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

[AVX512] Add 512-bit load/stores to fast isel. 

llvm-svn: 271486
This commit is contained in:
Craig Topper 2016-06-02 04:51:37 +00:00
parent 292a86db5b
commit 048a08af66
1 changed files with 46 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
llvm/lib/Target/X86/X86FastISel.cpp
View File

@ -435,6 +435,26 @@ bool X86FastISel::X86FastEmitLoad(EVT VT, X86AddressMode &AM,
Opc = (Alignment >= 32) ? X86::VMOVDQAYrm : X86::VMOVDQUYrm; Opc = (Alignment >= 32) ? X86::VMOVDQAYrm : X86::VMOVDQUYrm;
RC = &X86::VR256RegClass; RC = &X86::VR256RegClass;
break; break;
case MVT::v16f32:
assert(Subtarget->hasAVX512());
Opc = (Alignment >= 64) ? X86::VMOVAPSZrm : X86::VMOVUPSZrm;
RC = &X86::VR512RegClass;
break;
case MVT::v8f64:
assert(Subtarget->hasAVX512());
Opc = (Alignment >= 64) ? X86::VMOVAPDZrm : X86::VMOVUPDZrm;
RC = &X86::VR512RegClass;
break;
case MVT::v8i64:
case MVT::v16i32:
case MVT::v32i16:
case MVT::v64i8:
assert(Subtarget->hasAVX512());
// Note: There are a lot more choices based on type with AVX-512, but
// there's really no advantage when the load isn't masked.
Opc = (Alignment >= 64) ? X86::VMOVDQA64Zmr : X86::VMOVDQU64Zmr;
RC = &X86::VR512RegClass;
break;
} }
ResultReg = createResultReg(RC); ResultReg = createResultReg(RC);
@ -553,6 +573,32 @@ bool X86FastISel::X86FastEmitStore(EVT VT, unsigned ValReg, bool ValIsKill,
else else
Opc = X86::VMOVDQUYmr; Opc = X86::VMOVDQUYmr;
break; break;
case MVT::v16f32:
assert(Subtarget->hasAVX512());
if (Aligned)
Opc = IsNonTemporal ? X86::VMOVNTPSZmr : X86::VMOVAPSZmr;
else
Opc = X86::VMOVUPSZmr;
break;
case MVT::v8f64:
assert(Subtarget->hasAVX512());
if (Aligned) {
Opc = IsNonTemporal ? X86::VMOVNTPDZmr : X86::VMOVAPDZmr;
} else
Opc = X86::VMOVUPDZmr;
break;
case MVT::v8i64:
case MVT::v16i32:
case MVT::v32i16:
case MVT::v64i8:
assert(Subtarget->hasAVX512());
// Note: There are a lot more choices based on type with AVX-512, but
// there's really no advantage when the store isn't masked.
if (Aligned)
Opc = IsNonTemporal ? X86::VMOVNTDQZmr : X86::VMOVDQA64Zmr;
else
Opc = X86::VMOVDQU64Zmr;
break;
} }
const MCInstrDesc &Desc = TII.get(Opc); const MCInstrDesc &Desc = TII.get(Opc);