def X86pcmpgtd : SDNode<"X86ISD::PCMPGTD", SDTIntBinOp>;
def X86pcmpgtq : SDNode<"X86ISD::PCMPGTQ", SDTIntBinOp>;
-def SDTX86CmpPTest : SDTypeProfile<0, 2, [SDTCisVT<0, v4f32>, SDTCisVT<1, v4f32>]>;
+def SDTX86CmpPTest : SDTypeProfile<0, 2, [SDTCisVT<0, v4f32>,
+ SDTCisVT<1, v4f32>]>;
def X86ptest : SDNode<"X86ISD::PTEST", SDTX86CmpPTest>;
//===----------------------------------------------------------------------===//
def ssmem : Operand<v4f32> {
let PrintMethod = "printf32mem";
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
+ let ParserMatchClass = X86MemAsmOperand;
}
def sdmem : Operand<v2f64> {
let PrintMethod = "printf64mem";
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
+ let ParserMatchClass = X86MemAsmOperand;
}
//===----------------------------------------------------------------------===//
// that start with 'Fs'.
// Alias instructions that map fld0 to pxor for sse.
-let isReMaterializable = 1, isAsCheapAsAMove = 1 in
+let isReMaterializable = 1, isAsCheapAsAMove = 1, isCodeGenOnly = 1 in
def FsFLD0SS : I<0xEF, MRMInitReg, (outs FR32:$dst), (ins),
"pxor\t$dst, $dst", [(set FR32:$dst, fp32imm0)]>,
Requires<[HasSSE1]>, TB, OpSize;
// Alias instructions that map zero vector to pxor / xorp* for sse.
// We set canFoldAsLoad because this can be converted to a constant-pool
// load of an all-zeros value if folding it would be beneficial.
-let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1 in
+let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
+ isCodeGenOnly = 1 in
def V_SET0 : PSI<0x57, MRMInitReg, (outs VR128:$dst), (ins),
"xorps\t$dst, $dst",
[(set VR128:$dst, (v4i32 immAllZerosV))]>;
// that start with 'Fs'.
// Alias instructions that map fld0 to pxor for sse.
-let isReMaterializable = 1, isAsCheapAsAMove = 1 in
+let isReMaterializable = 1, isAsCheapAsAMove = 1, isCodeGenOnly = 1 in
def FsFLD0SD : I<0xEF, MRMInitReg, (outs FR64:$dst), (ins),
"pxor\t$dst, $dst", [(set FR64:$dst, fpimm0)]>,
Requires<[HasSSE2]>, TB, OpSize;
// Alias instructions that map zero vector to pxor / xorp* for sse.
// We set canFoldAsLoad because this can be converted to a constant-pool
// load of an all-ones value if folding it would be beneficial.
-let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1 in
+let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
+ isCodeGenOnly = 1 in
def V_SETALLONES : PDI<0x76, MRMInitReg, (outs VR128:$dst), (ins),
"pcmpeqd\t$dst, $dst",
[(set VR128:$dst, (v4i32 immAllOnesV))]>;
"movntdqa\t{$src, $dst|$dst, $src}",
[(set VR128:$dst, (int_x86_sse41_movntdqa addr:$src))]>;
+
+//===----------------------------------------------------------------------===//
+// SSE4.2 Instructions
+//===----------------------------------------------------------------------===//
+
/// SS42I_binop_rm_int - Simple SSE 4.2 binary operator
let Constraints = "$src1 = $dst" in {
multiclass SS42I_binop_rm_int<bits<8> opc, string OpcodeStr,
// This set of instructions are only rm, the only difference is the size
// of r and m.
let Constraints = "$src1 = $dst" in {
- def CRC32m8 : SS42FI<0xF0, MRMSrcMem, (outs GR32:$dst),
+ def CRC32m8 : SS42FI<0xF0, MRMSrcMem, (outs GR32:$dst),
(ins GR32:$src1, i8mem:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR32:$dst,
(int_x86_sse42_crc32_8 GR32:$src1,
(load addr:$src2)))]>, OpSize;
- def CRC32r8 : SS42FI<0xF0, MRMSrcReg, (outs GR32:$dst),
+ def CRC32r8 : SS42FI<0xF0, MRMSrcReg, (outs GR32:$dst),
(ins GR32:$src1, GR8:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR32:$dst,
- (int_x86_sse42_crc32_8 GR32:$src1, GR8:$src2))]>,
+ (int_x86_sse42_crc32_8 GR32:$src1, GR8:$src2))]>,
OpSize;
- def CRC32m16 : SS42FI<0xF1, MRMSrcMem, (outs GR32:$dst),
+ def CRC32m16 : SS42FI<0xF1, MRMSrcMem, (outs GR32:$dst),
(ins GR32:$src1, i16mem:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR32:$dst,
(int_x86_sse42_crc32_16 GR32:$src1,
(load addr:$src2)))]>,
OpSize;
- def CRC32r16 : SS42FI<0xF1, MRMSrcReg, (outs GR32:$dst),
+ def CRC32r16 : SS42FI<0xF1, MRMSrcReg, (outs GR32:$dst),
(ins GR32:$src1, GR16:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR32:$dst,
- (int_x86_sse42_crc32_16 GR32:$src1, GR16:$src2))]>,
+ (int_x86_sse42_crc32_16 GR32:$src1, GR16:$src2))]>,
OpSize;
- def CRC32m32 : SS42FI<0xF1, MRMSrcMem, (outs GR32:$dst),
+ def CRC32m32 : SS42FI<0xF1, MRMSrcMem, (outs GR32:$dst),
(ins GR32:$src1, i32mem:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR32:$dst,
(int_x86_sse42_crc32_32 GR32:$src1,
(load addr:$src2)))]>, OpSize;
- def CRC32r32 : SS42FI<0xF1, MRMSrcReg, (outs GR32:$dst),
+ def CRC32r32 : SS42FI<0xF1, MRMSrcReg, (outs GR32:$dst),
(ins GR32:$src1, GR32:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR32:$dst,
- (int_x86_sse42_crc32_32 GR32:$src1, GR32:$src2))]>,
+ (int_x86_sse42_crc32_32 GR32:$src1, GR32:$src2))]>,
OpSize;
- def CRC64m64 : SS42FI<0xF0, MRMSrcMem, (outs GR64:$dst),
+ def CRC64m64 : SS42FI<0xF0, MRMSrcMem, (outs GR64:$dst),
(ins GR64:$src1, i64mem:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR64:$dst,
(int_x86_sse42_crc32_64 GR64:$src1,
(load addr:$src2)))]>,
OpSize, REX_W;
- def CRC64r64 : SS42FI<0xF0, MRMSrcReg, (outs GR64:$dst),
+ def CRC64r64 : SS42FI<0xF0, MRMSrcReg, (outs GR64:$dst),
(ins GR64:$src1, GR64:$src2),
"crc32 \t{$src2, $src1|$src1, $src2}",
[(set GR64:$dst,
- (int_x86_sse42_crc32_64 GR64:$src1, GR64:$src2))]>,
+ (int_x86_sse42_crc32_64 GR64:$src1, GR64:$src2))]>,
OpSize, REX_W;
-
- // TODO: These correspond to int_x86_sse42_crc32_8 but with a 64-bit src
- // and dest, figure it out.
- //def CRC64m8 : SS42FI<0xF1, MRMSrcMem, (outs GR64:$dst),
- // (ins GR32:$src1, i8mem:$src2),
- // "crc32 \t{$src2, $src1|$src1, $src2}",
- // [(set GR64:$dst,
- // (int_x86_sse42_crc32_8 GR64:$src1,
- // (load addr:$src2)))]>,
- // OpSize, REX_W;
- //def CRC64r8 : SS42FI<0xF1, MRMSrcReg, (outs GR64:$dst),
- // (ins GR64:$src1, GR8:$src2),
- // "crc32 \t{$src2, $src1|$src1, $src2}",
- // [(set GR64:$dst,
- // (int_x86_sse42_crc32_8 GR32:$src1, GR8:$src2))]>,
- // OpSize, REX_W;
}
+
+// String/text processing instructions.
+let Defs = [EFLAGS], usesCustomDAGSchedInserter = 1 in {
+def PCMPISTRM128REG : SS42AI<0, Pseudo, (outs VR128:$dst),
+ (ins VR128:$src1, VR128:$src2, i8imm:$src3),
+ "#PCMPISTRM128rr PSEUDO!",
+ [(set VR128:$dst,
+ (int_x86_sse42_pcmpistrm128 VR128:$src1, VR128:$src2,
+ imm:$src3))]>, OpSize;
+def PCMPISTRM128MEM : SS42AI<0, Pseudo, (outs VR128:$dst),
+ (ins VR128:$src1, i128mem:$src2, i8imm:$src3),
+ "#PCMPISTRM128rm PSEUDO!",
+ [(set VR128:$dst,
+ (int_x86_sse42_pcmpistrm128 VR128:$src1,
+ (load addr:$src2),
+ imm:$src3))]>, OpSize;
+}
+
+let Defs = [XMM0, EFLAGS] in {
+def PCMPISTRM128rr : SS42AI<0x62, MRMSrcReg, (outs),
+ (ins VR128:$src1, VR128:$src2, i8imm:$src3),
+ "pcmpistrm\t{$src3, $src2, $src1|$src1, $src2, $src3}",
+ []>, OpSize;
+def PCMPISTRM128rm : SS42AI<0x62, MRMSrcMem, (outs),
+ (ins VR128:$src1, i128mem:$src2, i8imm:$src3),
+ "pcmpistrm\t{$src3, $src2, $src1|$src1, $src2, $src3}",
+ []>, OpSize;
+}
+
+let Defs = [EFLAGS], Uses = [EAX, EDX],
+ usesCustomDAGSchedInserter = 1 in {
+def PCMPESTRM128REG : SS42AI<0, Pseudo, (outs VR128:$dst),
+ (ins VR128:$src1, VR128:$src3, i8imm:$src5),
+ "#PCMPESTRM128rr PSEUDO!",
+ [(set VR128:$dst,
+ (int_x86_sse42_pcmpestrm128 VR128:$src1, EAX,
+ VR128:$src3,
+ EDX, imm:$src5))]>, OpSize;
+def PCMPESTRM128MEM : SS42AI<0, Pseudo, (outs VR128:$dst),
+ (ins VR128:$src1, i128mem:$src3, i8imm:$src5),
+ "#PCMPESTRM128rm PSEUDO!",
+ [(set VR128:$dst,
+ (int_x86_sse42_pcmpestrm128 VR128:$src1, EAX,
+ (load addr:$src3),
+ EDX, imm:$src5))]>, OpSize;
+}
+
+let Defs = [XMM0, EFLAGS], Uses = [EAX, EDX] in {
+def PCMPESTRM128rr : SS42AI<0x60, MRMSrcReg, (outs),
+ (ins VR128:$src1, VR128:$src3, i8imm:$src5),
+ "pcmpestrm\t{$src5, $src3, $src1|$src1, $src3, $src5}",
+ []>, OpSize;
+def PCMPESTRM128rm : SS42AI<0x60, MRMSrcMem, (outs),
+ (ins VR128:$src1, i128mem:$src3, i8imm:$src5),
+ "pcmpestrm\t{$src5, $src3, $src1|$src1, $src3, $src5}",
+ []>, OpSize;
+}
+
+let Defs = [ECX, EFLAGS] in {
+ multiclass SS42AI_pcmpistri<Intrinsic IntId128> {
+ def rr : SS42AI<0x63, MRMSrcReg, (outs),
+ (ins VR128:$src1, VR128:$src2, i8imm:$src3),
+ "pcmpistri\t{$src3, $src2, $src1|$src1, $src2, $src3}",
+ [(set ECX,
+ (IntId128 VR128:$src1, VR128:$src2, imm:$src3)),
+ (implicit EFLAGS)]>,
+ OpSize;
+ def rm : SS42AI<0x63, MRMSrcMem, (outs),
+ (ins VR128:$src1, i128mem:$src2, i8imm:$src3),
+ "pcmpistri\t{$src3, $src2, $src1|$src1, $src2, $src3}",
+ [(set ECX,
+ (IntId128 VR128:$src1, (load addr:$src2), imm:$src3)),
+ (implicit EFLAGS)]>,
+ OpSize;
+ }
+}
+
+defm PCMPISTRI : SS42AI_pcmpistri<int_x86_sse42_pcmpistri128>;
+defm PCMPISTRIA : SS42AI_pcmpistri<int_x86_sse42_pcmpistria128>;
+defm PCMPISTRIC : SS42AI_pcmpistri<int_x86_sse42_pcmpistric128>;
+defm PCMPISTRIO : SS42AI_pcmpistri<int_x86_sse42_pcmpistrio128>;
+defm PCMPISTRIS : SS42AI_pcmpistri<int_x86_sse42_pcmpistris128>;
+defm PCMPISTRIZ : SS42AI_pcmpistri<int_x86_sse42_pcmpistriz128>;
+
+let Defs = [ECX, EFLAGS] in {
+let Uses = [EAX, EDX] in {
+ multiclass SS42AI_pcmpestri<Intrinsic IntId128> {
+ def rr : SS42AI<0x61, MRMSrcReg, (outs),
+ (ins VR128:$src1, VR128:$src3, i8imm:$src5),
+ "pcmpestri\t{$src5, $src3, $src1|$src1, $src3, $src5}",
+ [(set ECX,
+ (IntId128 VR128:$src1, EAX, VR128:$src3, EDX, imm:$src5)),
+ (implicit EFLAGS)]>,
+ OpSize;
+ def rm : SS42AI<0x61, MRMSrcMem, (outs),
+ (ins VR128:$src1, i128mem:$src3, i8imm:$src5),
+ "pcmpestri\t{$src5, $src3, $src1|$src1, $src3, $src5}",
+ [(set ECX,
+ (IntId128 VR128:$src1, EAX, (load addr:$src3),
+ EDX, imm:$src5)),
+ (implicit EFLAGS)]>,
+ OpSize;
+ }
+}
+}
+
+defm PCMPESTRI : SS42AI_pcmpestri<int_x86_sse42_pcmpestri128>;
+defm PCMPESTRIA : SS42AI_pcmpestri<int_x86_sse42_pcmpestria128>;
+defm PCMPESTRIC : SS42AI_pcmpestri<int_x86_sse42_pcmpestric128>;
+defm PCMPESTRIO : SS42AI_pcmpestri<int_x86_sse42_pcmpestrio128>;
+defm PCMPESTRIS : SS42AI_pcmpestri<int_x86_sse42_pcmpestris128>;
+defm PCMPESTRIZ : SS42AI_pcmpestri<int_x86_sse42_pcmpestriz128>;
projects / oota-llvm.git / blobdiff