maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

One more round of reorg so sabre doesn't freak out. :-) 

llvm-svn: 26303
This commit is contained in:
Evan Cheng 2006-02-21 20:00:20 +00:00
parent 6fc1162855
commit d58478161f
4 changed files with 409 additions and 391 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
llvm/lib/Target/X86/X86InstrFPStack.td
View File

@ -13,6 +13,26 @@
//
//===----------------------------------------------------------------------===//
// Some 'special' instructions
let usesCustomDAGSchedInserter = 1 in { // Expanded by the scheduler.
def FP_TO_INT16_IN_MEM : I<0, Pseudo,
(ops i16mem:$dst, RFP:$src),
"#FP_TO_INT16_IN_MEM PSEUDO!",
[(X86fp_to_i16mem RFP:$src, addr:$dst)]>;
def FP_TO_INT32_IN_MEM : I<0, Pseudo,
(ops i32mem:$dst, RFP:$src),
"#FP_TO_INT32_IN_MEM PSEUDO!",
[(X86fp_to_i32mem RFP:$src, addr:$dst)]>;
def FP_TO_INT64_IN_MEM : I<0, Pseudo,
(ops i64mem:$dst, RFP:$src),
"#FP_TO_INT64_IN_MEM PSEUDO!",
[(X86fp_to_i64mem RFP:$src, addr:$dst)]>;
}
let isTerminator = 1 in
let Defs = [FP0, FP1, FP2, FP3, FP4, FP5, FP6] in
def FP_REG_KILL : I<0, Pseudo, (ops), "#FP_REG_KILL", []>;
// All FP Stack operations are represented with two instructions here. The
// first instruction, generated by the instruction selector, uses "RFP"
// registers: a traditional register file to reference floating point values.
@ -379,3 +399,22 @@ def FNSTCW16m : I<0xD9, MRM7m, // [mem16] = X87 control world
(ops i16mem:$dst), "fnstcw $dst", []>;
def FLDCW16m : I<0xD9, MRM5m, // X87 control world = [mem16]
(ops i16mem:$dst), "fldcw $dst", []>;
//===----------------------------------------------------------------------===//
// Non-Instruction Patterns
//===----------------------------------------------------------------------===//
// Required for RET of f32 / f64 values.
def : Pat<(X86fld addr:$src, f32), (FpLD32m addr:$src)>;
def : Pat<(X86fld addr:$src, f64), (FpLD64m addr:$src)>;
// Required for CALL which return f32 / f64 values.
def : Pat<(X86fst RFP:$src, addr:$op, f32), (FpST32m addr:$op, RFP:$src)>;
def : Pat<(X86fst RFP:$src, addr:$op, f64), (FpST64m addr:$op, RFP:$src)>;
// Floating point constant -0.0 and -1.0
def : Pat<(f64 fp64immneg0), (FpCHS (FpLD0))>, Requires<[FPStack]>;
def : Pat<(f64 fp64immneg1), (FpCHS (FpLD1))>, Requires<[FPStack]>;
// Used to conv. i64 to f64 since there isn't a SSE version.
def : Pat<(X86fildflag addr:$src, i64), (FpILD64m addr:$src)>;

94
llvm/lib/Target/X86/X86InstrInfo.td
View File

@ -403,47 +403,6 @@ def IMPLICIT_DEF_R16 : I<0, Pseudo, (ops R16:$dst),
def IMPLICIT_DEF_R32 : I<0, Pseudo, (ops R32:$dst),
"#IMPLICIT_DEF $dst",
[(set R32:$dst, (undef))]>;
def IMPLICIT_DEF_FR32 : I<0, Pseudo, (ops FR32:$dst),
"#IMPLICIT_DEF $dst",
[(set FR32:$dst, (undef))]>, Requires<[HasSSE2]>;
def IMPLICIT_DEF_FR64 : I<0, Pseudo, (ops FR64:$dst),
"#IMPLICIT_DEF $dst",
[(set FR64:$dst, (undef))]>, Requires<[HasSSE2]>;
// CMOV* - Used to implement the SSE SELECT DAG operation. Expanded by the
// scheduler into a branch sequence.
let usesCustomDAGSchedInserter = 1 in { // Expanded by the scheduler.
def CMOV_FR32 : I<0, Pseudo,
(ops FR32:$dst, FR32:$t, FR32:$f, i8imm:$cond),
"#CMOV_FR32 PSEUDO!",
[(set FR32:$dst, (X86cmov FR32:$t, FR32:$f, imm:$cond))]>;
def CMOV_FR64 : I<0, Pseudo,
(ops FR64:$dst, FR64:$t, FR64:$f, i8imm:$cond),
"#CMOV_FR64 PSEUDO!",
[(set FR64:$dst, (X86cmov FR64:$t, FR64:$f, imm:$cond))]>;
}
let usesCustomDAGSchedInserter = 1 in { // Expanded by the scheduler.
def FP_TO_INT16_IN_MEM : I<0, Pseudo,
(ops i16mem:$dst, RFP:$src),
"#FP_TO_INT16_IN_MEM PSEUDO!",
[(X86fp_to_i16mem RFP:$src, addr:$dst)]>;
def FP_TO_INT32_IN_MEM : I<0, Pseudo,
(ops i32mem:$dst, RFP:$src),
"#FP_TO_INT32_IN_MEM PSEUDO!",
[(X86fp_to_i32mem RFP:$src, addr:$dst)]>;
def FP_TO_INT64_IN_MEM : I<0, Pseudo,
(ops i64mem:$dst, RFP:$src),
"#FP_TO_INT64_IN_MEM PSEUDO!",
[(X86fp_to_i64mem RFP:$src, addr:$dst)]>;
}
let isTerminator = 1 in
let Defs = [FP0, FP1, FP2, FP3, FP4, FP5, FP6] in
def FP_REG_KILL : I<0, Pseudo, (ops), "#FP_REG_KILL", []>;
// Nop
def NOOP : I<0x90, RawFrm, (ops), "nop", []>;
@ -1690,7 +1649,6 @@ let isTwoAddress = 0 in {
// Double shift instructions (generalizations of rotate)
def SHLD32rrCL : I<0xA5, MRMDestReg, (ops R32:$dst, R32:$src1, R32:$src2),
"shld{l} {%cl, $src2, $dst|$dst, $src2, %CL}",
[(set R32:$dst, (X86shld R32:$src1, R32:$src2, CL))]>,
@ -2389,24 +2347,6 @@ def MOV32r0 : I<0x31, MRMInitReg, (ops R32:$dst),
"xor{l} $dst, $dst",
[(set R32:$dst, 0)]>;
//===----------------------------------------------------------------------===//
// Floating Point Stack Support
//===----------------------------------------------------------------------===//
include "X86InstrFPStack.td"
//===----------------------------------------------------------------------===//
// MMX and XMM Packed Integer support (requires MMX, SSE, and SSE2)
//===----------------------------------------------------------------------===//
include "X86InstrMMX.td"
//===----------------------------------------------------------------------===//
// XMM Floating point support (requires SSE / SSE2)
//===----------------------------------------------------------------------===//
include "X86InstrSSE.td"
//===----------------------------------------------------------------------===//
// Non-Instruction Patterns
//===----------------------------------------------------------------------===//
@ -2460,21 +2400,6 @@ def : Pat<(i16 (anyext R8 :$src)), (MOVZX16rr8 R8 :$src)>;
def : Pat<(i32 (anyext R8 :$src)), (MOVZX32rr8 R8 :$src)>;
def : Pat<(i32 (anyext R16:$src)), (MOVZX32rr16 R16:$src)>;
// Required for RET of f32 / f64 values.
def : Pat<(X86fld addr:$src, f32), (FpLD32m addr:$src)>;
def : Pat<(X86fld addr:$src, f64), (FpLD64m addr:$src)>;
// Required for CALL which return f32 / f64 values.
def : Pat<(X86fst RFP:$src, addr:$op, f32), (FpST32m addr:$op, RFP:$src)>;
def : Pat<(X86fst RFP:$src, addr:$op, f64), (FpST64m addr:$op, RFP:$src)>;
// Floating point constant -0.0 and -1.0
def : Pat<(f64 fp64immneg0), (FpCHS (FpLD0))>, Requires<[FPStack]>;
def : Pat<(f64 fp64immneg1), (FpCHS (FpLD1))>, Requires<[FPStack]>;
// Used to conv. i64 to f64 since there isn't a SSE version.
def : Pat<(X86fildflag addr:$src, i64), (FpILD64m addr:$src)>;
//===----------------------------------------------------------------------===//
// Some peepholes
//===----------------------------------------------------------------------===//
@ -2519,3 +2444,22 @@ def : Pat<(or (shl R16:$src1, CL:$amt),
def : Pat<(store (or (shl (loadi16 addr:$dst), CL:$amt),
(srl R16:$src2, (sub 16, CL:$amt))), addr:$dst),
(SHLD16mrCL addr:$dst, R16:$src2)>;
//===----------------------------------------------------------------------===//
// Floating Point Stack Support
//===----------------------------------------------------------------------===//
include "X86InstrFPStack.td"
//===----------------------------------------------------------------------===//
// MMX and XMM Packed Integer support (requires MMX, SSE, and SSE2)
//===----------------------------------------------------------------------===//
include "X86InstrMMX.td"
//===----------------------------------------------------------------------===//
// XMM Floating point support (requires SSE / SSE2)
//===----------------------------------------------------------------------===//
include "X86InstrSSE.td"

22
llvm/lib/Target/X86/X86InstrMMX.td
View File

@ -24,17 +24,6 @@ def MOVD64mr : I<0x7E, MRMDestMem, (ops i32mem:$dst, VR64:$src),
"movd {$src, $dst|$dst, $src}", []>, TB,
Requires<[HasMMX]>;
def MOVD128rr : I<0x6E, MRMSrcReg, (ops VR128:$dst, R32:$src),
"movd {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;
def MOVD128rm : I<0x6E, MRMSrcMem, (ops VR128:$dst, i32mem:$src),
"movd {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;
def MOVD128mr : I<0x7E, MRMDestMem, (ops i32mem:$dst, VR128:$src),
"movd {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;
def MOVQ64rr : I<0x6F, MRMSrcReg, (ops VR64:$dst, VR64:$src),
"movq {$src, $dst|$dst, $src}", []>, TB,
Requires<[HasMMX]>;
@ -44,14 +33,3 @@ def MOVQ64rm : I<0x6F, MRMSrcMem, (ops VR64:$dst, i64mem:$src),
def MOVQ64mr : I<0x7F, MRMDestMem, (ops i64mem:$dst, VR64:$src),
"movq {$src, $dst|$dst, $src}", []>, TB,
Requires<[HasMMX]>;
def MOVQ128rr : I<0x7E, MRMSrcReg, (ops VR128:$dst, VR64:$src),
"movq {$src, $dst|$dst, $src}", []>, XS,
Requires<[HasSSE2]>;
def MOVQ128rm : I<0x7E, MRMSrcMem, (ops VR128:$dst, i64mem:$src),
"movq {$src, $dst|$dst, $src}", []>, XS,
Requires<[HasSSE2]>;
def MOVQ128mr : I<0xD6, MRMSrcMem, (ops i64mem:$dst, VR128:$src),
"movq {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;

645
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -13,6 +13,337 @@
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// SSE scalar FP Instructions
//===----------------------------------------------------------------------===//
// Some 'special' instructions
def IMPLICIT_DEF_FR32 : I<0, Pseudo, (ops FR32:$dst),
"#IMPLICIT_DEF $dst",
[(set FR32:$dst, (undef))]>, Requires<[HasSSE2]>;
def IMPLICIT_DEF_FR64 : I<0, Pseudo, (ops FR64:$dst),
"#IMPLICIT_DEF $dst",
[(set FR64:$dst, (undef))]>, Requires<[HasSSE2]>;
// CMOV* - Used to implement the SSE SELECT DAG operation. Expanded by the
// scheduler into a branch sequence.
let usesCustomDAGSchedInserter = 1 in { // Expanded by the scheduler.
def CMOV_FR32 : I<0, Pseudo,
(ops FR32:$dst, FR32:$t, FR32:$f, i8imm:$cond),
"#CMOV_FR32 PSEUDO!",
[(set FR32:$dst, (X86cmov FR32:$t, FR32:$f, imm:$cond))]>;
def CMOV_FR64 : I<0, Pseudo,
(ops FR64:$dst, FR64:$t, FR64:$f, i8imm:$cond),
"#CMOV_FR64 PSEUDO!",
[(set FR64:$dst, (X86cmov FR64:$t, FR64:$f, imm:$cond))]>;
}
// Move Instructions
def MOVSSrr : I<0x10, MRMSrcReg, (ops FR32:$dst, FR32:$src),
"movss {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XS;
def MOVSDrr : I<0x10, MRMSrcReg, (ops FR64:$dst, FR64:$src),
"movsd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE2]>, XD;
def MOVSSrm : I<0x10, MRMSrcMem, (ops FR32:$dst, f32mem:$src),
"movss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (loadf32 addr:$src))]>,
Requires<[HasSSE1]>, XS;
def MOVSSmr : I<0x11, MRMDestMem, (ops f32mem:$dst, FR32:$src),
"movss {$src, $dst|$dst, $src}",
[(store FR32:$src, addr:$dst)]>,
Requires<[HasSSE1]>, XS;
def MOVSDrm : I<0x10, MRMSrcMem, (ops FR64:$dst, f64mem:$src),
"movsd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (loadf64 addr:$src))]>,
Requires<[HasSSE2]>, XD;
def MOVSDmr : I<0x11, MRMDestMem, (ops f64mem:$dst, FR64:$src),
"movsd {$src, $dst|$dst, $src}",
[(store FR64:$src, addr:$dst)]>,
Requires<[HasSSE2]>, XD;
// Conversion instructions
def CVTTSS2SIrr: I<0x2C, MRMSrcReg, (ops R32:$dst, FR32:$src),
"cvttss2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint FR32:$src))]>,
Requires<[HasSSE1]>, XS;
def CVTTSS2SIrm: I<0x2C, MRMSrcMem, (ops R32:$dst, f32mem:$src),
"cvttss2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint (loadf32 addr:$src)))]>,
Requires<[HasSSE1]>, XS;
def CVTTSD2SIrr: I<0x2C, MRMSrcReg, (ops R32:$dst, FR64:$src),
"cvttsd2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint FR64:$src))]>,
Requires<[HasSSE2]>, XD;
def CVTTSD2SIrm: I<0x2C, MRMSrcMem, (ops R32:$dst, f64mem:$src),
"cvttsd2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint (loadf64 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
def CVTSS2SDrr: I<0x5A, MRMSrcReg, (ops FR64:$dst, FR32:$src),
"cvtss2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fextend FR32:$src))]>,
Requires<[HasSSE2]>, XS;
def CVTSS2SDrm: I<0x5A, MRMSrcMem, (ops FR64:$dst, f32mem:$src),
"cvtss2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fextend (loadf32 addr:$src)))]>,
Requires<[HasSSE2]>, XS;
def CVTSD2SSrr: I<0x5A, MRMSrcReg, (ops FR32:$dst, FR64:$src),
"cvtsd2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fround FR64:$src))]>,
Requires<[HasSSE2]>, XD;
def CVTSD2SSrm: I<0x5A, MRMSrcMem, (ops FR32:$dst, f64mem:$src),
"cvtsd2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fround (loadf64 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
def CVTSI2SSrr: I<0x2A, MRMSrcReg, (ops FR32:$dst, R32:$src),
"cvtsi2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (sint_to_fp R32:$src))]>,
Requires<[HasSSE2]>, XS;
def CVTSI2SSrm: I<0x2A, MRMSrcMem, (ops FR32:$dst, i32mem:$src),
"cvtsi2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (sint_to_fp (loadi32 addr:$src)))]>,
Requires<[HasSSE2]>, XS;
def CVTSI2SDrr: I<0x2A, MRMSrcReg, (ops FR64:$dst, R32:$src),
"cvtsi2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (sint_to_fp R32:$src))]>,
Requires<[HasSSE2]>, XD;
def CVTSI2SDrm: I<0x2A, MRMSrcMem, (ops FR64:$dst, i32mem:$src),
"cvtsi2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (sint_to_fp (loadi32 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
// Arithmetic instructions
let isTwoAddress = 1 in {
let isCommutable = 1 in {
def ADDSSrr : I<0x58, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"addss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fadd FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def ADDSDrr : I<0x58, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"addsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fadd FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
def MULSSrr : I<0x59, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"mulss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fmul FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def MULSDrr : I<0x59, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"mulsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fmul FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
}
def ADDSSrm : I<0x58, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"addss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fadd FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def ADDSDrm : I<0x58, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"addsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fadd FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
def MULSSrm : I<0x59, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"mulss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fmul FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def MULSDrm : I<0x59, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"mulsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fmul FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
def DIVSSrr : I<0x5E, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"divss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fdiv FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def DIVSSrm : I<0x5E, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"divss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fdiv FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def DIVSDrr : I<0x5E, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"divsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fdiv FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
def DIVSDrm : I<0x5E, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"divsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fdiv FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
def SUBSSrr : I<0x5C, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"subss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fsub FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def SUBSSrm : I<0x5C, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"subss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fsub FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def SUBSDrr : I<0x5C, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"subsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fsub FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
def SUBSDrm : I<0x5C, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"subsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fsub FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
}
def SQRTSSrr : I<0x51, MRMSrcReg, (ops FR32:$dst, FR32:$src),
"sqrtss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fsqrt FR32:$src))]>,
Requires<[HasSSE1]>, XS;
def SQRTSSrm : I<0x51, MRMSrcMem, (ops FR32:$dst, f32mem:$src),
"sqrtss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fsqrt (loadf32 addr:$src)))]>,
Requires<[HasSSE1]>, XS;
def SQRTSDrr : I<0x51, MRMSrcReg, (ops FR64:$dst, FR64:$src),
"sqrtsd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fsqrt FR64:$src))]>,
Requires<[HasSSE2]>, XD;
def SQRTSDrm : I<0x51, MRMSrcMem, (ops FR64:$dst, f64mem:$src),
"sqrtsd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fsqrt (loadf64 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
// Comparison instructions
let isTwoAddress = 1 in {
def CMPSSrr : I<0xC2, MRMSrcReg,
(ops FR32:$dst, FR32:$src1, FR32:$src, SSECC:$cc),
"cmp${cc}ss {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XS;
def CMPSSrm : I<0xC2, MRMSrcMem,
(ops FR32:$dst, FR32:$src1, f32mem:$src, SSECC:$cc),
"cmp${cc}ss {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XS;
def CMPSDrr : I<0xC2, MRMSrcReg,
(ops FR64:$dst, FR64:$src1, FR64:$src, SSECC:$cc),
"cmp${cc}sd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XD;
def CMPSDrm : I<0xC2, MRMSrcMem,
(ops FR64:$dst, FR64:$src1, f64mem:$src, SSECC:$cc),
"cmp${cc}sd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE2]>, XD;
}
def UCOMISSrr: I<0x2E, MRMSrcReg, (ops FR32:$src1, FR32:$src2),
"ucomiss {$src2, $src1|$src1, $src2}",
[(X86cmp FR32:$src1, FR32:$src2)]>,
Requires<[HasSSE1]>, TB;
def UCOMISSrm: I<0x2E, MRMSrcMem, (ops FR32:$src1, f32mem:$src2),
"ucomiss {$src2, $src1|$src1, $src2}",
[(X86cmp FR32:$src1, (loadf32 addr:$src2))]>,
Requires<[HasSSE1]>, TB;
def UCOMISDrr: I<0x2E, MRMSrcReg, (ops FR64:$src1, FR64:$src2),
"ucomisd {$src2, $src1|$src1, $src2}",
[(X86cmp FR64:$src1, FR64:$src2)]>,
Requires<[HasSSE2]>, TB, OpSize;
def UCOMISDrm: I<0x2E, MRMSrcMem, (ops FR64:$src1, f64mem:$src2),
"ucomisd {$src2, $src1|$src1, $src2}",
[(X86cmp FR64:$src1, (loadf64 addr:$src2))]>,
Requires<[HasSSE2]>, TB, OpSize;
// Aliases of packed instructions for scalar use. These all have names that
// start with 'Fs'.
// Alias instructions that map fld0 to pxor for sse.
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
def FsFLD0SS : I<0xEF, MRMInitReg, (ops FR32:$dst),
"pxor $dst, $dst", [(set FR32:$dst, fp32imm0)]>,
Requires<[HasSSE1]>, TB, OpSize;
def FsFLD0SD : I<0xEF, MRMInitReg, (ops FR64:$dst),
"pxor $dst, $dst", [(set FR64:$dst, fp64imm0)]>,
Requires<[HasSSE2]>, TB, OpSize;
// Alias instructions to do FR32 / FR64 reg-to-reg copy using movaps / movapd.
// Upper bits are disregarded.
def FsMOVAPSrr : I<0x28, MRMSrcReg, (ops FR32:$dst, FR32:$src),
"movaps {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, TB;
def FsMOVAPDrr : I<0x28, MRMSrcReg, (ops FR64:$dst, FR64:$src),
"movapd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE2]>, TB, OpSize;
// Alias instructions to load FR32 / FR64 from f128mem using movaps / movapd.
// Upper bits are disregarded.
def FsMOVAPSrm : I<0x28, MRMSrcMem, (ops FR32:$dst, f128mem:$src),
"movaps {$src, $dst|$dst, $src}",
[(set FR32:$dst, (X86loadpf32 addr:$src))]>,
Requires<[HasSSE1]>, TB;
def FsMOVAPDrm : I<0x28, MRMSrcMem, (ops FR64:$dst, f128mem:$src),
"movapd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (X86loadpf64 addr:$src))]>,
Requires<[HasSSE2]>, TB, OpSize;
// Alias bitwise logical operations using SSE logical ops on packed FP values.
let isTwoAddress = 1 in {
let isCommutable = 1 in {
def FsANDPSrr : I<0x54, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"andps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fand FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, TB;
def FsANDPDrr : I<0x54, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"andpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fand FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, TB, OpSize;
def FsORPSrr : I<0x56, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"orps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsORPDrr : I<0x56, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"orpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
def FsXORPSrr : I<0x57, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"xorps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fxor FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, TB;
def FsXORPDrr : I<0x57, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"xorpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fxor FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, TB, OpSize;
}
def FsANDPSrm : I<0x54, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"andps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fand FR32:$src1,
(X86loadpf32 addr:$src2)))]>,
Requires<[HasSSE1]>, TB;
def FsANDPDrm : I<0x54, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"andpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fand FR64:$src1,
(X86loadpf64 addr:$src2)))]>,
Requires<[HasSSE2]>, TB, OpSize;
def FsORPSrm : I<0x56, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"orps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsORPDrm : I<0x56, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"orpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
def FsXORPSrm : I<0x57, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"xorps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fxor FR32:$src1,
(X86loadpf32 addr:$src2)))]>,
Requires<[HasSSE1]>, TB;
def FsXORPDrm : I<0x57, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"xorpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fxor FR64:$src1,
(X86loadpf64 addr:$src2)))]>,
Requires<[HasSSE2]>, TB, OpSize;
def FsANDNPSrr : I<0x55, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"andnps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsANDNPSrm : I<0x55, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"andnps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsANDNPDrr : I<0x55, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"andnpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
def FsANDNPDrm : I<0x55, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"andnpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
}
//===----------------------------------------------------------------------===//
// SSE packed FP Instructions
//===----------------------------------------------------------------------===//
// Move Instructions
def MOVAPSrr : I<0x28, MRMSrcReg, (ops V4F32:$dst, V4F32:$src),
"movaps {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, TB;
@ -100,301 +431,27 @@ def ANDNPDrm : I<0x55, MRMSrcMem, (ops V2F64:$dst, V2F64:$src1, f128mem:$src2),
Requires<[HasSSE2]>, TB, OpSize;
}
def MOVSSrr : I<0x10, MRMSrcReg, (ops FR32:$dst, FR32:$src),
"movss {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XS;
def MOVSDrr : I<0x10, MRMSrcReg, (ops FR64:$dst, FR64:$src),
"movsd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE2]>, XD;
def MOVSSrm : I<0x10, MRMSrcMem, (ops FR32:$dst, f32mem:$src),
"movss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (loadf32 addr:$src))]>,
Requires<[HasSSE1]>, XS;
def MOVSSmr : I<0x11, MRMDestMem, (ops f32mem:$dst, FR32:$src),
"movss {$src, $dst|$dst, $src}",
[(store FR32:$src, addr:$dst)]>,
Requires<[HasSSE1]>, XS;
def MOVSDrm : I<0x10, MRMSrcMem, (ops FR64:$dst, f64mem:$src),
"movsd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (loadf64 addr:$src))]>,
Requires<[HasSSE2]>, XD;
def MOVSDmr : I<0x11, MRMDestMem, (ops f64mem:$dst, FR64:$src),
"movsd {$src, $dst|$dst, $src}",
[(store FR64:$src, addr:$dst)]>,
Requires<[HasSSE2]>, XD;
def CVTTSS2SIrr: I<0x2C, MRMSrcReg, (ops R32:$dst, FR32:$src),
"cvttss2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint FR32:$src))]>,
Requires<[HasSSE1]>, XS;
def CVTTSS2SIrm: I<0x2C, MRMSrcMem, (ops R32:$dst, f32mem:$src),
"cvttss2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint (loadf32 addr:$src)))]>,
Requires<[HasSSE1]>, XS;
def CVTTSD2SIrr: I<0x2C, MRMSrcReg, (ops R32:$dst, FR64:$src),
"cvttsd2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint FR64:$src))]>,
Requires<[HasSSE2]>, XD;
def CVTTSD2SIrm: I<0x2C, MRMSrcMem, (ops R32:$dst, f64mem:$src),
"cvttsd2si {$src, $dst|$dst, $src}",
[(set R32:$dst, (fp_to_sint (loadf64 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
def CVTSS2SDrr: I<0x5A, MRMSrcReg, (ops FR64:$dst, FR32:$src),
"cvtss2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fextend FR32:$src))]>,
Requires<[HasSSE2]>, XS;
def CVTSS2SDrm: I<0x5A, MRMSrcMem, (ops FR64:$dst, f32mem:$src),
"cvtss2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fextend (loadf32 addr:$src)))]>,
Requires<[HasSSE2]>, XS;
def CVTSD2SSrr: I<0x5A, MRMSrcReg, (ops FR32:$dst, FR64:$src),
"cvtsd2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fround FR64:$src))]>,
Requires<[HasSSE2]>, XD;
def CVTSD2SSrm: I<0x5A, MRMSrcMem, (ops FR32:$dst, f64mem:$src),
"cvtsd2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fround (loadf64 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
def CVTSI2SSrr: I<0x2A, MRMSrcReg, (ops FR32:$dst, R32:$src),
"cvtsi2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (sint_to_fp R32:$src))]>,
Requires<[HasSSE2]>, XS;
def CVTSI2SSrm: I<0x2A, MRMSrcMem, (ops FR32:$dst, i32mem:$src),
"cvtsi2ss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (sint_to_fp (loadi32 addr:$src)))]>,
Requires<[HasSSE2]>, XS;
def CVTSI2SDrr: I<0x2A, MRMSrcReg, (ops FR64:$dst, R32:$src),
"cvtsi2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (sint_to_fp R32:$src))]>,
Requires<[HasSSE2]>, XD;
def CVTSI2SDrm: I<0x2A, MRMSrcMem, (ops FR64:$dst, i32mem:$src),
"cvtsi2sd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (sint_to_fp (loadi32 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
def SQRTSSrr : I<0x51, MRMSrcReg, (ops FR32:$dst, FR32:$src),
"sqrtss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fsqrt FR32:$src))]>,
Requires<[HasSSE1]>, XS;
def SQRTSSrm : I<0x51, MRMSrcMem, (ops FR32:$dst, f32mem:$src),
"sqrtss {$src, $dst|$dst, $src}",
[(set FR32:$dst, (fsqrt (loadf32 addr:$src)))]>,
Requires<[HasSSE1]>, XS;
def SQRTSDrr : I<0x51, MRMSrcReg, (ops FR64:$dst, FR64:$src),
"sqrtsd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fsqrt FR64:$src))]>,
Requires<[HasSSE2]>, XD;
def SQRTSDrm : I<0x51, MRMSrcMem, (ops FR64:$dst, f64mem:$src),
"sqrtsd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (fsqrt (loadf64 addr:$src)))]>,
Requires<[HasSSE2]>, XD;
def UCOMISSrr: I<0x2E, MRMSrcReg, (ops FR32:$src1, FR32:$src2),
"ucomiss {$src2, $src1|$src1, $src2}",
[(X86cmp FR32:$src1, FR32:$src2)]>,
Requires<[HasSSE1]>, TB;
def UCOMISSrm: I<0x2E, MRMSrcMem, (ops FR32:$src1, f32mem:$src2),
"ucomiss {$src2, $src1|$src1, $src2}",
[(X86cmp FR32:$src1, (loadf32 addr:$src2))]>,
Requires<[HasSSE1]>, TB;
def UCOMISDrr: I<0x2E, MRMSrcReg, (ops FR64:$src1, FR64:$src2),
"ucomisd {$src2, $src1|$src1, $src2}",
[(X86cmp FR64:$src1, FR64:$src2)]>,
Requires<[HasSSE2]>, TB, OpSize;
def UCOMISDrm: I<0x2E, MRMSrcMem, (ops FR64:$src1, f64mem:$src2),
"ucomisd {$src2, $src1|$src1, $src2}",
[(X86cmp FR64:$src1, (loadf64 addr:$src2))]>,
Requires<[HasSSE2]>, TB, OpSize;
let isTwoAddress = 1 in {
// SSE Scalar Arithmetic
let isCommutable = 1 in {
def ADDSSrr : I<0x58, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"addss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fadd FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def ADDSDrr : I<0x58, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"addsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fadd FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
def MULSSrr : I<0x59, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"mulss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fmul FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def MULSDrr : I<0x59, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"mulsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fmul FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
}
def ADDSSrm : I<0x58, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"addss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fadd FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def ADDSDrm : I<0x58, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"addsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fadd FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
def MULSSrm : I<0x59, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"mulss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fmul FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def MULSDrm : I<0x59, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"mulsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fmul FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
def DIVSSrr : I<0x5E, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"divss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fdiv FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def DIVSSrm : I<0x5E, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"divss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fdiv FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def DIVSDrr : I<0x5E, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"divsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fdiv FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
def DIVSDrm : I<0x5E, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"divsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fdiv FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
def SUBSSrr : I<0x5C, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"subss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fsub FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, XS;
def SUBSSrm : I<0x5C, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
"subss {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (fsub FR32:$src1, (loadf32 addr:$src2)))]>,
Requires<[HasSSE1]>, XS;
def SUBSDrr : I<0x5C, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"subsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fsub FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, XD;
def SUBSDrm : I<0x5C, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
"subsd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (fsub FR64:$src1, (loadf64 addr:$src2)))]>,
Requires<[HasSSE2]>, XD;
// SSE compare
def CMPSSrr : I<0xC2, MRMSrcReg,
(ops FR32:$dst, FR32:$src1, FR32:$src, SSECC:$cc),
"cmp${cc}ss {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XS;
def CMPSSrm : I<0xC2, MRMSrcMem,
(ops FR32:$dst, FR32:$src1, f32mem:$src, SSECC:$cc),
"cmp${cc}ss {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XS;
def CMPSDrr : I<0xC2, MRMSrcReg,
(ops FR64:$dst, FR64:$src1, FR64:$src, SSECC:$cc),
"cmp${cc}sd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, XD;
def CMPSDrm : I<0xC2, MRMSrcMem,
(ops FR64:$dst, FR64:$src1, f64mem:$src, SSECC:$cc),
"cmp${cc}sd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE2]>, XD;
}
//===----------------------------------------------------------------------===//
// Alias Instructions
// SSE integer instructions
//===----------------------------------------------------------------------===//
// Alias instructions that map fld0 to pxor for sse.
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
def FsFLD0SS : I<0xEF, MRMInitReg, (ops FR32:$dst),
"pxor $dst, $dst", [(set FR32:$dst, fp32imm0)]>,
Requires<[HasSSE1]>, TB, OpSize;
def FsFLD0SD : I<0xEF, MRMInitReg, (ops FR64:$dst),
"pxor $dst, $dst", [(set FR64:$dst, fp64imm0)]>,
Requires<[HasSSE2]>, TB, OpSize;
// Move Instructions
def MOVD128rr : I<0x6E, MRMSrcReg, (ops VR128:$dst, R32:$src),
"movd {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;
def MOVD128rm : I<0x6E, MRMSrcMem, (ops VR128:$dst, i32mem:$src),
"movd {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;
def MOVD128mr : I<0x7E, MRMDestMem, (ops i32mem:$dst, VR128:$src),
"movd {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;
// Alias instructions to do FR32 / FR64 reg-to-reg copy using movaps / movapd.
// Upper bits are disregarded.
def FsMOVAPSrr : I<0x28, MRMSrcReg, (ops V4F32:$dst, V4F32:$src),
"movaps {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE1]>, TB;
def FsMOVAPDrr : I<0x28, MRMSrcReg, (ops V2F64:$dst, V2F64:$src),
"movapd {$src, $dst|$dst, $src}", []>,
Requires<[HasSSE2]>, TB, OpSize;
// Alias instructions to load FR32 / FR64 from f128mem using movaps / movapd.
// Upper bits are disregarded.
def FsMOVAPSrm : I<0x28, MRMSrcMem, (ops FR32:$dst, f128mem:$src),
"movaps {$src, $dst|$dst, $src}",
[(set FR32:$dst, (X86loadpf32 addr:$src))]>,
Requires<[HasSSE1]>, TB;
def FsMOVAPDrm : I<0x28, MRMSrcMem, (ops FR64:$dst, f128mem:$src),
"movapd {$src, $dst|$dst, $src}",
[(set FR64:$dst, (X86loadpf64 addr:$src))]>,
Requires<[HasSSE2]>, TB, OpSize;
// Alias bitwise logical operations using SSE logical ops on packed FP values.
let isTwoAddress = 1 in {
let isCommutable = 1 in {
def FsANDPSrr : I<0x54, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"andps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fand FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, TB;
def FsANDPDrr : I<0x54, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"andpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fand FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, TB, OpSize;
def FsORPSrr : I<0x56, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"orps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsORPDrr : I<0x56, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"orpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
def FsXORPSrr : I<0x57, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"xorps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fxor FR32:$src1, FR32:$src2))]>,
Requires<[HasSSE1]>, TB;
def FsXORPDrr : I<0x57, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"xorpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fxor FR64:$src1, FR64:$src2))]>,
Requires<[HasSSE2]>, TB, OpSize;
}
def FsANDPSrm : I<0x54, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"andps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fand FR32:$src1,
(X86loadpf32 addr:$src2)))]>,
Requires<[HasSSE1]>, TB;
def FsANDPDrm : I<0x54, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"andpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fand FR64:$src1,
(X86loadpf64 addr:$src2)))]>,
Requires<[HasSSE2]>, TB, OpSize;
def FsORPSrm : I<0x56, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"orps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsORPDrm : I<0x56, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"orpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
def FsXORPSrm : I<0x57, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"xorps {$src2, $dst|$dst, $src2}",
[(set FR32:$dst, (X86fxor FR32:$src1,
(X86loadpf32 addr:$src2)))]>,
Requires<[HasSSE1]>, TB;
def FsXORPDrm : I<0x57, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"xorpd {$src2, $dst|$dst, $src2}",
[(set FR64:$dst, (X86fxor FR64:$src1,
(X86loadpf64 addr:$src2)))]>,
Requires<[HasSSE2]>, TB, OpSize;
def FsANDNPSrr : I<0x55, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
"andnps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsANDNPSrm : I<0x55, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
"andnps {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE1]>, TB;
def FsANDNPDrr : I<0x55, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
"andnpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
def FsANDNPDrm : I<0x55, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
"andnpd {$src2, $dst|$dst, $src2}", []>,
Requires<[HasSSE2]>, TB, OpSize;
}
def MOVQ128rr : I<0x7E, MRMSrcReg, (ops VR128:$dst, VR64:$src),
"movq {$src, $dst|$dst, $src}", []>, XS,
Requires<[HasSSE2]>;
def MOVQ128rm : I<0x7E, MRMSrcMem, (ops VR128:$dst, i64mem:$src),
"movq {$src, $dst|$dst, $src}", []>, XS,
Requires<[HasSSE2]>;
def MOVQ128mr : I<0xD6, MRMSrcMem, (ops i64mem:$dst, VR128:$src),
"movq {$src, $dst|$dst, $src}", []>, TB, OpSize,
Requires<[HasSSE2]>;