6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-01-15 23:31:37 +00:00
Code Issues Projects Releases Wiki Activity

Remove AVX2 specific X86ISD node types for PUNPCKH/L and instead just reuse the 128-bit versions and let the vector type distinguish.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@145125 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Craig Topper 2011-11-24 22:20:08 +00:00
parent 8a42633273
commit f475a55bd4
4 changed files with 32 additions and 80 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
lib/Target/X86/X86ISelLowering.cpp
View File

@ -2851,10 +2851,6 @@ static bool isTargetShuffle(unsigned Opcode) {
case X86ISD::PUNPCKLBW:
case X86ISD::PUNPCKLDQ:
case X86ISD::PUNPCKLQDQ:
case X86ISD::VPUNPCKLWDY:
case X86ISD::VPUNPCKLBWY:
case X86ISD::VPUNPCKLDQY:
case X86ISD::VPUNPCKLQDQY:
case X86ISD::UNPCKHPS:
case X86ISD::UNPCKHPD:
case X86ISD::VUNPCKHPSY:
@ -2863,10 +2859,6 @@ static bool isTargetShuffle(unsigned Opcode) {
case X86ISD::PUNPCKHBW:
case X86ISD::PUNPCKHDQ:
case X86ISD::PUNPCKHQDQ:
case X86ISD::VPUNPCKHWDY:
case X86ISD::VPUNPCKHBWY:
case X86ISD::VPUNPCKHDQY:
case X86ISD::VPUNPCKHQDQY:
case X86ISD::VPERMILPS:
case X86ISD::VPERMILPSY:
case X86ISD::VPERMILPD:
@ -2940,10 +2932,6 @@ static SDValue getTargetShuffleNode(unsigned Opc, DebugLoc dl, EVT VT,
case X86ISD::PUNPCKLBW:
case X86ISD::PUNPCKLDQ:
case X86ISD::PUNPCKLQDQ:
case X86ISD::VPUNPCKLWDY:
case X86ISD::VPUNPCKLBWY:
case X86ISD::VPUNPCKLDQY:
case X86ISD::VPUNPCKLQDQY:
case X86ISD::UNPCKHPS:
case X86ISD::UNPCKHPD:
case X86ISD::VUNPCKHPSY:
@ -2952,10 +2940,6 @@ static SDValue getTargetShuffleNode(unsigned Opc, DebugLoc dl, EVT VT,
case X86ISD::PUNPCKHBW:
case X86ISD::PUNPCKHDQ:
case X86ISD::PUNPCKHQDQ:
case X86ISD::VPUNPCKHWDY:
case X86ISD::VPUNPCKHBWY:
case X86ISD::VPUNPCKHDQY:
case X86ISD::VPUNPCKHQDQY:
return DAG.getNode(Opc, dl, VT, V1, V2);
}
return SDValue();
@ -4663,10 +4647,6 @@ static SDValue getShuffleScalarElt(SDNode *N, int Index, SelectionDAG &DAG,
case X86ISD::PUNPCKHWD:
case X86ISD::PUNPCKHDQ:
case X86ISD::PUNPCKHQDQ:
case X86ISD::VPUNPCKHBWY:
case X86ISD::VPUNPCKHWDY:
case X86ISD::VPUNPCKHDQY:
case X86ISD::VPUNPCKHQDQY:
DecodePUNPCKHMask(NumElems, ShuffleMask);
break;
case X86ISD::UNPCKHPS:
@ -4679,10 +4659,6 @@ static SDValue getShuffleScalarElt(SDNode *N, int Index, SelectionDAG &DAG,
case X86ISD::PUNPCKLWD:
case X86ISD::PUNPCKLDQ:
case X86ISD::PUNPCKLQDQ:
case X86ISD::VPUNPCKLBWY:
case X86ISD::VPUNPCKLWDY:
case X86ISD::VPUNPCKLDQY:
case X86ISD::VPUNPCKLQDQY:
DecodePUNPCKLMask(VT, ShuffleMask);
break;
case X86ISD::UNPCKLPS:
@ -6609,17 +6585,17 @@ static inline unsigned getUNPCKLOpcode(EVT VT, bool HasAVX2) {
case MVT::v4f32: return X86ISD::UNPCKLPS;
case MVT::v2f64: return X86ISD::UNPCKLPD;
case MVT::v8i32:
if (HasAVX2) return X86ISD::VPUNPCKLDQY;
if (HasAVX2) return X86ISD::PUNPCKLDQ;
// else use fp unit for int unpack.
case MVT::v8f32: return X86ISD::VUNPCKLPSY;
case MVT::v4i64:
if (HasAVX2) return X86ISD::VPUNPCKLQDQY;
if (HasAVX2) return X86ISD::PUNPCKLQDQ;
// else use fp unit for int unpack.
case MVT::v4f64: return X86ISD::VUNPCKLPDY;
case MVT::v32i8:
case MVT::v16i8: return X86ISD::PUNPCKLBW;
case MVT::v16i16:
case MVT::v8i16: return X86ISD::PUNPCKLWD;
case MVT::v16i16: return X86ISD::VPUNPCKLWDY;
case MVT::v32i8: return X86ISD::VPUNPCKLBWY;
default:
llvm_unreachable("Unknown type for unpckl");
}
@ -6633,17 +6609,17 @@ static inline unsigned getUNPCKHOpcode(EVT VT, bool HasAVX2) {
case MVT::v4f32: return X86ISD::UNPCKHPS;
case MVT::v2f64: return X86ISD::UNPCKHPD;
case MVT::v8i32:
if (HasAVX2) return X86ISD::VPUNPCKHDQY;
if (HasAVX2) return X86ISD::PUNPCKHDQ;
// else use fp unit for int unpack.
case MVT::v8f32: return X86ISD::VUNPCKHPSY;
case MVT::v4i64:
if (HasAVX2) return X86ISD::VPUNPCKHQDQY;
if (HasAVX2) return X86ISD::PUNPCKHQDQ;
// else use fp unit for int unpack.
case MVT::v4f64: return X86ISD::VUNPCKHPDY;
case MVT::v32i8:
case MVT::v16i8: return X86ISD::PUNPCKHBW;
case MVT::v16i16:
case MVT::v8i16: return X86ISD::PUNPCKHWD;
case MVT::v16i16: return X86ISD::VPUNPCKHWDY;
case MVT::v32i8: return X86ISD::VPUNPCKHBWY;
default:
llvm_unreachable("Unknown type for unpckh");
}
@ -11312,18 +11288,10 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const {
case X86ISD::PUNPCKLWD: return "X86ISD::PUNPCKLWD";
case X86ISD::PUNPCKLDQ: return "X86ISD::PUNPCKLDQ";
case X86ISD::PUNPCKLQDQ: return "X86ISD::PUNPCKLQDQ";
case X86ISD::VPUNPCKLBWY: return "X86ISD::VPUNPCKLBWY";
case X86ISD::VPUNPCKLWDY: return "X86ISD::VPUNPCKLWDY";
case X86ISD::VPUNPCKLDQY: return "X86ISD::VPUNPCKLDQY";
case X86ISD::VPUNPCKLQDQY: return "X86ISD::VPUNPCKLQDQY";
case X86ISD::PUNPCKHBW: return "X86ISD::PUNPCKHBW";
case X86ISD::PUNPCKHWD: return "X86ISD::PUNPCKHWD";
case X86ISD::PUNPCKHDQ: return "X86ISD::PUNPCKHDQ";
case X86ISD::PUNPCKHQDQ: return "X86ISD::PUNPCKHQDQ";
case X86ISD::VPUNPCKHBWY: return "X86ISD::VPUNPCKHBWY";
case X86ISD::VPUNPCKHWDY: return "X86ISD::VPUNPCKHWDY";
case X86ISD::VPUNPCKHDQY: return "X86ISD::VPUNPCKHDQY";
case X86ISD::VPUNPCKHQDQY: return "X86ISD::VPUNPCKHQDQY";
case X86ISD::VBROADCAST: return "X86ISD::VBROADCAST";
case X86ISD::VPERMILPS: return "X86ISD::VPERMILPS";
case X86ISD::VPERMILPSY: return "X86ISD::VPERMILPSY";
@ -14907,10 +14875,6 @@ SDValue X86TargetLowering::PerformDAGCombine(SDNode *N,
case X86ISD::PUNPCKHWD:
case X86ISD::PUNPCKHDQ:
case X86ISD::PUNPCKHQDQ:
case X86ISD::VPUNPCKHBWY:
case X86ISD::VPUNPCKHWDY:
case X86ISD::VPUNPCKHDQY:
case X86ISD::VPUNPCKHQDQY:
case X86ISD::UNPCKHPS:
case X86ISD::UNPCKHPD:
case X86ISD::VUNPCKHPSY:
@ -14919,10 +14883,6 @@ SDValue X86TargetLowering::PerformDAGCombine(SDNode *N,
case X86ISD::PUNPCKLWD:
case X86ISD::PUNPCKLDQ:
case X86ISD::PUNPCKLQDQ:
case X86ISD::VPUNPCKLBWY:
case X86ISD::VPUNPCKLWDY:
case X86ISD::VPUNPCKLDQY:
case X86ISD::VPUNPCKLQDQY:
case X86ISD::UNPCKLPS:
case X86ISD::UNPCKLPD:
case X86ISD::VUNPCKLPSY:

8
lib/Target/X86/X86ISelLowering.h
View File

@ -285,18 +285,10 @@ namespace llvm {
PUNPCKLWD,
PUNPCKLDQ,
PUNPCKLQDQ,
VPUNPCKLBWY,
VPUNPCKLWDY,
VPUNPCKLDQY,
VPUNPCKLQDQY,
PUNPCKHBW,
PUNPCKHWD,
PUNPCKHDQ,
PUNPCKHQDQ,
VPUNPCKHBWY,
VPUNPCKHWDY,
VPUNPCKHDQY,
VPUNPCKHQDQY,
VPERMILPS,
VPERMILPSY,
VPERMILPD,

8
lib/Target/X86/X86InstrFragmentsSIMD.td
View File

@ -144,19 +144,11 @@ def X86Punpcklbw : SDNode<"X86ISD::PUNPCKLBW", SDTShuff2Op>;
def X86Punpcklwd : SDNode<"X86ISD::PUNPCKLWD", SDTShuff2Op>;
def X86Punpckldq : SDNode<"X86ISD::PUNPCKLDQ", SDTShuff2Op>;
def X86Punpcklqdq : SDNode<"X86ISD::PUNPCKLQDQ", SDTShuff2Op>;
def X86Punpcklbwy : SDNode<"X86ISD::VPUNPCKLBWY", SDTShuff2Op>;
def X86Punpcklwdy : SDNode<"X86ISD::VPUNPCKLWDY", SDTShuff2Op>;
def X86Punpckldqy : SDNode<"X86ISD::VPUNPCKLDQY", SDTShuff2Op>;
def X86Punpcklqdqy : SDNode<"X86ISD::VPUNPCKLQDQY", SDTShuff2Op>;
def X86Punpckhbw : SDNode<"X86ISD::PUNPCKHBW", SDTShuff2Op>;
def X86Punpckhwd : SDNode<"X86ISD::PUNPCKHWD", SDTShuff2Op>;
def X86Punpckhdq : SDNode<"X86ISD::PUNPCKHDQ", SDTShuff2Op>;
def X86Punpckhqdq : SDNode<"X86ISD::PUNPCKHQDQ", SDTShuff2Op>;
def X86Punpckhbwy : SDNode<"X86ISD::VPUNPCKHBWY", SDTShuff2Op>;
def X86Punpckhwdy : SDNode<"X86ISD::VPUNPCKHWDY", SDTShuff2Op>;
def X86Punpckhdqy : SDNode<"X86ISD::VPUNPCKHDQY", SDTShuff2Op>;
def X86Punpckhqdqy : SDNode<"X86ISD::VPUNPCKHQDQY", SDTShuff2Op>;
def X86VPermilps : SDNode<"X86ISD::VPERMILPS", SDTShuff2OpI>;
def X86VPermilpsy : SDNode<"X86ISD::VPERMILPSY", SDTShuff2OpI>;

40
lib/Target/X86/X86InstrSSE.td
View File

@ -4218,35 +4218,43 @@ let Predicates = [HasAVX] in {
}
let Predicates = [HasAVX2] in {
defm VPUNPCKLBW : sse2_unpack_y<0x60, "vpunpcklbw", v32i8, X86Punpcklbwy,
defm VPUNPCKLBW : sse2_unpack_y<0x60, "vpunpcklbw", v32i8, X86Punpcklbw,
bc_v32i8>, VEX_4V;
defm VPUNPCKLWD : sse2_unpack_y<0x61, "vpunpcklwd", v16i16, X86Punpcklwdy,
defm VPUNPCKLWD : sse2_unpack_y<0x61, "vpunpcklwd", v16i16, X86Punpcklwd,
bc_v16i16>, VEX_4V;
defm VPUNPCKLDQ : sse2_unpack_y<0x62, "vpunpckldq", v8i32, X86Punpckldqy,
defm VPUNPCKLDQ : sse2_unpack_y<0x62, "vpunpckldq", v8i32, X86Punpckldq,
bc_v8i32>, VEX_4V;
defm VPUNPCKLQDQ : sse2_unpack_y<0x6C, "vpunpcklqdq", v4i64, X86Punpcklqdqy,
defm VPUNPCKLQDQ : sse2_unpack_y<0x6C, "vpunpcklqdq", v4i64, X86Punpcklqdq,
bc_v4i64>, VEX_4V;
defm VPUNPCKHBW : sse2_unpack_y<0x68, "vpunpckhbw", v32i8, X86Punpckhbwy,
defm VPUNPCKHBW : sse2_unpack_y<0x68, "vpunpckhbw", v32i8, X86Punpckhbw,
bc_v32i8>, VEX_4V;
defm VPUNPCKHWD : sse2_unpack_y<0x69, "vpunpckhwd", v16i16, X86Punpckhwdy,
defm VPUNPCKHWD : sse2_unpack_y<0x69, "vpunpckhwd", v16i16, X86Punpckhwd,
bc_v16i16>, VEX_4V;
defm VPUNPCKHDQ : sse2_unpack_y<0x6A, "vpunpckhdq", v8i32, X86Punpckhdqy,
defm VPUNPCKHDQ : sse2_unpack_y<0x6A, "vpunpckhdq", v8i32, X86Punpckhdq,
bc_v8i32>, VEX_4V;
defm VPUNPCKHQDQ : sse2_unpack_y<0x6D, "vpunpckhqdq", v4i64, X86Punpckhqdqy,
defm VPUNPCKHQDQ : sse2_unpack_y<0x6D, "vpunpckhqdq", v4i64, X86Punpckhqdq,
bc_v4i64>, VEX_4V;
}
let Constraints = "$src1 = $dst" in {
defm PUNPCKLBW : sse2_unpack<0x60, "punpcklbw", v16i8, X86Punpcklbw, bc_v16i8>;
defm PUNPCKLWD : sse2_unpack<0x61, "punpcklwd", v8i16, X86Punpcklwd, bc_v8i16>;
defm PUNPCKLDQ : sse2_unpack<0x62, "punpckldq", v4i32, X86Punpckldq, bc_v4i32>;
defm PUNPCKLQDQ : sse2_unpack<0x6C, "punpcklqdq", v2i64, X86Punpcklqdq, bc_v2i64>;
defm PUNPCKLBW : sse2_unpack<0x60, "punpcklbw", v16i8, X86Punpcklbw,
bc_v16i8>;
defm PUNPCKLWD : sse2_unpack<0x61, "punpcklwd", v8i16, X86Punpcklwd,
bc_v8i16>;
defm PUNPCKLDQ : sse2_unpack<0x62, "punpckldq", v4i32, X86Punpckldq,
bc_v4i32>;
defm PUNPCKLQDQ : sse2_unpack<0x6C, "punpcklqdq", v2i64, X86Punpcklqdq,
bc_v2i64>;
defm PUNPCKHBW : sse2_unpack<0x68, "punpckhbw", v16i8, X86Punpckhbw, bc_v16i8>;
defm PUNPCKHWD : sse2_unpack<0x69, "punpckhwd", v8i16, X86Punpckhwd, bc_v8i16>;
defm PUNPCKHDQ : sse2_unpack<0x6A, "punpckhdq", v4i32, X86Punpckhdq, bc_v4i32>;
defm PUNPCKHQDQ : sse2_unpack<0x6D, "punpckhqdq", v2i64, X86Punpckhqdq, bc_v2i64>;
defm PUNPCKHBW : sse2_unpack<0x68, "punpckhbw", v16i8, X86Punpckhbw,
bc_v16i8>;
defm PUNPCKHWD : sse2_unpack<0x69, "punpckhwd", v8i16, X86Punpckhwd,
bc_v8i16>;
defm PUNPCKHDQ : sse2_unpack<0x6A, "punpckhdq", v4i32, X86Punpckhdq,
bc_v4i32>;
defm PUNPCKHQDQ : sse2_unpack<0x6D, "punpckhqdq", v2i64, X86Punpckhqdq,
bc_v2i64>;
}
} // ExeDomain = SSEPackedInt