Index: llvm/lib/Target/PowerPC/PPCBranchSelector.cpp =================================================================== --- llvm/lib/Target/PowerPC/PPCBranchSelector.cpp +++ llvm/lib/Target/PowerPC/PPCBranchSelector.cpp @@ -31,6 +31,9 @@ #define DEBUG_TYPE "ppc-branch-select" STATISTIC(NumExpanded, "Number of branches expanded to long format"); +STATISTIC(NumPrefixed, "Number of prefixed instructions"); +STATISTIC(NumPrefixedAligned, + "Number of prefixed instructions that have been aligned"); namespace { struct PPCBSel : public MachineFunctionPass { @@ -134,10 +137,38 @@ } unsigned BlockSize = 0; + unsigned UnalignedBytesRemaining = 0; for (MachineInstr &MI : *MBB) { - BlockSize += TII->getInstSizeInBytes(MI); + unsigned MINumBytes = TII->getInstSizeInBytes(MI); if (MI.isInlineAsm() && (FirstImpreciseBlock < 0)) FirstImpreciseBlock = MBB->getNumber(); + if (TII->isPrefixed(MI.getOpcode())) { + NumPrefixed++; + + // All 8 byte instructions may require alignment. Each 8 byte + // instruction may be aligned by another 4 bytes. + // This means that an 8 byte instruction may require 12 bytes + // (8 for the instruction iteself and 4 for the alignment nop). + // This will happen if an 8 byte instruction can be aligned to 64 bytes + // by only adding a 4 byte nop. + // We don't know the alignment at this point in the code so we have to + // adopt a more pessimistic approach. If an instruction may need + // alignment we assume that it does need alignment and add 4 bytes to + // it. As a result we may end up with more long branches than before + // but we are in the safe position where if we need a long branch we + // have one. + // The if statement checks to make sure that two 8 byte instructions + // are at least 64 bytes away from each other. You cannot have two + // instructions that both need alignment that are within 64 bytes of + // each other. + if (!UnalignedBytesRemaining) { + BlockSize += 4; + UnalignedBytesRemaining = 60; + NumPrefixedAligned++; + } + } + UnalignedBytesRemaining -= std::min(UnalignedBytesRemaining, MINumBytes); + BlockSize += MINumBytes; } BlockSizes[MBB->getNumber()].first = BlockSize; Index: llvm/test/CodeGen/PowerPC/alignlongjumptest.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/PowerPC/alignlongjumptest.mir @@ -0,0 +1,82 @@ +# RUN: llc -mcpu=future -mtriple=powerpc64le-unknown-unknown %s \ +# RUN: -start-before=ppc-branch-select -verify-machineinstrs -filetype=obj -o - | \ +# RUN: llvm-objdump -mcpu=future -d -r - | FileCheck --check-prefix=CHECK-LE %s +# RUN: llc -mcpu=future -mtriple=powerpc64-unknown-unknown %s \ +# RUN: -start-before=ppc-branch-select -verify-machineinstrs -filetype=obj -o - | \ +# RUN: llvm-objdump -mcpu=future -d -r - | FileCheck --check-prefix=CHECK-BE %s + +# The purpose of this test is to check that long branches are selected correctly +# when we have prefixed instructions that may require alignment. Prefixed +# instructions may require alignment and so an additional 4 bytes may be added. +# If those 4 bytes put the target of the branch past the range of a short branch +# then we should use a long branch like in this test. + +--- +name: longbranchtest +alignment: 16 +exposesReturnsTwice: false +legalized: false +regBankSelected: false +selected: false +failedISel: false +tracksRegLiveness: true +hasWinCFI: false +registers: [] +liveins: + - { reg: '$x3', virtual-reg: '' } +frameInfo: + isFrameAddressTaken: false + isReturnAddressTaken: false + hasStackMap: false + hasPatchPoint: false + stackSize: 0 + offsetAdjustment: 0 + maxAlignment: 1 + adjustsStack: false + hasCalls: false + stackProtector: '' + maxCallFrameSize: 0 + cvBytesOfCalleeSavedRegisters: 0 + hasOpaqueSPAdjustment: false + hasVAStart: false + hasMustTailInVarArgFunc: false + localFrameSize: 0 + savePoint: '' + restorePoint: '' +fixedStack: [] +stack: [] +callSites: [] +constants: [] +machineFunctionInfo: {} +body: | + bb.0.entry: + successors: %bb.1(0x30000000), %bb.2(0x50000000) + liveins: $x3 + renamable $cr0 = CMPLWI killed renamable $r3, 0, implicit $x3 + BCC 76, killed renamable $cr0, %bb.1 + bb.2: + renamable $x3 = LI8 2 + INLINEASM &".space 32744", 1 + renamable $x3 = PADDI8 $x3, 13 + BLR8 implicit $lr8, implicit $rm, implicit killed $x3 + bb.1: + renamable $x3 = LI8 1 + INLINEASM &".space 32744", 1 + renamable $x3 = PADDI8 $x3, 21 + BLR8 implicit $lr8, implicit $rm, implicit killed $x3 + +... + +# Check for the long branch. +# CHECK-LE: 08 00 82 4{{[01]}} b{{[tf]}} 2, .+8 +# CHECK-LE-NEXT: fc 7f 00 48 b .+32764 +# CHECK-LE-DAG: paddi 3, 3, 13, 0 +# CHECK-LE-DAG: paddi 3, 3, 21, 0 +# CHECK-LE: blr +# CHECK-BE: 4{{[01]}} 82 00 08 b{{[tf]}} 2, .+8 +# CHECK-BE-NEXT: 48 00 7f fc b .+32764 +# CHECK-BE-DAG: paddi 3, 3, 13, 0 +# CHECK-BE-DAG: paddi 3, 3, 21, 0 +# CHECK-BE: blr + +