[X86][BF16] Add libcall for FP128 -> BF16 (#115825)

This is to fix #115710.

Author: fzou1

compiler-rt/lib/builtins/CMakeLists.txt

@@ -194,6 +194,7 @@ set(BF16_SOURCES
     truncdfbf2.c
     truncxfbf2.c
     truncsfbf2.c
+    trunctfbf2.c
 )
 
 set(GENERIC_TF_SOURCES

compiler-rt/lib/builtins/trunctfbf2.c

@@ -0,0 +1,18 @@
+//===--------- lib/trunctfbf2.c - quad -> bfloat conversion -------*- C -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+#define QUAD_PRECISION
+#include "fp_lib.h"
+
+#if defined(CRT_HAS_TF_MODE) && defined(__x86_64__)
+#define SRC_QUAD
+#define DST_BFLOAT
+#include "fp_trunc_impl.inc"
+
+COMPILER_RT_ABI dst_t __trunctfbf2(src_t a) { return __truncXfYf2__(a); }
+
+#endif

llvm/include/llvm/IR/RuntimeLibcalls.def

@@ -383,6 +383,7 @@ HANDLE_LIBCALL(FPROUND_PPCF128_F16, "__trunctfhf2")
 HANDLE_LIBCALL(FPROUND_F32_BF16, "__truncsfbf2")
 HANDLE_LIBCALL(FPROUND_F64_BF16, "__truncdfbf2")
 HANDLE_LIBCALL(FPROUND_F80_BF16, "__truncxfbf2")
+HANDLE_LIBCALL(FPROUND_F128_BF16, "__trunctfbf2")
 HANDLE_LIBCALL(FPROUND_F64_F32, "__truncdfsf2")
 HANDLE_LIBCALL(FPROUND_F80_F32, "__truncxfsf2")
 HANDLE_LIBCALL(FPROUND_F128_F32, "__trunctfsf2")

llvm/lib/CodeGen/TargetLoweringBase.cpp

@@ -171,6 +171,8 @@ RTLIB::Libcall RTLIB::getFPROUND(EVT OpVT, EVT RetVT) {
       return FPROUND_F64_BF16;
     if (OpVT == MVT::f80)
       return FPROUND_F80_BF16;
+    if (OpVT == MVT::f128)
+      return FPROUND_F128_BF16;
   } else if (RetVT == MVT::f32) {
     if (OpVT == MVT::f64)
       return FPROUND_F64_F32;

llvm/test/CodeGen/X86/bfloat.ll

@@ -1975,3 +1975,25 @@ define bfloat @PR108936(x86_fp80 %0) nounwind {
   %2 = fptrunc x86_fp80 %0 to bfloat
   ret bfloat %2
 }
+
+define bfloat @PR115710(fp128 %0) nounwind {
+; X86-LABEL: PR115710:
+; X86:       # %bb.0:
+; X86-NEXT:    subl $28, %esp
+; X86-NEXT:    vmovaps {{[0-9]+}}(%esp), %xmm0
+; X86-NEXT:    vmovups %xmm0, (%esp)
+; X86-NEXT:    calll __trunctfbf2
+; X86-NEXT:    # kill: def $ax killed $ax def $eax
+; X86-NEXT:    vmovw %eax, %xmm0
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    retl
+;
+; CHECK-LABEL: PR115710:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    callq __trunctfbf2@PLT
+; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    retq
+  %2 = fptrunc fp128 %0 to bfloat
+  ret bfloat %2
+}