def X86_COND_P : PatLeaf<(i8 14)>; // alt. COND_PE
def X86_COND_S : PatLeaf<(i8 15)>;
-def i16immSExt8 : PatLeaf<(i16 imm), [{
- // i16immSExt8 predicate - True if the 16-bit immediate fits in a 8-bit
- // sign extended field.
- return (int16_t)N->getZExtValue() == (int8_t)N->getZExtValue();
+def immSext8 : PatLeaf<(imm), [{
+ return N->getSExtValue() == (int8_t)N->getSExtValue();
}]>;
-def i32immSExt8 : PatLeaf<(i32 imm), [{
- // i32immSExt8 predicate - True if the 32-bit immediate fits in a 8-bit
- // sign extended field.
- return (int32_t)N->getZExtValue() == (int8_t)N->getZExtValue();
+def i16immSExt8 : PatLeaf<(i16 immSext8)>;
+def i32immSExt8 : PatLeaf<(i32 immSext8)>;
+
+/// Load patterns: these constraint the match to the right address space.
+def dsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ if (PT->getAddressSpace() > 255)
+ return false;
+ return true;
}]>;
+def gsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ return PT->getAddressSpace() == 256;
+ return false;
+}]>;
+
+def fsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
+ if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
+ if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
+ return PT->getAddressSpace() == 257;
+ return false;
+}]>;
+
+
// Helper fragments for loads.
// It's always safe to treat a anyext i16 load as a i32 load if the i16 is
// known to be 32-bit aligned or better. Ditto for i8 to i16.
return false;
}]>;
-def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)),
-[{
+def loadi16_anyext : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)),[{
LoadSDNode *LD = cast<LoadSDNode>(N);
if (const Value *Src = LD->getSrcValue())
if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
return false;
}]>;
-def nvloadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
- LoadSDNode *LD = cast<LoadSDNode>(N);
- if (const Value *Src = LD->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- if (LD->isVolatile())
- return false;
- ISD::LoadExtType ExtType = LD->getExtensionType();
- if (ExtType == ISD::NON_EXTLOAD)
- return true;
- if (ExtType == ISD::EXTLOAD)
- return LD->getAlignment() >= 4;
- return false;
-}]>;
-
-def gsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- return PT->getAddressSpace() == 256;
- return false;
-}]>;
-
-def fsload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- return PT->getAddressSpace() == 257;
- return false;
-}]>;
-
-def loadi8 : PatFrag<(ops node:$ptr), (i8 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-
-def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-def loadf64 : PatFrag<(ops node:$ptr), (f64 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
-def loadf80 : PatFrag<(ops node:$ptr), (f80 (load node:$ptr)), [{
- if (const Value *Src = cast<LoadSDNode>(N)->getSrcValue())
- if (const PointerType *PT = dyn_cast<PointerType>(Src->getType()))
- if (PT->getAddressSpace() > 255)
- return false;
- return true;
-}]>;
+def loadi8 : PatFrag<(ops node:$ptr), (i8 (dsload node:$ptr))>;
+def loadi64 : PatFrag<(ops node:$ptr), (i64 (dsload node:$ptr))>;
+def loadf32 : PatFrag<(ops node:$ptr), (f32 (dsload node:$ptr))>;
+def loadf64 : PatFrag<(ops node:$ptr), (f64 (dsload node:$ptr))>;
+def loadf80 : PatFrag<(ops node:$ptr), (f80 (dsload node:$ptr))>;
def sextloadi16i8 : PatFrag<(ops node:$ptr), (i16 (sextloadi8 node:$ptr))>;
def sextloadi32i8 : PatFrag<(ops node:$ptr), (i32 (sextloadi8 node:$ptr))>;
def RDTSC : I<0x31, RawFrm, (outs), (ins), "rdtsc", [(X86rdtsc)]>,
TB;
+let Defs = [RAX, RCX, RDX] in
+def RDTSCP : I<0x01, MRM_F9, (outs), (ins), "rdtscp", []>, TB;
+
let isBarrier = 1, hasCtrlDep = 1 in {
def TRAP : I<0x0B, RawFrm, (outs), (ins), "ud2", [(trap)]>, TB;
}
def MOV32rr_REV : I<0x8B, MRMSrcReg, (outs GR32:$dst), (ins GR32:$src),
"mov{l}\t{$src, $dst|$dst, $src}", []>;
-let canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
+let canFoldAsLoad = 1, isReMaterializable = 1 in {
def MOV8rm : I<0x8A, MRMSrcMem, (outs GR8 :$dst), (ins i8mem :$src),
"mov{b}\t{$src, $dst|$dst, $src}",
[(set GR8:$dst, (loadi8 addr:$src))]>;
(outs), (ins i8mem_NOREX:$dst, GR8_NOREX:$src),
"mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>;
let mayLoad = 1,
- canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in
+ canFoldAsLoad = 1, isReMaterializable = 1 in
def MOV8rm_NOREX : I<0x8A, MRMSrcMem,
(outs GR8_NOREX:$dst), (ins i8mem_NOREX:$src),
"mov{b}\t{$src, $dst|$dst, $src} # NOREX", []>;
//
// Extra precision multiplication
-let Defs = [AL,AH,EFLAGS], Uses = [AL] in
+
+// AL is really implied by AX, by the registers in Defs must match the
+// SDNode results (i8, i32).
+let Defs = [AL,EFLAGS,AX], Uses = [AL] in
def MUL8r : I<0xF6, MRM4r, (outs), (ins GR8:$src), "mul{b}\t$src",
// FIXME: Used for 8-bit mul, ignore result upper 8 bits.
// This probably ought to be moved to a def : Pat<> if the
"mul{l}\t$src",
[]>; // EAX,EDX = EAX*GR32
-let Defs = [AL,AH,EFLAGS], Uses = [AL] in
+let Defs = [AL,EFLAGS,AX], Uses = [AL] in
def MUL8m : I<0xF6, MRM4m, (outs), (ins i8mem :$src),
"mul{b}\t$src",
// FIXME: Used for 8-bit mul, ignore result upper 8 bits.
}
let neverHasSideEffects = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AL] in
+let Defs = [AL,EFLAGS,AX], Uses = [AL] in
def IMUL8r : I<0xF6, MRM5r, (outs), (ins GR8:$src), "imul{b}\t$src", []>;
// AL,AH = AL*GR8
let Defs = [AX,DX,EFLAGS], Uses = [AX] in
def IMUL32r : I<0xF7, MRM5r, (outs), (ins GR32:$src), "imul{l}\t$src", []>;
// EAX,EDX = EAX*GR32
let mayLoad = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AL] in
+let Defs = [AL,EFLAGS,AX], Uses = [AL] in
def IMUL8m : I<0xF6, MRM5m, (outs), (ins i8mem :$src),
"imul{b}\t$src", []>; // AL,AH = AL*[mem8]
let Defs = [AX,DX,EFLAGS], Uses = [AX] in
} // neverHasSideEffects
// unsigned division/remainder
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
+let Defs = [AL,EFLAGS,AX], Uses = [AX] in
def DIV8r : I<0xF6, MRM6r, (outs), (ins GR8:$src), // AX/r8 = AL,AH
"div{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def DIV32r : I<0xF7, MRM6r, (outs), (ins GR32:$src), // EDX:EAX/r32 = EAX,EDX
"div{l}\t$src", []>;
let mayLoad = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
+let Defs = [AL,EFLAGS,AX], Uses = [AX] in
def DIV8m : I<0xF6, MRM6m, (outs), (ins i8mem:$src), // AX/[mem8] = AL,AH
"div{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
}
// Signed division/remainder.
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
+let Defs = [AL,EFLAGS,AX], Uses = [AX] in
def IDIV8r : I<0xF6, MRM7r, (outs), (ins GR8:$src), // AX/r8 = AL,AH
"idiv{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def IDIV32r: I<0xF7, MRM7r, (outs), (ins GR32:$src), // EDX:EAX/r32 = EAX,EDX
"idiv{l}\t$src", []>;
let mayLoad = 1, mayLoad = 1 in {
-let Defs = [AL,AH,EFLAGS], Uses = [AX] in
+let Defs = [AL,EFLAGS,AX], Uses = [AX] in
def IDIV8m : I<0xF6, MRM7m, (outs), (ins i8mem:$src), // AX/[mem8] = AL,AH
"idiv{b}\t$src", []>;
let Defs = [AX,DX,EFLAGS], Uses = [AX,DX] in
def : Pat<(i32 (anyext GR8 :$src)), (MOVZX32rr8 GR8 :$src)>;
def : Pat<(i32 (anyext GR16:$src)), (MOVZX32rr16 GR16:$src)>;
-// (and (i32 load), 255) -> (zextload i8)
-def : Pat<(i32 (and (nvloadi32 addr:$src), (i32 255))),
- (MOVZX32rm8 addr:$src)>;
-def : Pat<(i32 (and (nvloadi32 addr:$src), (i32 65535))),
- (MOVZX32rm16 addr:$src)>;
-
//===----------------------------------------------------------------------===//
// Some peepholes
//===----------------------------------------------------------------------===//
def : Pat<(shl GR32:$src1, (i8 1)), (ADD32rr GR32:$src1, GR32:$src1)>;
// (shl x (and y, 31)) ==> (shl x, y)
-def : Pat<(shl GR8:$src1, (and CL:$amt, 31)),
+def : Pat<(shl GR8:$src1, (and CL, 31)),
(SHL8rCL GR8:$src1)>;
-def : Pat<(shl GR16:$src1, (and CL:$amt, 31)),
+def : Pat<(shl GR16:$src1, (and CL, 31)),
(SHL16rCL GR16:$src1)>;
-def : Pat<(shl GR32:$src1, (and CL:$amt, 31)),
+def : Pat<(shl GR32:$src1, (and CL, 31)),
(SHL32rCL GR32:$src1)>;
-def : Pat<(store (shl (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (shl (loadi8 addr:$dst), (and CL, 31)), addr:$dst),
(SHL8mCL addr:$dst)>;
-def : Pat<(store (shl (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (shl (loadi16 addr:$dst), (and CL, 31)), addr:$dst),
(SHL16mCL addr:$dst)>;
-def : Pat<(store (shl (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (shl (loadi32 addr:$dst), (and CL, 31)), addr:$dst),
(SHL32mCL addr:$dst)>;
-def : Pat<(srl GR8:$src1, (and CL:$amt, 31)),
+def : Pat<(srl GR8:$src1, (and CL, 31)),
(SHR8rCL GR8:$src1)>;
-def : Pat<(srl GR16:$src1, (and CL:$amt, 31)),
+def : Pat<(srl GR16:$src1, (and CL, 31)),
(SHR16rCL GR16:$src1)>;
-def : Pat<(srl GR32:$src1, (and CL:$amt, 31)),
+def : Pat<(srl GR32:$src1, (and CL, 31)),
(SHR32rCL GR32:$src1)>;
-def : Pat<(store (srl (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (srl (loadi8 addr:$dst), (and CL, 31)), addr:$dst),
(SHR8mCL addr:$dst)>;
-def : Pat<(store (srl (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (srl (loadi16 addr:$dst), (and CL, 31)), addr:$dst),
(SHR16mCL addr:$dst)>;
-def : Pat<(store (srl (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (srl (loadi32 addr:$dst), (and CL, 31)), addr:$dst),
(SHR32mCL addr:$dst)>;
-def : Pat<(sra GR8:$src1, (and CL:$amt, 31)),
+def : Pat<(sra GR8:$src1, (and CL, 31)),
(SAR8rCL GR8:$src1)>;
-def : Pat<(sra GR16:$src1, (and CL:$amt, 31)),
+def : Pat<(sra GR16:$src1, (and CL, 31)),
(SAR16rCL GR16:$src1)>;
-def : Pat<(sra GR32:$src1, (and CL:$amt, 31)),
+def : Pat<(sra GR32:$src1, (and CL, 31)),
(SAR32rCL GR32:$src1)>;
-def : Pat<(store (sra (loadi8 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (sra (loadi8 addr:$dst), (and CL, 31)), addr:$dst),
(SAR8mCL addr:$dst)>;
-def : Pat<(store (sra (loadi16 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (sra (loadi16 addr:$dst), (and CL, 31)), addr:$dst),
(SAR16mCL addr:$dst)>;
-def : Pat<(store (sra (loadi32 addr:$dst), (and CL:$amt, 31)), addr:$dst),
+def : Pat<(store (sra (loadi32 addr:$dst), (and CL, 31)), addr:$dst),
(SAR32mCL addr:$dst)>;
// (or (x >> c) | (y << (32 - c))) ==> (shrd32 x, y, c)
addr:$dst),
(SHRD32mrCL addr:$dst, GR32:$src2)>;
-def : Pat<(shrd GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm:$amt2)),
+def : Pat<(shrd GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm/*:$amt2*/)),
(SHRD32rri8 GR32:$src1, GR32:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shrd (loadi32 addr:$dst), (i8 imm:$amt1),
- GR32:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR32:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHRD32mri8 addr:$dst, GR32:$src2, (i8 imm:$amt1))>;
// (or (x << c) | (y >> (32 - c))) ==> (shld32 x, y, c)
addr:$dst),
(SHLD32mrCL addr:$dst, GR32:$src2)>;
-def : Pat<(shld GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm:$amt2)),
+def : Pat<(shld GR32:$src1, (i8 imm:$amt1), GR32:$src2, (i8 imm/*:$amt2*/)),
(SHLD32rri8 GR32:$src1, GR32:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shld (loadi32 addr:$dst), (i8 imm:$amt1),
- GR32:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR32:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHLD32mri8 addr:$dst, GR32:$src2, (i8 imm:$amt1))>;
// (or (x >> c) | (y << (16 - c))) ==> (shrd16 x, y, c)
addr:$dst),
(SHRD16mrCL addr:$dst, GR16:$src2)>;
-def : Pat<(shrd GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm:$amt2)),
+def : Pat<(shrd GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm/*:$amt2*/)),
(SHRD16rri8 GR16:$src1, GR16:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shrd (loadi16 addr:$dst), (i8 imm:$amt1),
- GR16:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR16:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHRD16mri8 addr:$dst, GR16:$src2, (i8 imm:$amt1))>;
// (or (x << c) | (y >> (16 - c))) ==> (shld16 x, y, c)
addr:$dst),
(SHLD16mrCL addr:$dst, GR16:$src2)>;
-def : Pat<(shld GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm:$amt2)),
+def : Pat<(shld GR16:$src1, (i8 imm:$amt1), GR16:$src2, (i8 imm/*:$amt2*/)),
(SHLD16rri8 GR16:$src1, GR16:$src2, (i8 imm:$amt1))>;
def : Pat<(store (shld (loadi16 addr:$dst), (i8 imm:$amt1),
- GR16:$src2, (i8 imm:$amt2)), addr:$dst),
+ GR16:$src2, (i8 imm/*:$amt2*/)), addr:$dst),
(SHLD16mri8 addr:$dst, GR16:$src2, (i8 imm:$amt1))>;
// (anyext (setcc_carry)) -> (setcc_carry)