Enable intrinsics of AVX512_BF16, which are supported for BFLOAT16 in Cooper Lake

Summary:
1. Enable infrastructure of AVX512_BF16, which is supported for BFLOAT16 in Cooper Lake;
2. Enable intrinsics for VCVTNE2PS2BF16, VCVTNEPS2BF16 and DPBF16PS instructions, which are Vector Neural Network Instructions supporting BFLOAT16 inputs and conversion instructions from IEEE single precision.
For more details about BF16 intrinsic, please refer to the latest ISE document: https://software.intel.com/en-us/download/intel-architecture-instruction-set-extensions-programming-reference

Patch by LiuTianle

Reviewers: craig.topper, smaslov, LuoYuanke, wxiao3, annita.zhang, spatel, RKSimon

Reviewed By: craig.topper

Subscribers: mgorny, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D60552

llvm-svn: 360018

1 files changed, 8 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 5abb62c560b..14b8d0b18d3 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -11851,6 +11851,14 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
   case X86::BI__builtin_ia32_cmpordsd:
     return getCmpIntrinsicCall(Intrinsic::x86_sse2_cmp_sd, 7);
 
+// AVX512 bf16 intrinsics
+  case X86::BI__builtin_ia32_cvtneps2bf16_128_mask: {
+    Ops[2] = getMaskVecValue(*this, Ops[2],
+                             Ops[0]->getType()->getVectorNumElements());
+    Intrinsic::ID IID = Intrinsic::x86_avx512bf16_mask_cvtneps2bf16_128;
+    return Builder.CreateCall(CGM.getIntrinsic(IID), Ops);
+  }
+
   case X86::BI__emul:
   case X86::BI__emulu: {
     llvm::Type *Int64Ty = llvm::IntegerType::get(getLLVMContext(), 64);