let ParserMatchClass = ImmSExti64i8AsmOperand;
}
+def lea64_32mem : Operand<i32> {
+ let PrintMethod = "printi32mem";
+ let AsmOperandLowerMethod = "lower_lea64_32mem";
+ let MIOperandInfo = (ops GR32, i8imm, GR32_NOSP, i32imm, i8imm);
+ let ParserMatchClass = X86MemAsmOperand;
+}
+
+
// Special i64mem for addresses of load folding tail calls. These are not
// allowed to use callee-saved registers since they must be scheduled
// after callee-saved register are popped.
let ParserMatchClass = X86MemAsmOperand;
}
-def lea64mem : Operand<i64> {
- let PrintMethod = "printlea64mem";
- let MIOperandInfo = (ops GR64, i8imm, GR64_NOSP, i32imm);
- let ParserMatchClass = X86NoSegMemAsmOperand;
-}
-
-def lea64_32mem : Operand<i32> {
- let PrintMethod = "printlea64_32mem";
- let AsmOperandLowerMethod = "lower_lea64_32mem";
- let MIOperandInfo = (ops GR32, i8imm, GR32_NOSP, i32imm);
- let ParserMatchClass = X86NoSegMemAsmOperand;
-}
-
//===----------------------------------------------------------------------===//
// Complex Pattern Definitions.
//
-def lea64addr : ComplexPattern<i64, 4, "SelectLEAAddr",
+def lea64addr : ComplexPattern<i64, 5, "SelectLEAAddr",
[add, sub, mul, X86mul_imm, shl, or, frameindex,
X86WrapperRIP], []>;
-def tls64addr : ComplexPattern<i64, 4, "SelectTLSADDRAddr",
+def tls64addr : ComplexPattern<i64, 5, "SelectTLSADDRAddr",
[tglobaltlsaddr], []>;
//===----------------------------------------------------------------------===//
return getI32Imm((unsigned)N->getZExtValue());
}]>;
-def i64immSExt32 : PatLeaf<(i64 imm), [{
- // i64immSExt32 predicate - True if the 64-bit immediate fits in a 32-bit
- // sign extended field.
- return (int64_t)N->getZExtValue() == (int32_t)N->getZExtValue();
-}]>;
+def i64immSExt32 : PatLeaf<(i64 imm), [{ return i64immSExt32(N); }]>;
def i64immZExt32 : PatLeaf<(i64 imm), [{
Requires<[In64BitMode]>;
}
-// Interrupt Instructions
-def IRET64 : RI<0xcf, RawFrm, (outs), (ins), "iret{q}", []>;
//===----------------------------------------------------------------------===//
// Call Instructions...
Requires<[In64BitMode, NotWin64]>;
def CALL64r : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
"call{q}\t{*}$dst", [(X86call GR64:$dst)]>,
- Requires<[NotWin64]>;
+ Requires<[In64BitMode, NotWin64]>;
def CALL64m : I<0xFF, MRM2m, (outs), (ins i64mem:$dst, variable_ops),
"call{q}\t{*}$dst", [(X86call (loadi64 addr:$dst))]>,
- Requires<[NotWin64]>;
+ Requires<[In64BitMode, NotWin64]>;
def FARCALL64 : RI<0xFF, MRM3m, (outs), (ins opaque80mem:$dst),
"lcall{q}\t{*}$dst", []>;
// FIXME: We need to teach codegen about single list of call-clobbered
// registers.
-let isCall = 1 in
+let isCall = 1, isCodeGenOnly = 1 in
// All calls clobber the non-callee saved registers. RSP is marked as
// a use to prevent stack-pointer assignments that appear immediately
// before calls from potentially appearing dead. Uses for argument
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, EFLAGS],
Uses = [RSP] in {
- def WINCALL64pcrel32 : I<0xE8, RawFrm,
+ def WINCALL64pcrel32 : Ii32PCRel<0xE8, RawFrm,
(outs), (ins i64i32imm_pcrel:$dst, variable_ops),
- "call\t$dst", []>,
+ "call{q}\t$dst", []>,
Requires<[IsWin64]>;
def WINCALL64r : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
- "call\t{*}$dst",
+ "call{q}\t{*}$dst",
[(X86call GR64:$dst)]>, Requires<[IsWin64]>;
- def WINCALL64m : I<0xFF, MRM2m, (outs),
- (ins i64mem:$dst, variable_ops), "call\t{*}$dst",
+ def WINCALL64m : I<0xFF, MRM2m, (outs), (ins i64mem:$dst,variable_ops),
+ "call{q}\t{*}$dst",
[(X86call (loadi64 addr:$dst))]>,
Requires<[IsWin64]>;
}
-let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
+let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1,
+ isCodeGenOnly = 1 in
let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
def JMP64pcrel32 : I<0xE9, RawFrm, (outs), (ins brtarget:$dst),
"jmp{q}\t$dst", []>;
def JMP64r : I<0xFF, MRM4r, (outs), (ins GR64:$dst), "jmp{q}\t{*}$dst",
- [(brind GR64:$dst)]>;
+ [(brind GR64:$dst)]>, Requires<[In64BitMode]>;
def JMP64m : I<0xFF, MRM4m, (outs), (ins i64mem:$dst), "jmp{q}\t{*}$dst",
- [(brind (loadi64 addr:$dst))]>;
+ [(brind (loadi64 addr:$dst))]>, Requires<[In64BitMode]>;
def FARJMP64 : RI<0xFF, MRM5m, (outs), (ins opaque80mem:$dst),
"ljmp{q}\t{*}$dst", []>;
}
let Defs = [RBP,RSP], Uses = [RBP,RSP], mayLoad = 1, neverHasSideEffects = 1 in
def LEAVE64 : I<0xC9, RawFrm,
- (outs), (ins), "leave", []>;
+ (outs), (ins), "leave", []>, Requires<[In64BitMode]>;
let Defs = [RSP], Uses = [RSP], neverHasSideEffects=1 in {
let mayLoad = 1 in {
def POP64r : I<0x58, AddRegFrm,
[(set GR32:$dst, lea32addr:$src)]>, Requires<[In64BitMode]>;
let isReMaterializable = 1 in
-def LEA64r : RI<0x8D, MRMSrcMem, (outs GR64:$dst), (ins lea64mem:$src),
+def LEA64r : RI<0x8D, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
"lea{q}\t{$src|$dst}, {$dst|$src}",
[(set GR64:$dst, lea64addr:$src)]>;
def CMPS64 : RI<0xA7, RawFrm, (outs), (ins), "cmpsq", []>;
-// Fast system-call instructions
-def SYSEXIT64 : RI<0x35, RawFrm,
- (outs), (ins), "sysexit", []>, TB;
//===----------------------------------------------------------------------===//
// Move Instructions...
[(store i64immSExt32:$src, addr:$dst)]>;
/// Versions of MOV64rr, MOV64rm, and MOV64mr for i64mem_TC and GR64_TC.
+let isCodeGenOnly = 1 in {
let neverHasSideEffects = 1 in
def MOV64rr_TC : RI<0x89, MRMDestReg, (outs GR64_TC:$dst), (ins GR64_TC:$src),
"mov{q}\t{$src, $dst|$dst, $src}", []>;
def MOV64mr_TC : RI<0x89, MRMDestMem, (outs), (ins i64mem_TC:$dst, GR64_TC:$src),
"mov{q}\t{$src, $dst|$dst, $src}",
[]>;
+}
+// FIXME: These definitions are utterly broken
+// Just leave them commented out for now because they're useless outside
+// of the large code model, and most compilers won't generate the instructions
+// in question.
+/*
def MOV64o8a : RIi8<0xA0, RawFrm, (outs), (ins offset8:$src),
"mov{q}\t{$src, %rax|%rax, $src}", []>;
def MOV64o64a : RIi32<0xA1, RawFrm, (outs), (ins offset64:$src),
"mov{q}\t{%rax, $dst|$dst, %rax}", []>;
def MOV64ao64 : RIi32<0xA3, RawFrm, (outs offset64:$dst), (ins),
"mov{q}\t{%rax, $dst|$dst, %rax}", []>;
+*/
// Moves to and from segment registers
def MOV64rs : RI<0x8C, MRMDestReg, (outs GR64:$dst), (ins SEGMENT_REG:$src),
[]
>, TB;
-def BT64ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR64:$src1, i64i8imm:$src2),
+def BT64ri8 : RIi8<0xBA, MRM4r, (outs), (ins GR64:$src1, i64i8imm:$src2),
"bt{q}\t{$src2, $src1|$src1, $src2}",
- [(set EFLAGS, (X86bt GR64:$src1, i64immSExt8:$src2))]>, TB,
- REX_W;
+ [(set EFLAGS, (X86bt GR64:$src1, i64immSExt8:$src2))]>, TB;
// Note that these instructions don't need FastBTMem because that
// only applies when the other operand is in a register. When it's
// an immediate, bt is still fast.
-def BT64mi8 : Ii8<0xBA, MRM4m, (outs), (ins i64mem:$src1, i64i8imm:$src2),
+def BT64mi8 : RIi8<0xBA, MRM4m, (outs), (ins i64mem:$src1, i64i8imm:$src2),
"bt{q}\t{$src2, $src1|$src1, $src2}",
[(set EFLAGS, (X86bt (loadi64 addr:$src1),
i64immSExt8:$src2))]>, TB;
(SETB_C64r)>;
//===----------------------------------------------------------------------===//
-// Conversion Instructions...
-//
-
-// f64 -> signed i64
-def CVTSD2SI64rr: RSDI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins FR64:$src),
- "cvtsd2si{q}\t{$src, $dst|$dst, $src}", []>;
-def CVTSD2SI64rm: RSDI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f64mem:$src),
- "cvtsd2si{q}\t{$src, $dst|$dst, $src}", []>;
-def Int_CVTSD2SI64rr: RSDI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
- "cvtsd2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst,
- (int_x86_sse2_cvtsd2si64 VR128:$src))]>;
-def Int_CVTSD2SI64rm: RSDI<0x2D, MRMSrcMem, (outs GR64:$dst),
- (ins f128mem:$src),
- "cvtsd2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst, (int_x86_sse2_cvtsd2si64
- (load addr:$src)))]>;
-def CVTTSD2SI64rr: RSDI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins FR64:$src),
- "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst, (fp_to_sint FR64:$src))]>;
-def CVTTSD2SI64rm: RSDI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f64mem:$src),
- "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst, (fp_to_sint (loadf64 addr:$src)))]>;
-def Int_CVTTSD2SI64rr: RSDI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
- "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst,
- (int_x86_sse2_cvttsd2si64 VR128:$src))]>;
-def Int_CVTTSD2SI64rm: RSDI<0x2C, MRMSrcMem, (outs GR64:$dst),
- (ins f128mem:$src),
- "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst,
- (int_x86_sse2_cvttsd2si64
- (load addr:$src)))]>;
-
-// Signed i64 -> f64
-def CVTSI2SD64rr: RSDI<0x2A, MRMSrcReg, (outs FR64:$dst), (ins GR64:$src),
- "cvtsi2sd{q}\t{$src, $dst|$dst, $src}",
- [(set FR64:$dst, (sint_to_fp GR64:$src))]>;
-def CVTSI2SD64rm: RSDI<0x2A, MRMSrcMem, (outs FR64:$dst), (ins i64mem:$src),
- "cvtsi2sd{q}\t{$src, $dst|$dst, $src}",
- [(set FR64:$dst, (sint_to_fp (loadi64 addr:$src)))]>;
-
-let Constraints = "$src1 = $dst" in {
-def Int_CVTSI2SD64rr: RSDI<0x2A, MRMSrcReg,
- (outs VR128:$dst), (ins VR128:$src1, GR64:$src2),
- "cvtsi2sd{q}\t{$src2, $dst|$dst, $src2}",
- [(set VR128:$dst,
- (int_x86_sse2_cvtsi642sd VR128:$src1,
- GR64:$src2))]>;
-def Int_CVTSI2SD64rm: RSDI<0x2A, MRMSrcMem,
- (outs VR128:$dst), (ins VR128:$src1, i64mem:$src2),
- "cvtsi2sd{q}\t{$src2, $dst|$dst, $src2}",
- [(set VR128:$dst,
- (int_x86_sse2_cvtsi642sd VR128:$src1,
- (loadi64 addr:$src2)))]>;
-} // Constraints = "$src1 = $dst"
-
-// Signed i64 -> f32
-def CVTSI2SS64rr: RSSI<0x2A, MRMSrcReg, (outs FR32:$dst), (ins GR64:$src),
- "cvtsi2ss{q}\t{$src, $dst|$dst, $src}",
- [(set FR32:$dst, (sint_to_fp GR64:$src))]>;
-def CVTSI2SS64rm: RSSI<0x2A, MRMSrcMem, (outs FR32:$dst), (ins i64mem:$src),
- "cvtsi2ss{q}\t{$src, $dst|$dst, $src}",
- [(set FR32:$dst, (sint_to_fp (loadi64 addr:$src)))]>;
-
-let Constraints = "$src1 = $dst" in {
- def Int_CVTSI2SS64rr : RSSI<0x2A, MRMSrcReg,
- (outs VR128:$dst), (ins VR128:$src1, GR64:$src2),
- "cvtsi2ss{q}\t{$src2, $dst|$dst, $src2}",
- [(set VR128:$dst,
- (int_x86_sse_cvtsi642ss VR128:$src1,
- GR64:$src2))]>;
- def Int_CVTSI2SS64rm : RSSI<0x2A, MRMSrcMem,
- (outs VR128:$dst),
- (ins VR128:$src1, i64mem:$src2),
- "cvtsi2ss{q}\t{$src2, $dst|$dst, $src2}",
- [(set VR128:$dst,
- (int_x86_sse_cvtsi642ss VR128:$src1,
- (loadi64 addr:$src2)))]>;
-} // Constraints = "$src1 = $dst"
-
-// f32 -> signed i64
-def CVTSS2SI64rr: RSSI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins FR32:$src),
- "cvtss2si{q}\t{$src, $dst|$dst, $src}", []>;
-def CVTSS2SI64rm: RSSI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
- "cvtss2si{q}\t{$src, $dst|$dst, $src}", []>;
-def Int_CVTSS2SI64rr: RSSI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
- "cvtss2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst,
- (int_x86_sse_cvtss2si64 VR128:$src))]>;
-def Int_CVTSS2SI64rm: RSSI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
- "cvtss2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst, (int_x86_sse_cvtss2si64
- (load addr:$src)))]>;
-def CVTTSS2SI64rr: RSSI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins FR32:$src),
- "cvttss2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst, (fp_to_sint FR32:$src))]>;
-def CVTTSS2SI64rm: RSSI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
- "cvttss2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst, (fp_to_sint (loadf32 addr:$src)))]>;
-def Int_CVTTSS2SI64rr: RSSI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
- "cvttss2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst,
- (int_x86_sse_cvttss2si64 VR128:$src))]>;
-def Int_CVTTSS2SI64rm: RSSI<0x2C, MRMSrcMem, (outs GR64:$dst),
- (ins f32mem:$src),
- "cvttss2si{q}\t{$src, $dst|$dst, $src}",
- [(set GR64:$dst,
- (int_x86_sse_cvttss2si64 (load addr:$src)))]>;
-
// Descriptor-table support instructions
// LLDT is not interpreted specially in 64-bit mode because there is no sign
// Thread Local Storage Instructions
//===----------------------------------------------------------------------===//
+// ELF TLS Support
// All calls clobber the non-callee saved registers. RSP is marked as
// a use to prevent stack-pointer assignments that appear immediately
// before calls from potentially appearing dead.
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
Uses = [RSP] in
-def TLS_addr64 : I<0, Pseudo, (outs), (ins lea64mem:$sym),
+def TLS_addr64 : I<0, Pseudo, (outs), (ins i64mem:$sym),
".byte\t0x66; "
"leaq\t$sym(%rip), %rdi; "
".word\t0x6666; "
[(X86tlsaddr tls64addr:$sym)]>,
Requires<[In64BitMode]>;
-// FIXME: Not true for darwin
-let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
- FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
- MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
- XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
- XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
- Uses = [RSP],
+// Darwin TLS Support
+// For x86_64, the address of the thunk is passed in %rdi, on return
+// the address of the variable is in %rax. All other registers are preserved.
+let Defs = [RAX],
+ Uses = [RDI],
usesCustomInserter = 1 in
def TLSCall_64 : I<0, Pseudo, (outs), (ins i64mem:$sym),
- "# Fixme into a call",
+ "# TLSCall_64",
[(X86TLSCall addr:$sym)]>,
Requires<[In64BitMode]>;
-let AddedComplexity = 5, isCodeGenOnly = 1 in
-def MOV64GSrm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
- "movq\t%gs:$src, $dst",
- [(set GR64:$dst, (gsload addr:$src))]>, SegGS;
-
-let AddedComplexity = 5, isCodeGenOnly = 1 in
-def MOV64FSrm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
- "movq\t%fs:$src, $dst",
- [(set GR64:$dst, (fsload addr:$src))]>, SegFS;
-
//===----------------------------------------------------------------------===//
// Atomic Instructions
//===----------------------------------------------------------------------===//
+// TODO: Get this to fold the constant into the instruction.
+let hasSideEffects = 1, Defs = [ESP] in
+def Int_MemBarrierNoSSE64 : RI<0x09, MRM1r, (outs), (ins GR64:$zero),
+ "lock\n\t"
+ "or{q}\t{$zero, (%rsp)|(%rsp), $zero}",
+ [(X86MemBarrierNoSSE GR64:$zero)]>,
+ Requires<[In64BitMode]>, LOCK;
+
let Defs = [RAX, EFLAGS], Uses = [RAX] in {
def LCMPXCHG64 : RI<0xB1, MRMDestMem, (outs), (ins i64mem:$ptr, GR64:$swap),
"lock\n\t"
// Optimized codegen when the non-memory output is not used.
let Defs = [EFLAGS], mayLoad = 1, mayStore = 1 in {
// FIXME: Use normal add / sub instructions and add lock prefix dynamically.
-def LOCK_ADD64mr : RI<0x03, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
+def LOCK_ADD64mr : RI<0x01, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
"lock\n\t"
"add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_ADD64mi8 : RIi8<0x83, MRM0m, (outs),
def SWAPGS : I<0x01, MRM_F8, (outs), (ins), "swapgs", []>, TB;
-def PUSHFS64 : I<0xa0, RawFrm, (outs), (ins),
- "push{q}\t%fs", []>, TB;
-def PUSHGS64 : I<0xa8, RawFrm, (outs), (ins),
- "push{q}\t%gs", []>, TB;
-
-def POPFS64 : I<0xa1, RawFrm, (outs), (ins),
- "pop{q}\t%fs", []>, TB;
-def POPGS64 : I<0xa9, RawFrm, (outs), (ins),
- "pop{q}\t%gs", []>, TB;
-
-def LSS64rm : RI<0xb2, MRMSrcMem, (outs GR64:$dst), (ins opaque80mem:$src),
- "lss{q}\t{$src, $dst|$dst, $src}", []>, TB;
-def LFS64rm : RI<0xb4, MRMSrcMem, (outs GR64:$dst), (ins opaque80mem:$src),
- "lfs{q}\t{$src, $dst|$dst, $src}", []>, TB;
-def LGS64rm : RI<0xb5, MRMSrcMem, (outs GR64:$dst), (ins opaque80mem:$src),
- "lgs{q}\t{$src, $dst|$dst, $src}", []>, TB;
-
-// Specialized register support
-
-// no m form encodable; use SMSW16m
-def SMSW64r : RI<0x01, MRM4r, (outs GR64:$dst), (ins),
- "smsw{q}\t$dst", []>, TB;
// String manipulation instructions
(TCRETURNdi64 texternalsym:$dst, imm:$off)>,
Requires<[In64BitMode]>;
+// tls has some funny stuff here...
+// This corresponds to movabs $foo@tpoff, %rax
+def : Pat<(i64 (X86Wrapper tglobaltlsaddr :$dst)),
+ (MOV64ri tglobaltlsaddr :$dst)>;
+// This corresponds to add $foo@tpoff, %rax
+def : Pat<(add GR64:$src1, (X86Wrapper tglobaltlsaddr :$dst)),
+ (ADD64ri32 GR64:$src1, tglobaltlsaddr :$dst)>;
+// This corresponds to mov foo@tpoff(%rbx), %eax
+def : Pat<(load (i64 (X86Wrapper tglobaltlsaddr :$dst))),
+ (MOV64rm tglobaltlsaddr :$dst)>;
+
// Comparisons.
// TEST R,R is smaller than CMP R,0
"movq\t{$src, $dst|$dst, $src}",
[(store (i64 (bitconvert FR64:$src)), addr:$dst)]>;
-//===----------------------------------------------------------------------===//
-// X86-64 SSE4.1 Instructions
-//===----------------------------------------------------------------------===//
-
-/// SS41I_extract32 - SSE 4.1 extract 32 bits to int reg or memory destination
-multiclass SS41I_extract64<bits<8> opc, string OpcodeStr> {
- def rr : SS4AIi8<opc, MRMDestReg, (outs GR64:$dst),
- (ins VR128:$src1, i32i8imm:$src2),
- !strconcat(OpcodeStr,
- "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
- [(set GR64:$dst,
- (extractelt (v2i64 VR128:$src1), imm:$src2))]>, OpSize, REX_W;
- def mr : SS4AIi8<opc, MRMDestMem, (outs),
- (ins i64mem:$dst, VR128:$src1, i32i8imm:$src2),
- !strconcat(OpcodeStr,
- "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
- [(store (extractelt (v2i64 VR128:$src1), imm:$src2),
- addr:$dst)]>, OpSize, REX_W;
-}
-
-defm PEXTRQ : SS41I_extract64<0x16, "pextrq">;
-
-let Constraints = "$src1 = $dst" in {
- multiclass SS41I_insert64<bits<8> opc, string OpcodeStr> {
- def rr : SS4AIi8<opc, MRMSrcReg, (outs VR128:$dst),
- (ins VR128:$src1, GR64:$src2, i32i8imm:$src3),
- !strconcat(OpcodeStr,
- "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
- [(set VR128:$dst,
- (v2i64 (insertelt VR128:$src1, GR64:$src2, imm:$src3)))]>,
- OpSize, REX_W;
- def rm : SS4AIi8<opc, MRMSrcMem, (outs VR128:$dst),
- (ins VR128:$src1, i64mem:$src2, i32i8imm:$src3),
- !strconcat(OpcodeStr,
- "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
- [(set VR128:$dst,
- (v2i64 (insertelt VR128:$src1, (loadi64 addr:$src2),
- imm:$src3)))]>, OpSize, REX_W;
- }
-} // Constraints = "$src1 = $dst"
-
-defm PINSRQ : SS41I_insert64<0x22, "pinsrq">;
projects / oota-llvm.git / blobdiff