diff --git a/llvm/lib/Target/X86/X86FrameLowering.h b/llvm/lib/Target/X86/X86FrameLowering.h --- a/llvm/lib/Target/X86/X86FrameLowering.h +++ b/llvm/lib/Target/X86/X86FrameLowering.h @@ -99,6 +99,8 @@ int getFrameIndexReference(const MachineFunction &MF, int FI, unsigned &FrameReg) const override; + int getSaveXMMFrameIndexRef(const MachineFunction &MF, + int FI, unsigned &SPReg) const; int getFrameIndexReferenceSP(const MachineFunction &MF, int FI, unsigned &SPReg, int Adjustment) const; int getFrameIndexReferencePreferSP(const MachineFunction &MF, int FI, diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp --- a/llvm/lib/Target/X86/X86FrameLowering.cpp +++ b/llvm/lib/Target/X86/X86FrameLowering.cpp @@ -1389,9 +1389,13 @@ int FI; if (unsigned Reg = TII.isStoreToStackSlot(FrameInstr, FI)) { if (X86::FR64RegClass.contains(Reg)) { + int Offset; unsigned IgnoredFrameReg; - int Offset = getFrameIndexReference(MF, FI, IgnoredFrameReg); - Offset += SEHFrameOffset; + if (IsWin64Prologue && IsFunclet) + Offset = getSaveXMMFrameIndexRef(MF, FI, IgnoredFrameReg); + else + Offset = getFrameIndexReference(MF, FI, IgnoredFrameReg) + + SEHFrameOffset; HasWinCFI = true; assert(!NeedsWinFPO && "SEH_SaveXMM incompatible with FPO data"); @@ -1547,9 +1551,11 @@ unsigned X86FrameLowering::getWinEHFuncletFrameSize(const MachineFunction &MF) const { + const X86MachineFunctionInfo *X86FI = MF.getInfo(); // This is the size of the pushed CSRs. - unsigned CSSize = - MF.getInfo()->getCalleeSavedFrameSize(); + unsigned CSSize = X86FI->getCalleeSavedFrameSize(); + // This is the size of callee saved XMMs. + unsigned XMMSize = X86FI->getXMMCalleeSavedFrameSize(); // This is the amount of stack a funclet needs to allocate. unsigned UsedSize; EHPersonality Personality = @@ -1569,7 +1575,7 @@ unsigned FrameSizeMinusRBP = alignTo(CSSize + UsedSize, getStackAlignment()); // Subtract out the size of the callee saved registers. This is how much stack // each funclet will allocate. - return FrameSizeMinusRBP - CSSize; + return FrameSizeMinusRBP + XMMSize - CSSize; } static bool isTailCallOpcode(unsigned Opc) { @@ -1843,6 +1849,19 @@ return Offset + FPDelta; } +int X86FrameLowering::getSaveXMMFrameIndexRef(const MachineFunction &MF, + int FI, unsigned &FrameReg) const { + const MachineFrameInfo &MFI = MF.getFrameInfo(); + const X86MachineFunctionInfo *X86FI = MF.getInfo(); + int XMMSpillSlotOffset = X86FI->getXMMSpillSlotOffset(); + + if (XMMSpillSlotOffset == INT32_MIN) + return getFrameIndexReference(MF, FI, FrameReg); + + FrameReg = TRI->getStackRegister(); + return 32 + XMMSpillSlotOffset - MFI.getObjectOffset(FI); +} + int X86FrameLowering::getFrameIndexReferenceSP(const MachineFunction &MF, int FI, unsigned &FrameReg, int Adjustment) const { @@ -1941,6 +1960,8 @@ X86MachineFunctionInfo *X86FI = MF.getInfo(); unsigned CalleeSavedFrameSize = 0; + unsigned XMMCalleeSavedFrameSize = 0; + int XMMSpillSlotOffset = INT32_MIN; int SpillSlotOffset = getOffsetOfLocalArea() + X86FI->getTCReturnAddrDelta(); int64_t TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta(); @@ -2018,14 +2039,28 @@ unsigned Size = TRI->getSpillSize(*RC); unsigned Align = TRI->getSpillAlignment(*RC); // ensure alignment - SpillSlotOffset -= std::abs(SpillSlotOffset) % Align; + int Remainder = SpillSlotOffset % Align; + if (Remainder < 0) + SpillSlotOffset -= Align + Remainder; + else + SpillSlotOffset -= Remainder; + // spill into slot SpillSlotOffset -= Size; int SlotIndex = MFI.CreateFixedSpillStackObject(Size, SpillSlotOffset); CSI[i - 1].setFrameIdx(SlotIndex); MFI.ensureMaxAlignment(Align); + + // Save the start offset and size of XMM in stack frame for funlets. + if (X86::VR128RegClass.contains(Reg)) { + if (XMMSpillSlotOffset == INT32_MIN) + XMMSpillSlotOffset = SpillSlotOffset; + XMMCalleeSavedFrameSize += Size; + } } + X86FI->setXMMSpillSlotOffset(XMMSpillSlotOffset); + X86FI->setXMMCalleeSavedFrameSize(XMMCalleeSavedFrameSize); return true; } diff --git a/llvm/lib/Target/X86/X86MachineFunctionInfo.h b/llvm/lib/Target/X86/X86MachineFunctionInfo.h --- a/llvm/lib/Target/X86/X86MachineFunctionInfo.h +++ b/llvm/lib/Target/X86/X86MachineFunctionInfo.h @@ -36,10 +36,18 @@ /// is stashed. signed char RestoreBasePointerOffset = 0; + /// XMMSpillSlotOffset - Offset of the first XMM register in the stack frame + /// in bytes. + int XMMSpillSlotOffset = 0; + /// CalleeSavedFrameSize - Size of the callee-saved register portion of the /// stack frame in bytes. unsigned CalleeSavedFrameSize = 0; + /// XMMCalleeSavedFrameSize - Size of the callee-saved XMM register portion of + /// the stack frame in bytes. + unsigned XMMCalleeSavedFrameSize = 0; + /// BytesToPopOnReturn - Number of bytes function pops on return (in addition /// to the space used by the return address). /// Used on windows platform for stdcall & fastcall name decoration @@ -120,6 +128,14 @@ void setRestoreBasePointer(const MachineFunction *MF); int getRestoreBasePointerOffset() const {return RestoreBasePointerOffset; } + int getXMMSpillSlotOffset() const { return XMMSpillSlotOffset; } + void setXMMSpillSlotOffset(int bytes) { XMMSpillSlotOffset = bytes; } + + unsigned getXMMCalleeSavedFrameSize() const { + return XMMCalleeSavedFrameSize; } + void setXMMCalleeSavedFrameSize(unsigned bytes) { + XMMCalleeSavedFrameSize = bytes; } + unsigned getCalleeSavedFrameSize() const { return CalleeSavedFrameSize; } void setCalleeSavedFrameSize(unsigned bytes) { CalleeSavedFrameSize = bytes; } diff --git a/llvm/lib/Target/X86/X86RegisterInfo.cpp b/llvm/lib/Target/X86/X86RegisterInfo.cpp --- a/llvm/lib/Target/X86/X86RegisterInfo.cpp +++ b/llvm/lib/Target/X86/X86RegisterInfo.cpp @@ -697,7 +697,8 @@ int SPAdj, unsigned FIOperandNum, RegScavenger *RS) const { MachineInstr &MI = *II; - MachineFunction &MF = *MI.getParent()->getParent(); + MachineBasicBlock &MBB = *MI.getParent(); + MachineFunction &MF = *MBB.getParent(); const X86FrameLowering *TFI = getFrameLowering(MF); int FrameIndex = MI.getOperand(FIOperandNum).getIndex(); @@ -709,6 +710,8 @@ MF.getFrameInfo().isFixedObjectIndex(FrameIndex)) && "Return instruction can only reference SP relative frame objects"); FIOffset = TFI->getFrameIndexReferenceSP(MF, FrameIndex, BasePtr, 0); + } else if (TFI->Is64Bit && MBB.isEHFuncletEntry()) { + FIOffset = TFI->getSaveXMMFrameIndexRef(MF, FrameIndex, BasePtr); } else { FIOffset = TFI->getFrameIndexReference(MF, FrameIndex, BasePtr); } diff --git a/llvm/test/CodeGen/X86/avx512-intel-ocl.ll b/llvm/test/CodeGen/X86/avx512-intel-ocl.ll --- a/llvm/test/CodeGen/X86/avx512-intel-ocl.ll +++ b/llvm/test/CodeGen/X86/avx512-intel-ocl.ll @@ -184,7 +184,7 @@ ; WIN64-KNL-LABEL: test_prolog_epilog: ; WIN64-KNL: # %bb.0: ; WIN64-KNL-NEXT: pushq %rbp -; WIN64-KNL-NEXT: subq $1328, %rsp # imm = 0x530 +; WIN64-KNL-NEXT: subq $1264, %rsp # imm = 0x4F0 ; WIN64-KNL-NEXT: leaq {{[0-9]+}}(%rsp), %rbp ; WIN64-KNL-NEXT: kmovw %k7, {{[-0-9]+}}(%r{{[sb]}}p) # 2-byte Spill ; WIN64-KNL-NEXT: kmovw %k6, {{[-0-9]+}}(%r{{[sb]}}p) # 2-byte Spill @@ -232,14 +232,14 @@ ; WIN64-KNL-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k5 # 2-byte Reload ; WIN64-KNL-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k6 # 2-byte Reload ; WIN64-KNL-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k7 # 2-byte Reload -; WIN64-KNL-NEXT: leaq 1200(%rbp), %rsp +; WIN64-KNL-NEXT: leaq 1136(%rbp), %rsp ; WIN64-KNL-NEXT: popq %rbp ; WIN64-KNL-NEXT: retq ; ; WIN64-SKX-LABEL: test_prolog_epilog: ; WIN64-SKX: # %bb.0: ; WIN64-SKX-NEXT: pushq %rbp -; WIN64-SKX-NEXT: subq $1328, %rsp # imm = 0x530 +; WIN64-SKX-NEXT: subq $1264, %rsp # imm = 0x4F0 ; WIN64-SKX-NEXT: leaq {{[0-9]+}}(%rsp), %rbp ; WIN64-SKX-NEXT: kmovq %k7, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; WIN64-SKX-NEXT: kmovq %k6, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill @@ -287,7 +287,7 @@ ; WIN64-SKX-NEXT: kmovq {{[-0-9]+}}(%r{{[sb]}}p), %k5 # 8-byte Reload ; WIN64-SKX-NEXT: kmovq {{[-0-9]+}}(%r{{[sb]}}p), %k6 # 8-byte Reload ; WIN64-SKX-NEXT: kmovq {{[-0-9]+}}(%r{{[sb]}}p), %k7 # 8-byte Reload -; WIN64-SKX-NEXT: leaq 1200(%rbp), %rsp +; WIN64-SKX-NEXT: leaq 1136(%rbp), %rsp ; WIN64-SKX-NEXT: popq %rbp ; WIN64-SKX-NEXT: retq ; @@ -346,7 +346,7 @@ ; X64-SKX: ## %bb.0: ; X64-SKX-NEXT: pushq %rsi ; X64-SKX-NEXT: pushq %rdi -; X64-SKX-NEXT: subq $1192, %rsp ## imm = 0x4A8 +; X64-SKX-NEXT: subq $1064, %rsp ## imm = 0x428 ; X64-SKX-NEXT: kmovq %k7, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill ; X64-SKX-NEXT: kmovq %k6, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill ; X64-SKX-NEXT: kmovq %k5, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill @@ -388,7 +388,7 @@ ; X64-SKX-NEXT: kmovq {{[-0-9]+}}(%r{{[sb]}}p), %k5 ## 8-byte Reload ; X64-SKX-NEXT: kmovq {{[-0-9]+}}(%r{{[sb]}}p), %k6 ## 8-byte Reload ; X64-SKX-NEXT: kmovq {{[-0-9]+}}(%r{{[sb]}}p), %k7 ## 8-byte Reload -; X64-SKX-NEXT: addq $1192, %rsp ## imm = 0x4A8 +; X64-SKX-NEXT: addq $1064, %rsp ## imm = 0x428 ; X64-SKX-NEXT: popq %rdi ; X64-SKX-NEXT: popq %rsi ; X64-SKX-NEXT: retq diff --git a/llvm/test/CodeGen/X86/catchpad-realign-savexmm.ll b/llvm/test/CodeGen/X86/catchpad-realign-savexmm.ll --- a/llvm/test/CodeGen/X86/catchpad-realign-savexmm.ll +++ b/llvm/test/CodeGen/X86/catchpad-realign-savexmm.ll @@ -51,3 +51,18 @@ ; CHECK: popq %rbp ; CHECK: retq ; CHECK: .seh_handlerdata +; CHECK: # %catch +; CHECK: movq %rdx, 16(%rsp) +; CHECK: pushq %rbp +; CHECK: .seh_pushreg 5 +; CHECK: subq $48, %rsp +; CHECK: .seh_stackalloc 48 +; CHECK: leaq 64(%rdx), %rbp +; CHECK: movapd %xmm6, 32(%rsp) +; CHECK: .seh_savexmm 6, 32 +; CHECK: .seh_endprologue +; CHECK: movapd 32(%rsp), %xmm6 +; CHECK: leaq .LBB0_1(%rip), %rax +; CHECK: addq $48, %rsp +; CHECK: popq %rbp +; CHECK: retq # CATCHRET diff --git a/llvm/test/CodeGen/X86/win64-funclet-savexmm.ll b/llvm/test/CodeGen/X86/win64-funclet-savexmm.ll new file mode 100644 --- /dev/null +++ b/llvm/test/CodeGen/X86/win64-funclet-savexmm.ll @@ -0,0 +1,95 @@ +; RUN: llc -mtriple=x86_64-pc-windows-msvc -mattr=+avx < %s | FileCheck %s + +; void bar(int a, int b, int c, int d, int e); +; +; void foo(int a, int b, int c, int d, int e) +; { +; __asm("nop" ::: "bx", "cx", "xmm5", "xmm6", "ymm7"); +; try { +; bar(a, b, c, d, e); +; } +; catch (...) { +; } +; } + +%rtti.TypeDescriptor2 = type { i8**, i8*, [3 x i8] } + +$"??_R0H@8" = comdat any + +@"??_7type_info@@6B@" = external constant i8* +@"??_R0H@8" = linkonce_odr global %rtti.TypeDescriptor2 { i8** @"??_7type_info@@6B@", i8* null, [3 x i8] c".H\00" }, comdat + +declare dso_local i32 @__CxxFrameHandler3(...) +declare dso_local void @"?bar@@YAXHHHHH@Z"(i32, i32, i32, i32, i32) + +define dso_local void @"?foo@@YAXHHHHH@Z"(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e) personality i8* bitcast (i32 (...)* @__CxxFrameHandler3 to i8*) { +entry: + %e.addr = alloca i32, align 4 + %d.addr = alloca i32, align 4 + %c.addr = alloca i32, align 4 + %b.addr = alloca i32, align 4 + %a.addr = alloca i32, align 4 + store i32 %e, i32* %e.addr, align 4 + store i32 %d, i32* %d.addr, align 4 + store i32 %c, i32* %c.addr, align 4 + store i32 %b, i32* %b.addr, align 4 + store i32 %a, i32* %a.addr, align 4 + call void asm sideeffect "nop", "~{bx},~{cx},~{xmm5},~{xmm6},~{ymm7}"() + %0 = load i32, i32* %e.addr, align 4 + %1 = load i32, i32* %d.addr, align 4 + %2 = load i32, i32* %c.addr, align 4 + %3 = load i32, i32* %b.addr, align 4 + %4 = load i32, i32* %a.addr, align 4 + invoke void @"?bar@@YAXHHHHH@Z"(i32 %4, i32 %3, i32 %2, i32 %1, i32 %0) + to label %invoke.cont unwind label %catch.dispatch + +catch.dispatch: ; preds = %entry + %5 = catchswitch within none [label %catch] unwind to caller + +catch: ; preds = %catch.dispatch + %6 = catchpad within %5 [i8* null, i32 64, i8* null] + catchret from %6 to label %catchret.dest + +catchret.dest: ; preds = %catch + br label %try.cont + +try.cont: ; preds = %catchret.dest, %invoke.cont + ret void + +invoke.cont: ; preds = %entry + br label %try.cont +} + +; CHECK: # %catch +; CHECK: movq %rdx, 16(%rsp) +; CHECK: pushq %rbp +; CHECK: .seh_pushreg 5 +; CHECK: pushq %rbx +; CHECK: .seh_pushreg 3 +; CHECK: subq $72, %rsp +; CHECK: .seh_stackalloc 72 +; CHECK: leaq 96(%rdx), %rbp +; CHECK: vmovaps %xmm7, 32(%rsp) +; CHECK: .seh_savexmm 7, 32 +; CHECK: vmovaps %xmm6, 48(%rsp) +; CHECK: .seh_savexmm 6, 48 +; CHECK: .seh_endprologue +; CHECK: vmovaps 48(%rsp), %xmm6 +; CHECK: vmovaps 32(%rsp), %xmm7 +; CHECK: leaq .LBB0_1(%rip), %rax +; CHECK: addq $72, %rsp +; CHECK: popq %rbx +; CHECK: popq %rbp +; CHECK: retq # CATCHRET + +; CHECK-LABEL: "$handlerMap$0$?foo@@YAXHHHHH@Z": +; CHECK-NEXT: .long 64 # Adjectives +; CHECK-NEXT: .long 0 # Type +; CHECK-NEXT: .long 0 # CatchObjOffset +; CHECK-NEXT: .long "?catch$2@?0??foo@@YAXHHHHH@Z@4HA"@IMGREL # Handler +; Sum of: +; 16 RDX store offset +; 16 two pushes +; 72 stack alloc +; CHECK-NEXT: .long 104 # ParentFrameOffset + diff --git a/llvm/test/CodeGen/X86/x86-interrupt_cc.ll b/llvm/test/CodeGen/X86/x86-interrupt_cc.ll --- a/llvm/test/CodeGen/X86/x86-interrupt_cc.ll +++ b/llvm/test/CodeGen/X86/x86-interrupt_cc.ll @@ -294,7 +294,7 @@ ; CHECK64-SKX-NEXT: kmovq %k0, {{[0-9]+}}(%rsp) ## 8-byte Spill ; CHECK64-SKX-NEXT: ## encoding: [0xc4,0xe1,0xf8,0x91,0x84,0x24,0x30,0x08,0x00,0x00] ; CHECK64-SKX-NEXT: vmovups %zmm31, {{[0-9]+}}(%rsp) ## 64-byte Spill -; CHECK64-SKX-NEXT: ## encoding: [0x62,0x61,0x7c,0x48,0x11,0xbc,0x24,0xe0,0x07,0x00,0x00] +; CHECK64-SKX-NEXT: ## encoding: [0x62,0x61,0x7c,0x48,0x11,0x7c,0x24,0x1f] ; CHECK64-SKX-NEXT: vmovups %zmm30, {{[0-9]+}}(%rsp) ## 64-byte Spill ; CHECK64-SKX-NEXT: ## encoding: [0x62,0x61,0x7c,0x48,0x11,0x74,0x24,0x1e] ; CHECK64-SKX-NEXT: vmovups %zmm29, {{[0-9]+}}(%rsp) ## 64-byte Spill @@ -398,7 +398,7 @@ ; CHECK64-SKX-NEXT: .cfi_offset %xmm28, -448 ; CHECK64-SKX-NEXT: .cfi_offset %xmm29, -384 ; CHECK64-SKX-NEXT: .cfi_offset %xmm30, -320 -; CHECK64-SKX-NEXT: .cfi_offset %xmm31, -224 +; CHECK64-SKX-NEXT: .cfi_offset %xmm31, -256 ; CHECK64-SKX-NEXT: .cfi_offset %k0, -144 ; CHECK64-SKX-NEXT: .cfi_offset %k1, -136 ; CHECK64-SKX-NEXT: .cfi_offset %k2, -128 @@ -474,7 +474,7 @@ ; CHECK64-SKX-NEXT: vmovups {{[0-9]+}}(%rsp), %zmm30 ## 64-byte Reload ; CHECK64-SKX-NEXT: ## encoding: [0x62,0x61,0x7c,0x48,0x10,0x74,0x24,0x1e] ; CHECK64-SKX-NEXT: vmovups {{[0-9]+}}(%rsp), %zmm31 ## 64-byte Reload -; CHECK64-SKX-NEXT: ## encoding: [0x62,0x61,0x7c,0x48,0x10,0xbc,0x24,0xe0,0x07,0x00,0x00] +; CHECK64-SKX-NEXT: ## encoding: [0x62,0x61,0x7c,0x48,0x10,0x7c,0x24,0x1f] ; CHECK64-SKX-NEXT: kmovq {{[0-9]+}}(%rsp), %k0 ## 8-byte Reload ; CHECK64-SKX-NEXT: ## encoding: [0xc4,0xe1,0xf8,0x90,0x84,0x24,0x30,0x08,0x00,0x00] ; CHECK64-SKX-NEXT: kmovq {{[0-9]+}}(%rsp), %k1 ## 8-byte Reload @@ -635,7 +635,7 @@ ; CHECK32-SKX-NEXT: kmovq %k0, {{[0-9]+}}(%esp) ## 8-byte Spill ; CHECK32-SKX-NEXT: ## encoding: [0xc4,0xe1,0xf8,0x91,0x84,0x24,0x30,0x02,0x00,0x00] ; CHECK32-SKX-NEXT: vmovups %zmm7, {{[0-9]+}}(%esp) ## 64-byte Spill -; CHECK32-SKX-NEXT: ## encoding: [0x62,0xf1,0x7c,0x48,0x11,0xbc,0x24,0xe0,0x01,0x00,0x00] +; CHECK32-SKX-NEXT: ## encoding: [0x62,0xf1,0x7c,0x48,0x11,0x7c,0x24,0x07] ; CHECK32-SKX-NEXT: vmovups %zmm6, {{[0-9]+}}(%esp) ## 64-byte Spill ; CHECK32-SKX-NEXT: ## encoding: [0x62,0xf1,0x7c,0x48,0x11,0x74,0x24,0x06] ; CHECK32-SKX-NEXT: vmovups %zmm5, {{[0-9]+}}(%esp) ## 64-byte Spill @@ -661,7 +661,7 @@ ; CHECK32-SKX-NEXT: .cfi_offset %xmm4, -384 ; CHECK32-SKX-NEXT: .cfi_offset %xmm5, -320 ; CHECK32-SKX-NEXT: .cfi_offset %xmm6, -256 -; CHECK32-SKX-NEXT: .cfi_offset %xmm7, -160 +; CHECK32-SKX-NEXT: .cfi_offset %xmm7, -192 ; CHECK32-SKX-NEXT: .cfi_offset %k0, -80 ; CHECK32-SKX-NEXT: .cfi_offset %k1, -72 ; CHECK32-SKX-NEXT: .cfi_offset %k2, -64 @@ -689,7 +689,7 @@ ; CHECK32-SKX-NEXT: vmovups {{[0-9]+}}(%esp), %zmm6 ## 64-byte Reload ; CHECK32-SKX-NEXT: ## encoding: [0x62,0xf1,0x7c,0x48,0x10,0x74,0x24,0x06] ; CHECK32-SKX-NEXT: vmovups {{[0-9]+}}(%esp), %zmm7 ## 64-byte Reload -; CHECK32-SKX-NEXT: ## encoding: [0x62,0xf1,0x7c,0x48,0x10,0xbc,0x24,0xe0,0x01,0x00,0x00] +; CHECK32-SKX-NEXT: ## encoding: [0x62,0xf1,0x7c,0x48,0x10,0x7c,0x24,0x07] ; CHECK32-SKX-NEXT: kmovq {{[0-9]+}}(%esp), %k0 ## 8-byte Reload ; CHECK32-SKX-NEXT: ## encoding: [0xc4,0xe1,0xf8,0x90,0x84,0x24,0x30,0x02,0x00,0x00] ; CHECK32-SKX-NEXT: kmovq {{[0-9]+}}(%esp), %k1 ## 8-byte Reload