forked from OSchip/llvm-project
Revert r359906, "RegAllocFast: Add heuristic to detect values not live-out of a block"
Makes clang/test/Misc/backend-stack-frame-diagnostics-fallback.cpp fail. llvm-svn: 359912
This commit is contained in:
Nico Weber
parent
308b5ec1ff
commit
bb852a9672
|
|
@ -101,10 +101,6 @@ namespace {
|
|||
|
||||
DenseMap<unsigned, SmallVector<MachineInstr *, 2>> LiveDbgValueMap;
|
||||
|
||||
/// Has a bit set for every virtual register for which it was determined
|
||||
/// that it is alive across blocks.
|
||||
BitVector MayLiveAcrossBlocks;
|
||||
|
||||
/// State of a physical register.
|
||||
enum RegState {
|
||||
/// A disabled register is not available for allocation, but an alias may
|
||||
|
|
@ -212,7 +208,7 @@ namespace {
|
|||
unsigned Hint);
|
||||
LiveReg &reloadVirtReg(MachineInstr &MI, unsigned OpNum, unsigned VirtReg,
|
||||
unsigned Hint);
|
||||
void spillAll(MachineBasicBlock::iterator MI, bool OnlyLiveOut);
|
||||
void spillAll(MachineBasicBlock::iterator MI);
|
||||
bool setPhysReg(MachineInstr &MI, MachineOperand &MO, MCPhysReg PhysReg);
|
||||
|
||||
int getStackSpaceFor(unsigned VirtReg);
|
||||
|
|
@ -221,8 +217,6 @@ namespace {
|
|||
void reload(MachineBasicBlock::iterator Before, unsigned VirtReg,
|
||||
MCPhysReg PhysReg);
|
||||
|
||||
bool mayLiveOut(unsigned VirtReg);
|
||||
|
||||
void dumpState();
|
||||
};
|
||||
|
||||
|
|
@ -257,33 +251,6 @@ int RegAllocFast::getStackSpaceFor(unsigned VirtReg) {
|
|||
return FrameIdx;
|
||||
}
|
||||
|
||||
/// Returns false if \p VirtReg is known to not live out of the current block.
|
||||
bool RegAllocFast::mayLiveOut(unsigned VirtReg) {
|
||||
if (MayLiveAcrossBlocks.test(TargetRegisterInfo::virtReg2Index(VirtReg))) {
|
||||
// Cannot be live-out if there are no successors.
|
||||
return !MBB->succ_empty();
|
||||
}
|
||||
|
||||
// If this block loops back to itself, it would be necessary to check whether
|
||||
// the use comes after the def.
|
||||
if (MBB->isSuccessor(MBB))
|
||||
return true;
|
||||
|
||||
// See if the first \p Limit uses of the register are all in the current
|
||||
// block.
|
||||
static const unsigned Limit = 8;
|
||||
unsigned C = 0;
|
||||
for (const MachineInstr &UseInst : MRI->reg_nodbg_instructions(VirtReg)) {
|
||||
if (UseInst.getParent() != MBB || ++C >= Limit) {
|
||||
MayLiveAcrossBlocks.set(TargetRegisterInfo::virtReg2Index(VirtReg));
|
||||
// Cannot be live-out if there are no successors.
|
||||
return !MBB->succ_empty();
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/// Insert spill instruction for \p AssignedReg before \p Before. Update
|
||||
/// DBG_VALUEs with \p VirtReg operands with the stack slot.
|
||||
void RegAllocFast::spill(MachineBasicBlock::iterator Before, unsigned VirtReg,
|
||||
|
|
@ -407,7 +374,7 @@ void RegAllocFast::spillVirtReg(MachineBasicBlock::iterator MI, LiveReg &LR) {
|
|||
}
|
||||
|
||||
/// Spill all dirty virtregs without killing them.
|
||||
void RegAllocFast::spillAll(MachineBasicBlock::iterator MI, bool OnlyLiveOut) {
|
||||
void RegAllocFast::spillAll(MachineBasicBlock::iterator MI) {
|
||||
if (LiveVirtRegs.empty())
|
||||
return;
|
||||
// The LiveRegMap is keyed by an unsigned (the virtreg number), so the order
|
||||
|
|
@ -415,8 +382,6 @@ void RegAllocFast::spillAll(MachineBasicBlock::iterator MI, bool OnlyLiveOut) {
|
|||
for (LiveReg &LR : LiveVirtRegs) {
|
||||
if (!LR.PhysReg)
|
||||
continue;
|
||||
if (OnlyLiveOut && !mayLiveOut(LR.VirtReg))
|
||||
continue;
|
||||
spillVirtReg(MI, LR);
|
||||
}
|
||||
LiveVirtRegs.clear();
|
||||
|
|
@ -1054,7 +1019,7 @@ void RegAllocFast::allocateInstruction(MachineInstr &MI) {
|
|||
// definitions may be used later on and we do not want to reuse
|
||||
// those for virtual registers in between.
|
||||
LLVM_DEBUG(dbgs() << " Spilling remaining registers before call.\n");
|
||||
spillAll(MI, /*OnlyLiveOut*/ false);
|
||||
spillAll(MI);
|
||||
}
|
||||
|
||||
// Third scan.
|
||||
|
|
@ -1164,7 +1129,7 @@ void RegAllocFast::allocateBasicBlock(MachineBasicBlock &MBB) {
|
|||
|
||||
// Spill all physical registers holding virtual registers now.
|
||||
LLVM_DEBUG(dbgs() << "Spilling live registers at end of block.\n");
|
||||
spillAll(MBB.getFirstTerminator(), /*OnlyLiveOut*/ true);
|
||||
spillAll(MBB.getFirstTerminator());
|
||||
|
||||
// Erase all the coalesced copies. We are delaying it until now because
|
||||
// LiveVirtRegs might refer to the instrs.
|
||||
|
|
@ -1193,8 +1158,6 @@ bool RegAllocFast::runOnMachineFunction(MachineFunction &MF) {
|
|||
unsigned NumVirtRegs = MRI->getNumVirtRegs();
|
||||
StackSlotForVirtReg.resize(NumVirtRegs);
|
||||
LiveVirtRegs.setUniverse(NumVirtRegs);
|
||||
MayLiveAcrossBlocks.clear();
|
||||
MayLiveAcrossBlocks.resize(NumVirtRegs);
|
||||
|
||||
// Loop over all of the basic blocks, eliminating virtual register references
|
||||
for (MachineBasicBlock &MBB : MF)
|
||||
|
|
|
|||
|
|
@ -188,10 +188,10 @@ define float @foo_loop(%swift_error** swifterror %error_ptr_ref, i32 %cc, float
|
|||
; CHECK-O0:[[BB2]]:
|
||||
; CHECK-O0: ldr x0, [sp, [[SLOT2]]]
|
||||
; CHECK-O0: fcmp
|
||||
; CHECK-O0: str x0, [sp]
|
||||
; CHECK-O0: str x0, [sp, [[SLOT3:#[0-9]+]]
|
||||
; CHECK-O0: b.le [[BB1]]
|
||||
; reload from stack
|
||||
; CHECK-O0: ldr [[ID3:x[0-9]+]], [sp]
|
||||
; CHECK-O0: ldr [[ID3:x[0-9]+]], [sp, [[SLOT3]]]
|
||||
; CHECK-O0: mov x21, [[ID3]]
|
||||
; CHECK-O0: ret
|
||||
entry:
|
||||
|
|
|
|||
|
|
@ -81,7 +81,6 @@ define amdgpu_kernel void @extract_w_offset_vgpr(i32 addrspace(1)* %out) {
|
|||
; GCN: bb.1:
|
||||
; GCN: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
||||
; GCN: $sgpr0_sgpr1 = SI_SPILL_S64_RESTORE %stack.5, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr3, implicit-def dead $m0 :: (load 8 from %stack.5, align 4, addrspace 5)
|
||||
; GCN: $vgpr0 = SI_SPILL_V32_RESTORE %stack.4, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr3, 0, implicit $exec :: (load 4 from %stack.4, addrspace 5)
|
||||
; GCN: $vgpr1 = SI_SPILL_V32_RESTORE %stack.0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr3, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
|
||||
; GCN: renamable $sgpr2 = V_READFIRSTLANE_B32 $vgpr1, implicit $exec
|
||||
; GCN: renamable $sgpr4_sgpr5 = V_CMP_EQ_U32_e64 $sgpr2, killed $vgpr1, implicit $exec
|
||||
|
|
@ -93,19 +92,17 @@ define amdgpu_kernel void @extract_w_offset_vgpr(i32 addrspace(1)* %out) {
|
|||
; GCN: renamable $vgpr19 = COPY renamable $vgpr18
|
||||
; GCN: renamable $sgpr6_sgpr7 = COPY renamable $sgpr4_sgpr5
|
||||
; GCN: SI_SPILL_S64_SAVE killed $sgpr6_sgpr7, %stack.5, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr3, implicit-def dead $m0 :: (store 8 into %stack.5, align 4, addrspace 5)
|
||||
; GCN: SI_SPILL_S64_SAVE killed $sgpr0_sgpr1, %stack.6, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr3, implicit-def dead $m0 :: (store 8 into %stack.6, align 4, addrspace 5)
|
||||
; GCN: SI_SPILL_V32_SAVE killed $vgpr19, %stack.4, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr3, 0, implicit $exec :: (store 4 into %stack.4, addrspace 5)
|
||||
; GCN: SI_SPILL_V32_SAVE killed $vgpr0, %stack.7, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr3, 0, implicit $exec :: (store 4 into %stack.7, addrspace 5)
|
||||
; GCN: SI_SPILL_V32_SAVE killed $vgpr18, %stack.8, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr3, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
|
||||
; GCN: $exec = S_XOR_B64_term $exec, killed renamable $sgpr4_sgpr5, implicit-def $scc
|
||||
; GCN: S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
||||
; GCN: bb.2:
|
||||
; GCN: $sgpr0_sgpr1 = SI_SPILL_S64_RESTORE %stack.3, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr3, implicit-def dead $m0 :: (load 8 from %stack.3, align 4, addrspace 5)
|
||||
; GCN: $exec = S_MOV_B64 renamable $sgpr0_sgpr1
|
||||
; GCN: $exec = S_MOV_B64 killed renamable $sgpr0_sgpr1
|
||||
; GCN: $vgpr0 = SI_SPILL_V32_RESTORE %stack.8, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr3, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
|
||||
; GCN: $sgpr4_sgpr5_sgpr6_sgpr7 = SI_SPILL_S128_RESTORE %stack.1, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr3, implicit-def dead $m0 :: (load 16 from %stack.1, align 4, addrspace 5)
|
||||
; GCN: BUFFER_STORE_DWORD_OFFSET renamable $vgpr0, renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %ir.out.load, addrspace 1)
|
||||
; GCN: S_ENDPGM 0
|
||||
; GCN: BUFFER_STORE_DWORD_OFFSET killed renamable $vgpr0, killed renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %ir.out.load, addrspace 1)
|
||||
; GCN: S_ENDPGM
|
||||
entry:
|
||||
%id = call i32 @llvm.amdgcn.workitem.id.x() #1
|
||||
%index = add i32 %id, 1
|
||||
|
|
|
|||
|
|
@ -1956,6 +1956,7 @@ define i32 @AtomicCmpSwap32(i32 signext %oldval, i32 signext %newval) nounwind {
|
|||
; MIPS32O0-NEXT: xor $1, $5, $4
|
||||
; MIPS32O0-NEXT: sltiu $1, $1, 1
|
||||
; MIPS32O0-NEXT: move $2, $5
|
||||
; MIPS32O0-NEXT: sw $1, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32O0-NEXT: jr $ra
|
||||
; MIPS32O0-NEXT: nop
|
||||
|
|
@ -2009,12 +2010,12 @@ define i32 @AtomicCmpSwap32(i32 signext %oldval, i32 signext %newval) nounwind {
|
|||
; MIPS32R6O0: # %bb.0: # %entry
|
||||
; MIPS32R6O0-NEXT: lui $2, %hi(_gp_disp)
|
||||
; MIPS32R6O0-NEXT: addiu $2, $2, %lo(_gp_disp)
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -16
|
||||
; MIPS32R6O0-NEXT: addu $1, $2, $25
|
||||
; MIPS32R6O0-NEXT: move $2, $5
|
||||
; MIPS32R6O0-NEXT: move $3, $4
|
||||
; MIPS32R6O0-NEXT: sw $5, 4($sp)
|
||||
; MIPS32R6O0-NEXT: lw $5, 4($sp)
|
||||
; MIPS32R6O0-NEXT: sw $5, 12($sp)
|
||||
; MIPS32R6O0-NEXT: lw $5, 12($sp)
|
||||
; MIPS32R6O0-NEXT: lw $1, %got(x)($1)
|
||||
; MIPS32R6O0-NEXT: $BB7_1: # %entry
|
||||
; MIPS32R6O0-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
|
|
@ -2026,9 +2027,10 @@ define i32 @AtomicCmpSwap32(i32 signext %oldval, i32 signext %newval) nounwind {
|
|||
; MIPS32R6O0-NEXT: sc $7, 0($1)
|
||||
; MIPS32R6O0-NEXT: beqzc $7, $BB7_1
|
||||
; MIPS32R6O0-NEXT: $BB7_3: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $2, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 8($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: move $2, $6
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: sw $3, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 16
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
;
|
||||
; MIPS4-LABEL: AtomicCmpSwap32:
|
||||
|
|
@ -2440,9 +2442,10 @@ define signext i8 @AtomicLoadAdd8(i8 signext %incr) nounwind {
|
|||
; MIPS32R6O0-NEXT: srlv $7, $7, $1
|
||||
; MIPS32R6O0-NEXT: seb $7, $7
|
||||
; MIPS32R6O0-NEXT: # %bb.3: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $7, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $7, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: seb $2, $1
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
|
|
@ -2956,9 +2959,10 @@ define signext i8 @AtomicLoadSub8(i8 signext %incr) nounwind {
|
|||
; MIPS32R6O0-NEXT: srlv $7, $7, $1
|
||||
; MIPS32R6O0-NEXT: seb $7, $7
|
||||
; MIPS32R6O0-NEXT: # %bb.3: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $7, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $7, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: seb $2, $1
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
|
|
@ -3478,9 +3482,10 @@ define signext i8 @AtomicLoadNand8(i8 signext %incr) nounwind {
|
|||
; MIPS32R6O0-NEXT: srlv $7, $7, $1
|
||||
; MIPS32R6O0-NEXT: seb $7, $7
|
||||
; MIPS32R6O0-NEXT: # %bb.3: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $7, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $7, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: seb $2, $1
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
|
|
@ -4000,9 +4005,10 @@ define signext i8 @AtomicSwap8(i8 signext %newval) nounwind {
|
|||
; MIPS32R6O0-NEXT: srlv $7, $7, $1
|
||||
; MIPS32R6O0-NEXT: seb $7, $7
|
||||
; MIPS32R6O0-NEXT: # %bb.3: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $7, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $7, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: seb $2, $1
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
|
|
@ -4498,7 +4504,7 @@ define signext i8 @AtomicCmpSwap8(i8 signext %oldval, i8 signext %newval) nounwi
|
|||
; MIPS32R6O0: # %bb.0: # %entry
|
||||
; MIPS32R6O0-NEXT: lui $2, %hi(_gp_disp)
|
||||
; MIPS32R6O0-NEXT: addiu $2, $2, %lo(_gp_disp)
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -16
|
||||
; MIPS32R6O0-NEXT: addu $1, $2, $25
|
||||
; MIPS32R6O0-NEXT: move $2, $5
|
||||
; MIPS32R6O0-NEXT: move $3, $4
|
||||
|
|
@ -4529,10 +4535,12 @@ define signext i8 @AtomicCmpSwap8(i8 signext %oldval, i8 signext %newval) nounwi
|
|||
; MIPS32R6O0-NEXT: srlv $9, $11, $1
|
||||
; MIPS32R6O0-NEXT: seb $9, $9
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $2, 12($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $3, 8($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $9, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.5: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 16
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
;
|
||||
; MIPS4-LABEL: AtomicCmpSwap8:
|
||||
|
|
@ -5074,7 +5082,7 @@ define i1 @AtomicCmpSwapRes8(i8* %ptr, i8 signext %oldval, i8 signext %newval) n
|
|||
;
|
||||
; MIPS32R6O0-LABEL: AtomicCmpSwapRes8:
|
||||
; MIPS32R6O0: # %bb.0: # %entry
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -24
|
||||
; MIPS32R6O0-NEXT: move $1, $6
|
||||
; MIPS32R6O0-NEXT: move $2, $5
|
||||
; MIPS32R6O0-NEXT: move $3, $4
|
||||
|
|
@ -5104,14 +5112,17 @@ define i1 @AtomicCmpSwapRes8(i8* %ptr, i8 signext %oldval, i8 signext %newval) n
|
|||
; MIPS32R6O0-NEXT: srlv $11, $13, $4
|
||||
; MIPS32R6O0-NEXT: seb $11, $11
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $5, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $11, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $5, 20($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $1, 16($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 12($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $3, 8($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $11, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.5: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $2, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $2, 20($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: xor $1, $1, $2
|
||||
; MIPS32R6O0-NEXT: sltiu $2, $1, 1
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 24
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
;
|
||||
; MIPS4-LABEL: AtomicCmpSwapRes8:
|
||||
|
|
@ -5256,7 +5267,7 @@ define i1 @AtomicCmpSwapRes8(i8* %ptr, i8 signext %oldval, i8 signext %newval) n
|
|||
;
|
||||
; MIPS64R6O0-LABEL: AtomicCmpSwapRes8:
|
||||
; MIPS64R6O0: # %bb.0: # %entry
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, -16
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, -32
|
||||
; MIPS64R6O0-NEXT: move $1, $6
|
||||
; MIPS64R6O0-NEXT: move $2, $5
|
||||
; MIPS64R6O0-NEXT: move $3, $4
|
||||
|
|
@ -5287,14 +5298,15 @@ define i1 @AtomicCmpSwapRes8(i8* %ptr, i8 signext %oldval, i8 signext %newval) n
|
|||
; MIPS64R6O0-NEXT: srlv $11, $13, $7
|
||||
; MIPS64R6O0-NEXT: seb $11, $11
|
||||
; MIPS64R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS64R6O0-NEXT: sw $2, 12($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sw $11, 8($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sw $2, 28($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sd $3, 16($sp) # 8-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sw $11, 12($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: # %bb.5: # %entry
|
||||
; MIPS64R6O0-NEXT: lw $1, 8($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: lw $2, 12($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: lw $2, 28($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: xor $1, $1, $2
|
||||
; MIPS64R6O0-NEXT: sltiu $2, $1, 1
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, 16
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, 32
|
||||
; MIPS64R6O0-NEXT: jrc $ra
|
||||
;
|
||||
; MM32-LABEL: AtomicCmpSwapRes8:
|
||||
|
|
@ -5658,9 +5670,10 @@ define signext i16 @AtomicLoadAdd16(i16 signext %incr) nounwind {
|
|||
; MIPS32R6O0-NEXT: srlv $7, $7, $1
|
||||
; MIPS32R6O0-NEXT: seh $7, $7
|
||||
; MIPS32R6O0-NEXT: # %bb.3: # %entry
|
||||
; MIPS32R6O0-NEXT: sw $7, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $7, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.4: # %entry
|
||||
; MIPS32R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: lw $1, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: seh $2, $1
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
|
|
@ -6173,8 +6186,8 @@ define {i16, i1} @foo(i16* %addr, i16 %l, i16 %r, i16 %new) {
|
|||
;
|
||||
; MIPS32R6O0-LABEL: foo:
|
||||
; MIPS32R6O0: # %bb.0:
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -8
|
||||
; MIPS32R6O0-NEXT: .cfi_def_cfa_offset 8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, -24
|
||||
; MIPS32R6O0-NEXT: .cfi_def_cfa_offset 24
|
||||
; MIPS32R6O0-NEXT: move $1, $7
|
||||
; MIPS32R6O0-NEXT: move $2, $6
|
||||
; MIPS32R6O0-NEXT: move $3, $5
|
||||
|
|
@ -6205,6 +6218,10 @@ define {i16, i1} @foo(i16* %addr, i16 %l, i16 %r, i16 %new) {
|
|||
; MIPS32R6O0-NEXT: srlv $12, $14, $4
|
||||
; MIPS32R6O0-NEXT: seh $12, $12
|
||||
; MIPS32R6O0-NEXT: # %bb.4:
|
||||
; MIPS32R6O0-NEXT: sw $1, 20($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $2, 16($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $3, 12($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $8, 8($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $5, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: sw $12, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS32R6O0-NEXT: # %bb.5:
|
||||
|
|
@ -6215,7 +6232,7 @@ define {i16, i1} @foo(i16* %addr, i16 %l, i16 %r, i16 %new) {
|
|||
; MIPS32R6O0-NEXT: sltiu $3, $2, 1
|
||||
; MIPS32R6O0-NEXT: sync
|
||||
; MIPS32R6O0-NEXT: lw $2, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32R6O0-NEXT: addiu $sp, $sp, 24
|
||||
; MIPS32R6O0-NEXT: jrc $ra
|
||||
;
|
||||
; MIPS4-LABEL: foo:
|
||||
|
|
@ -6417,16 +6434,17 @@ define {i16, i1} @foo(i16* %addr, i16 %l, i16 %r, i16 %new) {
|
|||
; MIPS64R6O0-NEXT: srlv $11, $13, $3
|
||||
; MIPS64R6O0-NEXT: seh $11, $11
|
||||
; MIPS64R6O0-NEXT: # %bb.4:
|
||||
; MIPS64R6O0-NEXT: sw $2, 12($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sw $11, 8($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sd $5, 8($sp) # 8-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sw $2, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sw $11, 0($sp) # 4-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: # %bb.5:
|
||||
; MIPS64R6O0-NEXT: lw $1, 12($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: lw $1, 4($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: seh $2, $1
|
||||
; MIPS64R6O0-NEXT: lw $3, 8($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: lw $3, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: xor $2, $3, $2
|
||||
; MIPS64R6O0-NEXT: sltiu $3, $2, 1
|
||||
; MIPS64R6O0-NEXT: sync
|
||||
; MIPS64R6O0-NEXT: lw $2, 8($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: lw $2, 0($sp) # 4-byte Folded Reload
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, 16
|
||||
; MIPS64R6O0-NEXT: jrc $ra
|
||||
;
|
||||
|
|
@ -6955,6 +6973,7 @@ define i32 @zeroreg() nounwind {
|
|||
; MIPS32O0: # %bb.0: # %entry
|
||||
; MIPS32O0-NEXT: lui $2, %hi(_gp_disp)
|
||||
; MIPS32O0-NEXT: addiu $2, $2, %lo(_gp_disp)
|
||||
; MIPS32O0-NEXT: addiu $sp, $sp, -8
|
||||
; MIPS32O0-NEXT: addu $1, $2, $25
|
||||
; MIPS32O0-NEXT: sync
|
||||
; MIPS32O0-NEXT: lw $1, %got(a)($1)
|
||||
|
|
@ -6980,6 +6999,8 @@ define i32 @zeroreg() nounwind {
|
|||
; MIPS32O0-NEXT: xor $2, $5, $2
|
||||
; MIPS32O0-NEXT: sltiu $2, $2, 1
|
||||
; MIPS32O0-NEXT: andi $2, $2, 1
|
||||
; MIPS32O0-NEXT: sw $1, 4($sp) # 4-byte Folded Spill
|
||||
; MIPS32O0-NEXT: addiu $sp, $sp, 8
|
||||
; MIPS32O0-NEXT: jr $ra
|
||||
; MIPS32O0-NEXT: nop
|
||||
;
|
||||
|
|
|
|||
|
|
@ -1274,14 +1274,14 @@ define i64 @AtomicCmpSwap64(i64 signext %oldval, i64 signext %newval) nounwind {
|
|||
;
|
||||
; MIPS64R6O0-LABEL: AtomicCmpSwap64:
|
||||
; MIPS64R6O0: # %bb.0: # %entry
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, -16
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, -32
|
||||
; MIPS64R6O0-NEXT: lui $1, %hi(%neg(%gp_rel(AtomicCmpSwap64)))
|
||||
; MIPS64R6O0-NEXT: daddu $1, $1, $25
|
||||
; MIPS64R6O0-NEXT: daddiu $1, $1, %lo(%neg(%gp_rel(AtomicCmpSwap64)))
|
||||
; MIPS64R6O0-NEXT: move $2, $5
|
||||
; MIPS64R6O0-NEXT: move $3, $4
|
||||
; MIPS64R6O0-NEXT: sd $5, 8($sp)
|
||||
; MIPS64R6O0-NEXT: ld $5, 8($sp)
|
||||
; MIPS64R6O0-NEXT: sd $5, 24($sp)
|
||||
; MIPS64R6O0-NEXT: ld $5, 24($sp)
|
||||
; MIPS64R6O0-NEXT: ld $1, %got_disp(x)($1)
|
||||
; MIPS64R6O0-NEXT: .LBB7_1: # %entry
|
||||
; MIPS64R6O0-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
|
|
@ -1293,9 +1293,10 @@ define i64 @AtomicCmpSwap64(i64 signext %oldval, i64 signext %newval) nounwind {
|
|||
; MIPS64R6O0-NEXT: scd $7, 0($1)
|
||||
; MIPS64R6O0-NEXT: beqzc $7, .LBB7_1
|
||||
; MIPS64R6O0-NEXT: .LBB7_3: # %entry
|
||||
; MIPS64R6O0-NEXT: sd $2, 0($sp) # 8-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: sd $2, 16($sp) # 8-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: move $2, $6
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, 16
|
||||
; MIPS64R6O0-NEXT: sd $3, 8($sp) # 8-byte Folded Spill
|
||||
; MIPS64R6O0-NEXT: daddiu $sp, $sp, 32
|
||||
; MIPS64R6O0-NEXT: jrc $ra
|
||||
;
|
||||
; O1-LABEL: AtomicCmpSwap64:
|
||||
|
|
|
|||
|
|
@ -11,6 +11,8 @@
|
|||
define void @foo(i32 %new, i32 %old) {
|
||||
; O32-LABEL: foo:
|
||||
; O32: # %bb.0: # %entry
|
||||
; O32-NEXT: addiu $sp, $sp, -16
|
||||
; O32-NEXT: .cfi_def_cfa_offset 16
|
||||
; O32-NEXT: move $1, $5
|
||||
; O32-NEXT: move $2, $4
|
||||
; O32-NEXT: lui $3, %hi(sym)
|
||||
|
|
@ -29,11 +31,17 @@ define void @foo(i32 %new, i32 %old) {
|
|||
; O32-NEXT: nop
|
||||
; O32-NEXT: $BB0_3: # %entry
|
||||
; O32-NEXT: sync
|
||||
; O32-NEXT: sw $1, 12($sp) # 4-byte Folded Spill
|
||||
; O32-NEXT: sw $2, 8($sp) # 4-byte Folded Spill
|
||||
; O32-NEXT: sw $6, 4($sp) # 4-byte Folded Spill
|
||||
; O32-NEXT: addiu $sp, $sp, 16
|
||||
; O32-NEXT: jr $ra
|
||||
; O32-NEXT: nop
|
||||
;
|
||||
; N32-LABEL: foo:
|
||||
; N32: # %bb.0: # %entry
|
||||
; N32-NEXT: addiu $sp, $sp, -16
|
||||
; N32-NEXT: .cfi_def_cfa_offset 16
|
||||
; N32-NEXT: move $1, $5
|
||||
; N32-NEXT: sll $1, $1, 0
|
||||
; N32-NEXT: move $2, $4
|
||||
|
|
@ -54,11 +62,15 @@ define void @foo(i32 %new, i32 %old) {
|
|||
; N32-NEXT: nop
|
||||
; N32-NEXT: .LBB0_3: # %entry
|
||||
; N32-NEXT: sync
|
||||
; N32-NEXT: sw $6, 12($sp) # 4-byte Folded Spill
|
||||
; N32-NEXT: addiu $sp, $sp, 16
|
||||
; N32-NEXT: jr $ra
|
||||
; N32-NEXT: nop
|
||||
;
|
||||
; N64-LABEL: foo:
|
||||
; N64: # %bb.0: # %entry
|
||||
; N64-NEXT: daddiu $sp, $sp, -16
|
||||
; N64-NEXT: .cfi_def_cfa_offset 16
|
||||
; N64-NEXT: move $1, $5
|
||||
; N64-NEXT: sll $1, $1, 0
|
||||
; N64-NEXT: move $2, $4
|
||||
|
|
@ -83,6 +95,8 @@ define void @foo(i32 %new, i32 %old) {
|
|||
; N64-NEXT: nop
|
||||
; N64-NEXT: .LBB0_3: # %entry
|
||||
; N64-NEXT: sync
|
||||
; N64-NEXT: sw $6, 12($sp) # 4-byte Folded Spill
|
||||
; N64-NEXT: daddiu $sp, $sp, 16
|
||||
; N64-NEXT: jr $ra
|
||||
; N64-NEXT: nop
|
||||
entry:
|
||||
|
|
|
|||
|
|
@ -23,10 +23,12 @@ entry:
|
|||
|
||||
; ASM: SWDSP
|
||||
; ASM: SWDSP
|
||||
; ASM: SWDSP
|
||||
|
||||
; MM-OBJ: sw ${{[0-9]+}}, {{[0-9]+}}($sp)
|
||||
; MM-OBJ: sw ${{[0-9]+}}, {{[0-9]+}}($sp)
|
||||
; MM-OBJ: sw ${{[0-9]+}}, {{[0-9]+}}($sp)
|
||||
; MM-OBJ: sw ${{[0-9]+}}, {{[0-9]+}}($sp)
|
||||
|
||||
true:
|
||||
ret <4 x i8> %c
|
||||
|
|
|
|||
|
|
@ -27,6 +27,7 @@ define void @bn_mul_comba8(i64* nocapture %r, i64* nocapture readonly %a, i64* n
|
|||
; CHECK-NEXT: mr 4, 10
|
||||
; CHECK-NEXT: clrldi 4, 4, 32
|
||||
; CHECK-NEXT: std 4, 0(3)
|
||||
; CHECK-NEXT: std 6, -8(1) # 8-byte Folded Spill
|
||||
; CHECK-NEXT: blr
|
||||
%1 = load i64, i64* %a, align 8
|
||||
%conv = zext i64 %1 to i128
|
||||
|
|
|
|||
|
|
@ -396,6 +396,8 @@ define <4 x i32> @test14(<4 x i32> %a, <4 x i32> %b) {
|
|||
; CHECK-FISL: # %bb.0: # %entry
|
||||
; CHECK-FISL-NEXT: xxlor vs0, v2, v3
|
||||
; CHECK-FISL-NEXT: xxlnor v2, v2, v3
|
||||
; CHECK-FISL-NEXT: li r3, -16
|
||||
; CHECK-FISL-NEXT: stxvd2x vs0, r1, r3 # 16-byte Folded Spill
|
||||
; CHECK-FISL-NEXT: blr
|
||||
;
|
||||
; CHECK-LE-LABEL: test14:
|
||||
|
|
@ -428,6 +430,8 @@ define <8 x i16> @test15(<8 x i16> %a, <8 x i16> %b) {
|
|||
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
|
||||
; CHECK-FISL-NEXT: xxlnor vs0, v2, v3
|
||||
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
|
||||
; CHECK-FISL-NEXT: li r3, -16
|
||||
; CHECK-FISL-NEXT: stxvd2x v4, r1, r3 # 16-byte Folded Spill
|
||||
; CHECK-FISL-NEXT: blr
|
||||
;
|
||||
; CHECK-LE-LABEL: test15:
|
||||
|
|
@ -460,6 +464,8 @@ define <16 x i8> @test16(<16 x i8> %a, <16 x i8> %b) {
|
|||
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
|
||||
; CHECK-FISL-NEXT: xxlnor vs0, v2, v3
|
||||
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
|
||||
; CHECK-FISL-NEXT: li r3, -16
|
||||
; CHECK-FISL-NEXT: stxvd2x v4, r1, r3 # 16-byte Folded Spill
|
||||
; CHECK-FISL-NEXT: blr
|
||||
;
|
||||
; CHECK-LE-LABEL: test16:
|
||||
|
|
@ -522,6 +528,8 @@ define <8 x i16> @test18(<8 x i16> %a, <8 x i16> %b) {
|
|||
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
|
||||
; CHECK-FISL-NEXT: xxlandc vs0, v2, v3
|
||||
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
|
||||
; CHECK-FISL-NEXT: li r3, -16
|
||||
; CHECK-FISL-NEXT: stxvd2x v4, r1, r3 # 16-byte Folded Spill
|
||||
; CHECK-FISL-NEXT: blr
|
||||
;
|
||||
; CHECK-LE-LABEL: test18:
|
||||
|
|
@ -554,6 +562,8 @@ define <16 x i8> @test19(<16 x i8> %a, <16 x i8> %b) {
|
|||
; CHECK-FISL-NEXT: xxlor v4, vs0, vs0
|
||||
; CHECK-FISL-NEXT: xxlandc vs0, v2, v3
|
||||
; CHECK-FISL-NEXT: xxlor v2, vs0, vs0
|
||||
; CHECK-FISL-NEXT: li r3, -16
|
||||
; CHECK-FISL-NEXT: stxvd2x v4, r1, r3 # 16-byte Folded Spill
|
||||
; CHECK-FISL-NEXT: blr
|
||||
;
|
||||
; CHECK-LE-LABEL: test19:
|
||||
|
|
@ -1680,6 +1690,8 @@ define <2 x double> @test51(<2 x double> %a, <2 x double> %b) {
|
|||
; CHECK-FISL-LABEL: test51:
|
||||
; CHECK-FISL: # %bb.0:
|
||||
; CHECK-FISL-NEXT: xxspltd v2, v2, 0
|
||||
; CHECK-FISL-NEXT: li r3, -16
|
||||
; CHECK-FISL-NEXT: stxvd2x v3, r1, r3 # 16-byte Folded Spill
|
||||
; CHECK-FISL-NEXT: blr
|
||||
;
|
||||
; CHECK-LE-LABEL: test51:
|
||||
|
|
|
|||
|
|
@ -46,5 +46,5 @@ body: |
|
|||
# CHECK-NEXT: renamable $r12 = COPY killed renamable $r0
|
||||
# CHECK-NEXT: t2STRi12 killed $r12, %stack.1, 0, 14, $noreg :: (store 4 into %stack.1)
|
||||
# CHECK-NEXT: $r8 = t2LDRi12 %stack.1, 0, 14, $noreg :: (load 4 from %stack.1)
|
||||
# CHECK-NEXT: INLINEASM &"@ $0", 1, 589833, renamable $r8, 12, implicit-def early-clobber $r12
|
||||
# CHECK-NEXT: INLINEASM &"@ $0", 1, 589833, killed renamable $r8, 12, implicit-def early-clobber $r12
|
||||
# CHECK-NEXT: tBX_RET 14, $noreg
|
||||
|
|
|
|||
|
|
@ -561,6 +561,8 @@ define void @widen_zero_init(i32* %p0, i32 %v1, i32 %v2) {
|
|||
; CHECK-O0: # %bb.0:
|
||||
; CHECK-O0-NEXT: movl $0, (%rdi)
|
||||
; CHECK-O0-NEXT: movl $0, 4(%rdi)
|
||||
; CHECK-O0-NEXT: movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-O0-NEXT: movl %edx, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: widen_zero_init:
|
||||
|
|
@ -580,6 +582,8 @@ define void @widen_zero_init_unaligned(i32* %p0, i32 %v1, i32 %v2) {
|
|||
; CHECK-O0: # %bb.0:
|
||||
; CHECK-O0-NEXT: movl $0, (%rdi)
|
||||
; CHECK-O0-NEXT: movl $0, 4(%rdi)
|
||||
; CHECK-O0-NEXT: movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-O0-NEXT: movl %edx, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: widen_zero_init_unaligned:
|
||||
|
|
@ -1533,6 +1537,7 @@ define void @rmw_fold_add1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: addq $15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_add1:
|
||||
|
|
@ -1571,6 +1576,7 @@ define void @rmw_fold_sub1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: addq $-15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_sub1:
|
||||
|
|
@ -1610,6 +1616,7 @@ define void @rmw_fold_mul1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: leaq (%rax,%rax,4), %rax
|
||||
; CHECK-O0-NEXT: leaq (%rax,%rax,2), %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_mul1:
|
||||
|
|
@ -1660,6 +1667,7 @@ define void @rmw_fold_sdiv1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: sarq $3, %rdx
|
||||
; CHECK-O0-NEXT: addq %rcx, %rdx
|
||||
; CHECK-O0-NEXT: movq %rdx, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_sdiv1:
|
||||
|
|
@ -1725,6 +1733,7 @@ define void @rmw_fold_udiv1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: mulq %rcx
|
||||
; CHECK-O0-NEXT: shrq $3, %rdx
|
||||
; CHECK-O0-NEXT: movq %rdx, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_udiv1:
|
||||
|
|
@ -1795,6 +1804,7 @@ define void @rmw_fold_srem1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: leaq (%rcx,%rcx,2), %rcx
|
||||
; CHECK-O0-NEXT: subq %rcx, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_srem1:
|
||||
|
|
@ -1868,6 +1878,7 @@ define void @rmw_fold_urem1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload
|
||||
; CHECK-O0-NEXT: subq %rax, %rcx
|
||||
; CHECK-O0-NEXT: movq %rcx, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_urem1:
|
||||
|
|
@ -1931,6 +1942,7 @@ define void @rmw_fold_shl1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: shlq $15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_shl1:
|
||||
|
|
@ -1975,6 +1987,7 @@ define void @rmw_fold_lshr1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: shrq $15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_lshr1:
|
||||
|
|
@ -2019,6 +2032,7 @@ define void @rmw_fold_ashr1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: sarq $15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_ashr1:
|
||||
|
|
@ -2065,6 +2079,7 @@ define void @rmw_fold_and1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: andl $15, %ecx
|
||||
; CHECK-O0-NEXT: movl %ecx, %eax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_and1:
|
||||
|
|
@ -2103,6 +2118,7 @@ define void @rmw_fold_or1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: orq $15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_or1:
|
||||
|
|
@ -2141,6 +2157,7 @@ define void @rmw_fold_xor1(i64* %p, i64 %v) {
|
|||
; CHECK-O0-NEXT: movq (%rdi), %rax
|
||||
; CHECK-O0-NEXT: xorq $15, %rax
|
||||
; CHECK-O0-NEXT: movq %rax, (%rdi)
|
||||
; CHECK-O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-O0-NEXT: retq
|
||||
;
|
||||
; CHECK-O3-LABEL: rmw_fold_xor1:
|
||||
|
|
|
|||
|
|
@ -324,7 +324,7 @@ define void @atomic_fetch_max32(i32 %x) nounwind {
|
|||
; X86-NOCMOV: # %bb.0:
|
||||
; X86-NOCMOV-NEXT: pushl %ebx
|
||||
; X86-NOCMOV-NEXT: pushl %esi
|
||||
; X86-NOCMOV-NEXT: subl $20, %esp
|
||||
; X86-NOCMOV-NEXT: subl $24, %esp
|
||||
; X86-NOCMOV-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X86-NOCMOV-NEXT: movl sc32, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
|
|
@ -337,6 +337,7 @@ define void @atomic_fetch_max32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: subl %edx, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, %esi
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: jge .LBB6_4
|
||||
; X86-NOCMOV-NEXT: # %bb.3: # %atomicrmw.start
|
||||
|
|
@ -357,7 +358,7 @@ define void @atomic_fetch_max32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: jne .LBB6_2
|
||||
; X86-NOCMOV-NEXT: jmp .LBB6_1
|
||||
; X86-NOCMOV-NEXT: .LBB6_2: # %atomicrmw.end
|
||||
; X86-NOCMOV-NEXT: addl $20, %esp
|
||||
; X86-NOCMOV-NEXT: addl $24, %esp
|
||||
; X86-NOCMOV-NEXT: popl %esi
|
||||
; X86-NOCMOV-NEXT: popl %ebx
|
||||
; X86-NOCMOV-NEXT: retl
|
||||
|
|
@ -419,7 +420,7 @@ define void @atomic_fetch_min32(i32 %x) nounwind {
|
|||
; X86-NOCMOV: # %bb.0:
|
||||
; X86-NOCMOV-NEXT: pushl %ebx
|
||||
; X86-NOCMOV-NEXT: pushl %esi
|
||||
; X86-NOCMOV-NEXT: subl $20, %esp
|
||||
; X86-NOCMOV-NEXT: subl $24, %esp
|
||||
; X86-NOCMOV-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X86-NOCMOV-NEXT: movl sc32, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
|
|
@ -432,6 +433,7 @@ define void @atomic_fetch_min32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: subl %edx, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, %esi
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: jle .LBB7_4
|
||||
; X86-NOCMOV-NEXT: # %bb.3: # %atomicrmw.start
|
||||
|
|
@ -452,7 +454,7 @@ define void @atomic_fetch_min32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: jne .LBB7_2
|
||||
; X86-NOCMOV-NEXT: jmp .LBB7_1
|
||||
; X86-NOCMOV-NEXT: .LBB7_2: # %atomicrmw.end
|
||||
; X86-NOCMOV-NEXT: addl $20, %esp
|
||||
; X86-NOCMOV-NEXT: addl $24, %esp
|
||||
; X86-NOCMOV-NEXT: popl %esi
|
||||
; X86-NOCMOV-NEXT: popl %ebx
|
||||
; X86-NOCMOV-NEXT: retl
|
||||
|
|
@ -514,7 +516,7 @@ define void @atomic_fetch_umax32(i32 %x) nounwind {
|
|||
; X86-NOCMOV: # %bb.0:
|
||||
; X86-NOCMOV-NEXT: pushl %ebx
|
||||
; X86-NOCMOV-NEXT: pushl %esi
|
||||
; X86-NOCMOV-NEXT: subl $20, %esp
|
||||
; X86-NOCMOV-NEXT: subl $24, %esp
|
||||
; X86-NOCMOV-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X86-NOCMOV-NEXT: movl sc32, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
|
|
@ -527,6 +529,7 @@ define void @atomic_fetch_umax32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: subl %edx, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, %esi
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: ja .LBB8_4
|
||||
; X86-NOCMOV-NEXT: # %bb.3: # %atomicrmw.start
|
||||
|
|
@ -547,7 +550,7 @@ define void @atomic_fetch_umax32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: jne .LBB8_2
|
||||
; X86-NOCMOV-NEXT: jmp .LBB8_1
|
||||
; X86-NOCMOV-NEXT: .LBB8_2: # %atomicrmw.end
|
||||
; X86-NOCMOV-NEXT: addl $20, %esp
|
||||
; X86-NOCMOV-NEXT: addl $24, %esp
|
||||
; X86-NOCMOV-NEXT: popl %esi
|
||||
; X86-NOCMOV-NEXT: popl %ebx
|
||||
; X86-NOCMOV-NEXT: retl
|
||||
|
|
@ -609,7 +612,7 @@ define void @atomic_fetch_umin32(i32 %x) nounwind {
|
|||
; X86-NOCMOV: # %bb.0:
|
||||
; X86-NOCMOV-NEXT: pushl %ebx
|
||||
; X86-NOCMOV-NEXT: pushl %esi
|
||||
; X86-NOCMOV-NEXT: subl $20, %esp
|
||||
; X86-NOCMOV-NEXT: subl $24, %esp
|
||||
; X86-NOCMOV-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X86-NOCMOV-NEXT: movl sc32, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
|
|
@ -622,6 +625,7 @@ define void @atomic_fetch_umin32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: subl %edx, %ecx
|
||||
; X86-NOCMOV-NEXT: movl %eax, %esi
|
||||
; X86-NOCMOV-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: jbe .LBB9_4
|
||||
; X86-NOCMOV-NEXT: # %bb.3: # %atomicrmw.start
|
||||
|
|
@ -642,7 +646,7 @@ define void @atomic_fetch_umin32(i32 %x) nounwind {
|
|||
; X86-NOCMOV-NEXT: jne .LBB9_2
|
||||
; X86-NOCMOV-NEXT: jmp .LBB9_1
|
||||
; X86-NOCMOV-NEXT: .LBB9_2: # %atomicrmw.end
|
||||
; X86-NOCMOV-NEXT: addl $20, %esp
|
||||
; X86-NOCMOV-NEXT: addl $24, %esp
|
||||
; X86-NOCMOV-NEXT: popl %esi
|
||||
; X86-NOCMOV-NEXT: popl %ebx
|
||||
; X86-NOCMOV-NEXT: retl
|
||||
|
|
@ -656,13 +660,17 @@ define void @atomic_fetch_cmpxchg32() nounwind {
|
|||
; X64-NEXT: xorl %eax, %eax
|
||||
; X64-NEXT: movl $1, %ecx
|
||||
; X64-NEXT: lock cmpxchgl %ecx, {{.*}}(%rip)
|
||||
; X64-NEXT: movl %eax, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; X64-NEXT: retq
|
||||
;
|
||||
; X86-LABEL: atomic_fetch_cmpxchg32:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: pushl %eax
|
||||
; X86-NEXT: xorl %eax, %eax
|
||||
; X86-NEXT: movl $1, %ecx
|
||||
; X86-NEXT: lock cmpxchgl %ecx, sc32
|
||||
; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
|
||||
; X86-NEXT: popl %eax
|
||||
; X86-NEXT: retl
|
||||
%t1 = cmpxchg i32* @sc32, i32 0, i32 1 acquire acquire
|
||||
ret void
|
||||
|
|
@ -687,12 +695,16 @@ define void @atomic_fetch_swap32(i32 %x) nounwind {
|
|||
; X64-LABEL: atomic_fetch_swap32:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: xchgl %edi, {{.*}}(%rip)
|
||||
; X64-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; X64-NEXT: retq
|
||||
;
|
||||
; X86-LABEL: atomic_fetch_swap32:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: pushl %eax
|
||||
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X86-NEXT: xchgl %eax, sc32
|
||||
; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
|
||||
; X86-NEXT: popl %eax
|
||||
; X86-NEXT: retl
|
||||
%t1 = atomicrmw xchg i32* @sc32, i32 %x acquire
|
||||
ret void
|
||||
|
|
@ -703,23 +715,28 @@ define void @atomic_fetch_swapf32(float %x) nounwind {
|
|||
; X64: # %bb.0:
|
||||
; X64-NEXT: movd %xmm0, %eax
|
||||
; X64-NEXT: xchgl %eax, {{.*}}(%rip)
|
||||
; X64-NEXT: movl %eax, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; X64-NEXT: retq
|
||||
;
|
||||
; X86-CMOV-LABEL: atomic_fetch_swapf32:
|
||||
; X86-CMOV: # %bb.0:
|
||||
; X86-CMOV-NEXT: pushl %eax
|
||||
; X86-CMOV-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; X86-CMOV-NEXT: movd %xmm0, %eax
|
||||
; X86-CMOV-NEXT: xchgl %eax, fsc32
|
||||
; X86-CMOV-NEXT: movl %eax, (%esp) # 4-byte Spill
|
||||
; X86-CMOV-NEXT: popl %eax
|
||||
; X86-CMOV-NEXT: retl
|
||||
;
|
||||
; X86-NOCMOV-LABEL: atomic_fetch_swapf32:
|
||||
; X86-NOCMOV: # %bb.0:
|
||||
; X86-NOCMOV-NEXT: pushl %eax
|
||||
; X86-NOCMOV-NEXT: subl $8, %esp
|
||||
; X86-NOCMOV-NEXT: flds {{[0-9]+}}(%esp)
|
||||
; X86-NOCMOV-NEXT: fstps (%esp)
|
||||
; X86-NOCMOV-NEXT: movl (%esp), %eax
|
||||
; X86-NOCMOV-NEXT: fstps {{[0-9]+}}(%esp)
|
||||
; X86-NOCMOV-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X86-NOCMOV-NEXT: xchgl %eax, fsc32
|
||||
; X86-NOCMOV-NEXT: popl %eax
|
||||
; X86-NOCMOV-NEXT: movl %eax, (%esp) # 4-byte Spill
|
||||
; X86-NOCMOV-NEXT: addl $8, %esp
|
||||
; X86-NOCMOV-NEXT: retl
|
||||
%t1 = atomicrmw xchg float* @fsc32, float %x acquire
|
||||
ret void
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ define void @atomic_fetch_add64() nounwind {
|
|||
; I486-LABEL: atomic_fetch_add64:
|
||||
; I486: # %bb.0: # %entry
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $48, %esp
|
||||
; I486-NEXT: subl $56, %esp
|
||||
; I486-NEXT: leal sc64, %eax
|
||||
; I486-NEXT: movl %esp, %ecx
|
||||
; I486-NEXT: movl $2, 12(%ecx)
|
||||
|
|
@ -55,7 +55,9 @@ define void @atomic_fetch_add64() nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_fetch_add_8
|
||||
; I486-NEXT: addl $48, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $56, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
entry:
|
||||
|
|
@ -79,7 +81,7 @@ define void @atomic_fetch_sub64() nounwind {
|
|||
; I486-LABEL: atomic_fetch_sub64:
|
||||
; I486: # %bb.0:
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $48, %esp
|
||||
; I486-NEXT: subl $56, %esp
|
||||
; I486-NEXT: leal sc64, %eax
|
||||
; I486-NEXT: movl %esp, %ecx
|
||||
; I486-NEXT: movl $2, 12(%ecx)
|
||||
|
|
@ -116,7 +118,9 @@ define void @atomic_fetch_sub64() nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_fetch_sub_8
|
||||
; I486-NEXT: addl $48, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $56, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
%t1 = atomicrmw sub i64* @sc64, i64 1 acquire
|
||||
|
|
@ -154,7 +158,7 @@ define void @atomic_fetch_and64() nounwind {
|
|||
; I486-LABEL: atomic_fetch_and64:
|
||||
; I486: # %bb.0:
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $36, %esp
|
||||
; I486-NEXT: subl $44, %esp
|
||||
; I486-NEXT: leal sc64, %eax
|
||||
; I486-NEXT: movl %esp, %ecx
|
||||
; I486-NEXT: movl $2, 12(%ecx)
|
||||
|
|
@ -181,7 +185,9 @@ define void @atomic_fetch_and64() nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_fetch_and_8
|
||||
; I486-NEXT: addl $36, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $44, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
%t1 = atomicrmw and i64* @sc64, i64 3 acquire
|
||||
|
|
@ -217,7 +223,7 @@ define void @atomic_fetch_or64() nounwind {
|
|||
; I486-LABEL: atomic_fetch_or64:
|
||||
; I486: # %bb.0:
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $36, %esp
|
||||
; I486-NEXT: subl $44, %esp
|
||||
; I486-NEXT: leal sc64, %eax
|
||||
; I486-NEXT: movl %esp, %ecx
|
||||
; I486-NEXT: movl $2, 12(%ecx)
|
||||
|
|
@ -244,7 +250,9 @@ define void @atomic_fetch_or64() nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_fetch_or_8
|
||||
; I486-NEXT: addl $36, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $44, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
%t1 = atomicrmw or i64* @sc64, i64 3 acquire
|
||||
|
|
@ -280,7 +288,7 @@ define void @atomic_fetch_xor64() nounwind {
|
|||
; I486-LABEL: atomic_fetch_xor64:
|
||||
; I486: # %bb.0:
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $36, %esp
|
||||
; I486-NEXT: subl $44, %esp
|
||||
; I486-NEXT: leal sc64, %eax
|
||||
; I486-NEXT: movl %esp, %ecx
|
||||
; I486-NEXT: movl $2, 12(%ecx)
|
||||
|
|
@ -307,7 +315,9 @@ define void @atomic_fetch_xor64() nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_fetch_xor_8
|
||||
; I486-NEXT: addl $36, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $44, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
%t1 = atomicrmw xor i64* @sc64, i64 3 acquire
|
||||
|
|
@ -341,7 +351,7 @@ define void @atomic_fetch_nand64(i64 %x) nounwind {
|
|||
; I486-LABEL: atomic_fetch_nand64:
|
||||
; I486: # %bb.0:
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $20, %esp
|
||||
; I486-NEXT: subl $28, %esp
|
||||
; I486-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; I486-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
||||
; I486-NEXT: leal sc64, %edx
|
||||
|
|
@ -352,7 +362,9 @@ define void @atomic_fetch_nand64(i64 %x) nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_fetch_nand_8
|
||||
; I486-NEXT: addl $20, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $28, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
%t1 = atomicrmw nand i64* @sc64, i64 %x acquire
|
||||
|
|
@ -390,7 +402,7 @@ define void @atomic_fetch_max64(i64 %x) nounwind {
|
|||
; I486-NEXT: pushl %edi
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: andl $-8, %esp
|
||||
; I486-NEXT: subl $72, %esp
|
||||
; I486-NEXT: subl $80, %esp
|
||||
; I486-NEXT: movl 12(%ebp), %eax
|
||||
; I486-NEXT: movl 8(%ebp), %ecx
|
||||
; I486-NEXT: movl sc64+4, %edx
|
||||
|
|
@ -414,6 +426,8 @@ define void @atomic_fetch_max64(i64 %x) nounwind {
|
|||
; I486-NEXT: movl %eax, %ebx
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: jge .LBB6_4
|
||||
|
|
@ -490,7 +504,7 @@ define void @atomic_fetch_min64(i64 %x) nounwind {
|
|||
; I486-NEXT: pushl %edi
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: andl $-8, %esp
|
||||
; I486-NEXT: subl $72, %esp
|
||||
; I486-NEXT: subl $80, %esp
|
||||
; I486-NEXT: movl 12(%ebp), %eax
|
||||
; I486-NEXT: movl 8(%ebp), %ecx
|
||||
; I486-NEXT: movl sc64+4, %edx
|
||||
|
|
@ -512,6 +526,8 @@ define void @atomic_fetch_min64(i64 %x) nounwind {
|
|||
; I486-NEXT: movl %eax, %ebx
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: jge .LBB7_4
|
||||
|
|
@ -588,7 +604,7 @@ define void @atomic_fetch_umax64(i64 %x) nounwind {
|
|||
; I486-NEXT: pushl %edi
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: andl $-8, %esp
|
||||
; I486-NEXT: subl $72, %esp
|
||||
; I486-NEXT: subl $80, %esp
|
||||
; I486-NEXT: movl 12(%ebp), %eax
|
||||
; I486-NEXT: movl 8(%ebp), %ecx
|
||||
; I486-NEXT: movl sc64+4, %edx
|
||||
|
|
@ -610,6 +626,8 @@ define void @atomic_fetch_umax64(i64 %x) nounwind {
|
|||
; I486-NEXT: movl %eax, %ebx
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: jb .LBB8_4
|
||||
|
|
@ -686,7 +704,7 @@ define void @atomic_fetch_umin64(i64 %x) nounwind {
|
|||
; I486-NEXT: pushl %edi
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: andl $-8, %esp
|
||||
; I486-NEXT: subl $72, %esp
|
||||
; I486-NEXT: subl $80, %esp
|
||||
; I486-NEXT: movl 12(%ebp), %eax
|
||||
; I486-NEXT: movl 8(%ebp), %ecx
|
||||
; I486-NEXT: movl sc64+4, %edx
|
||||
|
|
@ -708,6 +726,8 @@ define void @atomic_fetch_umin64(i64 %x) nounwind {
|
|||
; I486-NEXT: movl %eax, %ebx
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: jae .LBB9_4
|
||||
|
|
@ -760,6 +780,7 @@ define void @atomic_fetch_cmpxchg64() nounwind {
|
|||
; X64-NEXT: # kill: def $rax killed $eax
|
||||
; X64-NEXT: movl $1, %ecx
|
||||
; X64-NEXT: lock cmpxchgq %rcx, {{.*}}(%rip)
|
||||
; X64-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; X64-NEXT: retq
|
||||
;
|
||||
; I486-LABEL: atomic_fetch_cmpxchg64:
|
||||
|
|
@ -781,6 +802,7 @@ define void @atomic_fetch_cmpxchg64() nounwind {
|
|||
; I486-NEXT: movl $sc64, (%edx)
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_compare_exchange_8
|
||||
; I486-NEXT: movb %al, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
|
||||
; I486-NEXT: movl %ebp, %esp
|
||||
; I486-NEXT: popl %ebp
|
||||
; I486-NEXT: retl
|
||||
|
|
@ -819,12 +841,13 @@ define void @atomic_fetch_swap64(i64 %x) nounwind {
|
|||
; X64-LABEL: atomic_fetch_swap64:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: xchgq %rdi, {{.*}}(%rip)
|
||||
; X64-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; X64-NEXT: retq
|
||||
;
|
||||
; I486-LABEL: atomic_fetch_swap64:
|
||||
; I486: # %bb.0:
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: subl $20, %esp
|
||||
; I486-NEXT: subl $28, %esp
|
||||
; I486-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; I486-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
||||
; I486-NEXT: leal sc64, %edx
|
||||
|
|
@ -835,7 +858,9 @@ define void @atomic_fetch_swap64(i64 %x) nounwind {
|
|||
; I486-NEXT: movl $sc64, (%esi)
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_exchange_8
|
||||
; I486-NEXT: addl $20, %esp
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: addl $28, %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: retl
|
||||
%t1 = atomicrmw xchg i64* @sc64, i64 %x acquire
|
||||
|
|
@ -847,6 +872,7 @@ define void @atomic_fetch_swapf64(double %x) nounwind {
|
|||
; X64: # %bb.0:
|
||||
; X64-NEXT: movq %xmm0, %rax
|
||||
; X64-NEXT: xchgq %rax, {{.*}}(%rip)
|
||||
; X64-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; X64-NEXT: retq
|
||||
;
|
||||
; I486-LABEL: atomic_fetch_swapf64:
|
||||
|
|
@ -855,7 +881,7 @@ define void @atomic_fetch_swapf64(double %x) nounwind {
|
|||
; I486-NEXT: movl %esp, %ebp
|
||||
; I486-NEXT: pushl %esi
|
||||
; I486-NEXT: andl $-8, %esp
|
||||
; I486-NEXT: subl $40, %esp
|
||||
; I486-NEXT: subl $48, %esp
|
||||
; I486-NEXT: fldl 8(%ebp)
|
||||
; I486-NEXT: leal fsc64, %eax
|
||||
; I486-NEXT: fstpl {{[0-9]+}}(%esp)
|
||||
|
|
@ -868,6 +894,8 @@ define void @atomic_fetch_swapf64(double %x) nounwind {
|
|||
; I486-NEXT: movl $fsc64, (%esi)
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: calll __atomic_exchange_8
|
||||
; I486-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; I486-NEXT: leal -4(%ebp), %esp
|
||||
; I486-NEXT: popl %esi
|
||||
; I486-NEXT: popl %ebp
|
||||
|
|
|
|||
|
|
@ -816,14 +816,16 @@ define void @atomic_fetch_cmpxchg64() nounwind {
|
|||
; X32-LABEL: atomic_fetch_cmpxchg64:
|
||||
; X32: # %bb.0:
|
||||
; X32-NEXT: pushl %ebx
|
||||
; X32-NEXT: pushl %eax
|
||||
; X32-NEXT: subl $12, %esp
|
||||
; X32-NEXT: xorl %eax, %eax
|
||||
; X32-NEXT: movl $1, %ebx
|
||||
; X32-NEXT: movl %eax, (%esp) # 4-byte Spill
|
||||
; X32-NEXT: movl (%esp), %edx # 4-byte Reload
|
||||
; X32-NEXT: movl (%esp), %ecx # 4-byte Reload
|
||||
; X32-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X32-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
|
||||
; X32-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
|
||||
; X32-NEXT: lock cmpxchg8b sc64
|
||||
; X32-NEXT: addl $4, %esp
|
||||
; X32-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; X32-NEXT: movl %edx, (%esp) # 4-byte Spill
|
||||
; X32-NEXT: addl $12, %esp
|
||||
; X32-NEXT: popl %ebx
|
||||
; X32-NEXT: retl
|
||||
%t1 = cmpxchg i64* @sc64, i64 0, i64 1 acquire acquire
|
||||
|
|
|
|||
|
|
@ -17,8 +17,8 @@ declare i32 @check_mask16(i16 zeroext %res_mask, i16 zeroext %exp_mask, i8* %fna
|
|||
define void @test_xmm(i32 %shift, i32 %mulp, <2 x i64> %a,i8* %arraydecay,i8* %fname){
|
||||
; CHECK-LABEL: test_xmm:
|
||||
; CHECK: ## %bb.0:
|
||||
; CHECK-NEXT: subq $56, %rsp
|
||||
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
||||
; CHECK-NEXT: subq $72, %rsp
|
||||
; CHECK-NEXT: .cfi_def_cfa_offset 80
|
||||
; CHECK-NEXT: vpmovw2m %xmm0, %k0
|
||||
; CHECK-NEXT: movl $2, %esi
|
||||
; CHECK-NEXT: movl $8, %eax
|
||||
|
|
@ -50,16 +50,17 @@ define void @test_xmm(i32 %shift, i32 %mulp, <2 x i64> %a,i8* %arraydecay,i8* %f
|
|||
; CHECK-NEXT: movl {{[-0-9]+}}(%r{{[sb]}}p), %edx ## 4-byte Reload
|
||||
; CHECK-NEXT: movl %eax, {{[-0-9]+}}(%r{{[sb]}}p) ## 4-byte Spill
|
||||
; CHECK-NEXT: kmovw %k1, {{[-0-9]+}}(%r{{[sb]}}p) ## 2-byte Spill
|
||||
; CHECK-NEXT: movw %r8w, (%rsp) ## 2-byte Spill
|
||||
; CHECK-NEXT: movw %r8w, {{[-0-9]+}}(%r{{[sb]}}p) ## 2-byte Spill
|
||||
; CHECK-NEXT: callq _calc_expected_mask_val
|
||||
; CHECK-NEXT: movw %ax, %r8w
|
||||
; CHECK-NEXT: movw (%rsp), %r10w ## 2-byte Reload
|
||||
; CHECK-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %r10w ## 2-byte Reload
|
||||
; CHECK-NEXT: movzwl %r10w, %edi
|
||||
; CHECK-NEXT: movzwl %r8w, %esi
|
||||
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx ## 8-byte Reload
|
||||
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Reload
|
||||
; CHECK-NEXT: callq _check_mask16
|
||||
; CHECK-NEXT: addq $56, %rsp
|
||||
; CHECK-NEXT: movl %eax, {{[-0-9]+}}(%r{{[sb]}}p) ## 4-byte Spill
|
||||
; CHECK-NEXT: addq $72, %rsp
|
||||
; CHECK-NEXT: retq
|
||||
%d2 = bitcast <2 x i64> %a to <8 x i16>
|
||||
%m2 = call i8 @llvm.x86.avx512.cvtw2mask.128(<8 x i16> %d2)
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@
|
|||
; CHECK-NEXT: #APP
|
||||
; CHECK-NEXT: #NO_APP
|
||||
; CHECK-NEXT: movq %rdx, %rax
|
||||
; CHECK-NEXT: movq %rdx, -8(%rsp)
|
||||
; CHECK-NEXT: ret
|
||||
|
||||
define i64 @foo() {
|
||||
|
|
|
|||
|
|
@ -116,6 +116,14 @@ define <16 x float> @makefloat(float %f1, float %f2, float %f3, float %f4, float
|
|||
; CHECK-NEXT: vinsertf64x4 $1, %ymm1, %zmm24, %zmm24
|
||||
; CHECK-NEXT: vmovaps %zmm24, {{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %zmm0
|
||||
; CHECK-NEXT: vmovss %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm9, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
||||
; CHECK-NEXT: vmovss %xmm15, (%rsp) # 4-byte Spill
|
||||
; CHECK-NEXT: movq %rbp, %rsp
|
||||
; CHECK-NEXT: popq %rbp
|
||||
; CHECK-NEXT: .cfi_def_cfa %rsp, 8
|
||||
|
|
|
|||
|
|
@ -186,8 +186,8 @@ define void @f1() {
|
|||
; 686-O0-NEXT: .cfi_def_cfa_offset 16
|
||||
; 686-O0-NEXT: pushl %esi
|
||||
; 686-O0-NEXT: .cfi_def_cfa_offset 20
|
||||
; 686-O0-NEXT: subl $1, %esp
|
||||
; 686-O0-NEXT: .cfi_def_cfa_offset 21
|
||||
; 686-O0-NEXT: subl $24, %esp
|
||||
; 686-O0-NEXT: .cfi_def_cfa_offset 44
|
||||
; 686-O0-NEXT: .cfi_offset %esi, -20
|
||||
; 686-O0-NEXT: .cfi_offset %edi, -16
|
||||
; 686-O0-NEXT: .cfi_offset %ebx, -12
|
||||
|
|
@ -198,7 +198,7 @@ define void @f1() {
|
|||
; 686-O0-NEXT: xorl $208307499, %eax # imm = 0xC6A852B
|
||||
; 686-O0-NEXT: xorl $-2, %ecx
|
||||
; 686-O0-NEXT: orl %ecx, %eax
|
||||
; 686-O0-NEXT: setne (%esp)
|
||||
; 686-O0-NEXT: setne {{[0-9]+}}(%esp)
|
||||
; 686-O0-NEXT: movl var_5, %ecx
|
||||
; 686-O0-NEXT: movl %ecx, %edx
|
||||
; 686-O0-NEXT: sarl $31, %edx
|
||||
|
|
@ -220,7 +220,12 @@ define void @f1() {
|
|||
; 686-O0-NEXT: movzbl %bl, %ebp
|
||||
; 686-O0-NEXT: movl %ebp, _ZN8struct_210member_2_0E
|
||||
; 686-O0-NEXT: movl $0, _ZN8struct_210member_2_0E+4
|
||||
; 686-O0-NEXT: addl $1, %esp
|
||||
; 686-O0-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; 686-O0-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; 686-O0-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; 686-O0-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
|
||||
; 686-O0-NEXT: movl %edi, (%esp) # 4-byte Spill
|
||||
; 686-O0-NEXT: addl $24, %esp
|
||||
; 686-O0-NEXT: .cfi_def_cfa_offset 20
|
||||
; 686-O0-NEXT: popl %esi
|
||||
; 686-O0-NEXT: .cfi_def_cfa_offset 16
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@ define void @foo() {
|
|||
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
|
||||
; CHECK-NEXT: # implicit-def: $rax
|
||||
; CHECK-NEXT: movdqu %xmm1, (%rax)
|
||||
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp) # 16-byte Spill
|
||||
; CHECK-NEXT: .LBB0_2:
|
||||
; CHECK-NEXT: retq
|
||||
indirectbr i8* undef, [label %9, label %1]
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ define <16 x i64> @pluto(<16 x i64> %arg, <16 x i64> %arg1, <16 x i64> %arg2, <1
|
|||
; CHECK-NEXT: movq %rsp, %rbp
|
||||
; CHECK-NEXT: .cfi_def_cfa_register %rbp
|
||||
; CHECK-NEXT: andq $-32, %rsp
|
||||
; CHECK-NEXT: subq $128, %rsp
|
||||
; CHECK-NEXT: subq $320, %rsp # imm = 0x140
|
||||
; CHECK-NEXT: vmovaps 240(%rbp), %ymm8
|
||||
; CHECK-NEXT: vmovaps 208(%rbp), %ymm9
|
||||
; CHECK-NEXT: vmovaps 176(%rbp), %ymm10
|
||||
|
|
@ -48,8 +48,14 @@ define <16 x i64> @pluto(<16 x i64> %arg, <16 x i64> %arg1, <16 x i64> %arg2, <1
|
|||
; CHECK-NEXT: vpblendd {{.*#+}} ymm5 = ymm7[0,1,2,3,4,5],ymm5[6,7]
|
||||
; CHECK-NEXT: vmovaps %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm5, %ymm1
|
||||
; CHECK-NEXT: vmovaps %ymm3, (%rsp) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm9, %ymm3
|
||||
; CHECK-NEXT: vmovaps %ymm10, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm12, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm13, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm14, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm15, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps %ymm4, (%rsp) # 32-byte Spill
|
||||
; CHECK-NEXT: movq %rbp, %rsp
|
||||
; CHECK-NEXT: popq %rbp
|
||||
; CHECK-NEXT: .cfi_def_cfa %rsp, 8
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ define void @pr34653() {
|
|||
; CHECK-NEXT: movq %rsp, %rbp
|
||||
; CHECK-NEXT: .cfi_def_cfa_register %rbp
|
||||
; CHECK-NEXT: andq $-512, %rsp # imm = 0xFE00
|
||||
; CHECK-NEXT: subq $1536, %rsp # imm = 0x600
|
||||
; CHECK-NEXT: subq $2048, %rsp # imm = 0x800
|
||||
; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
|
||||
; CHECK-NEXT: callq test
|
||||
; CHECK-NEXT: vmovupd {{[0-9]+}}(%rsp), %xmm0
|
||||
|
|
@ -147,6 +147,38 @@ define void @pr34653() {
|
|||
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
|
||||
; CHECK-NEXT: # xmm0 = mem[0],zero
|
||||
; CHECK-NEXT: vmovsd %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm9, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm15, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm16, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm17, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm18, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm19, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm20, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm21, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm22, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm23, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm24, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm25, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm26, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm27, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm28, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm29, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm30, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm31, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: vmovsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
||||
; CHECK-NEXT: movq %rbp, %rsp
|
||||
; CHECK-NEXT: popq %rbp
|
||||
; CHECK-NEXT: .cfi_def_cfa %rsp, 8
|
||||
|
|
|
|||
|
|
@ -434,22 +434,23 @@ define swiftcc float @conditionally_forward_swifterror(%swift_error** swifterror
|
|||
; CHECK-APPLE: retq
|
||||
|
||||
; CHECK-O0-LABEL: conditionally_forward_swifterror:
|
||||
; CHECK-O0: pushq [[REG1:%[a-z0-9]+]]
|
||||
; CHECK-O0: movq %r12, [[REG1]]
|
||||
; CHECK-O0: subq $24, %rsp
|
||||
; CHECK-O0: movq %r12, [[REG1:%[a-z0-9]+]]
|
||||
; CHECK-O0: cmpl $0, %edi
|
||||
; CHECK-O0-DAG: movq %r12, (%rsp)
|
||||
; CHECK-O0-DAG: movq [[REG1]], [[STK:[0-9]+]](%rsp)
|
||||
; CHECK-O0-DAG: movq %r12, [[STK2:[0-9]+]](%rsp)
|
||||
; CHECK-O0: je
|
||||
|
||||
; CHECK-O0: movq (%rsp), [[REG:%[a-z0-9]+]]
|
||||
; CHECK-O0: movq [[STK2]](%rsp), [[REG:%[a-z0-9]+]]
|
||||
; CHECK-O0: movq [[REG]], %r12
|
||||
; CHECK-O0: callq _moo
|
||||
; CHECK-O0: popq [[REG1]]
|
||||
; CHECK-O0: addq $24, %rsp
|
||||
; CHECK-O0: retq
|
||||
|
||||
; CHECK-O0: movq (%rsp), [[REG:%[a-z0-9]+]]
|
||||
; CHECK-O0: movq [[STK2]](%rsp), [[REG:%[a-z0-9]+]]
|
||||
; CHECK-O0: xorps %xmm0, %xmm0
|
||||
; CHECK-O0: movq [[REG]], %r12
|
||||
; CHECK-O0: popq [[REG1]]
|
||||
; CHECK-O0: addq $24, %rsp
|
||||
; CHECK-O0: retq
|
||||
entry:
|
||||
%cond = icmp ne i32 %cc, 0
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@
|
|||
|
||||
; CHECK: [0x0000000000000000, 0x[[LTMP3:.*]]): DW_OP_reg5 RDI, DW_OP_piece 0x8, DW_OP_reg4 RSI, DW_OP_piece 0x4
|
||||
; 0x0000000000000006 - 0x0000000000000008: rbp-8, piece 0x8, rax, piece 0x4 )
|
||||
; CHECK: [0x[[LTMP3]], {{.*}}): DW_OP_breg6 RBP-8, DW_OP_piece 0x8, DW_OP_reg4 RSI, DW_OP_piece 0x4
|
||||
|
||||
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
|
||||
target triple = "x86_64-apple-macosx10.9.0"
|
||||
|
|
|
|||
Loading…
Reference in New Issue