[X86][Clang] Converting __mm{|256|512}_movm_epi{8|16|32|64} LLVMIR call into generic intrinsics.
This patch is a part two of two reviews, one for the clang and the other for LLVM.
In this patch, I covered the clang side, by introducing the intrinsic to the front end.
This is done by creating a generic replacement.
Differential Revision: https://reviews.llvm.org/D31394a
llvm-svn: 299431
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 463dda4..a23fa9e 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -7168,6 +7168,13 @@
return EmitX86Select(CGF, Ops[3], Res, Ops[2]);
}
+static Value *EmitX86SExtMask(CodeGenFunction &CGF, Value *Op,
+ llvm::Type *DstTy) {
+ unsigned NumberOfElements = DstTy->getVectorNumElements();
+ Value *Mask = getMaskVecValue(CGF, Op, NumberOfElements);
+ return CGF.Builder.CreateSExt(Mask, DstTy, "vpmovm2");
+}
+
Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
const CallExpr *E) {
if (BuiltinID == X86::BI__builtin_ms_va_start ||
@@ -7466,6 +7473,21 @@
case X86::BI__builtin_ia32_storesd128_mask: {
return EmitX86MaskedStore(*this, Ops, 16);
}
+
+ case X86::BI__builtin_ia32_cvtmask2b128:
+ case X86::BI__builtin_ia32_cvtmask2b256:
+ case X86::BI__builtin_ia32_cvtmask2b512:
+ case X86::BI__builtin_ia32_cvtmask2w128:
+ case X86::BI__builtin_ia32_cvtmask2w256:
+ case X86::BI__builtin_ia32_cvtmask2w512:
+ case X86::BI__builtin_ia32_cvtmask2d128:
+ case X86::BI__builtin_ia32_cvtmask2d256:
+ case X86::BI__builtin_ia32_cvtmask2d512:
+ case X86::BI__builtin_ia32_cvtmask2q128:
+ case X86::BI__builtin_ia32_cvtmask2q256:
+ case X86::BI__builtin_ia32_cvtmask2q512:
+ return EmitX86SExtMask(*this, Ops[0], ConvertType(E->getType()));
+
case X86::BI__builtin_ia32_movdqa32store128_mask:
case X86::BI__builtin_ia32_movdqa64store128_mask:
case X86::BI__builtin_ia32_storeaps128_mask: