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

Cleanup movsldup/movshdup matching. 

27 insertions(+), 62 deletions(-)

llvm-svn: 136047
This commit is contained in:
Bruno Cardoso Lopes 2011-07-26 02:39:13 +00:00
parent 980bdb9dfb
commit 957a6a13e0
2 changed files with 27 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
View File

@ -400,16 +400,6 @@ def movl : PatFrag<(ops node:$lhs, node:$rhs),
return X86::isMOVLMask(cast<ShuffleVectorSDNode>(N));
}]>;
def movshdup : PatFrag<(ops node:$lhs, node:$rhs),
(vector_shuffle node:$lhs, node:$rhs), [{
return X86::isMOVSHDUPMask(cast<ShuffleVectorSDNode>(N));
}]>;
def movsldup : PatFrag<(ops node:$lhs, node:$rhs),
(vector_shuffle node:$lhs, node:$rhs), [{
return X86::isMOVSLDUPMask(cast<ShuffleVectorSDNode>(N));
}]>;
def unpckl : PatFrag<(ops node:$lhs, node:$rhs),
(vector_shuffle node:$lhs, node:$rhs), [{
return X86::isUNPCKLMask(cast<ShuffleVectorSDNode>(N));

79
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -3219,19 +3219,19 @@ def : Pat<(int_x86_avx_cvt_pd2dq_256 (memopv4f64 addr:$src)),
// SSE3 - Move Instructions
//===---------------------------------------------------------------------===//
// Replicate Single FP
multiclass sse3_replicate_sfp<bits<8> op, PatFrag rep_frag, string OpcodeStr> {
//===---------------------------------------------------------------------===//
// Replicate Single FP - MOVSHDUP and MOVSLDUP
//
multiclass sse3_replicate_sfp<bits<8> op, SDNode OpNode, string OpcodeStr> {
def rr : S3SI<op, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (v4f32 (rep_frag
VR128:$src, (undef))))]>;
[(set VR128:$dst, (v4f32 (OpNode VR128:$src)))]>;
def rm : S3SI<op, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (rep_frag
(memopv4f32 addr:$src), (undef)))]>;
[(set VR128:$dst, (OpNode (memopv4f32 addr:$src)))]>;
}
multiclass sse3_replicate_sfp_y<bits<8> op, PatFrag rep_frag,
multiclass sse3_replicate_sfp_y<bits<8> op, SDNode OpNode,
string OpcodeStr> {
def rr : S3SI<op, MRMSrcReg, (outs VR256:$dst), (ins VR256:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"), []>;
@ -3241,15 +3241,28 @@ def rm : S3SI<op, MRMSrcMem, (outs VR256:$dst), (ins f256mem:$src),
let Predicates = [HasAVX] in {
// FIXME: Merge above classes when we have patterns for the ymm version
defm VMOVSHDUP : sse3_replicate_sfp<0x16, movshdup, "vmovshdup">, VEX;
defm VMOVSLDUP : sse3_replicate_sfp<0x12, movsldup, "vmovsldup">, VEX;
defm VMOVSHDUPY : sse3_replicate_sfp_y<0x16, movshdup, "vmovshdup">, VEX;
defm VMOVSLDUPY : sse3_replicate_sfp_y<0x12, movsldup, "vmovsldup">, VEX;
defm VMOVSHDUP : sse3_replicate_sfp<0x16, X86Movshdup, "vmovshdup">, VEX;
defm VMOVSLDUP : sse3_replicate_sfp<0x12, X86Movsldup, "vmovsldup">, VEX;
defm VMOVSHDUPY : sse3_replicate_sfp_y<0x16, X86Movshdup, "vmovshdup">, VEX;
defm VMOVSLDUPY : sse3_replicate_sfp_y<0x12, X86Movsldup, "vmovsldup">, VEX;
}
defm MOVSHDUP : sse3_replicate_sfp<0x16, movshdup, "movshdup">;
defm MOVSLDUP : sse3_replicate_sfp<0x12, movsldup, "movsldup">;
defm MOVSHDUP : sse3_replicate_sfp<0x16, X86Movshdup, "movshdup">;
defm MOVSLDUP : sse3_replicate_sfp<0x12, X86Movsldup, "movsldup">;
// Replicate Double FP
let Predicates = [HasSSE3] in {
def : Pat<(v4i32 (X86Movshdup VR128:$src)),
(MOVSHDUPrr VR128:$src)>;
def : Pat<(v4i32 (X86Movshdup (bc_v4i32 (memopv2i64 addr:$src)))),
(MOVSHDUPrm addr:$src)>;
def : Pat<(v4i32 (X86Movsldup VR128:$src)),
(MOVSLDUPrr VR128:$src)>;
def : Pat<(v4i32 (X86Movsldup (bc_v4i32 (memopv2i64 addr:$src)))),
(MOVSLDUPrm addr:$src)>;
}
//===---------------------------------------------------------------------===//
// Replicate Double FP - MOVDDUP
//
multiclass sse3_replicate_dfp<string OpcodeStr> {
def rr : S3DI<0x12, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
@ -3306,22 +3319,6 @@ def : Pat<(movddup (bc_v4i32 (memopv2i64 addr:$src)), (undef)),
(MOVDDUPrm addr:$src)>, Requires<[HasSSE3]>;
}
// vector_shuffle v1, <undef> <1, 1, 3, 3>
let AddedComplexity = 15 in
def : Pat<(v4i32 (movshdup VR128:$src, (undef))),
(MOVSHDUPrr VR128:$src)>, Requires<[HasSSE3]>;
let AddedComplexity = 20 in
def : Pat<(v4i32 (movshdup (bc_v4i32 (memopv2i64 addr:$src)), (undef))),
(MOVSHDUPrm addr:$src)>, Requires<[HasSSE3]>;
// vector_shuffle v1, <undef> <0, 0, 2, 2>
let AddedComplexity = 15 in
def : Pat<(v4i32 (movsldup VR128:$src, (undef))),
(MOVSLDUPrr VR128:$src)>, Requires<[HasSSE3]>;
let AddedComplexity = 20 in
def : Pat<(v4i32 (movsldup (bc_v4i32 (memopv2i64 addr:$src)), (undef))),
(MOVSLDUPrm addr:$src)>, Requires<[HasSSE3]>;
//===---------------------------------------------------------------------===//
// SSE3 - Arithmetic
//===---------------------------------------------------------------------===//
@ -5853,28 +5850,6 @@ def : Pat<(v4f32 (X86Movsd VR128:$src1, VR128:$src2)),
def : Pat<(v4i32 (X86Movsd VR128:$src1, VR128:$src2)),
(MOVSDrr VR128:$src1, (EXTRACT_SUBREG (v4i32 VR128:$src2), sub_sd))>;
// Shuffle with MOVSHDUP
def : Pat<(v4i32 (X86Movshdup VR128:$src)),
(MOVSHDUPrr VR128:$src)>;
def : Pat<(X86Movshdup (bc_v4i32 (memopv2i64 addr:$src))),
(MOVSHDUPrm addr:$src)>;
def : Pat<(v4f32 (X86Movshdup VR128:$src)),
(MOVSHDUPrr VR128:$src)>;
def : Pat<(X86Movshdup (memopv4f32 addr:$src)),
(MOVSHDUPrm addr:$src)>;
// Shuffle with MOVSLDUP
def : Pat<(v4i32 (X86Movsldup VR128:$src)),
(MOVSLDUPrr VR128:$src)>;
def : Pat<(X86Movsldup (bc_v4i32 (memopv2i64 addr:$src))),
(MOVSLDUPrm addr:$src)>;
def : Pat<(v4f32 (X86Movsldup VR128:$src)),
(MOVSLDUPrr VR128:$src)>;
def : Pat<(X86Movsldup (memopv4f32 addr:$src)),
(MOVSLDUPrm addr:$src)>;
// Shuffle with PSHUFHW
def : Pat<(v8i16 (X86PShufhw VR128:$src, (i8 imm:$imm))),
(PSHUFHWri VR128:$src, imm:$imm)>;