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

Move non-intruction patterns to a more appropriate place! 

llvm-svn: 138744
This commit is contained in:
Bruno Cardoso Lopes 2011-08-29 17:51:24 +00:00
parent 4327b32654
commit 50e0170fa5
1 changed files with 33 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -119,9 +119,42 @@ multiclass sse12_fp_packed_int<bits<8> opc, string OpcodeStr, RegisterClass RC,
// Non-instruction patterns // Non-instruction patterns
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
// A vector extract of the first f32 position is a subregister copy
def : Pat<(f32 (vector_extract (v4f32 VR128:$src), (iPTR 0))), def : Pat<(f32 (vector_extract (v4f32 VR128:$src), (iPTR 0))),
(f32 (EXTRACT_SUBREG (v4f32 VR128:$src), sub_ss))>; (f32 (EXTRACT_SUBREG (v4f32 VR128:$src), sub_ss))>;
// A 128-bit subvector extract from the first 256-bit vector position
// is a subregister copy that needs no instruction.
def : Pat<(v4i32 (extract_subvector (v8i32 VR256:$src), (i32 0))),
(v4i32 (EXTRACT_SUBREG (v8i32 VR256:$src), sub_xmm))>;
def : Pat<(v4f32 (extract_subvector (v8f32 VR256:$src), (i32 0))),
(v4f32 (EXTRACT_SUBREG (v8f32 VR256:$src), sub_xmm))>;
def : Pat<(v2i64 (extract_subvector (v4i64 VR256:$src), (i32 0))),
(v2i64 (EXTRACT_SUBREG (v4i64 VR256:$src), sub_xmm))>;
def : Pat<(v2f64 (extract_subvector (v4f64 VR256:$src), (i32 0))),
(v2f64 (EXTRACT_SUBREG (v4f64 VR256:$src), sub_xmm))>;
def : Pat<(v8i16 (extract_subvector (v16i16 VR256:$src), (i32 0))),
(v8i16 (EXTRACT_SUBREG (v16i16 VR256:$src), sub_xmm))>;
def : Pat<(v16i8 (extract_subvector (v32i8 VR256:$src), (i32 0))),
(v16i8 (EXTRACT_SUBREG (v32i8 VR256:$src), sub_xmm))>;
// A 128-bit subvector insert to the first 256-bit vector position
// is a subregister copy that needs no instruction.
def : Pat<(insert_subvector undef, (v2i64 VR128:$src), (i32 0)),
(INSERT_SUBREG (v4i64 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v2f64 VR128:$src), (i32 0)),
(INSERT_SUBREG (v4f64 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v4i32 VR128:$src), (i32 0)),
(INSERT_SUBREG (v8i32 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v4f32 VR128:$src), (i32 0)),
(INSERT_SUBREG (v8f32 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v8i16 VR128:$src), (i32 0)),
(INSERT_SUBREG (v16i16 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v16i8 VR128:$src), (i32 0)),
(INSERT_SUBREG (v32i8 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
// Implicitly promote a 32-bit scalar to a vector. // Implicitly promote a 32-bit scalar to a vector.
def : Pat<(v4f32 (scalar_to_vector FR32:$src)), def : Pat<(v4f32 (scalar_to_vector FR32:$src)),
(INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FR32:$src, sub_ss)>; (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FR32:$src, sub_ss)>;
@ -5951,20 +5984,6 @@ def : Pat<(vinsertf128_insert:$ins (v16i16 VR256:$src1), (v8i16 VR128:$src2),
(VINSERTF128rr VR256:$src1, VR128:$src2, (VINSERTF128rr VR256:$src1, VR128:$src2,
(INSERT_get_vinsertf128_imm VR256:$ins))>; (INSERT_get_vinsertf128_imm VR256:$ins))>;
// Special COPY patterns
def : Pat<(insert_subvector undef, (v2i64 VR128:$src), (i32 0)),
(INSERT_SUBREG (v4i64 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v2f64 VR128:$src), (i32 0)),
(INSERT_SUBREG (v4f64 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v4i32 VR128:$src), (i32 0)),
(INSERT_SUBREG (v8i32 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v4f32 VR128:$src), (i32 0)),
(INSERT_SUBREG (v8f32 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v8i16 VR128:$src), (i32 0)),
(INSERT_SUBREG (v16i16 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
def : Pat<(insert_subvector undef, (v16i8 VR128:$src), (i32 0)),
(INSERT_SUBREG (v32i8 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
// VEXTRACTF128 - Extract packed floating-point values // VEXTRACTF128 - Extract packed floating-point values
// //
@ -6009,23 +6028,6 @@ def : Pat<(vextractf128_extract:$ext VR256:$src1, (i32 imm)),
(v32i8 VR256:$src1), (v32i8 VR256:$src1),
(EXTRACT_get_vextractf128_imm VR128:$ext)))>; (EXTRACT_get_vextractf128_imm VR128:$ext)))>;
// Special COPY patterns
def : Pat<(v4i32 (extract_subvector (v8i32 VR256:$src), (i32 0))),
(v4i32 (EXTRACT_SUBREG (v8i32 VR256:$src), sub_xmm))>;
def : Pat<(v4f32 (extract_subvector (v8f32 VR256:$src), (i32 0))),
(v4f32 (EXTRACT_SUBREG (v8f32 VR256:$src), sub_xmm))>;
def : Pat<(v2i64 (extract_subvector (v4i64 VR256:$src), (i32 0))),
(v2i64 (EXTRACT_SUBREG (v4i64 VR256:$src), sub_xmm))>;
def : Pat<(v2f64 (extract_subvector (v4f64 VR256:$src), (i32 0))),
(v2f64 (EXTRACT_SUBREG (v4f64 VR256:$src), sub_xmm))>;
def : Pat<(v8i16 (extract_subvector (v16i16 VR256:$src), (i32 0))),
(v8i16 (EXTRACT_SUBREG (v16i16 VR256:$src), sub_xmm))>;
def : Pat<(v16i8 (extract_subvector (v32i8 VR256:$src), (i32 0))),
(v16i8 (EXTRACT_SUBREG (v32i8 VR256:$src), sub_xmm))>;
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
// VMASKMOV - Conditional SIMD Packed Loads and Stores // VMASKMOV - Conditional SIMD Packed Loads and Stores
// //