diff options
| author | Benjamin Kramer <benny.kra@googlemail.com> | 2011-12-09 15:44:03 +0000 |
|---|---|---|
| committer | Benjamin Kramer <benny.kra@googlemail.com> | 2011-12-09 15:44:03 +0000 |
| commit | b653397dcd34fe281286cf80d4c101000516e88e (patch) | |
| tree | 296a9dc3f967df0eee514d3251824e6c29d12266 /lib | |
| parent | a73fb9adbb2de7cd4837382b0fffd97d82ac675c (diff) | |
| download | external_llvm-b653397dcd34fe281286cf80d4c101000516e88e.tar.gz external_llvm-b653397dcd34fe281286cf80d4c101000516e88e.tar.bz2 external_llvm-b653397dcd34fe281286cf80d4c101000516e88e.zip | |
X86: Add patterns for the various rounding ops for SSE4.1 and AVX.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146257 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Target/X86/X86ISelLowering.cpp | 11 | ||||
| -rw-r--r-- | lib/Target/X86/X86InstrSSE.td | 42 |
2 files changed, 53 insertions, 0 deletions
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp index dc1aa42b95..cdc1f21743 100644 --- a/lib/Target/X86/X86ISelLowering.cpp +++ b/lib/Target/X86/X86ISelLowering.cpp @@ -914,6 +914,17 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM) } if (Subtarget->hasSSE41orAVX()) { + setOperationAction(ISD::FFLOOR, MVT::f32, Legal); + setOperationAction(ISD::FCEIL, MVT::f32, Legal); + setOperationAction(ISD::FTRUNC, MVT::f32, Legal); + setOperationAction(ISD::FRINT, MVT::f32, Legal); + setOperationAction(ISD::FNEARBYINT, MVT::f32, Legal); + setOperationAction(ISD::FFLOOR, MVT::f64, Legal); + setOperationAction(ISD::FCEIL, MVT::f64, Legal); + setOperationAction(ISD::FTRUNC, MVT::f64, Legal); + setOperationAction(ISD::FRINT, MVT::f64, Legal); + setOperationAction(ISD::FNEARBYINT, MVT::f64, Legal); + // FIXME: Do we need to handle scalar-to-vector here? setOperationAction(ISD::MUL, MVT::v4i32, Legal); diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td index 4c43952147..24e7ee430e 100644 --- a/lib/Target/X86/X86InstrSSE.td +++ b/lib/Target/X86/X86InstrSSE.td @@ -6134,6 +6134,27 @@ let Predicates = [HasAVX] in { defm VROUND : sse41_fp_binop_rm<0x0A, 0x0B, "vround", int_x86_sse41_round_ss, int_x86_sse41_round_sd, 0>, VEX_4V, VEX_LIG; + + def : Pat<(ffloor FR32:$src), + (VROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x1))>; + def : Pat<(f64 (ffloor FR64:$src)), + (VROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x1))>; + def : Pat<(f32 (fnearbyint FR32:$src)), + (VROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0xC))>; + def : Pat<(f64 (fnearbyint FR64:$src)), + (VROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0xC))>; + def : Pat<(f32 (fceil FR32:$src)), + (VROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x2))>; + def : Pat<(f64 (fceil FR64:$src)), + (VROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x2))>; + def : Pat<(f32 (frint FR32:$src)), + (VROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x4))>; + def : Pat<(f64 (frint FR64:$src)), + (VROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x4))>; + def : Pat<(f32 (ftrunc FR32:$src)), + (VROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x3))>; + def : Pat<(f64 (ftrunc FR64:$src)), + (VROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x3))>; } defm ROUND : sse41_fp_unop_rm<0x08, 0x09, "round", f128mem, VR128, @@ -6143,6 +6164,27 @@ let Constraints = "$src1 = $dst" in defm ROUND : sse41_fp_binop_rm<0x0A, 0x0B, "round", int_x86_sse41_round_ss, int_x86_sse41_round_sd>; +def : Pat<(ffloor FR32:$src), + (ROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x1))>; +def : Pat<(f64 (ffloor FR64:$src)), + (ROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x1))>; +def : Pat<(f32 (fnearbyint FR32:$src)), + (ROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0xC))>; +def : Pat<(f64 (fnearbyint FR64:$src)), + (ROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0xC))>; +def : Pat<(f32 (fceil FR32:$src)), + (ROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x2))>; +def : Pat<(f64 (fceil FR64:$src)), + (ROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x2))>; +def : Pat<(f32 (frint FR32:$src)), + (ROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x4))>; +def : Pat<(f64 (frint FR64:$src)), + (ROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x4))>; +def : Pat<(f32 (ftrunc FR32:$src)), + (ROUNDSSr (f32 (IMPLICIT_DEF)), FR32:$src, (i32 0x3))>; +def : Pat<(f64 (ftrunc FR64:$src)), + (ROUNDSDr (f64 (IMPLICIT_DEF)), FR64:$src, (i32 0x3))>; + //===----------------------------------------------------------------------===// // SSE4.1 - Packed Bit Test //===----------------------------------------------------------------------===// |