,46 @@ +//===- IntrinsicsSystemZ.td - Defines SystemZ intrinsics ---*- tablegen -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file defines all of the SystemZ-specific intrinsics. +// +//===----------------------------------------------------------------------===// + +//===----------------------------------------------------------------------===// +// +// Transactional-execution intrinsics +// +//===----------------------------------------------------------------------===// + +let TargetPrefix = "s390" in { + def int_s390_tbegin : Intrinsic<[llvm_i32_ty], [llvm_ptr_ty, llvm_i32_ty], + [IntrNoDuplicate]>; + + def int_s390_tbegin_nofloat : Intrinsic<[llvm_i32_ty], + [llvm_ptr_ty, llvm_i32_ty], + [IntrNoDuplicate]>; + + def int_s390_tbeginc : Intrinsic<[], [llvm_ptr_ty, llvm_i32_ty], + [IntrNoDuplicate]>; + + def int_s390_tabort : Intrinsic<[], [llvm_i64_ty], + [IntrNoReturn, Throws]>; + + def int_s390_tend : GCCBuiltin<"__builtin_tend">, + Intrinsic<[llvm_i32_ty], []>; + + def int_s390_etnd : GCCBuiltin<"__builtin_tx_nesting_depth">, + Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>; + + def int_s390_ntstg : Intrinsic<[], [llvm_i64_ty, llvm_ptr64_ty], + [IntrReadWriteArgMem]>; + + def int_s390_ppa_txassist : GCCBuiltin<"__builtin_tx_assist">, + Intrinsic<[], [llvm_i32_ty]>; +} + Index: llvm-head/lib/Target/SystemZ/SystemZ.h =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZ.h +++ llvm-head/lib/Target/SystemZ/SystemZ.h @@ -68,6 +68,18 @@ const unsigned CCMASK_TM_MSB_0 = C const unsigned CCMASK_TM_MSB_1 = CCMASK_2 | CCMASK_3; const unsigned CCMASK_TM = CCMASK_ANY; +// Condition-code mask assignments for TRANSACTION_BEGIN. +const unsigned CCMASK_TBEGIN_STARTED = CCMASK_0; +const unsigned CCMASK_TBEGIN_INDETERMINATE = CCMASK_1; +const unsigned CCMASK_TBEGIN_TRANSIENT = CCMASK_2; +const unsigned CCMASK_TBEGIN_PERSISTENT = CCMASK_3; +const unsigned CCMASK_TBEGIN = CCMASK_ANY; + +// Condition-code mask assignments for TRANSACTION_END. +const unsigned CCMASK_TEND_TX = CCMASK_0; +const unsigned CCMASK_TEND_NOTX = CCMASK_2; +const unsigned CCMASK_TEND = CCMASK_TEND_TX | CCMASK_TEND_NOTX; + // The position of the low CC bit in an IPM result. const unsigned IPM_CC = 28; Index: llvm-head/lib/Target/SystemZ/SystemZISelLowering.h =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZISelLowering.h +++ llvm-head/lib/Target/SystemZ/SystemZISelLowering.h @@ -146,6 +146,15 @@ enum { // Perform a serialization operation. (BCR 15,0 or BCR 14,0.) SERIALIZE, + // Transaction begin. The first operand is the chain, the second + // the TDB pointer, and the third the immediate control field. + // Returns chain and glue. + TBEGIN, + TBEGIN_NOFLOAT, + + // Transaction end. Just the chain operand. Returns chain and glue. + TEND, + // Wrappers around the inner loop of an 8- or 16-bit ATOMIC_SWAP or // ATOMIC_LOAD_<op>. // @@ -318,6 +327,7 @@ private: SDValue lowerSTACKSAVE(SDValue Op, SelectionDAG &DAG) const; SDValue lowerSTACKRESTORE(SDValue Op, SelectionDAG &DAG) const; SDValue lowerPREFETCH(SDValue Op, SelectionDAG &DAG) const; + SDValue lowerINTRINSIC_W_CHAIN(SDValue Op, SelectionDAG &DAG) const; // If the last instruction before MBBI in MBB was some form of COMPARE, // try to replace it with a COMPARE AND BRANCH just before MBBI. @@ -355,6 +365,10 @@ private: MachineBasicBlock *emitStringWrapper(MachineInstr *MI, MachineBasicBlock *BB, unsigned Opcode) const; + MachineBasicBlock *emitTransactionBegin(MachineInstr *MI, + MachineBasicBlock *MBB, + unsigned Opcode, + bool NoFloat) const; }; } // end namespace llvm Index: llvm-head/lib/Target/SystemZ/SystemZISelLowering.cpp =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZISelLowering.cpp +++ llvm-head/lib/Target/SystemZ/SystemZISelLowering.cpp @@ -20,6 +20,7 @@ #include "llvm/CodeGen/MachineInstrBuilder.h" #include "llvm/CodeGen/MachineRegisterInfo.h" #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h" +#include "llvm/IR/Intrinsics.h" #include <cctype> using namespace llvm; @@ -304,6 +305,9 @@ SystemZTargetLowering::SystemZTargetLowe // Codes for which we want to perform some z-specific combinations. setTargetDAGCombine(ISD::SIGN_EXTEND); + // Handle intrinsics. + setOperationAction(ISD::INTRINSIC_W_CHAIN, MVT::Other, Custom); + // We want to use MVC in preference to even a single load/store pair. MaxStoresPerMemcpy = 0; MaxStoresPerMemcpyOptSize = 0; @@ -1031,6 +1035,53 @@ prepareVolatileOrAtomicLoad(SDValue Chai return DAG.getNode(SystemZISD::SERIALIZE, DL, MVT::Other, Chain); } +// Return true if Op is an intrinsic node with chain that returns the CC value +// as its only (other) argument. Provide the associated SystemZISD opcode and +// the mask of valid CC values if so. +static bool isIntrinsicWithCCAndChain(SDValue Op, unsigned &Opcode, + unsigned &CCValid) { + unsigned Id = cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue(); + switch (Id) { + case Intrinsic::s390_tbegin: + Opcode = SystemZISD::TBEGIN; + CCValid = SystemZ::CCMASK_TBEGIN; + return true; + + case Intrinsic::s390_tbegin_nofloat: + Opcode = SystemZISD::TBEGIN_NOFLOAT; + CCValid = SystemZ::CCMASK_TBEGIN; + return true; + + case Intrinsic::s390_tend: + Opcode = SystemZISD::TEND; + CCValid = SystemZ::CCMASK_TEND; + return true; + + default: + return false; + } +} + +// Emit an intrinsic with chain with a glued value instead of its CC result. +static SDValue emitIntrinsicWithChainAndGlue(SelectionDAG &DAG, SDValue Op, + unsigned Opcode) { + // Copy all operands except the intrinsic ID. + unsigned NumOps = Op.getNumOperands(); + SmallVector<SDValue, 6> Ops; + Ops.reserve(NumOps - 1); + Ops.push_back(Op.getOperand(0)); + for (unsigned I = 2; I < NumOps; ++I) + Ops.push_back(Op.getOperand(I)); + + assert(Op->getNumValues() == 2 && "Expected only CC result and chain"); + SDVTList RawVTs = DAG.getVTList(MVT::Other, MVT::Glue); + SDValue Intr = DAG.getNode(Opcode, SDLoc(Op), RawVTs, Ops); + SDValue OldChain = SDValue(Op.getNode(), 1); + SDValue NewChain = SDValue(Intr.getNode(), 0); + DAG.ReplaceAllUsesOfValueWith(OldChain, NewChain); + return Intr; +} + // 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 @@ -1588,9 +1639,53 @@ static void adjustForTestUnderMask(Selec C.CCMask = NewCCMask; } +// Return a Comparison that tests the condition-code result of intrinsic +// node Call against constant integer CC using comparison code Cond. +// Opcode is the opcode of the SystemZISD operation for the intrinsic +// and CCValid is the set of possible condition-code results. +static Comparison getIntrinsicCmp(SelectionDAG &DAG, unsigned Opcode, + SDValue Call, unsigned CCValid, uint64_t CC, + ISD::CondCode Cond) { + Comparison C(Call, SDValue()); + C.Opcode = Opcode; + C.CCValid = CCValid; + if (Cond == ISD::SETEQ) + // bit 3 for CC==0, bit 0 for CC==3, always false for CC>3. + C.CCMask = CC < 4 ? 1 << (3 - CC) : 0; + else if (Cond == ISD::SETNE) + // ...and the inverse of that. + C.CCMask = CC < 4 ? ~(1 << (3 - CC)) : -1; + else if (Cond == ISD::SETLT || Cond == ISD::SETULT) + // bits above bit 3 for CC==0 (always false), bits above bit 0 for CC==3, + // always true for CC>3. + C.CCMask = CC < 4 ? -1 << (4 - CC) : -1; + else if (Cond == ISD::SETGE || Cond == ISD::SETUGE) + // ...and the inverse of that. + C.CCMask = CC < 4 ? ~(-1 << (4 - CC)) : 0; + else if (Cond == ISD::SETLE || Cond == ISD::SETULE) + // bit 3 and above for CC==0, bit 0 and above for CC==3 (always true), + // always true for CC>3. + C.CCMask = CC < 4 ? -1 << (3 - CC) : -1; + else if (Cond == ISD::SETGT || Cond == ISD::SETUGT) + // ...and the inverse of that. + C.CCMask = CC < 4 ? ~(-1 << (3 - CC)) : 0; + else + llvm_unreachable("Unexpected integer comparison type"); + C.CCMask &= CCValid; + return C; +} + // Decide how to implement a comparison of type Cond between CmpOp0 with CmpOp1. static Comparison getCmp(SelectionDAG &DAG, SDValue CmpOp0, SDValue CmpOp1, ISD::CondCode Cond) { + if (CmpOp1.getOpcode() == ISD::Constant) { + uint64_t Constant = cast<ConstantSDNode>(CmpOp1)->getZExtValue(); + unsigned Opcode, CCValid; + if (CmpOp0.getOpcode() == ISD::INTRINSIC_W_CHAIN && + CmpOp0.getResNo() == 0 && CmpOp0->hasNUsesOfValue(1, 0) && + isIntrinsicWithCCAndChain(CmpOp0, Opcode, CCValid)) + return getIntrinsicCmp(DAG, Opcode, CmpOp0, CCValid, Constant, Cond); + } Comparison C(CmpOp0, CmpOp1); C.CCMask = CCMaskForCondCode(Cond); if (C.Op0.getValueType().isFloatingPoint()) { @@ -1632,6 +1727,17 @@ static Comparison getCmp(SelectionDAG &D // Emit the comparison instruction described by C. static SDValue emitCmp(SelectionDAG &DAG, SDLoc DL, Comparison &C) { + if (!C.Op1.getNode()) { + SDValue Op; + switch (C.Op0.getOpcode()) { + case ISD::INTRINSIC_W_CHAIN: + Op = emitIntrinsicWithChainAndGlue(DAG, C.Op0, C.Opcode); + break; + default: + llvm_unreachable("Invalid comparison operands"); + } + return SDValue(Op.getNode(), Op->getNumValues() - 1); + } if (C.Opcode == SystemZISD::ICMP) return DAG.getNode(SystemZISD::ICMP, DL, MVT::Glue, C.Op0, C.Op1, DAG.getConstant(C.ICmpType, MVT::i32)); @@ -1713,7 +1819,6 @@ SDValue SystemZTargetLowering::lowerSETC } SDValue SystemZTargetLowering::lowerBR_CC(SDValue Op, SelectionDAG &DAG) const { - SDValue Chain = Op.getOperand(0); ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(1))->get(); SDValue CmpOp0 = Op.getOperand(2); SDValue CmpOp1 = Op.getOperand(3); @@ -1723,7 +1828,7 @@ SDValue SystemZTargetLowering::lowerBR_C Comparison C(getCmp(DAG, CmpOp0, CmpOp1, CC)); SDValue Glue = emitCmp(DAG, DL, C); return DAG.getNode(SystemZISD::BR_CCMASK, DL, Op.getValueType(), - Chain, DAG.getConstant(C.CCValid, MVT::i32), + Op.getOperand(0), DAG.getConstant(C.CCValid, MVT::i32), DAG.getConstant(C.CCMask, MVT::i32), Dest, Glue); } @@ -2561,6 +2666,30 @@ SDValue SystemZTargetLowering::lowerPREF Node->getMemoryVT(), Node->getMemOperand()); } +// Return an i32 that contains the value of CC immediately after After, +// whose final operand must be MVT::Glue. +static SDValue getCCResult(SelectionDAG &DAG, SDNode *After) { + SDValue Glue = SDValue(After, After->getNumValues() - 1); + SDValue IPM = DAG.getNode(SystemZISD::IPM, SDLoc(After), MVT::i32, Glue); + return DAG.getNode(ISD::SRL, SDLoc(After), MVT::i32, IPM, + DAG.getConstant(SystemZ::IPM_CC, MVT::i32)); +} + +SDValue +SystemZTargetLowering::lowerINTRINSIC_W_CHAIN(SDValue Op, + SelectionDAG &DAG) const { + unsigned Opcode, CCValid; + if (isIntrinsicWithCCAndChain(Op, Opcode, CCValid)) { + assert(Op->getNumValues() == 2 && "Expected only CC result and chain"); + SDValue Glued = emitIntrinsicWithChainAndGlue(DAG, Op, Opcode); + SDValue CC = getCCResult(DAG, Glued.getNode()); + DAG.ReplaceAllUsesOfValueWith(SDValue(Op.getNode(), 0), CC); + return SDValue(); + } + + return SDValue(); +} + SDValue SystemZTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const { switch (Op.getOpcode()) { @@ -2634,6 +2763,8 @@ SDValue SystemZTargetLowering::LowerOper return lowerSTACKRESTORE(Op, DAG); case ISD::PREFETCH: return lowerPREFETCH(Op, DAG); + case ISD::INTRINSIC_W_CHAIN: + return lowerINTRINSIC_W_CHAIN(Op, DAG); default: llvm_unreachable("Unexpected node to lower"); } @@ -2674,6 +2805,9 @@ const char *SystemZTargetLowering::getTa OPCODE(SEARCH_STRING); OPCODE(IPM); OPCODE(SERIALIZE); + OPCODE(TBEGIN); + OPCODE(TBEGIN_NOFLOAT); + OPCODE(TEND); OPCODE(ATOMIC_SWAPW); OPCODE(ATOMIC_LOADW_ADD); OPCODE(ATOMIC_LOADW_SUB); @@ -3501,6 +3635,50 @@ SystemZTargetLowering::emitStringWrapper return DoneMBB; } +// Update TBEGIN instruction with final opcode and register clobbers. +MachineBasicBlock * +SystemZTargetLowering::emitTransactionBegin(MachineInstr *MI, + MachineBasicBlock *MBB, + unsigned Opcode, + bool NoFloat) const { + MachineFunction &MF = *MBB->getParent(); + const TargetFrameLowering *TFI = Subtarget.getFrameLowering(); + const SystemZInstrInfo *TII = Subtarget.getInstrInfo(); + + // Update opcode. + MI->setDesc(TII->get(Opcode)); + + // We cannot handle a TBEGIN that clobbers the stack or frame pointer. + // Make sure to add the corresponding GRSM bits if they are missing. + uint64_t Control = MI->getOperand(2).getImm(); + static const unsigned GPRControlBit[16] = { + 0x8000, 0x8000, 0x4000, 0x4000, 0x2000, 0x2000, 0x1000, 0x1000, + 0x0800, 0x0800, 0x0400, 0x0400, 0x0200, 0x0200, 0x0100, 0x0100 + }; + Control |= GPRControlBit[15]; + if (TFI->hasFP(MF)) + Control |= GPRControlBit[11]; + MI->getOperand(2).setImm(Control); + + // Add GPR clobbers. + for (int I = 0; I < 16; I++) { + if ((Control & GPRControlBit[I]) == 0) { + unsigned Reg = SystemZMC::GR64Regs[I]; + MI->addOperand(MachineOperand::CreateReg(Reg, true, true)); + } + } + + // Add FPR clobbers. + if (!NoFloat && (Control & 4) != 0) { + for (int I = 0; I < 16; I++) { + unsigned Reg = SystemZMC::FP64Regs[I]; + MI->addOperand(MachineOperand::CreateReg(Reg, true, true)); + } + } + + return MBB; +} + MachineBasicBlock *SystemZTargetLowering:: EmitInstrWithCustomInserter(MachineInstr *MI, MachineBasicBlock *MBB) const { switch (MI->getOpcode()) { @@ -3742,6 +3920,12 @@ EmitInstrWithCustomInserter(MachineInstr return emitStringWrapper(MI, MBB, SystemZ::MVST); case SystemZ::SRSTLoop: return emitStringWrapper(MI, MBB, SystemZ::SRST); + case SystemZ::TBEGIN: + return emitTransactionBegin(MI, MBB, SystemZ::TBEGIN, false); + case SystemZ::TBEGIN_nofloat: + return emitTransactionBegin(MI, MBB, SystemZ::TBEGIN, true); + case SystemZ::TBEGINC: + return emitTransactionBegin(MI, MBB, SystemZ::TBEGINC, true); default: llvm_unreachable("Unexpected instr type to insert"); } Index: llvm-head/test/CodeGen/SystemZ/htm-intrinsics.ll =================================================================== --- /dev/null +++ llvm-head/test/CodeGen/SystemZ/htm-intrinsics.ll @@ -0,0 +1,352 @@ +; Test transactional-execution intrinsics. +; +; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=zEC12 | FileCheck %s + +declare i32 @llvm.s390.tbegin(i8 *, i32) +declare i32 @llvm.s390.tbegin.nofloat(i8 *, i32) +declare void @llvm.s390.tbeginc(i8 *, i32) +declare i32 @llvm.s390.tend() +declare void @llvm.s390.tabort(i64) +declare void @llvm.s390.ntstg(i64, i64 *) +declare i32 @llvm.s390.etnd() +declare void @llvm.s390.ppa.txassist(i32) + +; TBEGIN. +define void @test_tbegin() { +; CHECK-LABEL: test_tbegin: +; CHECK-NOT: stmg +; CHECK: std %f8, +; CHECK: std %f9, +; CHECK: std %f10, +; CHECK: std %f11, +; CHECK: std %f12, +; CHECK: std %f13, +; CHECK: std %f14, +; CHECK: std %f15, +; CHECK: tbegin 0, 65292 +; CHECK: ld %f8, +; CHECK: ld %f9, +; CHECK: ld %f10, +; CHECK: ld %f11, +; CHECK: ld %f12, +; CHECK: ld %f13, +; CHECK: ld %f14, +; CHECK: ld %f15, +; CHECK: br %r14 + call i32 @llvm.s390.tbegin(i8 *null, i32 65292) + ret void +} + +; TBEGIN (nofloat). +define void @test_tbegin_nofloat1() { +; CHECK-LABEL: test_tbegin_nofloat1: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + ret void +} + +; TBEGIN (nofloat) with integer CC return value. +define i32 @test_tbegin_nofloat2() { +; CHECK-LABEL: test_tbegin_nofloat2: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + ret i32 %res +} + +; TBEGIN (nofloat) with implicit CC check. +define void @test_tbegin_nofloat3(i32 *%ptr) { +; CHECK-LABEL: test_tbegin_nofloat3: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: jnh {{\.L*}} +; CHECK: mvhi 0(%r2), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret void +} + +; TBEGIN (nofloat) with dual CC use. +define i32 @test_tbegin_nofloat4(i32 %pad, i32 *%ptr) { +; CHECK-LABEL: test_tbegin_nofloat4: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: cijlh %r2, 2, {{\.L*}} +; CHECK: mvhi 0(%r3), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret i32 %res +} + +; TBEGIN (nofloat) with register. +define void @test_tbegin_nofloat5(i8 *%ptr) { +; CHECK-LABEL: test_tbegin_nofloat5: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0(%r2), 65292 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *%ptr, i32 65292) + ret void +} + +; TBEGIN (nofloat) with GRSM 0x0f00. +define void @test_tbegin_nofloat6() { +; CHECK-LABEL: test_tbegin_nofloat6: +; CHECK: stmg %r6, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 3840 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 3840) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xf100. +define void @test_tbegin_nofloat7() { +; CHECK-LABEL: test_tbegin_nofloat7: +; CHECK: stmg %r8, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 61696 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 61696) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xfe00 -- stack pointer added automatically. +define void @test_tbegin_nofloat8() { +; CHECK-LABEL: test_tbegin_nofloat8: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65280 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65024) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xfb00 -- no frame pointer needed. +define void @test_tbegin_nofloat9() { +; CHECK-LABEL: test_tbegin_nofloat9: +; CHECK: stmg %r10, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 64256 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 64256) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xfb00 -- frame pointer added automatically. +define void @test_tbegin_nofloat10(i64 %n) { +; CHECK-LABEL: test_tbegin_nofloat10: +; CHECK: stmg %r11, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 65280 +; CHECK: br %r14 + %buf = alloca i8, i64 %n + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 64256) + ret void +} + +; TBEGINC. +define void @test_tbeginc() { +; CHECK-LABEL: test_tbeginc: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbeginc 0, 65288 +; CHECK: br %r14 + call void @llvm.s390.tbeginc(i8 *null, i32 65288) + ret void +} + +; TEND with integer CC return value. +define i32 @test_tend1() { +; CHECK-LABEL: test_tend1: +; CHECK: tend +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tend() + ret i32 %res +} + +; TEND with implicit CC check. +define void @test_tend3(i32 *%ptr) { +; CHECK-LABEL: test_tend3: +; CHECK: tend +; CHECK: je {{\.L*}} +; CHECK: mvhi 0(%r2), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tend() + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret void +} + +; TEND with dual CC use. +define i32 @test_tend2(i32 %pad, i32 *%ptr) { +; CHECK-LABEL: test_tend2: +; CHECK: tend +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: cijlh %r2, 2, {{\.L*}} +; CHECK: mvhi 0(%r3), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tend() + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret i32 %res +} + +; TABORT with register only. +define void @test_tabort1(i64 %val) { +; CHECK-LABEL: test_tabort1: +; CHECK: tabort 0(%r2) +; CHECK: br %r14 + call void @llvm.s390.tabort(i64 %val) + ret void +} + +; TABORT with immediate only. +define void @test_tabort2(i64 %val) { +; CHECK-LABEL: test_tabort2: +; CHECK: tabort 1234 +; CHECK: br %r14 + call void @llvm.s390.tabort(i64 1234) + ret void +} + +; TABORT with register + immediate. +define void @test_tabort3(i64 %val) { +; CHECK-LABEL: test_tabort3: +; CHECK: tabort 1234(%r2) +; CHECK: br %r14 + %sum = add i64 %val, 1234 + call void @llvm.s390.tabort(i64 %sum) + ret void +} + +; TABORT with out-of-range immediate. +define void @test_tabort4(i64 %val) { +; CHECK-LABEL: test_tabort4: +; CHECK: tabort 0({{%r[1-5]}}) +; CHECK: br %r14 + call void @llvm.s390.tabort(i64 4096) + ret void +} + +; NTSTG with base pointer only. +define void @test_ntstg1(i64 *%ptr, i64 %val) { +; CHECK-LABEL: test_ntstg1: +; CHECK: ntstg %r3, 0(%r2) +; CHECK: br %r14 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with base and index. +; Check that VSTL doesn't allow an index. +define void @test_ntstg2(i64 *%base, i64 %index, i64 %val) { +; CHECK-LABEL: test_ntstg2: +; CHECK: sllg [[REG:%r[1-5]]], %r3, 3 +; CHECK: ntstg %r4, 0([[REG]],%r2) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 %index + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with the highest in-range displacement. +define void @test_ntstg3(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg3: +; CHECK: ntstg %r3, 524280(%r2) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 65535 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with an out-of-range positive displacement. +define void @test_ntstg4(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg4: +; CHECK: ntstg %r3, 0({{%r[1-5]}}) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 65536 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with the lowest in-range displacement. +define void @test_ntstg5(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg5: +; CHECK: ntstg %r3, -524288(%r2) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 -65536 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with an out-of-range negative displacement. +define void @test_ntstg6(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg6: +; CHECK: ntstg %r3, 0({{%r[1-5]}}) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 -65537 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; ETND. +define i32 @test_etnd() { +; CHECK-LABEL: test_etnd: +; CHECK: etnd %r2 +; CHECK: br %r14 + %res = call i32 @llvm.s390.etnd() + ret i32 %res +} + +; PPA (Transaction-Abort Assist) +define void @test_ppa_txassist(i32 %val) { +; CHECK-LABEL: test_ppa_txassist: +; CHECK: ppa %r2, 0, 1 +; CHECK: br %r14 + call void @llvm.s390.ppa.txassist(i32 %val) + ret void +} + Index: llvm-head/test/MC/SystemZ/insn-bad-zEC12.s =================================================================== --- llvm-head.orig/test/MC/SystemZ/insn-bad-zEC12.s +++ llvm-head/test/MC/SystemZ/insn-bad-zEC12.s @@ -3,6 +3,22 @@ # RUN: FileCheck < %t %s #CHECK: error: invalid operand +#CHECK: ntstg %r0, -524289 +#CHECK: error: invalid operand +#CHECK: ntstg %r0, 524288 + + ntstg %r0, -524289 + ntstg %r0, 524288 + +#CHECK: error: invalid operand +#CHECK: ppa %r0, %r0, -1 +#CHECK: error: invalid operand +#CHECK: ppa %r0, %r0, 16 + + ppa %r0, %r0, -1 + ppa %r0, %r0, 16 + +#CHECK: error: invalid operand #CHECK: risbgn %r0,%r0,0,0,-1 #CHECK: error: invalid operand #CHECK: risbgn %r0,%r0,0,0,64 @@ -22,3 +38,47 @@ risbgn %r0,%r0,-1,0,0 risbgn %r0,%r0,256,0,0 +#CHECK: error: invalid operand +#CHECK: tabort -1 +#CHECK: error: invalid operand +#CHECK: tabort 4096 +#CHECK: error: invalid use of indexed addressing +#CHECK: tabort 0(%r1,%r2) + + tabort -1 + tabort 4096 + tabort 0(%r1,%r2) + +#CHECK: error: invalid operand +#CHECK: tbegin -1, 0 +#CHECK: error: invalid operand +#CHECK: tbegin 4096, 0 +#CHECK: error: invalid use of indexed addressing +#CHECK: tbegin 0(%r1,%r2), 0 +#CHECK: error: invalid operand +#CHECK: tbegin 0, -1 +#CHECK: error: invalid operand +#CHECK: tbegin 0, 65536 + + tbegin -1, 0 + tbegin 4096, 0 + tbegin 0(%r1,%r2), 0 + tbegin 0, -1 + tbegin 0, 65536 + +#CHECK: error: invalid operand +#CHECK: tbeginc -1, 0 +#CHECK: error: invalid operand +#CHECK: tbeginc 4096, 0 +#CHECK: error: invalid use of indexed addressing +#CHECK: tbeginc 0(%r1,%r2), 0 +#CHECK: error: invalid operand +#CHECK: tbeginc 0, -1 +#CHECK: error: invalid operand +#CHECK: tbeginc 0, 65536 + + tbeginc -1, 0 + tbeginc 4096, 0 + tbeginc 0(%r1,%r2), 0 + tbeginc 0, -1 + tbeginc 0, 65536 Index: llvm-head/test/MC/SystemZ/insn-good-zEC12.s =================================================================== --- llvm-head.orig/test/MC/SystemZ/insn-good-zEC12.s +++ llvm-head/test/MC/SystemZ/insn-good-zEC12.s @@ -1,6 +1,48 @@ # For zEC12 and above. # RUN: llvm-mc -triple s390x-linux-gnu -mcpu=zEC12 -show-encoding %s | FileCheck %s +#CHECK: etnd %r0 # encoding: [0xb2,0xec,0x00,0x00] +#CHECK: etnd %r15 # encoding: [0xb2,0xec,0x00,0xf0] +#CHECK: etnd %r7 # encoding: [0xb2,0xec,0x00,0x70] + + etnd %r0 + etnd %r15 + etnd %r7 + +#CHECK: ntstg %r0, -524288 # encoding: [0xe3,0x00,0x00,0x00,0x80,0x25] +#CHECK: ntstg %r0, -1 # encoding: [0xe3,0x00,0x0f,0xff,0xff,0x25] +#CHECK: ntstg %r0, 0 # encoding: [0xe3,0x00,0x00,0x00,0x00,0x25] +#CHECK: ntstg %r0, 1 # encoding: [0xe3,0x00,0x00,0x01,0x00,0x25] +#CHECK: ntstg %r0, 524287 # encoding: [0xe3,0x00,0x0f,0xff,0x7f,0x25] +#CHECK: ntstg %r0, 0(%r1) # encoding: [0xe3,0x00,0x10,0x00,0x00,0x25] +#CHECK: ntstg %r0, 0(%r15) # encoding: [0xe3,0x00,0xf0,0x00,0x00,0x25] +#CHECK: ntstg %r0, 524287(%r1,%r15) # encoding: [0xe3,0x01,0xff,0xff,0x7f,0x25] +#CHECK: ntstg %r0, 524287(%r15,%r1) # encoding: [0xe3,0x0f,0x1f,0xff,0x7f,0x25] +#CHECK: ntstg %r15, 0 # encoding: [0xe3,0xf0,0x00,0x00,0x00,0x25] + + ntstg %r0, -524288 + ntstg %r0, -1 + ntstg %r0, 0 + ntstg %r0, 1 + ntstg %r0, 524287 + ntstg %r0, 0(%r1) + ntstg %r0, 0(%r15) + ntstg %r0, 524287(%r1,%r15) + ntstg %r0, 524287(%r15,%r1) + ntstg %r15, 0 + +#CHECK: ppa %r0, %r0, 0 # encoding: [0xb2,0xe8,0x00,0x00] +#CHECK: ppa %r0, %r0, 15 # encoding: [0xb2,0xe8,0xf0,0x00] +#CHECK: ppa %r0, %r15, 0 # encoding: [0xb2,0xe8,0x00,0x0f] +#CHECK: ppa %r4, %r6, 7 # encoding: [0xb2,0xe8,0x70,0x46] +#CHECK: ppa %r15, %r0, 0 # encoding: [0xb2,0xe8,0x00,0xf0] + + ppa %r0, %r0, 0 + ppa %r0, %r0, 15 + ppa %r0, %r15, 0 + ppa %r4, %r6, 7 + ppa %r15, %r0, 0 + #CHECK: risbgn %r0, %r0, 0, 0, 0 # encoding: [0xec,0x00,0x00,0x00,0x00,0x59] #CHECK: risbgn %r0, %r0, 0, 0, 63 # encoding: [0xec,0x00,0x00,0x00,0x3f,0x59] #CHECK: risbgn %r0, %r0, 0, 255, 0 # encoding: [0xec,0x00,0x00,0xff,0x00,0x59] @@ -17,3 +59,68 @@ risbgn %r15,%r0,0,0,0 risbgn %r4,%r5,6,7,8 +#CHECK: tabort 0 # encoding: [0xb2,0xfc,0x00,0x00] +#CHECK: tabort 0(%r1) # encoding: [0xb2,0xfc,0x10,0x00] +#CHECK: tabort 0(%r15) # encoding: [0xb2,0xfc,0xf0,0x00] +#CHECK: tabort 4095 # encoding: [0xb2,0xfc,0x0f,0xff] +#CHECK: tabort 4095(%r1) # encoding: [0xb2,0xfc,0x1f,0xff] +#CHECK: tabort 4095(%r15) # encoding: [0xb2,0xfc,0xff,0xff] + + tabort 0 + tabort 0(%r1) + tabort 0(%r15) + tabort 4095 + tabort 4095(%r1) + tabort 4095(%r15) + +#CHECK: tbegin 0, 0 # encoding: [0xe5,0x60,0x00,0x00,0x00,0x00] +#CHECK: tbegin 4095, 0 # encoding: [0xe5,0x60,0x0f,0xff,0x00,0x00] +#CHECK: tbegin 0, 0 # encoding: [0xe5,0x60,0x00,0x00,0x00,0x00] +#CHECK: tbegin 0, 1 # encoding: [0xe5,0x60,0x00,0x00,0x00,0x01] +#CHECK: tbegin 0, 32767 # encoding: [0xe5,0x60,0x00,0x00,0x7f,0xff] +#CHECK: tbegin 0, 32768 # encoding: [0xe5,0x60,0x00,0x00,0x80,0x00] +#CHECK: tbegin 0, 65535 # encoding: [0xe5,0x60,0x00,0x00,0xff,0xff] +#CHECK: tbegin 0(%r1), 42 # encoding: [0xe5,0x60,0x10,0x00,0x00,0x2a] +#CHECK: tbegin 0(%r15), 42 # encoding: [0xe5,0x60,0xf0,0x00,0x00,0x2a] +#CHECK: tbegin 4095(%r1), 42 # encoding: [0xe5,0x60,0x1f,0xff,0x00,0x2a] +#CHECK: tbegin 4095(%r15), 42 # encoding: [0xe5,0x60,0xff,0xff,0x00,0x2a] + + tbegin 0, 0 + tbegin 4095, 0 + tbegin 0, 0 + tbegin 0, 1 + tbegin 0, 32767 + tbegin 0, 32768 + tbegin 0, 65535 + tbegin 0(%r1), 42 + tbegin 0(%r15), 42 + tbegin 4095(%r1), 42 + tbegin 4095(%r15), 42 + +#CHECK: tbeginc 0, 0 # encoding: [0xe5,0x61,0x00,0x00,0x00,0x00] +#CHECK: tbeginc 4095, 0 # encoding: [0xe5,0x61,0x0f,0xff,0x00,0x00] +#CHECK: tbeginc 0, 0 # encoding: [0xe5,0x61,0x00,0x00,0x00,0x00] +#CHECK: tbeginc 0, 1 # encoding: [0xe5,0x61,0x00,0x00,0x00,0x01] +#CHECK: tbeginc 0, 32767 # encoding: [0xe5,0x61,0x00,0x00,0x7f,0xff] +#CHECK: tbeginc 0, 32768 # encoding: [0xe5,0x61,0x00,0x00,0x80,0x00] +#CHECK: tbeginc 0, 65535 # encoding: [0xe5,0x61,0x00,0x00,0xff,0xff] +#CHECK: tbeginc 0(%r1), 42 # encoding: [0xe5,0x61,0x10,0x00,0x00,0x2a] +#CHECK: tbeginc 0(%r15), 42 # encoding: [0xe5,0x61,0xf0,0x00,0x00,0x2a] +#CHECK: tbeginc 4095(%r1), 42 # encoding: [0xe5,0x61,0x1f,0xff,0x00,0x2a] +#CHECK: tbeginc 4095(%r15), 42 # encoding: [0xe5,0x61,0xff,0xff,0x00,0x2a] + + tbeginc 0, 0 + tbeginc 4095, 0 + tbeginc 0, 0 + tbeginc 0, 1 + tbeginc 0, 32767 + tbeginc 0, 32768 + tbeginc 0, 65535 + tbeginc 0(%r1), 42 + tbeginc 0(%r15), 42 + tbeginc 4095(%r1), 42 + tbeginc 4095(%r15), 42 + +#CHECK: tend # encoding: [0xb2,0xf8,0x00,0x00] + + tend Index: llvm-head/test/MC/SystemZ/insn-bad-z196.s =================================================================== --- llvm-head.orig/test/MC/SystemZ/insn-bad-z196.s +++ llvm-head/test/MC/SystemZ/insn-bad-z196.s @@ -244,6 +244,11 @@ cxlgbr %f0, 16, %r0, 0 cxlgbr %f2, 0, %r0, 0 +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: etnd %r7 + + etnd %r7 + #CHECK: error: invalid operand #CHECK: fidbra %f0, 0, %f0, -1 #CHECK: error: invalid operand @@ -546,6 +551,16 @@ locr %r0,%r0,-1 locr %r0,%r0,16 +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: ntstg %r0, 524287(%r1,%r15) + + ntstg %r0, 524287(%r1,%r15) + +#CHECK: error: {{(instruction requires: processor-assist)?}} +#CHECK: ppa %r4, %r6, 7 + + ppa %r4, %r6, 7 + #CHECK: error: {{(instruction requires: miscellaneous-extensions)?}} #CHECK: risbgn %r1, %r2, 0, 0, 0 @@ -690,3 +705,24 @@ stocg %r0,-524289,1 stocg %r0,524288,1 stocg %r0,0(%r1,%r2),1 + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tabort 4095(%r1) + + tabort 4095(%r1) + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tbegin 4095(%r1), 42 + + tbegin 4095(%r1), 42 + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tbeginc 4095(%r1), 42 + + tbeginc 4095(%r1), 42 + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tend + + tend + Index: llvm-head/test/MC/Disassembler/SystemZ/insns.txt =================================================================== --- llvm-head.orig/test/MC/Disassembler/SystemZ/insns.txt +++ llvm-head/test/MC/Disassembler/SystemZ/insns.txt @@ -2503,6 +2503,15 @@ # CHECK: ear %r15, %a15 0xb2 0x4f 0x00 0xff +# CHECK: etnd %r0 +0xb2 0xec 0x00 0x00 + +# CHECK: etnd %r15 +0xb2 0xec 0x00 0xf0 + +# CHECK: etnd %r7 +0xb2 0xec 0x00 0x70 + # CHECK: fidbr %f0, 0, %f0 0xb3 0x5f 0x00 0x00 @@ -6034,6 +6043,36 @@ # CHECK: ny %r15, 0 0xe3 0xf0 0x00 0x00 0x00 0x54 +# CHECK: ntstg %r0, -524288 +0xe3 0x00 0x00 0x00 0x80 0x25 + +# CHECK: ntstg %r0, -1 +0xe3 0x00 0x0f 0xff 0xff 0x25 + +# CHECK: ntstg %r0, 0 +0xe3 0x00 0x00 0x00 0x00 0x25 + +# CHECK: ntstg %r0, 1 +0xe3 0x00 0x00 0x01 0x00 0x25 + +# CHECK: ntstg %r0, 524287 +0xe3 0x00 0x0f 0xff 0x7f 0x25 + +# CHECK: ntstg %r0, 0(%r1) +0xe3 0x00 0x10 0x00 0x00 0x25 + +# CHECK: ntstg %r0, 0(%r15) +0xe3 0x00 0xf0 0x00 0x00 0x25 + +# CHECK: ntstg %r0, 524287(%r1,%r15) +0xe3 0x01 0xff 0xff 0x7f 0x25 + +# CHECK: ntstg %r0, 524287(%r15,%r1) +0xe3 0x0f 0x1f 0xff 0x7f 0x25 + +# CHECK: ntstg %r15, 0 +0xe3 0xf0 0x00 0x00 0x00 0x25 + # CHECK: oc 0(1), 0 0xd6 0x00 0x00 0x00 0x00 0x00 @@ -6346,6 +6385,21 @@ # CHECK: popcnt %r7, %r8 0xb9 0xe1 0x00 0x78 +# CHECK: ppa %r0, %r0, 0 +0xb2 0xe8 0x00 0x00 + +# CHECK: ppa %r0, %r0, 15 +0xb2 0xe8 0xf0 0x00 + +# CHECK: ppa %r0, %r15, 0 +0xb2 0xe8 0x00 0x0f + +# CHECK: ppa %r4, %r6, 7 +0xb2 0xe8 0x70 0x46 + +# CHECK: ppa %r15, %r0, 0 +0xb2 0xe8 0x00 0xf0 + # CHECK: risbg %r0, %r0, 0, 0, 0 0xec 0x00 0x00 0x00 0x00 0x55 @@ -8062,6 +8116,93 @@ # CHECK: sy %r15, 0 0xe3 0xf0 0x00 0x00 0x00 0x5b +# CHECK: tabort 0 +0xb2 0xfc 0x00 0x00 + +# CHECK: tabort 0(%r1) +0xb2 0xfc 0x10 0x00 + +# CHECK: tabort 0(%r15) +0xb2 0xfc 0xf0 0x00 + +# CHECK: tabort 4095 +0xb2 0xfc 0x0f 0xff + +# CHECK: tabort 4095(%r1) +0xb2 0xfc 0x1f 0xff + +# CHECK: tabort 4095(%r15) +0xb2 0xfc 0xff 0xff + +# CHECK: tbegin 0, 0 +0xe5 0x60 0x00 0x00 0x00 0x00 + +# CHECK: tbegin 4095, 0 +0xe5 0x60 0x0f 0xff 0x00 0x00 + +# CHECK: tbegin 0, 0 +0xe5 0x60 0x00 0x00 0x00 0x00 + +# CHECK: tbegin 0, 1 +0xe5 0x60 0x00 0x00 0x00 0x01 + +# CHECK: tbegin 0, 32767 +0xe5 0x60 0x00 0x00 0x7f 0xff + +# CHECK: tbegin 0, 32768 +0xe5 0x60 0x00 0x00 0x80 0x00 + +# CHECK: tbegin 0, 65535 +0xe5 0x60 0x00 0x00 0xff 0xff + +# CHECK: tbegin 0(%r1), 42 +0xe5 0x60 0x10 0x00 0x00 0x2a + +# CHECK: tbegin 0(%r15), 42 +0xe5 0x60 0xf0 0x00 0x00 0x2a + +# CHECK: tbegin 4095(%r1), 42 +0xe5 0x60 0x1f 0xff 0x00 0x2a + +# CHECK: tbegin 4095(%r15), 42 +0xe5 0x60 0xff 0xff 0x00 0x2a + +# CHECK: tbeginc 0, 0 +0xe5 0x61 0x00 0x00 0x00 0x00 + +# CHECK: tbeginc 4095, 0 +0xe5 0x61 0x0f 0xff 0x00 0x00 + +# CHECK: tbeginc 0, 0 +0xe5 0x61 0x00 0x00 0x00 0x00 + +# CHECK: tbeginc 0, 1 +0xe5 0x61 0x00 0x00 0x00 0x01 + +# CHECK: tbeginc 0, 32767 +0xe5 0x61 0x00 0x00 0x7f 0xff + +# CHECK: tbeginc 0, 32768 +0xe5 0x61 0x00 0x00 0x80 0x00 + +# CHECK: tbeginc 0, 65535 +0xe5 0x61 0x00 0x00 0xff 0xff + +# CHECK: tbeginc 0(%r1), 42 +0xe5 0x61 0x10 0x00 0x00 0x2a + +# CHECK: tbeginc 0(%r15), 42 +0xe5 0x61 0xf0 0x00 0x00 0x2a + +# CHECK: tbeginc 4095(%r1), 42 +0xe5 0x61 0x1f 0xff 0x00 0x2a + +# CHECK: tbeginc 4095(%r15), 42 +0xe5 0x61 0xff 0xff 0x00 0x2a + +# CHECK: tend +0xb2 0xf8 0x00 0x00 + # CHECK: tm 0, 0 0x91 0x00 0x00 0x00 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@233803 91177308-0d34-0410-b5e6-96231b3b80d8
2015-04-01 12:51:43 +00:00
case systemz: return "s390";
case x86:
case x86_64: return "x86";
case xcore: return "xcore";
case nvptx: return "nvptx";
case nvptx64: return "nvptx";
case le32: return "le32";
case le64: return "le64";
case amdil:
case amdil64: return "amdil";
case hsail:
case hsail64: return "hsail";
case spir:
case spir64: return "spir";
case kalimba: return "kalimba";
}
}
const char *Triple::getVendorTypeName(VendorType Kind) {
switch (Kind) {
case UnknownVendor: return "unknown";
case Apple: return "apple";
case PC: return "pc";
case SCEI: return "scei";
case BGP: return "bgp";
case BGQ: return "bgq";
case Freescale: return "fsl";
case IBM: return "ibm";
case ImaginationTechnologies: return "img";
case MipsTechnologies: return "mti";
case NVIDIA: return "nvidia";
case CSR: return "csr";
}
llvm_unreachable("Invalid VendorType!");
}
const char *Triple::getOSTypeName(OSType Kind) {
switch (Kind) {
case UnknownOS: return "unknown";
case CloudABI: return "cloudabi";
case Darwin: return "darwin";
case DragonFly: return "dragonfly";
case FreeBSD: return "freebsd";
case IOS: return "ios";
case KFreeBSD: return "kfreebsd";
case Linux: return "linux";
case Lv2: return "lv2";
case MacOSX: return "macosx";
case NetBSD: return "netbsd";
case OpenBSD: return "openbsd";
case Solaris: return "solaris";
case Win32: return "windows";
case Haiku: return "haiku";
case Minix: return "minix";
case RTEMS: return "rtems";
case NaCl: return "nacl";
case CNK: return "cnk";
case Bitrig: return "bitrig";
case AIX: return "aix";
case CUDA: return "cuda";
case NVCL: return "nvcl";
case AMDHSA: return "amdhsa";
case PS4: return "ps4";
}
llvm_unreachable("Invalid OSType");
}
const char *Triple::getEnvironmentTypeName(EnvironmentType Kind) {
switch (Kind) {
case UnknownEnvironment: return "unknown";
case GNU: return "gnu";
case GNUEABIHF: return "gnueabihf";
case GNUEABI: return "gnueabi";
case GNUX32: return "gnux32";
case CODE16: return "code16";
case EABI: return "eabi";
case EABIHF: return "eabihf";
case Android: return "android";
case MSVC: return "msvc";
case Itanium: return "itanium";
case Cygnus: return "cygnus";
}
llvm_unreachable("Invalid EnvironmentType!");
}
Triple::ArchType Triple::getArchTypeForLLVMName(StringRef Name) {
return StringSwitch<Triple::ArchType>(Name)
.Case("aarch64", aarch64)
.Case("aarch64_be", aarch64_be)
.Case("arm64", aarch64) // "arm64" is an alias for "aarch64"
.Case("arm", arm)
.Case("armeb", armeb)
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
.Case("bpf", bpf)
.Case("mips", mips)
.Case("mipsel", mipsel)
.Case("mips64", mips64)
.Case("mips64el", mips64el)
.Case("msp430", msp430)
.Case("ppc64", ppc64)
.Case("ppc32", ppc)
.Case("ppc", ppc)
.Case("ppc64le", ppc64le)
.Case("r600", r600)
.Case("amdgcn", amdgcn)
.Case("hexagon", hexagon)
.Case("sparc", sparc)
.Case("sparcel", sparcel)
.Case("sparcv9", sparcv9)
.Case("systemz", systemz)
.Case("tce", tce)
.Case("thumb", thumb)
.Case("thumbeb", thumbeb)
.Case("x86", x86)
.Case("x86-64", x86_64)
.Case("xcore", xcore)
.Case("nvptx", nvptx)
.Case("nvptx64", nvptx64)
.Case("le32", le32)
.Case("le64", le64)
.Case("amdil", amdil)
.Case("amdil64", amdil64)
.Case("hsail", hsail)
.Case("hsail64", hsail64)
.Case("spir", spir)
.Case("spir64", spir64)
.Case("kalimba", kalimba)
.Default(UnknownArch);
}
TargetParser: FPU/ARCH/EXT parsing refactory - NFC This new class in a global context contain arch-specific knowledge in order to provide LLVM libraries, tools and projects with the ability to understand the architectures. For now, only FPU, ARCH and ARCH extensions on ARM are supported. Current behaviour it to parse from free-text to enum values and back, so that all users can share the same parser and codes. This simplifies a lot both the ASM/Obj streamers in the back-end (where this came from), and the front-end parsers for command line arguments (where this is going to be used next). The previous implementation, using .def/.h includes is deprecated due to its inflexibility to be built without the backend support and for being too cumbersome. As more architectures join this scheme, and as more features of such architectures are added (such as hardware features, type sizes, etc) into a full blown TargetDescription class, having a set of classes is the most sane implementation. The ultimate goal of this refactor both LLVM's and Clang's target description classes into one unique interface, so that we can de-duplicate and standardise the descriptions, as well as make it available for other front-ends, tools, etc. The FPU parsing for command line options in Clang has been converted to use this new library and a number of aliases were added for compatibility: * A bogus neon-vfpv3 alias (neon defaults to vfp3) * armv5/v6 * {fp4/fp5}-{sp/dp}-d16 Next steps: * Port Clang's ARCH/EXT parsing to use this library. * Create a TableGen back-end to generate this information. * Run this TableGen process regardless of which back-ends are built. * Expose more information and rename it to TargetDescription. * Continue re-factoring Clang to use as much of it as possible. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236900 91177308-0d34-0410-b5e6-96231b3b80d8
2015-05-08 21:04:27 +00:00
// FIXME: Use ARMTargetParser. This would require Triple::arm/thumb
// to be recogniseable universally.
static Triple::ArchType parseARMArch(StringRef ArchName) {
size_t offset = StringRef::npos;
Triple::ArchType arch = Triple::UnknownArch;
bool isThumb = ArchName.startswith("thumb");
if (ArchName.equals("arm"))
return Triple::arm;
if (ArchName.equals("armeb"))
return Triple::armeb;
if (ArchName.equals("thumb"))
return Triple::thumb;
if (ArchName.equals("thumbeb"))
return Triple::thumbeb;
if (ArchName.equals("arm64") || ArchName.equals("aarch64"))
return Triple::aarch64;
if (ArchName.equals("aarch64_be"))
return Triple::aarch64_be;
if (ArchName.startswith("armv")) {
offset = 3;
if (ArchName.endswith("eb")) {
arch = Triple::armeb;
ArchName = ArchName.substr(0, ArchName.size() - 2);
} else
arch = Triple::arm;
} else if (ArchName.startswith("armebv")) {
offset = 5;
arch = Triple::armeb;
} else if (ArchName.startswith("thumbv")) {
offset = 5;
if (ArchName.endswith("eb")) {
arch = Triple::thumbeb;
ArchName = ArchName.substr(0, ArchName.size() - 2);
} else
arch = Triple::thumb;
} else if (ArchName.startswith("thumbebv")) {
offset = 7;
arch = Triple::thumbeb;
}
return StringSwitch<Triple::ArchType>(ArchName.substr(offset))
.Cases("v2", "v2a", isThumb ? Triple::UnknownArch : arch)
.Cases("v3", "v3m", isThumb ? Triple::UnknownArch : arch)
.Cases("v4", "v4t", arch)
.Cases("v5", "v5e", "v5t", "v5te", "v5tej", arch)
.Cases("v6", "v6hl", "v6j", "v6k", arch)
.Cases("v6m", "v6sm", arch)
.Cases("v6t2", "v6z", "v6zk", arch)
.Cases("v7", "v7a", "v7em", "v7hl", "v7l", arch)
.Cases("v7m", "v7r", "v7s", arch)
.Cases("v8", "v8a", arch)
.Cases("v8.1", "v8.1a", arch)
.Default(Triple::UnknownArch);
}
static Triple::ArchType parseArch(StringRef ArchName) {
Triple::ArchType ARMArch(parseARMArch(ArchName));
return StringSwitch<Triple::ArchType>(ArchName)
.Cases("i386", "i486", "i586", "i686", Triple::x86)
// FIXME: Do we need to support these?
.Cases("i786", "i886", "i986", Triple::x86)
.Cases("amd64", "x86_64", "x86_64h", Triple::x86_64)
.Case("powerpc", Triple::ppc)
.Cases("powerpc64", "ppu", Triple::ppc64)
.Case("powerpc64le", Triple::ppc64le)
.Case("xscale", Triple::arm)
.Case("xscaleeb", Triple::armeb)
.StartsWith("arm", ARMArch)
.StartsWith("thumb", ARMArch)
.StartsWith("aarch64", ARMArch)
.Case("msp430", Triple::msp430)
.Cases("mips", "mipseb", "mipsallegrex", Triple::mips)
.Cases("mipsel", "mipsallegrexel", Triple::mipsel)
.Cases("mips64", "mips64eb", Triple::mips64)
.Case("mips64el", Triple::mips64el)
.Case("r600", Triple::r600)
.Case("amdgcn", Triple::amdgcn)
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
.Case("bpf", Triple::bpf)
.Case("hexagon", Triple::hexagon)
.Case("s390x", Triple::systemz)
.Case("sparc", Triple::sparc)
.Case("sparcel", Triple::sparcel)
.Cases("sparcv9", "sparc64", Triple::sparcv9)
.Case("tce", Triple::tce)
.Case("xcore", Triple::xcore)
.Case("nvptx", Triple::nvptx)
.Case("nvptx64", Triple::nvptx64)
.Case("le32", Triple::le32)
.Case("le64", Triple::le64)
.Case("amdil", Triple::amdil)
.Case("amdil64", Triple::amdil64)
.Case("hsail", Triple::hsail)
.Case("hsail64", Triple::hsail64)
.Case("spir", Triple::spir)
.Case("spir64", Triple::spir64)
.StartsWith("kalimba", Triple::kalimba)
.Default(Triple::UnknownArch);
}
static Triple::VendorType parseVendor(StringRef VendorName) {
return StringSwitch<Triple::VendorType>(VendorName)
.Case("apple", Triple::Apple)
.Case("pc", Triple::PC)
.Case("scei", Triple::SCEI)
.Case("bgp", Triple::BGP)
.Case("bgq", Triple::BGQ)
.Case("fsl", Triple::Freescale)
.Case("ibm", Triple::IBM)
.Case("img", Triple::ImaginationTechnologies)
.Case("mti", Triple::MipsTechnologies)
.Case("nvidia", Triple::NVIDIA)
.Case("csr", Triple::CSR)
.Default(Triple::UnknownVendor);
}
static Triple::OSType parseOS(StringRef OSName) {
return StringSwitch<Triple::OSType>(OSName)
.StartsWith("cloudabi", Triple::CloudABI)
.StartsWith("darwin", Triple::Darwin)
.StartsWith("dragonfly", Triple::DragonFly)
.StartsWith("freebsd", Triple::FreeBSD)
.StartsWith("ios", Triple::IOS)
.StartsWith("kfreebsd", Triple::KFreeBSD)
.StartsWith("linux", Triple::Linux)
.StartsWith("lv2", Triple::Lv2)
.StartsWith("macosx", Triple::MacOSX)
.StartsWith("netbsd", Triple::NetBSD)
.StartsWith("openbsd", Triple::OpenBSD)
.StartsWith("solaris", Triple::Solaris)
.StartsWith("win32", Triple::Win32)
.StartsWith("windows", Triple::Win32)
.StartsWith("haiku", Triple::Haiku)
.StartsWith("minix", Triple::Minix)
.StartsWith("rtems", Triple::RTEMS)
.StartsWith("nacl", Triple::NaCl)
.StartsWith("cnk", Triple::CNK)
.StartsWith("bitrig", Triple::Bitrig)
.StartsWith("aix", Triple::AIX)
.StartsWith("cuda", Triple::CUDA)
.StartsWith("nvcl", Triple::NVCL)
.StartsWith("amdhsa", Triple::AMDHSA)
.StartsWith("ps4", Triple::PS4)
.Default(Triple::UnknownOS);
}
static Triple::EnvironmentType parseEnvironment(StringRef EnvironmentName) {
return StringSwitch<Triple::EnvironmentType>(EnvironmentName)
.StartsWith("eabihf", Triple::EABIHF)
.StartsWith("eabi", Triple::EABI)
.StartsWith("gnueabihf", Triple::GNUEABIHF)
.StartsWith("gnueabi", Triple::GNUEABI)
.StartsWith("gnux32", Triple::GNUX32)
.StartsWith("code16", Triple::CODE16)
.StartsWith("gnu", Triple::GNU)
.StartsWith("android", Triple::Android)
.StartsWith("msvc", Triple::MSVC)
.StartsWith("itanium", Triple::Itanium)
.StartsWith("cygnus", Triple::Cygnus)
.Default(Triple::UnknownEnvironment);
}
static Triple::ObjectFormatType parseFormat(StringRef EnvironmentName) {
return StringSwitch<Triple::ObjectFormatType>(EnvironmentName)
.EndsWith("coff", Triple::COFF)
.EndsWith("elf", Triple::ELF)
.EndsWith("macho", Triple::MachO)
.Default(Triple::UnknownObjectFormat);
}
TargetParser: FPU/ARCH/EXT parsing refactory - NFC This new class in a global context contain arch-specific knowledge in order to provide LLVM libraries, tools and projects with the ability to understand the architectures. For now, only FPU, ARCH and ARCH extensions on ARM are supported. Current behaviour it to parse from free-text to enum values and back, so that all users can share the same parser and codes. This simplifies a lot both the ASM/Obj streamers in the back-end (where this came from), and the front-end parsers for command line arguments (where this is going to be used next). The previous implementation, using .def/.h includes is deprecated due to its inflexibility to be built without the backend support and for being too cumbersome. As more architectures join this scheme, and as more features of such architectures are added (such as hardware features, type sizes, etc) into a full blown TargetDescription class, having a set of classes is the most sane implementation. The ultimate goal of this refactor both LLVM's and Clang's target description classes into one unique interface, so that we can de-duplicate and standardise the descriptions, as well as make it available for other front-ends, tools, etc. The FPU parsing for command line options in Clang has been converted to use this new library and a number of aliases were added for compatibility: * A bogus neon-vfpv3 alias (neon defaults to vfp3) * armv5/v6 * {fp4/fp5}-{sp/dp}-d16 Next steps: * Port Clang's ARCH/EXT parsing to use this library. * Create a TableGen back-end to generate this information. * Run this TableGen process regardless of which back-ends are built. * Expose more information and rename it to TargetDescription. * Continue re-factoring Clang to use as much of it as possible. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236900 91177308-0d34-0410-b5e6-96231b3b80d8
2015-05-08 21:04:27 +00:00
// FIXME: Use ARMTargetParser. This would require using Triple::ARMSubArch*
// in ARMBuildAttrs and in ARCHNames' DefaultArch fields.
static Triple::SubArchType parseSubArch(StringRef SubArchName) {
if (SubArchName.endswith("eb"))
SubArchName = SubArchName.substr(0, SubArchName.size() - 2);
return StringSwitch<Triple::SubArchType>(SubArchName)
.EndsWith("v8.1a", Triple::ARMSubArch_v8_1a)
.EndsWith("v8", Triple::ARMSubArch_v8)
.EndsWith("v8a", Triple::ARMSubArch_v8)
.EndsWith("v7", Triple::ARMSubArch_v7)
.EndsWith("v7a", Triple::ARMSubArch_v7)
.EndsWith("v7em", Triple::ARMSubArch_v7em)
.EndsWith("v7l", Triple::ARMSubArch_v7)
.EndsWith("v7m", Triple::ARMSubArch_v7m)
.EndsWith("v7r", Triple::ARMSubArch_v7)
.EndsWith("v7s", Triple::ARMSubArch_v7s)
.EndsWith("v6", Triple::ARMSubArch_v6)
.EndsWith("v6m", Triple::ARMSubArch_v6m)
.EndsWith("v6sm", Triple::ARMSubArch_v6m)
.EndsWith("v6k", Triple::ARMSubArch_v6k)
.EndsWith("v6t2", Triple::ARMSubArch_v6t2)
.EndsWith("v5", Triple::ARMSubArch_v5)
.EndsWith("v5e", Triple::ARMSubArch_v5)
.EndsWith("v5t", Triple::ARMSubArch_v5)
.EndsWith("v5te", Triple::ARMSubArch_v5te)
.EndsWith("v4t", Triple::ARMSubArch_v4t)
.EndsWith("kalimba3", Triple::KalimbaSubArch_v3)
.EndsWith("kalimba4", Triple::KalimbaSubArch_v4)
.EndsWith("kalimba5", Triple::KalimbaSubArch_v5)
.Default(Triple::NoSubArch);
}
static const char *getObjectFormatTypeName(Triple::ObjectFormatType Kind) {
switch (Kind) {
case Triple::UnknownObjectFormat: return "";
case Triple::COFF: return "coff";
case Triple::ELF: return "elf";
case Triple::MachO: return "macho";
}
llvm_unreachable("unknown object format type");
}
static Triple::ObjectFormatType getDefaultFormat(const Triple &T) {
switch (T.getArch()) {
default:
break;
case Triple::hexagon:
case Triple::mips:
case Triple::mipsel:
case Triple::mips64:
case Triple::mips64el:
case Triple::r600:
case Triple::amdgcn:
case Triple::sparc:
case Triple::sparcv9:
case Triple::systemz:
case Triple::xcore:
case Triple::ppc64le:
return Triple::ELF;
case Triple::ppc:
case Triple::ppc64:
if (T.isOSDarwin())
return Triple::MachO;
return Triple::ELF;
}
if (T.isOSDarwin())
return Triple::MachO;
else if (T.isOSWindows())
return Triple::COFF;
return Triple::ELF;
}
/// \brief Construct a triple from the string representation provided.
///
/// This stores the string representation and parses the various pieces into
/// enum members.
Triple::Triple(const Twine &Str)
: Data(Str.str()),
Arch(parseArch(getArchName())),
SubArch(parseSubArch(getArchName())),
Vendor(parseVendor(getVendorName())),
OS(parseOS(getOSName())),
Environment(parseEnvironment(getEnvironmentName())),
ObjectFormat(parseFormat(getEnvironmentName())) {
if (ObjectFormat == Triple::UnknownObjectFormat)
ObjectFormat = getDefaultFormat(*this);
}
/// \brief Construct a triple from string representations of the architecture,
/// vendor, and OS.
///
/// This joins each argument into a canonical string representation and parses
/// them into enum members. It leaves the environment unknown and omits it from
/// the string representation.
Triple::Triple(const Twine &ArchStr, const Twine &VendorStr, const Twine &OSStr)
: Data((ArchStr + Twine('-') + VendorStr + Twine('-') + OSStr).str()),
Arch(parseArch(ArchStr.str())),
SubArch(parseSubArch(ArchStr.str())),
Vendor(parseVendor(VendorStr.str())),
OS(parseOS(OSStr.str())),
Environment(), ObjectFormat(Triple::UnknownObjectFormat) {
ObjectFormat = getDefaultFormat(*this);
}
/// \brief Construct a triple from string representations of the architecture,
/// vendor, OS, and environment.
///
/// This joins each argument into a canonical string representation and parses
/// them into enum members.
Triple::Triple(const Twine &ArchStr, const Twine &VendorStr, const Twine &OSStr,
const Twine &EnvironmentStr)
: Data((ArchStr + Twine('-') + VendorStr + Twine('-') + OSStr + Twine('-') +
EnvironmentStr).str()),
Arch(parseArch(ArchStr.str())),
SubArch(parseSubArch(ArchStr.str())),
Vendor(parseVendor(VendorStr.str())),
OS(parseOS(OSStr.str())),
Environment(parseEnvironment(EnvironmentStr.str())),
ObjectFormat(parseFormat(EnvironmentStr.str())) {
if (ObjectFormat == Triple::UnknownObjectFormat)
ObjectFormat = getDefaultFormat(*this);
}
std::string Triple::normalize(StringRef Str) {
bool IsMinGW32 = false;
bool IsCygwin = false;
// Parse into components.
SmallVector<StringRef, 4> Components;
Str.split(Components, "-");
// If the first component corresponds to a known architecture, preferentially
// use it for the architecture. If the second component corresponds to a
// known vendor, preferentially use it for the vendor, etc. This avoids silly
// component movement when a component parses as (eg) both a valid arch and a
// valid os.
ArchType Arch = UnknownArch;
if (Components.size() > 0)
Arch = parseArch(Components[0]);
VendorType Vendor = UnknownVendor;
if (Components.size() > 1)
Vendor = parseVendor(Components[1]);
OSType OS = UnknownOS;
if (Components.size() > 2) {
OS = parseOS(Components[2]);
IsCygwin = Components[2].startswith("cygwin");
IsMinGW32 = Components[2].startswith("mingw");
}
EnvironmentType Environment = UnknownEnvironment;
if (Components.size() > 3)
Environment = parseEnvironment(Components[3]);
ObjectFormatType ObjectFormat = UnknownObjectFormat;
if (Components.size() > 4)
ObjectFormat = parseFormat(Components[4]);
// Note which components are already in their final position. These will not
// be moved.
bool Found[4];
Found[0] = Arch != UnknownArch;
Found[1] = Vendor != UnknownVendor;
Found[2] = OS != UnknownOS;
Found[3] = Environment != UnknownEnvironment;
// If they are not there already, permute the components into their canonical
// positions by seeing if they parse as a valid architecture, and if so moving
// the component to the architecture position etc.
for (unsigned Pos = 0; Pos != array_lengthof(Found); ++Pos) {
if (Found[Pos])
continue; // Already in the canonical position.
for (unsigned Idx = 0; Idx != Components.size(); ++Idx) {
// Do not reparse any components that already matched.
if (Idx < array_lengthof(Found) && Found[Idx])
continue;
// Does this component parse as valid for the target position?
bool Valid = false;
StringRef Comp = Components[Idx];
switch (Pos) {
default: llvm_unreachable("unexpected component type!");
case 0:
Arch = parseArch(Comp);
Valid = Arch != UnknownArch;
break;
case 1:
Vendor = parseVendor(Comp);
Valid = Vendor != UnknownVendor;
break;
case 2:
OS = parseOS(Comp);
IsCygwin = Comp.startswith("cygwin");
IsMinGW32 = Comp.startswith("mingw");
Valid = OS != UnknownOS || IsCygwin || IsMinGW32;
break;
case 3:
Environment = parseEnvironment(Comp);
Valid = Environment != UnknownEnvironment;
if (!Valid) {
ObjectFormat = parseFormat(Comp);
Valid = ObjectFormat != UnknownObjectFormat;
}
break;
}
if (!Valid)
continue; // Nope, try the next component.
// Move the component to the target position, pushing any non-fixed
// components that are in the way to the right. This tends to give
// good results in the common cases of a forgotten vendor component
// or a wrongly positioned environment.
if (Pos < Idx) {
// Insert left, pushing the existing components to the right. For
// example, a-b-i386 -> i386-a-b when moving i386 to the front.
StringRef CurrentComponent(""); // The empty component.
// Replace the component we are moving with an empty component.
std::swap(CurrentComponent, Components[Idx]);
// Insert the component being moved at Pos, displacing any existing
// components to the right.
for (unsigned i = Pos; !CurrentComponent.empty(); ++i) {
// Skip over any fixed components.
while (i < array_lengthof(Found) && Found[i])
++i;
// Place the component at the new position, getting the component
// that was at this position - it will be moved right.
std::swap(CurrentComponent, Components[i]);
}
} else if (Pos > Idx) {
// Push right by inserting empty components until the component at Idx
// reaches the target position Pos. For example, pc-a -> -pc-a when
// moving pc to the second position.
do {
// Insert one empty component at Idx.
StringRef CurrentComponent(""); // The empty component.
for (unsigned i = Idx; i < Components.size();) {
// Place the component at the new position, getting the component
// that was at this position - it will be moved right.
std::swap(CurrentComponent, Components[i]);
// If it was placed on top of an empty component then we are done.
if (CurrentComponent.empty())
break;
// Advance to the next component, skipping any fixed components.
while (++i < array_lengthof(Found) && Found[i])
;
}
// The last component was pushed off the end - append it.
if (!CurrentComponent.empty())
Components.push_back(CurrentComponent);
// Advance Idx to the component's new position.
while (++Idx < array_lengthof(Found) && Found[Idx])
;
} while (Idx < Pos); // Add more until the final position is reached.
}
assert(Pos < Components.size() && Components[Pos] == Comp &&
"Component moved wrong!");
Found[Pos] = true;
break;
}
}
// Special case logic goes here. At this point Arch, Vendor and OS have the
// correct values for the computed components.
if (OS == Triple::Win32) {
Components.resize(4);
Components[2] = "windows";
if (Environment == UnknownEnvironment) {
if (ObjectFormat == UnknownObjectFormat || ObjectFormat == Triple::COFF)
Components[3] = "msvc";
else
Components[3] = getObjectFormatTypeName(ObjectFormat);
}
} else if (IsMinGW32) {
Components.resize(4);
Components[2] = "windows";
Components[3] = "gnu";
} else if (IsCygwin) {
Components.resize(4);
Components[2] = "windows";
Components[3] = "cygnus";
}
if (IsMinGW32 || IsCygwin ||
(OS == Triple::Win32 && Environment != UnknownEnvironment)) {
if (ObjectFormat != UnknownObjectFormat && ObjectFormat != Triple::COFF) {
Components.resize(5);
Components[4] = getObjectFormatTypeName(ObjectFormat);
}
}
// Stick the corrected components back together to form the normalized string.
std::string Normalized;
for (unsigned i = 0, e = Components.size(); i != e; ++i) {
if (i) Normalized += '-';
Normalized += Components[i];
}
return Normalized;
}
StringRef Triple::getArchName() const {
return StringRef(Data).split('-').first; // Isolate first component
}
StringRef Triple::getVendorName() const {
StringRef Tmp = StringRef(Data).split('-').second; // Strip first component
return Tmp.split('-').first; // Isolate second component
}
StringRef Triple::getOSName() const {
StringRef Tmp = StringRef(Data).split('-').second; // Strip first component
Tmp = Tmp.split('-').second; // Strip second component
return Tmp.split('-').first; // Isolate third component
}
StringRef Triple::getEnvironmentName() const {
StringRef Tmp = StringRef(Data).split('-').second; // Strip first component
Tmp = Tmp.split('-').second; // Strip second component
return Tmp.split('-').second; // Strip third component
}
StringRef Triple::getOSAndEnvironmentName() const {
StringRef Tmp = StringRef(Data).split('-').second; // Strip first component
return Tmp.split('-').second; // Strip second component
}
static unsigned EatNumber(StringRef &Str) {
assert(!Str.empty() && Str[0] >= '0' && Str[0] <= '9' && "Not a number");
unsigned Result = 0;
do {
// Consume the leading digit.
Result = Result*10 + (Str[0] - '0');
// Eat the digit.
Str = Str.substr(1);
} while (!Str.empty() && Str[0] >= '0' && Str[0] <= '9');
return Result;
}
void Triple::getOSVersion(unsigned &Major, unsigned &Minor,
unsigned &Micro) const {
StringRef OSName = getOSName();
// For Android, we care about the Android version rather than the Linux
// version.
if (getEnvironment() == Android) {
OSName = getEnvironmentName().substr(strlen("android"));
if (OSName.startswith("eabi"))
OSName = OSName.substr(strlen("eabi"));
}
// Assume that the OS portion of the triple starts with the canonical name.
StringRef OSTypeName = getOSTypeName(getOS());
if (OSName.startswith(OSTypeName))
OSName = OSName.substr(OSTypeName.size());
// Any unset version defaults to 0.
Major = Minor = Micro = 0;
// Parse up to three components.
unsigned *Components[3] = { &Major, &Minor, &Micro };
for (unsigned i = 0; i != 3; ++i) {
if (OSName.empty() || OSName[0] < '0' || OSName[0] > '9')
break;
// Consume the leading number.
*Components[i] = EatNumber(OSName);
// Consume the separator, if present.
if (OSName.startswith("."))
OSName = OSName.substr(1);
}
}
bool Triple::getMacOSXVersion(unsigned &Major, unsigned &Minor,
unsigned &Micro) const {
getOSVersion(Major, Minor, Micro);
switch (getOS()) {
default: llvm_unreachable("unexpected OS for Darwin triple");
case Darwin:
// Default to darwin8, i.e., MacOSX 10.4.
if (Major == 0)
Major = 8;
// Darwin version numbers are skewed from OS X versions.
if (Major < 4)
return false;
Micro = 0;
Minor = Major - 4;
Major = 10;
break;
case MacOSX:
// Default to 10.4.
if (Major == 0) {
Major = 10;
Minor = 4;
}
if (Major != 10)
return false;
break;
case IOS:
// Ignore the version from the triple. This is only handled because the
// the clang driver combines OS X and IOS support into a common Darwin
// toolchain that wants to know the OS X version number even when targeting
// IOS.
Major = 10;
Minor = 4;
Micro = 0;
break;
}
return true;
}
void Triple::getiOSVersion(unsigned &Major, unsigned &Minor,
unsigned &Micro) const {
switch (getOS()) {
default: llvm_unreachable("unexpected OS for Darwin triple");
case Darwin:
case MacOSX:
// Ignore the version from the triple. This is only handled because the
// the clang driver combines OS X and IOS support into a common Darwin
// toolchain that wants to know the iOS version number even when targeting
// OS X.
Major = 5;
Minor = 0;
Micro = 0;
break;
case IOS:
getOSVersion(Major, Minor, Micro);
// Default to 5.0 (or 7.0 for arm64).
if (Major == 0)
Major = (getArch() == aarch64) ? 7 : 5;
break;
}
}
void Triple::setTriple(const Twine &Str) {
*this = Triple(Str);
}
void Triple::setArch(ArchType Kind) {
setArchName(getArchTypeName(Kind));
}
void Triple::setVendor(VendorType Kind) {
setVendorName(getVendorTypeName(Kind));
}
void Triple::setOS(OSType Kind) {
setOSName(getOSTypeName(Kind));
}
void Triple::setEnvironment(EnvironmentType Kind) {
if (ObjectFormat == getDefaultFormat(*this))
return setEnvironmentName(getEnvironmentTypeName(Kind));
setEnvironmentName((getEnvironmentTypeName(Kind) + Twine("-") +
getObjectFormatTypeName(ObjectFormat)).str());
}
void Triple::setObjectFormat(ObjectFormatType Kind) {
if (Environment == UnknownEnvironment)
return setEnvironmentName(getObjectFormatTypeName(Kind));
setEnvironmentName((getEnvironmentTypeName(Environment) + Twine("-") +
getObjectFormatTypeName(Kind)).str());
}
void Triple::setArchName(StringRef Str) {
// Work around a miscompilation bug for Twines in gcc 4.0.3.
SmallString<64> Triple;
Triple += Str;
Triple += "-";
Triple += getVendorName();
Triple += "-";
Triple += getOSAndEnvironmentName();
setTriple(Triple);
}
void Triple::setVendorName(StringRef Str) {
setTriple(getArchName() + "-" + Str + "-" + getOSAndEnvironmentName());
}
void Triple::setOSName(StringRef Str) {
if (hasEnvironment())
setTriple(getArchName() + "-" + getVendorName() + "-" + Str +
"-" + getEnvironmentName());
else
setTriple(getArchName() + "-" + getVendorName() + "-" + Str);
}
void Triple::setEnvironmentName(StringRef Str) {
setTriple(getArchName() + "-" + getVendorName() + "-" + getOSName() +
"-" + Str);
}
void Triple::setOSAndEnvironmentName(StringRef Str) {
setTriple(getArchName() + "-" + getVendorName() + "-" + Str);
}
static unsigned getArchPointerBitWidth(llvm::Triple::ArchType Arch) {
switch (Arch) {
case llvm::Triple::UnknownArch:
return 0;
case llvm::Triple::msp430:
return 16;
case llvm::Triple::arm:
case llvm::Triple::armeb:
case llvm::Triple::hexagon:
case llvm::Triple::le32:
case llvm::Triple::mips:
case llvm::Triple::mipsel:
case llvm::Triple::nvptx:
case llvm::Triple::ppc:
case llvm::Triple::r600:
case llvm::Triple::sparc:
case llvm::Triple::sparcel:
case llvm::Triple::tce:
case llvm::Triple::thumb:
case llvm::Triple::thumbeb:
case llvm::Triple::x86:
case llvm::Triple::xcore:
case llvm::Triple::amdil:
case llvm::Triple::hsail:
case llvm::Triple::spir:
case llvm::Triple::kalimba:
return 32;
case llvm::Triple::aarch64:
case llvm::Triple::aarch64_be:
case llvm::Triple::amdgcn:
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
case llvm::Triple::bpf:
case llvm::Triple::le64:
case llvm::Triple::mips64:
case llvm::Triple::mips64el:
case llvm::Triple::nvptx64:
case llvm::Triple::ppc64:
case llvm::Triple::ppc64le:
case llvm::Triple::sparcv9:
case llvm::Triple::systemz:
case llvm::Triple::x86_64:
case llvm::Triple::amdil64:
case llvm::Triple::hsail64:
case llvm::Triple::spir64:
return 64;
}
llvm_unreachable("Invalid architecture value");
}
bool Triple::isArch64Bit() const {
return getArchPointerBitWidth(getArch()) == 64;
}
bool Triple::isArch32Bit() const {
return getArchPointerBitWidth(getArch()) == 32;
}
bool Triple::isArch16Bit() const {
return getArchPointerBitWidth(getArch()) == 16;
}
Triple Triple::get32BitArchVariant() const {
Triple T(*this);
switch (getArch()) {
case Triple::UnknownArch:
case Triple::aarch64:
case Triple::aarch64_be:
case Triple::amdgcn:
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
case Triple::bpf:
case Triple::msp430:
case Triple::systemz:
case Triple::ppc64le:
T.setArch(UnknownArch);
break;
case Triple::amdil:
case Triple::hsail:
case Triple::spir:
case Triple::arm:
case Triple::armeb:
case Triple::hexagon:
case Triple::kalimba:
case Triple::le32:
case Triple::mips:
case Triple::mipsel:
case Triple::nvptx:
case Triple::ppc:
case Triple::r600:
case Triple::sparc:
case Triple::sparcel:
case Triple::tce:
case Triple::thumb:
case Triple::thumbeb:
case Triple::x86:
case Triple::xcore:
// Already 32-bit.
break;
case Triple::le64: T.setArch(Triple::le32); break;
case Triple::mips64: T.setArch(Triple::mips); break;
case Triple::mips64el: T.setArch(Triple::mipsel); break;
case Triple::nvptx64: T.setArch(Triple::nvptx); break;
case Triple::ppc64: T.setArch(Triple::ppc); break;
case Triple::sparcv9: T.setArch(Triple::sparc); break;
case Triple::x86_64: T.setArch(Triple::x86); break;
case Triple::amdil64: T.setArch(Triple::amdil); break;
case Triple::hsail64: T.setArch(Triple::hsail); break;
case Triple::spir64: T.setArch(Triple::spir); break;
}
return T;
}
Triple Triple::get64BitArchVariant() const {
Triple T(*this);
switch (getArch()) {
case Triple::UnknownArch:
case Triple::arm:
case Triple::armeb:
case Triple::hexagon:
case Triple::kalimba:
case Triple::msp430:
case Triple::r600:
case Triple::tce:
case Triple::thumb:
case Triple::thumbeb:
case Triple::xcore:
case Triple::sparcel:
T.setArch(UnknownArch);
break;
case Triple::aarch64:
case Triple::aarch64_be:
BPF backend Summary: V8->V9: - cleanup tests V7->V8: - addressed feedback from David: - switched to range-based 'for' loops - fixed formatting of tests V6->V7: - rebased and adjusted AsmPrinter args - CamelCased .td, fixed formatting, cleaned up names, removed unused patterns - diffstat: 3 files changed, 203 insertions(+), 227 deletions(-) V5->V6: - addressed feedback from Chandler: - reinstated full verbose standard banner in all files - fixed variables that were not in CamelCase - fixed names of #ifdef in header files - removed redundant braces in if/else chains with single statements - fixed comments - removed trailing empty line - dropped debug annotations from tests - diffstat of these changes: 46 files changed, 456 insertions(+), 469 deletions(-) V4->V5: - fix setLoadExtAction() interface - clang-formated all where it made sense V3->V4: - added CODE_OWNERS entry for BPF backend V2->V3: - fix metadata in tests V1->V2: - addressed feedback from Tom and Matt - removed top level change to configure (now everything via 'experimental-backend') - reworked error reporting via DiagnosticInfo (similar to R600) - added few more tests - added cmake build - added Triple::bpf - tested on linux and darwin V1 cover letter: --------------------- recently linux gained "universal in-kernel virtual machine" which is called eBPF or extended BPF. The name comes from "Berkeley Packet Filter", since new instruction set is based on it. This patch adds a new backend that emits extended BPF instruction set. The concept and development are covered by the following articles: http://lwn.net/Articles/599755/ http://lwn.net/Articles/575531/ http://lwn.net/Articles/603983/ http://lwn.net/Articles/606089/ http://lwn.net/Articles/612878/ One of use cases: dtrace/systemtap alternative. bpf syscall manpage: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fc1a460f3017e958e6a8ea560ea0afd91bf6fe instruction set description and differences vs classic BPF: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/networking/filter.txt Short summary of instruction set: - 64-bit registers R0 - return value from in-kernel function, and exit value for BPF program R1 - R5 - arguments from BPF program to in-kernel function R6 - R9 - callee saved registers that in-kernel function will preserve R10 - read-only frame pointer to access stack - two-operand instructions like +, -, *, mov, load/store - implicit prologue/epilogue (invisible stack pointer) - no floating point, no simd Short history of extended BPF in kernel: interpreter in 3.15, x64 JIT in 3.16, arm64 JIT, verifier, bpf syscall in 3.18, more to come in the future. It's a very small and simple backend. There is no support for global variables, arbitrary function calls, floating point, varargs, exceptions, indirect jumps, arbitrary pointer arithmetic, alloca, etc. From C front-end point of view it's very restricted. It's done on purpose, since kernel rejects all programs that it cannot prove safe. It rejects programs with loops and with memory accesses via arbitrary pointers. When kernel accepts the program it is guaranteed that program will terminate and will not crash the kernel. This patch implements all 'must have' bits. There are several things on TODO list, so this is not the end of development. Most of the code is a boiler plate code, copy-pasted from other backends. Only odd things are lack or < and <= instructions, specialized load_byte intrinsics and 'compare and goto' as single instruction. Current instruction set is fixed, but more instructions can be added in the future. Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Subscribers: majnemer, chandlerc, echristo, joerg, pete, rengolin, kristof.beyls, arsenm, t.p.northover, tstellarAMD, aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D6494 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227008 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-24 17:51:26 +00:00
case Triple::bpf:
case Triple::le64:
case Triple::amdil64:
case Triple::amdgcn:
case Triple::hsail64:
case Triple::spir64:
case Triple::mips64:
case Triple::mips64el:
case Triple::nvptx64:
case Triple::ppc64:
case Triple::ppc64le:
case Triple::sparcv9:
case Triple::systemz:
case Triple::x86_64:
// Already 64-bit.
break;
case Triple::le32: T.setArch(Triple::le64); break;
case Triple::mips: T.setArch(Triple::mips64); break;
case Triple::mipsel: T.setArch(Triple::mips64el); break;
case Triple::nvptx: T.setArch(Triple::nvptx64); break;
case Triple::ppc: T.setArch(Triple::ppc64); break;
case Triple::sparc: T.setArch(Triple::sparcv9); break;
case Triple::x86: T.setArch(Triple::x86_64); break;
case Triple::amdil: T.setArch(Triple::amdil64); break;
case Triple::hsail: T.setArch(Triple::hsail64); break;
case Triple::spir: T.setArch(Triple::spir64); break;
}
return T;
}
TargetParser: FPU/ARCH/EXT parsing refactory - NFC This new class in a global context contain arch-specific knowledge in order to provide LLVM libraries, tools and projects with the ability to understand the architectures. For now, only FPU, ARCH and ARCH extensions on ARM are supported. Current behaviour it to parse from free-text to enum values and back, so that all users can share the same parser and codes. This simplifies a lot both the ASM/Obj streamers in the back-end (where this came from), and the front-end parsers for command line arguments (where this is going to be used next). The previous implementation, using .def/.h includes is deprecated due to its inflexibility to be built without the backend support and for being too cumbersome. As more architectures join this scheme, and as more features of such architectures are added (such as hardware features, type sizes, etc) into a full blown TargetDescription class, having a set of classes is the most sane implementation. The ultimate goal of this refactor both LLVM's and Clang's target description classes into one unique interface, so that we can de-duplicate and standardise the descriptions, as well as make it available for other front-ends, tools, etc. The FPU parsing for command line options in Clang has been converted to use this new library and a number of aliases were added for compatibility: * A bogus neon-vfpv3 alias (neon defaults to vfp3) * armv5/v6 * {fp4/fp5}-{sp/dp}-d16 Next steps: * Port Clang's ARCH/EXT parsing to use this library. * Create a TableGen back-end to generate this information. * Run this TableGen process regardless of which back-ends are built. * Expose more information and rename it to TargetDescription. * Continue re-factoring Clang to use as much of it as possible. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236900 91177308-0d34-0410-b5e6-96231b3b80d8
2015-05-08 21:04:27 +00:00
// FIXME: Use ARMTargetParser. This would require ARCHNames to hold
// specific CPU names, as well as default CPU arch.
const char *Triple::getARMCPUForArch(StringRef MArch) const {
if (MArch.empty())
MArch = getArchName();
switch (getOS()) {
case llvm::Triple::FreeBSD:
case llvm::Triple::NetBSD:
if (MArch == "armv6")
return "arm1176jzf-s";
break;
case llvm::Triple::Win32:
// FIXME: this is invalid for WindowsCE
return "cortex-a9";
default:
break;
}
// MArch is expected to be of the form (arm|thumb)?(eb)?(v.+)?(eb)?
// Only the (v.+) part is relevant for determining the CPU, as it determines
// the architecture version, so we first remove the surrounding parts.
// (ep9312|iwmmxt|xscale)(eb)? is also permitted, so we have to be a bit
// careful when removing the leading (arm|thumb)?(eb)? as we don't want to
// permit things like armep9312.
const char *result = nullptr;
size_t offset = StringRef::npos;
if (MArch.startswith("arm"))
offset = 3;
else if (MArch.startswith("thumb"))
offset = 5;
if (offset != StringRef::npos && MArch.substr(offset, 2) == "eb")
offset += 2;
else if (MArch.endswith("eb"))
MArch = MArch.substr(0, MArch.size() - 2);
if (offset != StringRef::npos && (offset == MArch.size() || MArch[offset] == 'v'))
MArch = MArch.substr(offset);
if (MArch == "") {
// If no specific architecture version is requested, return the minimum CPU
// required by the OS and environment.
switch (getOS()) {
case llvm::Triple::NetBSD:
switch (getEnvironment()) {
case llvm::Triple::GNUEABIHF:
case llvm::Triple::GNUEABI:
case llvm::Triple::EABIHF:
case llvm::Triple::EABI:
return "arm926ej-s";
default:
return "strongarm";
}
case llvm::Triple::NaCl:
return "cortex-a8";
default:
switch (getEnvironment()) {
case llvm::Triple::EABIHF:
case llvm::Triple::GNUEABIHF:
return "arm1176jzf-s";
default:
return "arm7tdmi";
}
}
} else {
result = llvm::StringSwitch<const char *>(MArch)
.Cases("v2", "v2a", "arm2")
.Case("v3", "arm6")
.Case("v3m", "arm7m")
.Case("v4", "strongarm")
.Case("v4t", "arm7tdmi")
.Cases("v5", "v5t", "arm10tdmi")
.Cases("v5e", "v5te", "arm1022e")
.Case("v5tej", "arm926ej-s")
.Case("v6", "arm1136jf-s")
.Case("v6j", "arm1136j-s")
.Cases("v6k", "v6z", "v6zk", "arm1176jzf-s")
.Case("v6t2", "arm1156t2-s")
.Cases("v6m", "v6-m", "v6sm", "v6s-m", "cortex-m0")
.Cases("v7", "v7a", "v7-a", "v7l", "v7-l", "cortex-a8")
.Cases("v7s", "v7-s", "swift")
.Cases("v7r", "v7-r", "cortex-r4")
.Cases("v7m", "v7-m", "cortex-m3")
.Cases("v7em", "v7e-m", "cortex-m4")
.Cases("v8", "v8a", "v8-a", "cortex-a53")
.Cases("v8.1a", "v8.1-a", "generic")
.Case("ep9312", "ep9312")
.Case("iwmmxt", "iwmmxt")
.Case("xscale", "xscale")
.Default(nullptr);
}
return result;
}